2022
GILLHAM, Jack; BENTZ, Evan C.; HOULT, Neil A.
Measuring support reactions and damage detection in steel beams using distributed strain sensing Journal Article
In: Engineering Structures, vol. 262, pp. 114389, 2022, ISSN: 0141-0296.
Abstract | Links | BibTeX | Tags: Beams, Damage detection, Distributed fiber optic sensing, Support reactions
@article{GILLHAM2022114389,
title = {Measuring support reactions and damage detection in steel beams using distributed strain sensing},
author = {Jack GILLHAM and Evan C. BENTZ and Neil A. HOULT},
url = {https://www.sciencedirect.com/science/article/pii/S0141029622005041},
doi = {https://doi.org/10.1016/j.engstruct.2022.114389},
issn = {0141-0296},
year = {2022},
date = {2022-07-01},
urldate = {2022-01-01},
journal = {Engineering Structures},
volume = {262},
pages = {114389},
abstract = {While visual inspections are an important tool in the assessment of steel bridges, they cannot provide quantitative information about the bridge’s behavior. Distributed fiber optic sensors (DFOS) have the potential to provide added insight into the performance of bridges through the measurement of full strain profiles along a member as well as other key performance indicators that can be derived from these measurements. This study investigates the use of DFOS measurements to derive support reactions and detect local damage along the flexural members in a bridge. A series of load tests were undertaken to develop the method for support reaction estimation, starting with a simply supported beam, then continuous beams, and then finally a full model bridge. The beam test support reactions were evaluated against load cell measurements and variations in geometry were shown to have an impact on the measurements that could be accounted for through calibration. The model bridge reactions matched the total applied load and showed the expected distribution for the loading configuration applied. A second model bridge test was undertaken where the shear stress in the connection between the beams and the slab exceeded the capacity of the connection and localized damage occurred. Using the DFOS measurements, the neutral axis was calculated and used to detect this localized damage.},
keywords = {Beams, Damage detection, Distributed fiber optic sensing, Support reactions},
pubstate = {published},
tppubtype = {article}
}
While visual inspections are an important tool in the assessment of steel bridges, they cannot provide quantitative information about the bridge’s behavior. Distributed fiber optic sensors (DFOS) have the potential to provide added insight into the performance of bridges through the measurement of full strain profiles along a member as well as other key performance indicators that can be derived from these measurements. This study investigates the use of DFOS measurements to derive support reactions and detect local damage along the flexural members in a bridge. A series of load tests were undertaken to develop the method for support reaction estimation, starting with a simply supported beam, then continuous beams, and then finally a full model bridge. The beam test support reactions were evaluated against load cell measurements and variations in geometry were shown to have an impact on the measurements that could be accounted for through calibration. The model bridge reactions matched the total applied load and showed the expected distribution for the loading configuration applied. A second model bridge test was undertaken where the shear stress in the connection between the beams and the slab exceeded the capacity of the connection and localized damage occurred. Using the DFOS measurements, the neutral axis was calculated and used to detect this localized damage.
Khaleghi, Leyla; Marshall, Joshua; Etemad, Ali
Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation Miscellaneous
2022.
Abstract | Links | BibTeX | Tags: Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences
@misc{https://doi.org/10.48550/arxiv.2206.00171,
title = {Learning Sequential Contexts using Transformer for 3D Hand Pose Estimation},
author = {Leyla Khaleghi and Joshua Marshall and Ali Etemad},
url = {https://arxiv.org/abs/2206.00171},
doi = {10.48550/ARXIV.2206.00171},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
publisher = {arXiv},
abstract = {3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction applications. Recent HPE methods have demonstrated the advantages of employing videos or multi-view images, allowing for more robust HPE systems. Accordingly, in this study, we propose a new method to perform Sequential learning with Transformer for Hand Pose (SeTHPose) estimation. Our SeTHPose pipeline begins by extracting visual embeddings from individual hand images. We then use a transformer encoder to learn the sequential context along time or viewing angles and generate accurate 2D hand joint locations. Then, a graph convolutional neural network with a U-Net configuration is used to convert the 2D hand joint locations to 3D poses. Our experiments show that SeTHPose performs well on both hand sequence varieties, temporal and angular. Also, SeTHPose outperforms other methods in the field to achieve new state-of-the-art results on two public available sequential datasets, STB and MuViHand. },
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences},
pubstate = {published},
tppubtype = {misc}
}
3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction applications. Recent HPE methods have demonstrated the advantages of employing videos or multi-view images, allowing for more robust HPE systems. Accordingly, in this study, we propose a new method to perform Sequential learning with Transformer for Hand Pose (SeTHPose) estimation. Our SeTHPose pipeline begins by extracting visual embeddings from individual hand images. We then use a transformer encoder to learn the sequential context along time or viewing angles and generate accurate 2D hand joint locations. Then, a graph convolutional neural network with a U-Net configuration is used to convert the 2D hand joint locations to 3D poses. Our experiments show that SeTHPose performs well on both hand sequence varieties, temporal and angular. Also, SeTHPose outperforms other methods in the field to achieve new state-of-the-art results on two public available sequential datasets, STB and MuViHand.
Callanan, Ethan; Venezia, Rebecca De; Armstrong, Victoria; Paredes, Alison; Chakraborti, Tathagata; Muise, Christian
MACQ: A Holistic View of Model Acquisition Techniques Journal Article
In: 2022.
BibTeX | Tags:
@article{callananmacq,
title = {MACQ: A Holistic View of Model Acquisition Techniques},
author = {Ethan Callanan and Rebecca De Venezia and Victoria Armstrong and Alison Paredes and Tathagata Chakraborti and Christian Muise},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Delamer, Jean-Alexis; Givigi, Sidney
Controller Based Interactive Proof to Ensure Trust in Multi-Agent Systems Journal Article
In: IEEE Transactions on Automatic Control, pp. 1-1, 2022, ISSN: 1558-2523.
Abstract | Links | BibTeX | Tags:
@article{9785901,
title = {Controller Based Interactive Proof to Ensure Trust in Multi-Agent Systems},
author = {Jean-Alexis Delamer and Sidney Givigi},
url = {https://ieeexplore.ieee.org/abstract/document/9785901},
doi = {10.1109/TAC.2022.3179217},
issn = {1558-2523},
year = {2022},
date = {2022-05-31},
urldate = {2022-01-01},
journal = {IEEE Transactions on Automatic Control},
pages = {1-1},
abstract = {When multiple agents need to perform tasks that need cooperation, communication is necessary for coordination and also to assess completion. In these cases, trust needs to be guaranteed so agents know if others are following a common strategy or if they are not cooperating. If communication is explicit, other agents, including agents not involved directly in the mission, can forge information and lead agents to believe that they are behaving according to the mission plan. Several methods have been proposed in the literature and in this paper, we propose a novel method based on interactive proofs in which trust between two agents is asserted by one agent demonstrating to the other that both follow the same mission plan. We formally represent the problem as a series of Markov Decision Processes and demonstrate that the formulation is complete and sound. Simulations of multiple agents in a maze problem demonstrate the behaviour of the system.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
When multiple agents need to perform tasks that need cooperation, communication is necessary for coordination and also to assess completion. In these cases, trust needs to be guaranteed so agents know if others are following a common strategy or if they are not cooperating. If communication is explicit, other agents, including agents not involved directly in the mission, can forge information and lead agents to believe that they are behaving according to the mission plan. Several methods have been proposed in the literature and in this paper, we propose a novel method based on interactive proofs in which trust between two agents is asserted by one agent demonstrating to the other that both follow the same mission plan. We formally represent the problem as a series of Markov Decision Processes and demonstrate that the formulation is complete and sound. Simulations of multiple agents in a maze problem demonstrate the behaviour of the system.
Soltanieh, Sahar; Etemad, Ali; Hashemi, Javad
Analysis of Augmentations for Contrastive ECG Representation Learning Miscellaneous
2022.
Abstract | Links | BibTeX | Tags: Artificial Intelligence (cs.AI), electronic engineering, FOS: Computer and information sciences, FOS: Electrical engineering, information engineering, Machine Learning (cs.LG), Signal Processing (eess.SP)
@misc{https://doi.org/10.48550/arxiv.2206.07656,
title = {Analysis of Augmentations for Contrastive ECG Representation Learning},
author = {Sahar Soltanieh and Ali Etemad and Javad Hashemi},
url = {https://arxiv.org/abs/2206.07656},
doi = {10.48550/ARXIV.2206.07656},
year = {2022},
date = {2022-05-22},
urldate = {2022-05-22},
publisher = {arXiv},
abstract = {This paper systematically investigates the effectiveness of various augmentations for contrastive self-supervised learning of electrocardiogram (ECG) signals and identifies the best parameters. The baseline of our proposed self-supervised framework consists of two main parts: the contrastive learning and the downstream task. In the first stage, we train an encoder using a number of augmentations to extract generalizable ECG signal representations. We then freeze the encoder and finetune a few linear layers with different amounts of labelled data for downstream arrhythmia detection. We then experiment with various augmentations techniques and explore a range of parameters. Our experiments are done on PTB-XL, a large and publicly available 12-lead ECG dataset. The results show that applying augmentations in a specific range of complexities works better for self-supervised contrastive learning. For instance, when adding Gaussian noise, a sigma in the range of 0.1 to 0.2 achieves better results, while poor training occurs when the added noise is too small or too large (outside of the specified range). A similar trend is observed with other augmentations, demonstrating the importance of selecting the optimum level of difficulty for the added augmentations, as augmentations that are too simple will not result in effective training, while augmentations that are too difficult will also prevent the model from effective learning of generalized representations. Our work can influence future research on self-supervised contrastive learning on bio-signals and aid in selecting optimum parameters for different augmentations. },
keywords = {Artificial Intelligence (cs.AI), electronic engineering, FOS: Computer and information sciences, FOS: Electrical engineering, information engineering, Machine Learning (cs.LG), Signal Processing (eess.SP)},
pubstate = {published},
tppubtype = {misc}
}
This paper systematically investigates the effectiveness of various augmentations for contrastive self-supervised learning of electrocardiogram (ECG) signals and identifies the best parameters. The baseline of our proposed self-supervised framework consists of two main parts: the contrastive learning and the downstream task. In the first stage, we train an encoder using a number of augmentations to extract generalizable ECG signal representations. We then freeze the encoder and finetune a few linear layers with different amounts of labelled data for downstream arrhythmia detection. We then experiment with various augmentations techniques and explore a range of parameters. Our experiments are done on PTB-XL, a large and publicly available 12-lead ECG dataset. The results show that applying augmentations in a specific range of complexities works better for self-supervised contrastive learning. For instance, when adding Gaussian noise, a sigma in the range of 0.1 to 0.2 achieves better results, while poor training occurs when the added noise is too small or too large (outside of the specified range). A similar trend is observed with other augmentations, demonstrating the importance of selecting the optimum level of difficulty for the added augmentations, as augmentations that are too simple will not result in effective training, while augmentations that are too difficult will also prevent the model from effective learning of generalized representations. Our work can influence future research on self-supervised contrastive learning on bio-signals and aid in selecting optimum parameters for different augmentations.
Heaton, Jacqueline; Givigi, Sidney
A Deep CNN System for Classification of Emotions Using EEG Signals Inproceedings
In: 2022 IEEE International Systems Conference (SysCon), pp. 1-7, 2022, ISSN: 2472-9647.
Abstract | Links | BibTeX | Tags:
@inproceedings{9773832,
title = {A Deep CNN System for Classification of Emotions Using EEG Signals},
author = {Jacqueline Heaton and Sidney Givigi},
url = {https://ieeexplore.ieee.org/abstract/document/9773832},
doi = {10.1109/SysCon53536.2022.9773832},
issn = {2472-9647},
year = {2022},
date = {2022-05-16},
urldate = {2022-04-01},
booktitle = {2022 IEEE International Systems Conference (SysCon)},
pages = {1-7},
abstract = {Emotion classification has many applications in human-computer interaction, and is a necessary mode of communication for many different tasks where humans and robots must work together or in close quarters. When working with people who have trouble using verbal communication, or when it is unrealistic to expect verbal communication, robots must still be capable of taking the person’s emotions into account, whether through facial cues, body language, or other signals. Electroencephalograms are capable of capturing the signals of the brain, which can be processed and classified using various artificial intelligence architectures. In this paper, a deep convolutional neural network is applied to an emotion classification task, where it successfully learns to identify six second windows as one of four emotions: boredom, relaxation, horror, and humour. The neural network is applied to 14 individuals and a high accuracy of nearly 100% is achieved when the test data is chosen randomly from the dataset. A study is performed to find what conditions in the data are necessary for high classification accuracy. The emotion data was collected from subjects as they played four games of different genres, designed to evoke one emotion out of boredom, relaxation, humour, or fear, as assessed by the professional game critic services.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Emotion classification has many applications in human-computer interaction, and is a necessary mode of communication for many different tasks where humans and robots must work together or in close quarters. When working with people who have trouble using verbal communication, or when it is unrealistic to expect verbal communication, robots must still be capable of taking the person’s emotions into account, whether through facial cues, body language, or other signals. Electroencephalograms are capable of capturing the signals of the brain, which can be processed and classified using various artificial intelligence architectures. In this paper, a deep convolutional neural network is applied to an emotion classification task, where it successfully learns to identify six second windows as one of four emotions: boredom, relaxation, horror, and humour. The neural network is applied to 14 individuals and a high accuracy of nearly 100% is achieved when the test data is chosen randomly from the dataset. A study is performed to find what conditions in the data are necessary for high classification accuracy. The emotion data was collected from subjects as they played four games of different genres, designed to evoke one emotion out of boredom, relaxation, humour, or fear, as assessed by the professional game critic services.
Sudo, Marcelo A.; Santos, Sérgio R. Barros Dos; de Oliveira, André M.; Givigi, Sidney N.
Design and Analysis of a Low-Cost Weather Monitoring System based on Standard IoT Data Protocols Inproceedings
In: 2022 IEEE International Systems Conference (SysCon), pp. 1-7, 2022, ISSN: 2472-9647.
Abstract | Links | BibTeX | Tags:
@inproceedings{9773845,
title = {Design and Analysis of a Low-Cost Weather Monitoring System based on Standard IoT Data Protocols},
author = {Marcelo A. Sudo and Sérgio R. Barros Dos Santos and André M. de Oliveira and Sidney N. Givigi},
url = {https://ieeexplore.ieee.org/abstract/document/9773845
},
doi = {10.1109/SysCon53536.2022.9773845},
issn = {2472-9647},
year = {2022},
date = {2022-05-16},
urldate = {2022-04-01},
booktitle = {2022 IEEE International Systems Conference (SysCon)},
pages = {1-7},
abstract = {The world is converting to the use of 5G, and it will certainly boost IoT services, devices and business in general. One vital characteristic of 5G is the velocity of data transference, which reflects on performance matters. So this paper presents an analysis of performance of some IoT Protocols, such as MQTT, CoAP and HTTP REST, in a case study of a weather monitoring system built with a NodeMCU ESP8266 linked to an Arduino UNO. The meteorological station reads temperature and humidity (DHT11), atmospheric pressure and altitude (BMP180), luminosity (LDR), toxic gases (MQ135), and presence of flamable and smoke (MQ2) with several sensors. On the other side of the link, there is a Java application which reads the measures through the mentioned protocols stressing them by varying the message length and the time interval between requests. All data are stored in a MySQL database which may be available to any kind of user interface that needs to present them, which is not tackled in this study. The results showed that MQTT is the most appropriate for this application, as it transmits the messages in shorter time and with higher reliability of completeness of the information sent, regardless of their size. On the other hand, CoAP is the less reliable for this application being the one which missed almost half of the messages for a very short time interval.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The world is converting to the use of 5G, and it will certainly boost IoT services, devices and business in general. One vital characteristic of 5G is the velocity of data transference, which reflects on performance matters. So this paper presents an analysis of performance of some IoT Protocols, such as MQTT, CoAP and HTTP REST, in a case study of a weather monitoring system built with a NodeMCU ESP8266 linked to an Arduino UNO. The meteorological station reads temperature and humidity (DHT11), atmospheric pressure and altitude (BMP180), luminosity (LDR), toxic gases (MQ135), and presence of flamable and smoke (MQ2) with several sensors. On the other side of the link, there is a Java application which reads the measures through the mentioned protocols stressing them by varying the message length and the time interval between requests. All data are stored in a MySQL database which may be available to any kind of user interface that needs to present them, which is not tackled in this study. The results showed that MQTT is the most appropriate for this application, as it transmits the messages in shorter time and with higher reliability of completeness of the information sent, regardless of their size. On the other hand, CoAP is the less reliable for this application being the one which missed almost half of the messages for a very short time interval.
Delamer, Jean-Alexis; Givigi, Sidney
A System Based on Deep-Learning for Dynamic Routing problems Inproceedings
In: 2022 IEEE International Systems Conference (SysCon), pp. 1-7, 2022, ISSN: 2472-9647.
Abstract | Links | BibTeX | Tags:
@inproceedings{9773930,
title = {A System Based on Deep-Learning for Dynamic Routing problems},
author = {Jean-Alexis Delamer and Sidney Givigi},
url = {https://ieeexplore.ieee.org/abstract/document/9773930},
doi = {10.1109/SysCon53536.2022.9773930},
issn = {2472-9647},
year = {2022},
date = {2022-05-16},
urldate = {2022-04-01},
booktitle = {2022 IEEE International Systems Conference (SysCon)},
pages = {1-7},
abstract = {This paper analyzes the use of reinforcement learning with the Proximal Policy Optimization algorithm (PPO) in the context of the Dynamic Travelling Repairman Problem (DTRP). DTRP are routing problems in which one or multiple agents needs to optimize the processing time of dynamically generated requests. The study case of this paper is of a Unmanned Aerial Vehicle with no motion constraints and unlimited sensing that needs to service multiple targets in bounded environments, while minimizing the waiting time of each target. We analyze the performance of two different types of neural networks architecture, a feed-forward network and convolutional neural network (CNN). The performance of each network is analyzed in terms of the number of targets serviced and the average waiting time. Two heuristic policies, ‘Nearest-first’ (NF) and ‘First Generated First Served’ (FGFS), are used as baselines to compare the performance of the neural networks. The results show that CNNs perform better than a feed forward network. Differently from the feed forward network, the CNN network is able to capture the spatial features of the environment reducing the average waiting times of the targets. The CNN architecture also shows potential to perform as well as the heuristics. Further work is necessary to extend the proposed solution to other situations.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper analyzes the use of reinforcement learning with the Proximal Policy Optimization algorithm (PPO) in the context of the Dynamic Travelling Repairman Problem (DTRP). DTRP are routing problems in which one or multiple agents needs to optimize the processing time of dynamically generated requests. The study case of this paper is of a Unmanned Aerial Vehicle with no motion constraints and unlimited sensing that needs to service multiple targets in bounded environments, while minimizing the waiting time of each target. We analyze the performance of two different types of neural networks architecture, a feed-forward network and convolutional neural network (CNN). The performance of each network is analyzed in terms of the number of targets serviced and the average waiting time. Two heuristic policies, ‘Nearest-first’ (NF) and ‘First Generated First Served’ (FGFS), are used as baselines to compare the performance of the neural networks. The results show that CNNs perform better than a feed forward network. Differently from the feed forward network, the CNN network is able to capture the spatial features of the environment reducing the average waiting times of the targets. The CNN architecture also shows potential to perform as well as the heuristics. Further work is necessary to extend the proposed solution to other situations.
Souza, Bruno Vilela De; Santos, Sérgio R. Barros Dos; Oliveira, André M. De; Givigi, Sidney N.
Analyzing and Predicting Overall Equipment Effectiveness in Manufacturing Industries using Machine Learning Inproceedings
In: 2022 IEEE International Systems Conference (SysCon), pp. 1-8, 2022, ISSN: 2472-9647.
Abstract | Links | BibTeX | Tags:
@inproceedings{9773846,
title = {Analyzing and Predicting Overall Equipment Effectiveness in Manufacturing Industries using Machine Learning},
author = {Bruno Vilela De Souza and Sérgio R. Barros Dos Santos and André M. De Oliveira and Sidney N. Givigi},
url = { https://ieeexplore.ieee.org/abstract/document/9773846},
doi = {10.1109/SysCon53536.2022.9773846},
issn = {2472-9647},
year = {2022},
date = {2022-05-16},
urldate = {2022-04-01},
booktitle = {2022 IEEE International Systems Conference (SysCon)},
pages = {1-8},
abstract = {This paper investigates the use of machine learning algorithms to derive an approximated metric model for predicting the Overall Equipment Effectiveness (OEE) from an industrial process. Analyzing this information, it is possible to ensure better understanding of the business and stimulating the search for improvements of the productive efficiency in industries. In this context, our objective is to explore and apply different ML techniques (supervised and unsupervised learning algorithms) to derive an approximated metric for estimating the overall efficiency in a production line using historical data (dataset) obtained from actual machines in a factory. By using the manufacturing data of a product and specific learning algorithms, a prediction model is created to identify the ideal OEE metric, indicating that the equipment will be used according to its capacity and productive efficiency. Thus, we are able to predict the OEE of a given machine, and to analyze the behavior obtained in order to improve production. From the learning OEE metric, it is possible to analyze the equipment behavior and verify the existence of some patterns which could be used to propose improvements in the manufacturing process. Experimental results have demonstrated the feasibility and evaluation of the proposed models for verifying the efficiency of the industrial plant for different business standards.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper investigates the use of machine learning algorithms to derive an approximated metric model for predicting the Overall Equipment Effectiveness (OEE) from an industrial process. Analyzing this information, it is possible to ensure better understanding of the business and stimulating the search for improvements of the productive efficiency in industries. In this context, our objective is to explore and apply different ML techniques (supervised and unsupervised learning algorithms) to derive an approximated metric for estimating the overall efficiency in a production line using historical data (dataset) obtained from actual machines in a factory. By using the manufacturing data of a product and specific learning algorithms, a prediction model is created to identify the ideal OEE metric, indicating that the equipment will be used according to its capacity and productive efficiency. Thus, we are able to predict the OEE of a given machine, and to analyze the behavior obtained in order to improve production. From the learning OEE metric, it is possible to analyze the equipment behavior and verify the existence of some patterns which could be used to propose improvements in the manufacturing process. Experimental results have demonstrated the feasibility and evaluation of the proposed models for verifying the efficiency of the industrial plant for different business standards.
Souza, Fabrício C.; Santos, Sérgio R. Barros Dos; de Oliveira, André M.; Givigi, Sidney N.
Influence of Network Topology on UAVs Formation Control based on Distributed Consensus Inproceedings
In: 2022 IEEE International Systems Conference (SysCon), pp. 1-8, 2022, ISSN: 2472-9647.
Abstract | Links | BibTeX | Tags:
@inproceedings{9773824,
title = {Influence of Network Topology on UAVs Formation Control based on Distributed Consensus},
author = {Fabrício C. Souza and Sérgio R. Barros Dos Santos and André M. de Oliveira and Sidney N. Givigi},
url = {https://ieeexplore.ieee.org/abstract/document/9773824
},
doi = {10.1109/SysCon53536.2022.9773824},
issn = {2472-9647},
year = {2022},
date = {2022-05-16},
urldate = {2022-04-01},
booktitle = {2022 IEEE International Systems Conference (SysCon)},
pages = {1-8},
abstract = {In the task of formation control, there are many autonomous agents with detection and communication capabilities, with positions defined in different reference coordinates. Through a consensus algorithm, agents reach a common understanding of information shared locally through a communication topology, allowing UAVs to move while following a reference trajectory and maintaining the desired geometric configuration. Motivated by the fact that the communication topology is essential for the task of coordinating multi-agent systems, in this article we investigate the influence and characteristics of the fixed communication network topology on the distributed consensus performance, considering four communication network models. The simulations are performed using a multi-agent software-in-the-loop simulation platform in a ROS/Gazebo architecture for the control and three-dimensional simulation of UAVs and Matlab/Simulink for the implementation and execution of the formation control algorithm based on consensus distributed with a leader-follower approach. We performed simulations for different parameters of the considered network topology models, using the same trajectory and formation shape. We present the results of simulation tests, visually and quantitatively evaluating the performance of the distributed consensus, and relating this performance to the communication network models considered in this work and the metrics extracted from these randomly generated communication topologies.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In the task of formation control, there are many autonomous agents with detection and communication capabilities, with positions defined in different reference coordinates. Through a consensus algorithm, agents reach a common understanding of information shared locally through a communication topology, allowing UAVs to move while following a reference trajectory and maintaining the desired geometric configuration. Motivated by the fact that the communication topology is essential for the task of coordinating multi-agent systems, in this article we investigate the influence and characteristics of the fixed communication network topology on the distributed consensus performance, considering four communication network models. The simulations are performed using a multi-agent software-in-the-loop simulation platform in a ROS/Gazebo architecture for the control and three-dimensional simulation of UAVs and Matlab/Simulink for the implementation and execution of the formation control algorithm based on consensus distributed with a leader-follower approach. We performed simulations for different parameters of the considered network topology models, using the same trajectory and formation shape. We present the results of simulation tests, visually and quantitatively evaluating the performance of the distributed consensus, and relating this performance to the communication network models considered in this work and the metrics extracted from these randomly generated communication topologies.
Sarkar, Pritam; Posen, Aaron; Etemad, Ali
AVCAffe: A Large Scale Audio-Visual Dataset of Cognitive Load and Affect for Remote Work Miscellaneous
2022.
Abstract | Links | BibTeX | Tags: Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, Human-Computer Interaction (cs.HC), Machine Learning (cs.LG)
@misc{https://doi.org/10.48550/arxiv.2205.06887,
title = {AVCAffe: A Large Scale Audio-Visual Dataset of Cognitive Load and Affect for Remote Work},
author = {Pritam Sarkar and Aaron Posen and Ali Etemad},
url = {https://arxiv.org/abs/2205.06887},
doi = {10.48550/ARXIV.2205.06887},
year = {2022},
date = {2022-05-13},
urldate = {2022-01-01},
publisher = {arXiv},
abstract = {We introduce AVCAffe, the first Audio-Visual dataset consisting of Cognitive load and Affect attributes. We record AVCAffe by simulating remote work scenarios over a video-conferencing platform, where subjects collaborate to complete a number of cognitively engaging tasks. AVCAffe is the largest originally collected (not collected from the Internet) affective dataset in English language. We recruit 106 participants from 18 different countries of origin, spanning an age range of 18 to 57 years old, with a balanced male-female ratio. AVCAffe comprises a total of 108 hours of video, equivalent to more than 58,000 clips along with task-based self-reported ground truth labels for arousal, valence, and cognitive load attributes such as mental demand, temporal demand, effort, and a few others. We believe AVCAffe would be a challenging benchmark for the deep learning research community given the inherent difficulty of classifying affect and cognitive load in particular. Moreover, our dataset fills an existing timely gap by facilitating the creation of learning systems for better self-management of remote work meetings, and further study of hypotheses regarding the impact of remote work on cognitive load and affective states.
},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, Human-Computer Interaction (cs.HC), Machine Learning (cs.LG)},
pubstate = {published},
tppubtype = {misc}
}
We introduce AVCAffe, the first Audio-Visual dataset consisting of Cognitive load and Affect attributes. We record AVCAffe by simulating remote work scenarios over a video-conferencing platform, where subjects collaborate to complete a number of cognitively engaging tasks. AVCAffe is the largest originally collected (not collected from the Internet) affective dataset in English language. We recruit 106 participants from 18 different countries of origin, spanning an age range of 18 to 57 years old, with a balanced male-female ratio. AVCAffe comprises a total of 108 hours of video, equivalent to more than 58,000 clips along with task-based self-reported ground truth labels for arousal, valence, and cognitive load attributes such as mental demand, temporal demand, effort, and a few others. We believe AVCAffe would be a challenging benchmark for the deep learning research community given the inherent difficulty of classifying affect and cognitive load in particular. Moreover, our dataset fills an existing timely gap by facilitating the creation of learning systems for better self-management of remote work meetings, and further study of hypotheses regarding the impact of remote work on cognitive load and affective states.
Khaleghi, Leyla; Artan, Unal; Etemad, Ali; Marshall, Joshua A.
Touchless Control of Heavy Equipment Using Low-Cost Hand Gesture Recognition Journal Article
In: IEEE Internet of Things Magazine, vol. 5, no. 1, pp. 54-57, 2022, ISSN: 2576-3199.
Abstract | Links | BibTeX | Tags:
@article{9773085,
title = {Touchless Control of Heavy Equipment Using Low-Cost Hand Gesture Recognition},
author = {Leyla Khaleghi and Unal Artan and Ali Etemad and Joshua A. Marshall},
url = {https://ieeexplore.ieee.org/abstract/document/9773085},
doi = {10.1109/IOTM.002.2200022},
issn = {2576-3199},
year = {2022},
date = {2022-05-11},
urldate = {2022-03-01},
journal = {IEEE Internet of Things Magazine},
volume = {5},
number = {1},
pages = {54-57},
abstract = {Human-machine interaction using remote hand gestures is becoming increasingly prevalent across various industries. However, their potential application to heavy construction equipment is often overlooked. This article presents a robust and inexpensive hand gesture recognition system that was implemented and tested on a robotic 1-tonne wheel loader. The system uses an RGB camera paired with a laptop to process, in real time, hand gestures to control the loader. We first design four unique gestures for controlling the loader and then collect 26,000 images to train and test a neural network for hand gesture recognition. Our system uses robust landmark detection using an off-the-shelf system prior to gesture recognition. We successfully controlled the loader to excavate in a rock pile by using the proposed hand gesture recognition system.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Human-machine interaction using remote hand gestures is becoming increasingly prevalent across various industries. However, their potential application to heavy construction equipment is often overlooked. This article presents a robust and inexpensive hand gesture recognition system that was implemented and tested on a robotic 1-tonne wheel loader. The system uses an RGB camera paired with a laptop to process, in real time, hand gestures to control the loader. We first design four unique gestures for controlling the loader and then collect 26,000 images to train and test a neural network for hand gesture recognition. Our system uses robust landmark detection using an off-the-shelf system prior to gesture recognition. We successfully controlled the loader to excavate in a rock pile by using the proposed hand gesture recognition system.
Khaleghi, Leyla; Artan, Unal; Etemad, Ali; Marshall, Joshua A.
Touchless Control of Heavy Equipment Using Low-Cost Hand Gesture Recognition Journal Article
In: IEEE Internet of Things Magazine, vol. 5, no. 1, pp. 54-57, 2022, ISSN: 2576-3199.
Abstract | Links | BibTeX | Tags:
@article{9773085b,
title = {Touchless Control of Heavy Equipment Using Low-Cost Hand Gesture Recognition},
author = {Leyla Khaleghi and Unal Artan and Ali Etemad and Joshua A. Marshall},
url = {https://ieeexplore.ieee.org/abstract/document/9773085
},
doi = {10.1109/IOTM.002.2200022},
issn = {2576-3199},
year = {2022},
date = {2022-05-11},
urldate = {2022-03-01},
journal = {IEEE Internet of Things Magazine},
volume = {5},
number = {1},
pages = {54-57},
abstract = {Human-machine interaction using remote hand gestures is becoming increasingly prevalent across various industries. However, their potential application to heavy construction equipment is often overlooked. This article presents a robust and inexpensive hand gesture recognition system that was implemented and tested on a robotic 1-tonne wheel loader. The system uses an RGB camera paired with a laptop to process, in real time, hand gestures to control the loader. We first design four unique gestures for controlling the loader and then collect 26,000 images to train and test a neural network for hand gesture recognition. Our system uses robust landmark detection using an off-the-shelf system prior to gesture recognition. We successfully controlled the loader to excavate in a rock pile by using the proposed hand gesture recognition system.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Human-machine interaction using remote hand gestures is becoming increasingly prevalent across various industries. However, their potential application to heavy construction equipment is often overlooked. This article presents a robust and inexpensive hand gesture recognition system that was implemented and tested on a robotic 1-tonne wheel loader. The system uses an RGB camera paired with a laptop to process, in real time, hand gestures to control the loader. We first design four unique gestures for controlling the loader and then collect 26,000 images to train and test a neural network for hand gesture recognition. Our system uses robust landmark detection using an off-the-shelf system prior to gesture recognition. We successfully controlled the loader to excavate in a rock pile by using the proposed hand gesture recognition system.
Wang, Dong; Moore, Ian D.; Hoult, Neil; Lan, Haitao
Evaluation and comparison of different detection technologies on simulated voids near buried pipes Journal Article
In: Tunnelling and Underground Space Technology, vol. 123, pp. 104440, 2022, ISSN: 0886-7798.
Abstract | Links | BibTeX | Tags: Controlled evaluation, Corrugated steel pipe, Detection accuracy, Erosion voids, Reinforced concrete pipe
@article{WANG2022104440,
title = {Evaluation and comparison of different detection technologies on simulated voids near buried pipes},
author = {Dong Wang and Ian D. Moore and Neil Hoult and Haitao Lan},
url = {https://www.sciencedirect.com/science/article/pii/S0886779822000803},
doi = {https://doi.org/10.1016/j.tust.2022.104440},
issn = {0886-7798},
year = {2022},
date = {2022-05-01},
urldate = {2022-05-01},
journal = {Tunnelling and Underground Space Technology},
volume = {123},
pages = {104440},
abstract = {Erosion voids near buried pipes may reduce the service lives of buried infrastructure assets and present a concern to municipalities as they are difficult to detect accurately and effectively. Various technologies exist to detect erosion voids but limited testing has been performed to evaluate their effectiveness. In order to evaluate and compare different existing erosion void detection technologies, a blind experiment (i.e., without operators having prior information about void locations and geometries) was conducted. Two kinds of pipes were used for the evaluation: a corrugated steel pipe and a reinforced concrete pipe. A total of five artificial voids were made near the pipes. Four commercially available void detection technologies were evaluated: (i) conventional Backscatter Computed Tomography (BCT), (ii) handheld BCT, (iii) Ground Penetrating Radar (GPR) and (iv) Pipe Penetrating Radar (PPR). Additionally, Infrared Thermography (IRT) was also employed by the authors although this was not a blind study. Each technology and the data provided by that technology are presented. Based on the results, Handheld BCT and IRT were recommended for initial detection of the voids near corrugated steel pipes. To obtain higher accuracy and geometry detail, conventional BCT and PPR were suggested for the corrugated steel pipe and concrete pipe, respectively. GPR was able to detect a large void simulated between the two test pipes.},
keywords = {Controlled evaluation, Corrugated steel pipe, Detection accuracy, Erosion voids, Reinforced concrete pipe},
pubstate = {published},
tppubtype = {article}
}
Erosion voids near buried pipes may reduce the service lives of buried infrastructure assets and present a concern to municipalities as they are difficult to detect accurately and effectively. Various technologies exist to detect erosion voids but limited testing has been performed to evaluate their effectiveness. In order to evaluate and compare different existing erosion void detection technologies, a blind experiment (i.e., without operators having prior information about void locations and geometries) was conducted. Two kinds of pipes were used for the evaluation: a corrugated steel pipe and a reinforced concrete pipe. A total of five artificial voids were made near the pipes. Four commercially available void detection technologies were evaluated: (i) conventional Backscatter Computed Tomography (BCT), (ii) handheld BCT, (iii) Ground Penetrating Radar (GPR) and (iv) Pipe Penetrating Radar (PPR). Additionally, Infrared Thermography (IRT) was also employed by the authors although this was not a blind study. Each technology and the data provided by that technology are presented. Based on the results, Handheld BCT and IRT were recommended for initial detection of the voids near corrugated steel pipes. To obtain higher accuracy and geometry detail, conventional BCT and PPR were suggested for the corrugated steel pipe and concrete pipe, respectively. GPR was able to detect a large void simulated between the two test pipes.
Cimolino, Gabriele; Graham, T. C. Nicholas
Two Heads Are Better Than One: A Dimension Space for Unifying Human and Artificial Intelligence in Shared Control Inproceedings
In: CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery, New Orleans, LA, USA, 2022, ISBN: 9781450391573.
Abstract | Links | BibTeX | Tags: Design Space Analysis, Human-Machine Cooperation, shared control
@inproceedings{10.1145/3491102.3517610,
title = {Two Heads Are Better Than One: A Dimension Space for Unifying Human and Artificial Intelligence in Shared Control},
author = {Gabriele Cimolino and T. C. Nicholas Graham},
url = {https://doi.org/10.1145/3491102.3517610},
doi = {10.1145/3491102.3517610},
isbn = {9781450391573},
year = {2022},
date = {2022-04-28},
urldate = {2022-01-01},
booktitle = {CHI Conference on Human Factors in Computing Systems},
publisher = {Association for Computing Machinery},
address = {New Orleans, LA, USA},
series = {CHI '22},
abstract = {Shared control is an emerging interaction paradigm in which a human and an AI partner collaboratively control a system. Shared control unifies human and artificial intelligence, making the human’s interactions with computers more accessible, safe, precise, effective, creative, and playful. This form of interaction has independently emerged in contexts as varied as mobility assistance, driving, surgery, and digital games. These domains each have their own problems, terminology, and design philosophies. Without a common language for describing interactions in shared control, it is difficult for designers working in one domain to share their knowledge with designers working in another. To address this problem, we present a dimension space for shared control, based on a survey of 55 shared control systems from six different problem domains. This design space analysis tool enables designers to classify existing systems, make comparisons between them, identify higher-level design patterns, and imagine solutions to novel problems.},
keywords = {Design Space Analysis, Human-Machine Cooperation, shared control},
pubstate = {published},
tppubtype = {inproceedings}
}
Shared control is an emerging interaction paradigm in which a human and an AI partner collaboratively control a system. Shared control unifies human and artificial intelligence, making the human’s interactions with computers more accessible, safe, precise, effective, creative, and playful. This form of interaction has independently emerged in contexts as varied as mobility assistance, driving, surgery, and digital games. These domains each have their own problems, terminology, and design philosophies. Without a common language for describing interactions in shared control, it is difficult for designers working in one domain to share their knowledge with designers working in another. To address this problem, we present a dimension space for shared control, based on a survey of 55 shared control systems from six different problem domains. This design space analysis tool enables designers to classify existing systems, make comparisons between them, identify higher-level design patterns, and imagine solutions to novel problems.
Ean, Richard; Rudie, Karen
A correspondence between control and observation problems in decentralized discrete-event systems Miscellaneous
2022.
Abstract | Links | BibTeX | Tags: electronic engineering, FOS: Electrical engineering, information engineering, Systems and Control (eess.SY)
@misc{https://doi.org/10.48550/arxiv.2204.10792,
title = {A correspondence between control and observation problems in decentralized discrete-event systems},
author = {Richard Ean and Karen Rudie},
url = {https://arxiv.org/abs/2204.10792},
doi = {10.48550/ARXIV.2204.10792},
year = {2022},
date = {2022-04-22},
urldate = {2022-04-22},
publisher = {arXiv},
abstract = { This paper demonstrates a correspondence between control problems (with partial observation) and observation problems in decentralized discrete-event systems, namely, the two classes of problems are Turing equivalent, as one class Turing reduces to the other. The correspondence allows decomposition of a control problem
into a collection of simpler control sub-problems. Since observation problems in their most general formulation
have been shown to be undecidable in previous work, the correspondence produced in this paper demonstrates that
control problems — in their most general form — is also undecidable.},
keywords = {electronic engineering, FOS: Electrical engineering, information engineering, Systems and Control (eess.SY)},
pubstate = {published},
tppubtype = {misc}
}
This paper demonstrates a correspondence between control problems (with partial observation) and observation problems in decentralized discrete-event systems, namely, the two classes of problems are Turing equivalent, as one class Turing reduces to the other. The correspondence allows decomposition of a control problem
into a collection of simpler control sub-problems. Since observation problems in their most general formulation
have been shown to be undecidable in previous work, the correspondence produced in this paper demonstrates that
control problems — in their most general form — is also undecidable.
into a collection of simpler control sub-problems. Since observation problems in their most general formulation
have been shown to be undecidable in previous work, the correspondence produced in this paper demonstrates that
control problems — in their most general form — is also undecidable.
Qiu, R.; Moore, I. D.; Hoult, N. A.
FE Analysis to Simulate Pressure Pipe Liners Spanning Across Perforations Inproceedings
In: Walbridge, Scott; Nik-Bakht, Mazdak; Ng, Kelvin Tsun Wai; Shome, Manas; Alam, M. Shahria; Damatty, Ashraf; Lovegrove, Gordon (Ed.): Proceedings of the Canadian Society of Civil Engineering Annual Conference 2021, pp. 223–234, Springer Singapore, Singapore, 2022, ISBN: 978-981-19-0656-5.
Abstract | Links | BibTeX | Tags:
@inproceedings{10.1007/978-981-19-0656-5_19,
title = {FE Analysis to Simulate Pressure Pipe Liners Spanning Across Perforations},
author = {R. Qiu and I. D. Moore and N. A. Hoult},
editor = {Scott Walbridge and Mazdak Nik-Bakht and Kelvin Tsun Wai Ng and Manas Shome and M. Shahria Alam and Ashraf Damatty and Gordon Lovegrove},
url = {https://link.springer.com/chapter/10.1007/978-981-19-0656-5_19#rightslink},
isbn = {978-981-19-0656-5},
year = {2022},
date = {2022-04-14},
urldate = {2022-04-14},
booktitle = {Proceedings of the Canadian Society of Civil Engineering Annual Conference 2021},
pages = {223--234},
publisher = {Springer Singapore},
address = {Singapore},
abstract = {It has been more than twenty years since the idea of implementing cured-in-place-pipe (CIPP) as a trenchless technology to rehabilitate pressurized water mains was first introduced. The pressurized nature of CIPP repaired water main systems creates technical challenges for any form of laboratory testing. This study explored the development of a finite element model for a CIPP liner system crossing a void in a pipe wall and compared the model to experimental results as a precursor to being able to undertake parametric studies with this model. The choice of specimen length, element selection, and loading increment were explored. The final model was then compared to experimental strain measurements. The model provided strain measurements in the liner at the centre of the void within 3% of the measurement, but was less accurate at the perimeter of the void where the strains were overestimated by the model while the development length of the strains was underestimated.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
It has been more than twenty years since the idea of implementing cured-in-place-pipe (CIPP) as a trenchless technology to rehabilitate pressurized water mains was first introduced. The pressurized nature of CIPP repaired water main systems creates technical challenges for any form of laboratory testing. This study explored the development of a finite element model for a CIPP liner system crossing a void in a pipe wall and compared the model to experimental results as a precursor to being able to undertake parametric studies with this model. The choice of specimen length, element selection, and loading increment were explored. The final model was then compared to experimental strain measurements. The model provided strain measurements in the liner at the centre of the void within 3% of the measurement, but was less accurate at the perimeter of the void where the strains were overestimated by the model while the development length of the strains was underestimated.
Poldon, Jack J.; Bentz, Evan C.; Hoult, Neil A.
Assessing beam shear behavior with distributed longitudinal strains Journal Article
In: Structural Concrete, vol. n/a, no. n/a, 2022.
Abstract | Links | BibTeX | Tags: distributed fiber-optic sensors, large beams, localized behaviour, longitudinal reinforcement, shear, shrinkage
@article{https://doi.org/10.1002/suco.202100730,
title = {Assessing beam shear behavior with distributed longitudinal strains},
author = {Jack J. Poldon and Evan C. Bentz and Neil A. Hoult},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/suco.202100730},
doi = {https://doi.org/10.1002/suco.202100730},
year = {2022},
date = {2022-04-11},
urldate = {2022-04-11},
journal = {Structural Concrete},
volume = {n/a},
number = {n/a},
abstract = {Abstract The demand on the longitudinal reinforcement due to shear has been traditionally based on statics but has rarely been measured. Empirical assumptions needed for the concrete stiffness and the variability of reinforcement strain due to cracking and disturbed regions complicate these measurements, and make the use of conventional strain gauges impractical. This paper investigates the use of distributed measurements from a large reinforced concrete beam test to study the effects of disturbed regions, forces at a crack, shrinkage, and the in situ modulus of elasticity of concrete. The increased demand due to shear on the longitudinal reinforcement was observed, and the Canadian code was shown to provide an accurate upper bound to the measured strain at service loads. The measured longitudinal strains were also used to estimate the average angle of principal compressive stress, and it was observed to decrease with applied load, reaching values as low as 14° near failure.},
keywords = {distributed fiber-optic sensors, large beams, localized behaviour, longitudinal reinforcement, shear, shrinkage},
pubstate = {published},
tppubtype = {article}
}
Abstract The demand on the longitudinal reinforcement due to shear has been traditionally based on statics but has rarely been measured. Empirical assumptions needed for the concrete stiffness and the variability of reinforcement strain due to cracking and disturbed regions complicate these measurements, and make the use of conventional strain gauges impractical. This paper investigates the use of distributed measurements from a large reinforced concrete beam test to study the effects of disturbed regions, forces at a crack, shrinkage, and the in situ modulus of elasticity of concrete. The increased demand due to shear on the longitudinal reinforcement was observed, and the Canadian code was shown to provide an accurate upper bound to the measured strain at service loads. The measured longitudinal strains were also used to estimate the average angle of principal compressive stress, and it was observed to decrease with applied load, reaching values as low as 14° near failure.
Goodwin, Jodie; Woods, Joshua E.; Hoult, Neil A.
Assessing the structural behaviour of glued-laminated timber beams using distributed strain sensing Journal Article
In: Construction and Building Materials, vol. 325, pp. 126844, 2022, ISSN: 0950-0618.
Abstract | Links | BibTeX | Tags: Defect localization, Distributed strain sensing, In-situ elastic modulus measurement, Timber beam tests
@article{GOODWIN2022126844,
title = {Assessing the structural behaviour of glued-laminated timber beams using distributed strain sensing},
author = {Jodie Goodwin and Joshua E. Woods and Neil A. Hoult},
url = {https://www.sciencedirect.com/science/article/pii/S095006182200530X},
doi = {https://doi.org/10.1016/j.conbuildmat.2022.126844},
issn = {0950-0618},
year = {2022},
date = {2022-03-28},
urldate = {2022-03-28},
journal = {Construction and Building Materials},
volume = {325},
pages = {126844},
abstract = {Global efforts to reduce the environmental impact of the construction industry have fueled the use of mass timber as a building material. However, the behaviour of mass timber elements is not fully understood, including the effects of localized anomalies (e.g., knots and joints) on global structural performance. To address this need, this study uses distributed fibre optic sensors (DFOS) to better understand the structural behaviour of mass timber elements through the testing of three glued-laminated (glulam) beams instrumented with DFOS under four-point bending. Results of the study demonstrated that DFOS data can be used to identify anomalies (e.g., knots, cracks, and finger joints) in glulam members, capture local strain distributions, and examine the influence of local effects on global structural response. Furthermore, distributed sensing was also found to be an effective tool to measure the in-situ elastic modulus of the timber material.},
keywords = {Defect localization, Distributed strain sensing, In-situ elastic modulus measurement, Timber beam tests},
pubstate = {published},
tppubtype = {article}
}
Global efforts to reduce the environmental impact of the construction industry have fueled the use of mass timber as a building material. However, the behaviour of mass timber elements is not fully understood, including the effects of localized anomalies (e.g., knots and joints) on global structural performance. To address this need, this study uses distributed fibre optic sensors (DFOS) to better understand the structural behaviour of mass timber elements through the testing of three glued-laminated (glulam) beams instrumented with DFOS under four-point bending. Results of the study demonstrated that DFOS data can be used to identify anomalies (e.g., knots, cracks, and finger joints) in glulam members, capture local strain distributions, and examine the influence of local effects on global structural response. Furthermore, distributed sensing was also found to be an effective tool to measure the in-situ elastic modulus of the timber material.
Pecly, Leonam; Hashtrudi-Zaad, Keyvan
Effect of Voltage Driver on Uncoupled Stability and Fidelity of Kinesthetic Haptic Systems Inproceedings
In: 2022 IEEE Haptics Symposium (HAPTICS), pp. 1-6, 2022.
Abstract | Links | BibTeX | Tags:
@inproceedings{9765611,
title = {Effect of Voltage Driver on Uncoupled Stability and Fidelity of Kinesthetic Haptic Systems},
author = {Leonam Pecly and Keyvan Hashtrudi-Zaad},
url = {https://ieeexplore.ieee.org/abstract/document/9765611
},
doi = {10.1109/HAPTICS52432.2022.9765611},
year = {2022},
date = {2022-03-24},
urldate = {2022-03-24},
booktitle = {2022 IEEE Haptics Symposium (HAPTICS)},
pages = {1-6},
abstract = {The stability and fidelity of haptic simulation systems have been studied for a safer and more faithful haptic interaction with virtual environments. The theoretical analysis, which use a second-order model for the actuator does not match well with the experimental results at high sampling rates. In this work, we propose more accurate models and analyze the uncoupled stability and fidelity for a system actuated by a permanent magnet DC motor and its voltage driver when implementing a linear viscoelastic environment. Through theoretical work and experiments, we show that the stability and fidelity of the system are more accurately represented when a high-order dynamic model is used for the motor and its driver.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The stability and fidelity of haptic simulation systems have been studied for a safer and more faithful haptic interaction with virtual environments. The theoretical analysis, which use a second-order model for the actuator does not match well with the experimental results at high sampling rates. In this work, we propose more accurate models and analyze the uncoupled stability and fidelity for a system actuated by a permanent magnet DC motor and its voltage driver when implementing a linear viscoelastic environment. Through theoretical work and experiments, we show that the stability and fidelity of the system are more accurately represented when a high-order dynamic model is used for the motor and its driver.
Belle, Shakir; Gittens, Curtis; Graham, T. C. Nicholas
A Framework for Creating Non-Player Characters That Make Psychologically-Driven Decisions Inproceedings
In: 2022 IEEE International Conference on Consumer Electronics (ICCE), pp. 1-7, 2022.
Abstract | Links | BibTeX | Tags:
@inproceedings{9730383,
title = {A Framework for Creating Non-Player Characters That Make Psychologically-Driven Decisions},
author = {Shakir Belle and Curtis Gittens and T. C. Nicholas Graham},
url = {https://ieeexplore.ieee.org/abstract/document/9730383
},
doi = {10.1109/ICCE53296.2022.9730383},
year = {2022},
date = {2022-03-15},
urldate = {2022-01-01},
booktitle = {2022 IEEE International Conference on Consumer Electronics (ICCE)},
pages = {1-7},
abstract = {The behavior of non-player characters (NPCs) affects player immersion and, by extension, engagement. A realistic NPC can provide great satisfaction to the completion of the story a game is attempting to tell; but an unrealistic NPC can spoil the entire experience. Numerous systems have been developed to build NPCs with psychological underpinnings. These tools can be based on one, or some combination of emotion, mood, personality, or memory. This article describes a framework that incorporates these psychological components. This framework can be used to create NPCs that exhibit psychologically-driven behaviors and make decisions based on a combination of their emotions, moods, and personalities.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The behavior of non-player characters (NPCs) affects player immersion and, by extension, engagement. A realistic NPC can provide great satisfaction to the completion of the story a game is attempting to tell; but an unrealistic NPC can spoil the entire experience. Numerous systems have been developed to build NPCs with psychological underpinnings. These tools can be based on one, or some combination of emotion, mood, personality, or memory. This article describes a framework that incorporates these psychological components. This framework can be used to create NPCs that exhibit psychologically-driven behaviors and make decisions based on a combination of their emotions, moods, and personalities.
Mokogwu, Chiedu; Hashtrudi-Zaad, Keyvan
Energy-Based Analysis of String Stability in Vehicle Platoons Journal Article
In: IEEE Transactions on Vehicular Technology, pp. 1-1, 2022, ISSN: 1939-9359.
Abstract | Links | BibTeX | Tags:
@article{9733214,
title = {Energy-Based Analysis of String Stability in Vehicle Platoons},
author = {Chiedu Mokogwu and Keyvan Hashtrudi-Zaad},
url = {https://ieeexplore.ieee.org/document/9733214},
doi = {10.1109/TVT.2022.3158624},
issn = {1939-9359},
year = {2022},
date = {2022-03-11},
urldate = {2022-01-01},
journal = {IEEE Transactions on Vehicular Technology},
pages = {1-1},
abstract = {String stability is a vital property of vehicle platoons which ensures that the system states are not amplified downstream along the string of vehicles. In this paper, a passivity-based approach to stability analysis of vehicle platoons is presented. This is motivated by a case study of an adaptive cruise-controlled platoon. We link the string stability of the platoon to the output strict passivity of each subsystem (vehicle) in the string. We show that a sufficient condition for the platoon to be string stable is that the output strict passivity index of each vehicle in the string be lower bounded by one. For a linear time-invariant (LTI) system, this means the Nyquist plot of the transfer function of each subsystem is within the unit circle. Modeling the platoon as a cascade of LTI subsystems, we present a visual tool to assess string stability. By constraining the output strict passivity index of each subsystem in a string to unity through a two-stage control strategy, the condition for string stability is met. The proposed string stability control strategy, accounting for uncertainties and delays in the drive and sensory systems, is validated using numerical simulations.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
String stability is a vital property of vehicle platoons which ensures that the system states are not amplified downstream along the string of vehicles. In this paper, a passivity-based approach to stability analysis of vehicle platoons is presented. This is motivated by a case study of an adaptive cruise-controlled platoon. We link the string stability of the platoon to the output strict passivity of each subsystem (vehicle) in the string. We show that a sufficient condition for the platoon to be string stable is that the output strict passivity index of each vehicle in the string be lower bounded by one. For a linear time-invariant (LTI) system, this means the Nyquist plot of the transfer function of each subsystem is within the unit circle. Modeling the platoon as a cascade of LTI subsystems, we present a visual tool to assess string stability. By constraining the output strict passivity index of each subsystem in a string to unity through a two-stage control strategy, the condition for string stability is met. The proposed string stability control strategy, accounting for uncertainties and delays in the drive and sensory systems, is validated using numerical simulations.
Zand, Mohsen; Damirchi, Haleh; Farley, Andrew; Molahasani, Mahdiyar; Greenspan, Michael; Etemad, Ali
Multiscale Crowd Counting and Localization By Multitask Point Supervision Miscellaneous
2022.
Abstract | Links | BibTeX | Tags:
@misc{zand2022multiscale,
title = {Multiscale Crowd Counting and Localization By Multitask Point Supervision},
author = {Mohsen Zand and Haleh Damirchi and Andrew Farley and Mahdiyar Molahasani and Michael Greenspan and Ali Etemad},
url = {https://arxiv.org/abs/2202.09942},
year = {2022},
date = {2022-02-21},
urldate = {2022-01-01},
abstract = {We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them. In contrast to the relatively more popular density-based methods, our model uses point supervision to allow for crowd locations to be accurately identified. We test our model on two popular crowd counting datasets, ShanghaiTech A and B, and demonstrate that our method achieves strong results on both counting and localization tasks, with MSE measures of 110.7 and 15.0 for crowd counting and AP measures of 0.71 and 0.75 for localization, on ShanghaiTech A and B respectively. Our detailed ablation experiments show the impact of our multiscale approach as well as the effectiveness of the fusion module embedded in our network. },
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We propose a multitask approach for crowd counting and person localization in a unified framework. As the detection and localization tasks are well-correlated and can be jointly tackled, our model benefits from a multitask solution by learning multiscale representations of encoded crowd images, and subsequently fusing them. In contrast to the relatively more popular density-based methods, our model uses point supervision to allow for crowd locations to be accurately identified. We test our model on two popular crowd counting datasets, ShanghaiTech A and B, and demonstrate that our method achieves strong results on both counting and localization tasks, with MSE measures of 110.7 and 15.0 for crowd counting and AP measures of 0.71 and 0.75 for localization, on ShanghaiTech A and B respectively. Our detailed ablation experiments show the impact of our multiscale approach as well as the effectiveness of the fusion module embedded in our network.
Yun, Sangseok; Choi, Wan; Kim, Il-Min
Cooperative Inference of DNNs for Delay-and Memory-Constrained Wireless IoT Systems Journal Article
In: IEEE Internet of Things Journal, pp. 1-1, 2022, ISSN: 2327-4662.
Abstract | Links | BibTeX | Tags:
@article{9716055,
title = {Cooperative Inference of DNNs for Delay-and Memory-Constrained Wireless IoT Systems},
author = {Sangseok Yun and Wan Choi and Il-Min Kim},
url = {https://ieeexplore.ieee.org/abstract/document/9716055},
doi = {10.1109/JIOT.2022.3152359},
issn = {2327-4662},
year = {2022},
date = {2022-02-17},
urldate = {2022-02-17},
journal = {IEEE Internet of Things Journal},
pages = {1-1},
abstract = {This work studies cooperative inference of deep neural networks (DNNs) in which a memory-constrained end-device performs a delay-constrained inference process with an aid of an edge server. Although several works considered the cooperative inference of DNNs in the literature, it was assumed in those works that the memory footprints at end-devices are unlimited, which is in practice not realistic. To address this issue, in this work, a memory-aware cooperative DNN inference is proposed. Specifically, we propose to adopt knowledge distillation to obtain high-performing lightweight DNNs. To minimize the inference delay, we first analyze the end-to-end delay required for processing the proposed cooperative DNN inference, and then we minimize the delay by jointly optimizing the DNN partitioning point and the intermediate data transmission rate. Also, a dynamic DNN selection scheme is developed by fully exploiting the available memory resource in order to maximize the performance of the inference task in terms of inference accuracy. Experimental results demonstrate that the proposed cooperative DNN inference considerably outperforms the comparable schemes while satisfying both the delay constraint and the memory constraint.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This work studies cooperative inference of deep neural networks (DNNs) in which a memory-constrained end-device performs a delay-constrained inference process with an aid of an edge server. Although several works considered the cooperative inference of DNNs in the literature, it was assumed in those works that the memory footprints at end-devices are unlimited, which is in practice not realistic. To address this issue, in this work, a memory-aware cooperative DNN inference is proposed. Specifically, we propose to adopt knowledge distillation to obtain high-performing lightweight DNNs. To minimize the inference delay, we first analyze the end-to-end delay required for processing the proposed cooperative DNN inference, and then we minimize the delay by jointly optimizing the DNN partitioning point and the intermediate data transmission rate. Also, a dynamic DNN selection scheme is developed by fully exploiting the available memory resource in order to maximize the performance of the inference task in terms of inference accuracy. Experimental results demonstrate that the proposed cooperative DNN inference considerably outperforms the comparable schemes while satisfying both the delay constraint and the memory constraint.
Liu, Dongxiao; Huang, Cheng; Ni, Jianbing; Lin, Xiaodong; Shen, Xuemin Sherman
Blockchain-Cloud Transparent Data Marketing: Consortium Management and Fairness Journal Article
In: IEEE Transactions on Computers, pp. 1-1, 2022.
Abstract | Links | BibTeX | Tags:
@article{9712447,
title = {Blockchain-Cloud Transparent Data Marketing: Consortium Management and Fairness},
author = {Dongxiao Liu and Cheng Huang and Jianbing Ni and Xiaodong Lin and Xuemin Sherman Shen},
url = {https://ieeexplore.ieee.org/abstract/document/9712447},
doi = {10.1109/TC.2022.3150724},
year = {2022},
date = {2022-02-14},
urldate = {2022-01-01},
journal = {IEEE Transactions on Computers},
pages = {1-1},
abstract = {Data are generated by Internet of Things (IoT) devices and centralized at a cloud server, that can later be traded with third parties, i.e., data marketing, to enable various data-intensive applications. However, the centralized approach is recently under debate due to the lack of (1) transparent and distributed marketplace management, and (2) marketing fairness for both IoT users (data sellers) and third parties (data buyers). In this paper, we propose a Blockchain-Cloud Transparent Data Marketing (Block-DM) with consortium management and executable fairness. First, we introduce a hybrid data-marketing architecture, where the cloud acts as an efficient data management unit and a consortium blockchain serves as a transparent marketing controller. Under the architecture, consent-based secure data trading and identity privacy for data owners are achieved with the distributed credential issuance and threshold credential openings. Second, with a consortium committee, we design a fair on/off-chain data marketing protocol. By financial incentives and succinct ‘commitments’ of marketing operations, the protocol can achieve the marketing fairness and effective detection of unfair marketing operations. We demonstrate the security of Block-DM with thorough analysis. We conduct extensive experiments with a consortium blockchain network on Hyperledger Fabric to show the feasibility and practicality of Block-DM.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Data are generated by Internet of Things (IoT) devices and centralized at a cloud server, that can later be traded with third parties, i.e., data marketing, to enable various data-intensive applications. However, the centralized approach is recently under debate due to the lack of (1) transparent and distributed marketplace management, and (2) marketing fairness for both IoT users (data sellers) and third parties (data buyers). In this paper, we propose a Blockchain-Cloud Transparent Data Marketing (Block-DM) with consortium management and executable fairness. First, we introduce a hybrid data-marketing architecture, where the cloud acts as an efficient data management unit and a consortium blockchain serves as a transparent marketing controller. Under the architecture, consent-based secure data trading and identity privacy for data owners are achieved with the distributed credential issuance and threshold credential openings. Second, with a consortium committee, we design a fair on/off-chain data marketing protocol. By financial incentives and succinct ‘commitments’ of marketing operations, the protocol can achieve the marketing fairness and effective detection of unfair marketing operations. We demonstrate the security of Block-DM with thorough analysis. We conduct extensive experiments with a consortium blockchain network on Hyperledger Fabric to show the feasibility and practicality of Block-DM.
Zhang, Guangyi; Etemad, Ali
PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition Miscellaneous
2022.
Abstract | Links | BibTeX | Tags:
@misc{zhang2022parse,
title = {PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition},
author = {Guangyi Zhang and Ali Etemad},
url = {https://arxiv.org/pdf/2202.05400.pdf},
year = {2022},
date = {2022-02-11},
urldate = {2022-01-01},
abstract = {We propose PARSE, a novel semi-supervised architecture for learning strong EEG representations for emotion recognition. To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of labeled data, PARSE uses pairwise representation alignment. First, our model performs data augmentation followed by label guessing for large amounts of original and augmented unlabeled data. This is then followed by sharpening of the guessed labels and convex combinations of the unlabeled and labeled data. Finally, representation alignment and emotion classification are performed. To rigorously test our model, we compare PARSE to several state-of-the-art semi-supervised approaches which we implement and adapt for EEG learning. We perform these experiments on four public EEG-based emotion recognition datasets, SEED, SEED-IV, SEED-V and AMIGOS (valence and arousal). The experiments show that our proposed framework achieves the overall best results with varying amounts of limited labeled samples in SEED, SEED-IV and AMIGOS (valence), while approaching the overall best result (reaching the second-best) in SEED-V and AMIGOS (arousal). The analysis shows that our pairwise representation alignment considerably improves the performance by reducing the distribution alignment between unlabeled and labeled data, especially when only 1 sample per class is labeled. },
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We propose PARSE, a novel semi-supervised architecture for learning strong EEG representations for emotion recognition. To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of labeled data, PARSE uses pairwise representation alignment. First, our model performs data augmentation followed by label guessing for large amounts of original and augmented unlabeled data. This is then followed by sharpening of the guessed labels and convex combinations of the unlabeled and labeled data. Finally, representation alignment and emotion classification are performed. To rigorously test our model, we compare PARSE to several state-of-the-art semi-supervised approaches which we implement and adapt for EEG learning. We perform these experiments on four public EEG-based emotion recognition datasets, SEED, SEED-IV, SEED-V and AMIGOS (valence and arousal). The experiments show that our proposed framework achieves the overall best results with varying amounts of limited labeled samples in SEED, SEED-IV and AMIGOS (valence), while approaching the overall best result (reaching the second-best) in SEED-V and AMIGOS (arousal). The analysis shows that our pairwise representation alignment considerably improves the performance by reducing the distribution alignment between unlabeled and labeled data, especially when only 1 sample per class is labeled.
Liu, Dongxiao; Wu, Huaqing; Ni, Jianbing; Shen, Xuemin
Efficient and Anonymous Authentication With Succinct Multi-Subscription Credential in SAGVN Journal Article
In: IEEE Transactions on Intelligent Transportation Systems, pp. 1-11, 2022.
Abstract | Links | BibTeX | Tags:
@article{9707744,
title = {Efficient and Anonymous Authentication With Succinct Multi-Subscription Credential in SAGVN},
author = {Dongxiao Liu and Huaqing Wu and Jianbing Ni and Xuemin Shen},
url = {https://ieeexplore.ieee.org/abstract/document/9707744},
doi = {10.1109/TITS.2022.3147354},
year = {2022},
date = {2022-02-08},
urldate = {2022-01-01},
journal = {IEEE Transactions on Intelligent Transportation Systems},
pages = {1-11},
abstract = {In this paper, we propose an efficient and anonymous authentication protocol with a succinct multi-subscription credential (AnMsc) in Space-air-ground integrated vehicular networks (SAGVN). First, we adopt a subscription-based service model in SAGVN. Specifically, vehicular users (VEs) can subscribe to network services and conduct direct mutual authentication with subscribed access points (APs) to avoid message exchanges with VEs' home network. Early application data can also be transmitted with authentication messages to improve communication efficiency. Second, we carefully tailor the design of the redactable signature and propose an efficient credential management mechanism in SAGVN. Multiple service subscriptions can be embedded into a succinct (constant-size) credential. With the credential, VEs can anonymously access any subscribed AP without revealing other subscription information. Thorough security analysis and comprehensive performance evaluation demonstrate that AnMsc can guarantee key-exchange security, VE anonymity, and service fairness while ensuring credential management and authentication efficiency.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, we propose an efficient and anonymous authentication protocol with a succinct multi-subscription credential (AnMsc) in Space-air-ground integrated vehicular networks (SAGVN). First, we adopt a subscription-based service model in SAGVN. Specifically, vehicular users (VEs) can subscribe to network services and conduct direct mutual authentication with subscribed access points (APs) to avoid message exchanges with VEs' home network. Early application data can also be transmitted with authentication messages to improve communication efficiency. Second, we carefully tailor the design of the redactable signature and propose an efficient credential management mechanism in SAGVN. Multiple service subscriptions can be embedded into a succinct (constant-size) credential. With the credential, VEs can anonymously access any subscribed AP without revealing other subscription information. Thorough security analysis and comprehensive performance evaluation demonstrate that AnMsc can guarantee key-exchange security, VE anonymity, and service fairness while ensuring credential management and authentication efficiency.
Jeong, Cheol; Chun, Chang-Jae; Shin, Won-Yong; Kim, Il-Min
Transport Capacity Optimization for Resource Allocation in Tera-IoT Networks Miscellaneous
2022.
Abstract | Links | BibTeX | Tags:
@misc{jeong2022transport,
title = {Transport Capacity Optimization for Resource Allocation in Tera-IoT Networks},
author = {Cheol Jeong and Chang-Jae Chun and Won-Yong Shin and Il-Min Kim},
url = {https://arxiv.org/abs/2201.12548v1},
year = {2022},
date = {2022-01-29},
urldate = {2022-01-01},
abstract = {We present a new adaptive resource optimization strategy that jointly allocates the subwindow and transmit power in multi-device terahertz (THz) band Internet of Things (Tera-IoT) networks. Unlike the prior studies focusing mostly on maximizing the sum distance, we incorporate both rate and transmission distance into the objective function of our problem formulation with key features of THz bands, including the spreading and molecular absorption losses. More specifically, as a performance metric of Tera-IoT networks, we adopt the transport capacity (TC), which is defined as the sum of the rate-distance products over all users. This metric has been widely adopted in large-scale ad hoc networks, and would also be appropriate for evaluating the performance of various Tera-IoT applications. We then formulate an optimization problem that aims at maximizing the TC. Moreover, motivated by the importance of the transmission distance that is very limited due to the high path loss in THz bands, our optimization problem is extended to the case of allocating the subwindow, transmit power, and transmission distance. We show how to solve our problems via an effective two-stage resource allocation strategy. We demonstrate the superiority of our adaptive solution over benchmark methods via intensive numerical evaluations for various environmental setups of large-scale Tera-IoT networks. },
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We present a new adaptive resource optimization strategy that jointly allocates the subwindow and transmit power in multi-device terahertz (THz) band Internet of Things (Tera-IoT) networks. Unlike the prior studies focusing mostly on maximizing the sum distance, we incorporate both rate and transmission distance into the objective function of our problem formulation with key features of THz bands, including the spreading and molecular absorption losses. More specifically, as a performance metric of Tera-IoT networks, we adopt the transport capacity (TC), which is defined as the sum of the rate-distance products over all users. This metric has been widely adopted in large-scale ad hoc networks, and would also be appropriate for evaluating the performance of various Tera-IoT applications. We then formulate an optimization problem that aims at maximizing the TC. Moreover, motivated by the importance of the transmission distance that is very limited due to the high path loss in THz bands, our optimization problem is extended to the case of allocating the subwindow, transmit power, and transmission distance. We show how to solve our problems via an effective two-stage resource allocation strategy. We demonstrate the superiority of our adaptive solution over benchmark methods via intensive numerical evaluations for various environmental setups of large-scale Tera-IoT networks.
Xue, Liang; Liu, Dongxiao; Ni, Jianbing; Lin, Xiaodong; Shen, Xuemin Sherman
Enabling Regulatory Compliance and Enforcement in Decentralized Anonymous Payment Journal Article
In: IEEE Transactions on Dependable and Secure Computing, pp. 1-1, 2022.
Abstract | Links | BibTeX | Tags:
@article{9693200,
title = {Enabling Regulatory Compliance and Enforcement in Decentralized Anonymous Payment},
author = {Liang Xue and Dongxiao Liu and Jianbing Ni and Xiaodong Lin and Xuemin Sherman Shen},
url = {https://ieeexplore.ieee.org/abstract/document/9693200},
doi = {10.1109/TDSC.2022.3144991},
year = {2022},
date = {2022-01-25},
urldate = {2022-01-25},
journal = {IEEE Transactions on Dependable and Secure Computing},
pages = {1-1},
abstract = {Decentralized anonymous payment (DAP) enables users to directly transfer cryptocurrencies privately without passing through a central authority. Anonymous cryptocurrencies have been proposed to improve the privacy degree of DAP systems, such as Zerocash and Monero. However, the strong degree of privacy may cause new regulatory concerns, i.e., the anonymity of transactions can be used for illegal activities, such as money laundering and terrorist financing. In this paper, we propose a novel DAP scheme that supports regulatory compliance and enforcement. We first introduce regulators into the system, who define regulatory policies for anonymous payment, and the policies are enforced through commitments and non-interactive zero-knowledge proofs for compostable statements. By which, users can prove that transactions are valid and comply with regulations. A tracing mechanism is embedded in the scheme to allow regulators to recover the real identities of users when suspicious transactions are detected. The formal security model and proof are provided to demonstrate that the proposed scheme can achieve desired security properties, and the performance evaluation shows its high efficiency.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Decentralized anonymous payment (DAP) enables users to directly transfer cryptocurrencies privately without passing through a central authority. Anonymous cryptocurrencies have been proposed to improve the privacy degree of DAP systems, such as Zerocash and Monero. However, the strong degree of privacy may cause new regulatory concerns, i.e., the anonymity of transactions can be used for illegal activities, such as money laundering and terrorist financing. In this paper, we propose a novel DAP scheme that supports regulatory compliance and enforcement. We first introduce regulators into the system, who define regulatory policies for anonymous payment, and the policies are enforced through commitments and non-interactive zero-knowledge proofs for compostable statements. By which, users can prove that transactions are valid and comply with regulations. A tracing mechanism is embedded in the scheme to allow regulators to recover the real identities of users when suspicious transactions are detected. The formal security model and proof are provided to demonstrate that the proposed scheme can achieve desired security properties, and the performance evaluation shows its high efficiency.
Xue, Liang; Liu, Dongxiao; Ni, Jianbing; Lin, Xiaodong; Shen, Xuemin Sherman
Enabling Regulatory Compliance and Enforcement in Decentralized Anonymous Payment Journal Article
In: IEEE Transactions on Dependable and Secure Computing, pp. 1-1, 2022.
Abstract | Links | BibTeX | Tags:
@article{9693200b,
title = {Enabling Regulatory Compliance and Enforcement in Decentralized Anonymous Payment},
author = {Liang Xue and Dongxiao Liu and Jianbing Ni and Xiaodong Lin and Xuemin Sherman Shen},
url = {https://ieeexplore.ieee.org/abstract/document/9693200},
doi = {10.1109/TDSC.2022.3144991},
year = {2022},
date = {2022-01-25},
urldate = {2022-01-01},
journal = {IEEE Transactions on Dependable and Secure Computing},
pages = {1-1},
abstract = {Decentralized anonymous payment (DAP) enables users to directly transfer cryptocurrencies privately without passing through a central authority. Anonymous cryptocurrencies have been proposed to improve the privacy degree of DAP systems, such as Zerocash and Monero. However, the strong degree of privacy may cause new regulatory concerns, i.e., the anonymity of transactions can be used for illegal activities, such as money laundering and terrorist financing. In this paper, we propose a novel DAP scheme that supports regulatory compliance and enforcement. We first introduce regulators into the system, who define regulatory policies for anonymous payment, and the policies are enforced through commitments and non-interactive zero-knowledge proofs for compostable statements. By which, users can prove that transactions are valid and comply with regulations. A tracing mechanism is embedded in the scheme to allow regulators to recover the real identities of users when suspicious transactions are detected. The formal security model and proof are provided to demonstrate that the proposed scheme can achieve desired security properties, and the performance evaluation shows its high efficiency.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Decentralized anonymous payment (DAP) enables users to directly transfer cryptocurrencies privately without passing through a central authority. Anonymous cryptocurrencies have been proposed to improve the privacy degree of DAP systems, such as Zerocash and Monero. However, the strong degree of privacy may cause new regulatory concerns, i.e., the anonymity of transactions can be used for illegal activities, such as money laundering and terrorist financing. In this paper, we propose a novel DAP scheme that supports regulatory compliance and enforcement. We first introduce regulators into the system, who define regulatory policies for anonymous payment, and the policies are enforced through commitments and non-interactive zero-knowledge proofs for compostable statements. By which, users can prove that transactions are valid and comply with regulations. A tracing mechanism is embedded in the scheme to allow regulators to recover the real identities of users when suspicious transactions are detected. The formal security model and proof are provided to demonstrate that the proposed scheme can achieve desired security properties, and the performance evaluation shows its high efficiency.
He, Yuanyuan; Ni, Jianbing; Yang, Laurence T.; Wei, Wei; Deng, Xianjun; Zou, Deqing; Ahmed, Syed Hassan
Differentially Private Tripartite Intelligent Matching Against Inference Attacks in Ride-Sharing Services Journal Article
In: IEEE Transactions on Intelligent Transportation Systems, pp. 1-13, 2022.
Abstract | Links | BibTeX | Tags:
@article{9673680,
title = {Differentially Private Tripartite Intelligent Matching Against Inference Attacks in Ride-Sharing Services},
author = {Yuanyuan He and Jianbing Ni and Laurence T. Yang and Wei Wei and Xianjun Deng and Deqing Zou and Syed Hassan Ahmed},
url = {https://ieeexplore.ieee.org/abstract/document/9673680},
doi = {10.1109/TITS.2021.3136386},
year = {2022},
date = {2022-01-06},
urldate = {2022-01-01},
journal = {IEEE Transactions on Intelligent Transportation Systems},
pages = {1-13},
abstract = {In intelligent transportation systems, the key issue of the Ride-Sharing Service (RSS) is to find proper drivers for the passengers by Intelligent Matching (IM) of two or three objects, including the positions of drivers, the travel information of passengers, and the spots where passengers and drivers meet and separate. Unfortunately, the exposure of travel plans of passengers in the IM process due to inference attacks has raised concerns about the privacy violation. To resist the inference attacks, we propose a Differentially Private Tripartite IM (DPTIM) protocol for RSS. DPTIM is based on the tripartite IM process, which intelligently finds the suitable threshold to filter out the matched objects with satisfaction scores below the threshold, so as to provide the high average satisfaction score of matched passengers. Compared to existing relevant mechanisms, DPTIM is distinguished by the feature that it leverages the inference error and differential privacy techniques to prevent the prior-information-based inference attacks and constrain the posterior information leakage, while providing satisfactory matching results. Furthermore, DPTIM meets the personalized demand of location privacy by using the passenger-specific tolerance estimation on inference errors and the personalized privacy budget. Finally, we implement DPTIM on real-world datasets, and demonstrate the satisfactory performance of DPTIM in terms of the average satisfaction score of passengers, the anti-inference-attack capability, and the passenger-specific privacy requirement.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In intelligent transportation systems, the key issue of the Ride-Sharing Service (RSS) is to find proper drivers for the passengers by Intelligent Matching (IM) of two or three objects, including the positions of drivers, the travel information of passengers, and the spots where passengers and drivers meet and separate. Unfortunately, the exposure of travel plans of passengers in the IM process due to inference attacks has raised concerns about the privacy violation. To resist the inference attacks, we propose a Differentially Private Tripartite IM (DPTIM) protocol for RSS. DPTIM is based on the tripartite IM process, which intelligently finds the suitable threshold to filter out the matched objects with satisfaction scores below the threshold, so as to provide the high average satisfaction score of matched passengers. Compared to existing relevant mechanisms, DPTIM is distinguished by the feature that it leverages the inference error and differential privacy techniques to prevent the prior-information-based inference attacks and constrain the posterior information leakage, while providing satisfactory matching results. Furthermore, DPTIM meets the personalized demand of location privacy by using the passenger-specific tolerance estimation on inference errors and the personalized privacy budget. Finally, we implement DPTIM on real-world datasets, and demonstrate the satisfactory performance of DPTIM in terms of the average satisfaction score of passengers, the anti-inference-attack capability, and the passenger-specific privacy requirement.
Adebola, Titilope O.; Moore, Ian D.; Hoult, Neil A.
Use of optical fibers to investigate the performance of pressure pipe liners spanning across a ring fracture Journal Article
In: Tunnelling and Underground Space Technology, vol. 119, pp. 104229, 2022, ISSN: 0886-7798.
Abstract | Links | BibTeX | Tags: Additively printed model, Assembled lining structures, Optical measurement, Phase shifting method, Pipe rehabilitation, Quantification
@article{ADEBOLA2022104229,
title = {Use of optical fibers to investigate the performance of pressure pipe liners spanning across a ring fracture},
author = {Titilope O. Adebola and Ian D. Moore and Neil A. Hoult},
url = {https://www.sciencedirect.com/science/article/pii/S088677982100420X},
doi = {https://doi.org/10.1016/j.tust.2021.104229},
issn = {0886-7798},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Tunnelling and Underground Space Technology},
volume = {119},
pages = {104229},
abstract = {Cured in place pipe liners have been used in the rehabilitation of cast iron water pipes for over twenty years. Previous research has established that the liner’s performance may be controlled by local strain concentrations that develop where the liner spans across a ring fracture in a pipe subjected to differential ground movement. This paper reports on the application of distributed strain sensing using optical fibers to quantify the longitudinal strain distribution along the inside surface of a polymer composite liner. It was confirmed that the location of maximum opening in the fracture is the critical location where the liner could experience failure. The measurements quantify how debonding (due to slip and separation between the liner and the host pipe) decreases the maximum strain in a liner and how the extent of debonding is impacted by internal pressure and the alignment of the two pipe segments across the fracture. At rotation angles of approximately 0.3°, longitudinal strains of up to 17,000 microstrain were observed in a liner subjected to internal pressure of 600 kPa. Findings from this investigation confirm that the behavior of CIPP liners installed in pressure pipes containing pre-existing ring fractures, and subsequently subjected to angular movements, should be considered in design standards.},
keywords = {Additively printed model, Assembled lining structures, Optical measurement, Phase shifting method, Pipe rehabilitation, Quantification},
pubstate = {published},
tppubtype = {article}
}
Cured in place pipe liners have been used in the rehabilitation of cast iron water pipes for over twenty years. Previous research has established that the liner’s performance may be controlled by local strain concentrations that develop where the liner spans across a ring fracture in a pipe subjected to differential ground movement. This paper reports on the application of distributed strain sensing using optical fibers to quantify the longitudinal strain distribution along the inside surface of a polymer composite liner. It was confirmed that the location of maximum opening in the fracture is the critical location where the liner could experience failure. The measurements quantify how debonding (due to slip and separation between the liner and the host pipe) decreases the maximum strain in a liner and how the extent of debonding is impacted by internal pressure and the alignment of the two pipe segments across the fracture. At rotation angles of approximately 0.3°, longitudinal strains of up to 17,000 microstrain were observed in a liner subjected to internal pressure of 600 kPa. Findings from this investigation confirm that the behavior of CIPP liners installed in pressure pipes containing pre-existing ring fractures, and subsequently subjected to angular movements, should be considered in design standards.
Treitz, Josh; Lan, Haitao; Moore, Ian D.; Hoult, Neil A.
Testing and analysis of PVC liners under simulated grouting pressure Journal Article
In: Engineering Structures, vol. 250, pp. 113496, 2022, ISSN: 0141-0296.
Abstract | Links | BibTeX | Tags: Buckling, Deformation, Moment, Pipe, Pressure, Strain, Thrust
@article{TREITZ2022113496,
title = {Testing and analysis of PVC liners under simulated grouting pressure},
author = {Josh Treitz and Haitao Lan and Ian D. Moore and Neil A. Hoult},
url = {https://www.sciencedirect.com/science/article/pii/S0141029621015996},
doi = {https://doi.org/10.1016/j.engstruct.2021.113496},
issn = {0141-0296},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Engineering Structures},
volume = {250},
pages = {113496},
abstract = {Sliplining is often selected for rehabilitation of deteriorated culverts and drainage structures, and involves placing a liner pipe within the deteriorated host pipe and filling the gap between the two with grout. However, currently the design of these liners to resist buckling during the critical grouting phase has not been evaluated experimentally. In addition to obtaining test data to evaluate existing buckling models, the tests permit assessment of the influence of buoyancy on liner stability and the influence of the size of the gap between the liner and host pipe. Therefore, this paper presents an experimental study undertaken after adapting an existing test cell. Two tests were conducted, one on a liner within the host pipe with their axes oriented vertically (so not affected by buoyancy) and another where pipe and liner axes were oriented horizontally and so subject to buoyancy. The liners were instrumented with distributed strain and displacement sensors, and subjected to simulated external grouting pressure using water pressure applied to a rubber bladder. Both liners first buckled under hydrostatic pressure and had greatly reduced incremental flexural stiffness until liner deformations brought it into contact with the test cell, at which point the liners took additional pressures until finally failing due to nonlinear buckling. Analytical and numerical estimates of the thrust forces in the liner and the hydrostatic buckling pressure were within 10% of the experimental values of maximum pressure on the liner (at the invert). However, it is not conservative to estimate the critical buckling pressure (the maximum or peak pressure before the pipe fails) using the existing buckling model. For the current tests, the hydrostatic and critical buckling pressures are almost independent of the distance between the axes of the liner and host pipe (i.e. where the contractor positions the liner within the post pipe)},
keywords = {Buckling, Deformation, Moment, Pipe, Pressure, Strain, Thrust},
pubstate = {published},
tppubtype = {article}
}
Sliplining is often selected for rehabilitation of deteriorated culverts and drainage structures, and involves placing a liner pipe within the deteriorated host pipe and filling the gap between the two with grout. However, currently the design of these liners to resist buckling during the critical grouting phase has not been evaluated experimentally. In addition to obtaining test data to evaluate existing buckling models, the tests permit assessment of the influence of buoyancy on liner stability and the influence of the size of the gap between the liner and host pipe. Therefore, this paper presents an experimental study undertaken after adapting an existing test cell. Two tests were conducted, one on a liner within the host pipe with their axes oriented vertically (so not affected by buoyancy) and another where pipe and liner axes were oriented horizontally and so subject to buoyancy. The liners were instrumented with distributed strain and displacement sensors, and subjected to simulated external grouting pressure using water pressure applied to a rubber bladder. Both liners first buckled under hydrostatic pressure and had greatly reduced incremental flexural stiffness until liner deformations brought it into contact with the test cell, at which point the liners took additional pressures until finally failing due to nonlinear buckling. Analytical and numerical estimates of the thrust forces in the liner and the hydrostatic buckling pressure were within 10% of the experimental values of maximum pressure on the liner (at the invert). However, it is not conservative to estimate the critical buckling pressure (the maximum or peak pressure before the pipe fails) using the existing buckling model. For the current tests, the hydrostatic and critical buckling pressures are almost independent of the distance between the axes of the liner and host pipe (i.e. where the contractor positions the liner within the post pipe)
Barker, Christian; Woods, Joshua; Hoult, Neil A.; Le, Hoat; Tolikonda, Vamsi
Pre- and Post-Rehabilitation Monitoring of a Steel Railway Bridge with Distributed and Discrete Sensors Journal Article
In: Journal of Bridge Engineering, vol. 27, no. 4, pp. 05022002, 2022.
Abstract | Links | BibTeX | Tags:
@article{doi:10.1061/(ASCE)BE.1943-5592.0001847,
title = {Pre- and Post-Rehabilitation Monitoring of a Steel Railway Bridge with Distributed and Discrete Sensors},
author = {Christian Barker and Joshua Woods and Neil A. Hoult and Hoat Le and Vamsi Tolikonda},
url = {https://ascelibrary.org/doi/abs/10.1061/%28ASCE%29BE.1943-5592.0001847},
doi = {10.1061/(ASCE)BE.1943-5592.0001847},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Journal of Bridge Engineering},
volume = {27},
number = {4},
pages = {05022002},
abstract = {North America’s growing demand for rail transportation capacity, in terms of both train weight and length, has raised concerns regarding the performance of older bridges and has presented the need for improved assessment technologies. A monitoring system composed of discrete and distributed strain sensors combined with a finite-element analysis (FEA) may be able to provide critical insights for assessment. One specific area of concern in older railway bridges is their ability to resist longitudinal forces generated by the braking and acceleration of modern diesel-electric engines. To investigate this, two experimental campaigns were undertaken on a steel railway bridge in North Bay, Canada, using data from sensors and an FEA to study longitudinal force transfer and the impact of rehabilitation with traction bracing. Data from both pre- and post-rehabilitation tests indicated that most axial force in the rail is transferred along its length to a reaction point off the bridge, rather than being transferred immediately into the superstructure. Furthermore, data from the post-rehabilitation tests suggested that the added traction bracing did not significantly affect bridge behavior. Overall, the results demonstrate how field monitoring using conventional and fiber optic strain sensors can be used to assess force transfer between the rail and a superstructure, which could be used as a first step in assessing whether a bridge requires longitudinal strengthening prior to a more comprehensive assessment.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
North America’s growing demand for rail transportation capacity, in terms of both train weight and length, has raised concerns regarding the performance of older bridges and has presented the need for improved assessment technologies. A monitoring system composed of discrete and distributed strain sensors combined with a finite-element analysis (FEA) may be able to provide critical insights for assessment. One specific area of concern in older railway bridges is their ability to resist longitudinal forces generated by the braking and acceleration of modern diesel-electric engines. To investigate this, two experimental campaigns were undertaken on a steel railway bridge in North Bay, Canada, using data from sensors and an FEA to study longitudinal force transfer and the impact of rehabilitation with traction bracing. Data from both pre- and post-rehabilitation tests indicated that most axial force in the rail is transferred along its length to a reaction point off the bridge, rather than being transferred immediately into the superstructure. Furthermore, data from the post-rehabilitation tests suggested that the added traction bracing did not significantly affect bridge behavior. Overall, the results demonstrate how field monitoring using conventional and fiber optic strain sensors can be used to assess force transfer between the rail and a superstructure, which could be used as a first step in assessing whether a bridge requires longitudinal strengthening prior to a more comprehensive assessment.
2021
He, Miao; Ni, Jianbing; He, Yuanyuan; Zhang, Ning
Low-Complexity Phased-Array Physical Layer Security in Millimeter-Wave Communication for Cybertwin-Driven V2X Applications Journal Article
In: IEEE Transactions on Vehicular Technology, pp. 1-1, 2021.
Abstract | Links | BibTeX | Tags:
@article{9664372,
title = {Low-Complexity Phased-Array Physical Layer Security in Millimeter-Wave Communication for Cybertwin-Driven V2X Applications},
author = {Miao He and Jianbing Ni and Yuanyuan He and Ning Zhang},
url = {https://ieeexplore.ieee.org/abstract/document/9664372},
doi = {10.1109/TVT.2021.3138702},
year = {2021},
date = {2021-12-28},
urldate = {2021-01-01},
journal = {IEEE Transactions on Vehicular Technology},
pages = {1-1},
abstract = {Cybertwin is a promising networking paradigm that supports complex wireless interconnectivity and enhances reliable communications by using edge capability in different applications. However, the computation-heavy phased-array weight vector generation is a significant barrier for the implementation of physical layer security (PLS) for millimeter-wave (mmWave) in cybertwin-driven resource-restricted scenarios, like vehicle-to-everything (V2X) applications. In this paper, we propose a low-complexity phased-array PLS scheme in mmWave wireless communications for cybertwin-driven V2X applications. The computational complexity is much reduced in a cost-effective way, where the transmitting phased-array weight vectors are updated at the symbol rate by randomly swapping the pre-calculated initial weight vector elements instead of directly calculating a new weight vector. Performance evaluation shows the proposed scheme possesses a lower computational complexity than the compared PLS schemes. The simulation demonstrates that the constellations are scrambled at undesired directions, while the constellation at target direction remains clear and constant. Thus, the communication secrecy is preserved for the receiver at the target direction in cybertwin-driven vehicular communications. Finally, we demonstrate that the proposed scheme achieves good security performances in terms of symbol error rate (SER) and secrecy outage probability.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cybertwin is a promising networking paradigm that supports complex wireless interconnectivity and enhances reliable communications by using edge capability in different applications. However, the computation-heavy phased-array weight vector generation is a significant barrier for the implementation of physical layer security (PLS) for millimeter-wave (mmWave) in cybertwin-driven resource-restricted scenarios, like vehicle-to-everything (V2X) applications. In this paper, we propose a low-complexity phased-array PLS scheme in mmWave wireless communications for cybertwin-driven V2X applications. The computational complexity is much reduced in a cost-effective way, where the transmitting phased-array weight vectors are updated at the symbol rate by randomly swapping the pre-calculated initial weight vector elements instead of directly calculating a new weight vector. Performance evaluation shows the proposed scheme possesses a lower computational complexity than the compared PLS schemes. The simulation demonstrates that the constellations are scrambled at undesired directions, while the constellation at target direction remains clear and constant. Thus, the communication secrecy is preserved for the receiver at the target direction in cybertwin-driven vehicular communications. Finally, we demonstrate that the proposed scheme achieves good security performances in terms of symbol error rate (SER) and secrecy outage probability.
Kang, Jae-Mo; Yun, Sangseok; Kim, Il-Min; Jung, Heechul
MSE-Based Joint Transceiver and Passive Beamforming Designs for Intelligent Reflecting Surface-Aided MIMO Systems Journal Article
In: IEEE Wireless Communications Letters, pp. 1-1, 2021.
Abstract | Links | BibTeX | Tags:
@article{9663533,
title = {MSE-Based Joint Transceiver and Passive Beamforming Designs for Intelligent Reflecting Surface-Aided MIMO Systems},
author = {Jae-Mo Kang and Sangseok Yun and Il-Min Kim and Heechul Jung},
url = {https://ieeexplore.ieee.org/abstract/document/9663533},
doi = {10.1109/LWC.2021.3139024},
year = {2021},
date = {2021-12-28},
urldate = {2021-01-01},
journal = {IEEE Wireless Communications Letters},
pages = {1-1},
abstract = {In this letter, novel schemes for joint transceiver and passive beamforming design in an intelligent reflecting surface (IRS)-aided multiple-input multiple-output (MIMO) system are developed. Specifically, active beamformer at the BS, passive beamfomer at the IRS, and receive filter at the user are jointly optimized based on two realistic mean square error (MSE) criteria for signal estimation: (i) total MSE minimization and (ii) maximum per-stream MSE minimization. To tackle these challenging nonconvex problems effectively, two efficient iterative algorithms are proposed for both MSE criteria, in which the receive filter, active and passive beamformers are designed in alternating manner through solving the corresponding convex subproblems, respectively. Numerical results demonstrate better performance of the proposed schemes compared to baseline schemes in terms of the MSE and error rate performance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this letter, novel schemes for joint transceiver and passive beamforming design in an intelligent reflecting surface (IRS)-aided multiple-input multiple-output (MIMO) system are developed. Specifically, active beamformer at the BS, passive beamfomer at the IRS, and receive filter at the user are jointly optimized based on two realistic mean square error (MSE) criteria for signal estimation: (i) total MSE minimization and (ii) maximum per-stream MSE minimization. To tackle these challenging nonconvex problems effectively, two efficient iterative algorithms are proposed for both MSE criteria, in which the receive filter, active and passive beamformers are designed in alternating manner through solving the corresponding convex subproblems, respectively. Numerical results demonstrate better performance of the proposed schemes compared to baseline schemes in terms of the MSE and error rate performance.
He, Miao; Li, Xiangman; Ni, Jianbing; Yang, Haomiao
Balancing Efficiency and Security for Network Access Control in Space-Air-Ground Integrated Networks Inproceedings
In: 2021 18th International Conference on Privacy, Security and Trust (PST), pp. 1-10, 2021.
Abstract | Links | BibTeX | Tags:
@inproceedings{9647772,
title = {Balancing Efficiency and Security for Network Access Control in Space-Air-Ground Integrated Networks},
author = {Miao He and Xiangman Li and Jianbing Ni and Haomiao Yang},
url = {https://ieeexplore.ieee.org/abstract/document/9647772},
doi = {10.1109/PST52912.2021.9647772},
year = {2021},
date = {2021-12-21},
urldate = {2021-12-21},
booktitle = {2021 18th International Conference on Privacy, Security and Trust (PST)},
pages = {1-10},
abstract = {In this paper, we investigate the efficiency of network access control with the co-existence of multiple network operators and propose an efficient and secure network access control architecture (ESNAC) that offers fast identity authentication and access authorization in space-air-ground integrated networks. The major challenge lies in enabling multiple independent network operators to authorize and authenticate mobile users for network access in a secure and efficient way, even they are not mutually trusted. To address this challenge, we introduce an aggregate anonymous credential mechanism to enable a mobile user to present network access authorization of a group of network operators based on the consolidated anonymous credential that is aggregated from the partial anonymous credentials of the network operators. In addition, the efficient authentication of packet delivery is provided based on a sequential aggregate signature that allows each network operator to sign network packets for authentication and sequentially aggregate signatures for communication efficiency. Finally, we discuss the desired security properties of ESNAC and demonstrate its computational and communication efficiency by comparing with the conventional scheme without aggregation.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we investigate the efficiency of network access control with the co-existence of multiple network operators and propose an efficient and secure network access control architecture (ESNAC) that offers fast identity authentication and access authorization in space-air-ground integrated networks. The major challenge lies in enabling multiple independent network operators to authorize and authenticate mobile users for network access in a secure and efficient way, even they are not mutually trusted. To address this challenge, we introduce an aggregate anonymous credential mechanism to enable a mobile user to present network access authorization of a group of network operators based on the consolidated anonymous credential that is aggregated from the partial anonymous credentials of the network operators. In addition, the efficient authentication of packet delivery is provided based on a sequential aggregate signature that allows each network operator to sign network packets for authentication and sequentially aggregate signatures for communication efficiency. Finally, we discuss the desired security properties of ESNAC and demonstrate its computational and communication efficiency by comparing with the conventional scheme without aggregation.
Mahmud, Zunayed; Hungler, Paul; Etemad, Ali
Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning Miscellaneous
2021.
Abstract | Links | BibTeX | Tags:
@misc{mahmud2021gaze,
title = {Gaze Estimation with Eye Region Segmentation and Self-Supervised Multistream Learning},
author = {Zunayed Mahmud and Paul Hungler and Ali Etemad},
url = {https://arxiv.org/pdf/2112.07878.pdf},
year = {2021},
date = {2021-12-15},
urldate = {2021-01-01},
abstract = {We present a novel multistream network that learns robust eye representations for gaze estimation. We first create a synthetic dataset containing eye region masks detailing the visible eyeball and iris using a simulator. We then perform eye region segmentation with a U-Net type model which we later use to generate eye region masks for real-world eye images. Next, we pretrain an eye image encoder in the real domain with self-supervised contrastive learning to learn generalized eye representations. Finally, this pretrained eye encoder, along with two additional encoders for visible eyeball region and iris, are used in parallel in our multistream framework to extract salient features for gaze estimation from real-world images. We demonstrate the performance of our method on the EYEDIAP dataset in two different evaluation settings and achieve state-of-the-art results, outperforming all the existing benchmarks on this dataset. We also conduct additional experiments to validate the robustness of our self-supervised network with respect to different amounts of labeled data used for training. },
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We present a novel multistream network that learns robust eye representations for gaze estimation. We first create a synthetic dataset containing eye region masks detailing the visible eyeball and iris using a simulator. We then perform eye region segmentation with a U-Net type model which we later use to generate eye region masks for real-world eye images. Next, we pretrain an eye image encoder in the real domain with self-supervised contrastive learning to learn generalized eye representations. Finally, this pretrained eye encoder, along with two additional encoders for visible eyeball region and iris, are used in parallel in our multistream framework to extract salient features for gaze estimation from real-world images. We demonstrate the performance of our method on the EYEDIAP dataset in two different evaluation settings and achieve state-of-the-art results, outperforming all the existing benchmarks on this dataset. We also conduct additional experiments to validate the robustness of our self-supervised network with respect to different amounts of labeled data used for training.
Ni, Jianbing; Au, Man Ho; Wu, Wei; Luo, Xiapu; Lin, Xiaodong; Shen, Xuemin Sherman
Dual-Anonymous Off-Line Electronic Cash for Mobile Payment Journal Article
In: IEEE Transactions on Mobile Computing, pp. 1-1, 2021.
Abstract | Links | BibTeX | Tags:
@article{9650670,
title = {Dual-Anonymous Off-Line Electronic Cash for Mobile Payment},
author = {Jianbing Ni and Man Ho Au and Wei Wu and Xiapu Luo and Xiaodong Lin and Xuemin Sherman Shen},
url = {https://ieeexplore.ieee.org/abstract/document/9650670},
doi = {10.1109/TMC.2021.3135301},
year = {2021},
date = {2021-12-14},
urldate = {2021-01-01},
journal = {IEEE Transactions on Mobile Computing},
pages = {1-1},
abstract = {Mobile devices have become near-ubiquitous tools in our daily lives. Following this trend, mobile commence is developed rapidly which in turns stimulates interests in mobile payment. Some prominent examples include Google's Wallet, WeChat Pay, and Apple Pay. Most of these technologies, however, are designed for users to be able to pay conveniently to the business. In other words, they are designed with the business to user model in mind. Besides, an active network connection with an external payment server is required either from payer or payee during transaction. Our work intends to supplement existing solutions, which allows payment to be made in an off-line and dual-anonymous manner. In doing so, a dual-anonymous off-line electronic cash scheme is proposed by utilizing BBS+ signature. The feature of our scheme is dual-anonymous payment, which means that both the payer and the payee in any transaction cannot be identified even all other users and the payment server collude. Through security proof and performance analysis, we also demonstrate that the security of the proposed scheme can be reduced to standard assumptions and it is suitable for applications in mobile commerce.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mobile devices have become near-ubiquitous tools in our daily lives. Following this trend, mobile commence is developed rapidly which in turns stimulates interests in mobile payment. Some prominent examples include Google's Wallet, WeChat Pay, and Apple Pay. Most of these technologies, however, are designed for users to be able to pay conveniently to the business. In other words, they are designed with the business to user model in mind. Besides, an active network connection with an external payment server is required either from payer or payee during transaction. Our work intends to supplement existing solutions, which allows payment to be made in an off-line and dual-anonymous manner. In doing so, a dual-anonymous off-line electronic cash scheme is proposed by utilizing BBS+ signature. The feature of our scheme is dual-anonymous payment, which means that both the payer and the payee in any transaction cannot be identified even all other users and the payment server collude. Through security proof and performance analysis, we also demonstrate that the security of the proposed scheme can be reduced to standard assumptions and it is suitable for applications in mobile commerce.
Pan, Yanghe; Ni, Jianbing; Su, Zhou
FL-PATE: Differentially Private Federated Learning with Knowledge Transfer Inproceedings
In: 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1-6, 2021.
Abstract | Links | BibTeX | Tags:
@inproceedings{9685079,
title = {FL-PATE: Differentially Private Federated Learning with Knowledge Transfer},
author = {Yanghe Pan and Jianbing Ni and Zhou Su},
url = {https://ieeexplore.ieee.org/abstract/document/9685079},
doi = {10.1109/GLOBECOM46510.2021.9685079},
year = {2021},
date = {2021-12-11},
urldate = {2021-01-01},
booktitle = {2021 IEEE Global Communications Conference (GLOBECOM)},
pages = {1-6},
abstract = {Federated learning provides a solution for data privacy protection, while enabling training over the local data samples, without exchanging them. However, it is far from practical and secure because data privacy is still vulnerable due to the well-studied attacks, e.g., membership inference attacks and model inversion attacks. In this paper, to further prevent data leakage against these attacks, we propose FL-PATE, a differentially private federated learning framework with knowledge transfer. Specifically, participants with sensitive data are grouped to train teacher models under federated learning settings, and the knowledge of teacher models is transferred to a publicly accessible student model for prediction via aggregating teacher models' outputs of public datasets. A modified client-level differential privacy mechanism is used to guarantee each participant's data privacy during the corresponding teacher model's training process. The proposed framework preserves participant's privacy against membership inference attacks and the differential privacy cost is fixed. The privacy analysis and experiments demonstrate that trained teacher and student models have an excellent performance in accuracy and robustness theoretically and empirically.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Federated learning provides a solution for data privacy protection, while enabling training over the local data samples, without exchanging them. However, it is far from practical and secure because data privacy is still vulnerable due to the well-studied attacks, e.g., membership inference attacks and model inversion attacks. In this paper, to further prevent data leakage against these attacks, we propose FL-PATE, a differentially private federated learning framework with knowledge transfer. Specifically, participants with sensitive data are grouped to train teacher models under federated learning settings, and the knowledge of teacher models is transferred to a publicly accessible student model for prediction via aggregating teacher models' outputs of public datasets. A modified client-level differential privacy mechanism is used to guarantee each participant's data privacy during the corresponding teacher model's training process. The proposed framework preserves participant's privacy against membership inference attacks and the differential privacy cost is fixed. The privacy analysis and experiments demonstrate that trained teacher and student models have an excellent performance in accuracy and robustness theoretically and empirically.
Patricia N. Pena Michel R. C. Alves, Karen Rudie
Discrete-event systems subject to unknown sensor attacks Bachelor Thesis
2021.
Abstract | Links | BibTeX | Tags:
@bachelorthesis{Alves2021,
title = {Discrete-event systems subject to unknown sensor attacks},
author = {Michel R. C. Alves, Patricia N. Pena, Karen Rudie},
url = {https://link.springer.com/article/10.1007/s10626-021-00351-3#citeas},
doi = {10.1007/s10626-021-00351-3},
year = {2021},
date = {2021-12-10},
urldate = {2021-12-10},
journal = {Discrete Event Dynamic Systems},
abstract = {This work is set in the context of supervisory control of discrete-event systems under partial observation. Attackers that are able to insert or erase occurrences of particular output symbols can tamper with the supervisor’s observation and by doing so, can lead the controlled system to undesirable states. We consider a scenario with multiple attackers, each one being an element of a set, called the attack set. We also assume that only one of the attackers within an attack set is acting, although we don’t know which one. According to previous results in the literature, a supervisor that enforces a given legal language, regardless of which attacker is acting, can be designed if the legal language is controllable and satisfies a property called P-observability for an attack set. The latter is an extended notion of observability and is related with the supervisor’s ability to always distinguish between outputs that require different control actions, even if the outputs were attacked. We present a new approach for checking if a given language is P-observable for an attack set, by first introducing a visual representation as well as some definitions that capture the attack’s effect. Additionally, we present two algorithms that together allow us to verify if a given language is P-observable for an attack set, when it is represented as an automaton.},
keywords = {},
pubstate = {published},
tppubtype = {bachelorthesis}
}
This work is set in the context of supervisory control of discrete-event systems under partial observation. Attackers that are able to insert or erase occurrences of particular output symbols can tamper with the supervisor’s observation and by doing so, can lead the controlled system to undesirable states. We consider a scenario with multiple attackers, each one being an element of a set, called the attack set. We also assume that only one of the attackers within an attack set is acting, although we don’t know which one. According to previous results in the literature, a supervisor that enforces a given legal language, regardless of which attacker is acting, can be designed if the legal language is controllable and satisfies a property called P-observability for an attack set. The latter is an extended notion of observability and is related with the supervisor’s ability to always distinguish between outputs that require different control actions, even if the outputs were attacked. We present a new approach for checking if a given language is P-observable for an attack set, by first introducing a visual representation as well as some definitions that capture the attack’s effect. Additionally, we present two algorithms that together allow us to verify if a given language is P-observable for an attack set, when it is represented as an automaton.
Kolahdouzi, Mojtaba; Sepas-Moghaddam, Alireza; Etemad, Ali
Face Trees for Expression Recognition Miscellaneous
2021.
@misc{kolahdouzi2021face,
title = {Face Trees for Expression Recognition},
author = {Mojtaba Kolahdouzi and Alireza Sepas-Moghaddam and Ali Etemad},
url = {https://arxiv.org/pdf/2112.02487.pdf},
year = {2021},
date = {2021-12-05},
urldate = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Wang, Yuntao; Su, Zhou; Ni, Jianbing; Zhang, Ning; Shen, Xuemin
Blockchain-Empowered Space-Air-Ground Integrated Networks: Opportunities, Challenges, and Solutions Journal Article
In: IEEE Communications Surveys Tutorials, pp. 1-1, 2021.
@article{9631953,
title = {Blockchain-Empowered Space-Air-Ground Integrated Networks: Opportunities, Challenges, and Solutions},
author = {Yuntao Wang and Zhou Su and Jianbing Ni and Ning Zhang and Xuemin Shen},
doi = {10.1109/COMST.2021.3131711},
year = {2021},
date = {2021-12-01},
urldate = {2021-01-01},
journal = {IEEE Communications Surveys Tutorials},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Edraki, Amin; Chan, Wai-Yip; Jensen, Jesper; Fogerty, Daniel
Speech Intelligibility Prediction Using Spectro-Temporal Modulation Analysis Journal Article
In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 210-225, 2021.
@article{9269417,
title = {Speech Intelligibility Prediction Using Spectro-Temporal Modulation Analysis},
author = {Amin Edraki and Wai-Yip Chan and Jesper Jensen and Daniel Fogerty},
doi = {10.1109/TASLP.2020.3039929},
year = {2021},
date = {2021-11-24},
journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
volume = {29},
pages = {210-225},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Siahkouhi, Mohammad; Razaqpur, Ghani; Hoult, N. A.; Baghban, Mohammad Hajmohammadian; Jing, Guoqing
Utilization of carbon nanotubes (CNTs) in concrete for structural health monitoring (SHM) purposes: A review Journal Article
In: Construction and Building Materials, vol. 309, pp. 125137, 2021, ISSN: 0950-0618.
Abstract | Links | BibTeX | Tags: Carbon Nanotube, Cement composite, Concrete, Infrastructure, Self-healing, Self-sensing property, Structural health monitoring
@article{SIAHKOUHI2021125137,
title = {Utilization of carbon nanotubes (CNTs) in concrete for structural health monitoring (SHM) purposes: A review},
author = {Mohammad Siahkouhi and Ghani Razaqpur and N. A. Hoult and Mohammad Hajmohammadian Baghban and Guoqing Jing},
url = {https://www.sciencedirect.com/science/article/pii/S0950061821028816},
doi = {https://doi.org/10.1016/j.conbuildmat.2021.125137},
issn = {0950-0618},
year = {2021},
date = {2021-11-21},
urldate = {2021-01-01},
journal = {Construction and Building Materials},
volume = {309},
pages = {125137},
abstract = {Carbon nanotubes (CNT) as a functional filler can increase the electrical conductivity property of concrete and thus provide intrinsic self-sensing properties with no need for external sensors to monitor the behavior of concrete infrastructure and structures containing CNT. CNT-cement composites also improve mechanical strength and have higher energy absorption capacity. The sensitivity of their electrical conductivity to external physical parameters, such as strain, stress, load, temperature, displacement, and pressure, makes them suitable for structural health monitoring (SHM) applications. This paper presents a comprehensive review of the CNT properties, fabrication process, composition, and sensing characteristics as well as challenges for applying CNT concrete as part of a self-sensing structure. Furthermore, the self-healing property of CNT, as an integral feature of future smart concrete infrastructure is discussed.},
keywords = {Carbon Nanotube, Cement composite, Concrete, Infrastructure, Self-healing, Self-sensing property, Structural health monitoring},
pubstate = {published},
tppubtype = {article}
}
Carbon nanotubes (CNT) as a functional filler can increase the electrical conductivity property of concrete and thus provide intrinsic self-sensing properties with no need for external sensors to monitor the behavior of concrete infrastructure and structures containing CNT. CNT-cement composites also improve mechanical strength and have higher energy absorption capacity. The sensitivity of their electrical conductivity to external physical parameters, such as strain, stress, load, temperature, displacement, and pressure, makes them suitable for structural health monitoring (SHM) applications. This paper presents a comprehensive review of the CNT properties, fabrication process, composition, and sensing characteristics as well as challenges for applying CNT concrete as part of a self-sensing structure. Furthermore, the self-healing property of CNT, as an integral feature of future smart concrete infrastructure is discussed.
Sarkar, Pritam; Etemad, Ali
Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Temporal Synchronicity Miscellaneous
2021.
Abstract | Links | BibTeX | Tags:
@misc{sarkar2021selfsupervised,
title = {Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Temporal Synchronicity},
author = {Pritam Sarkar and Ali Etemad},
url = {https://arxiv.org/pdf/2111.05329.pdf},
year = {2021},
date = {2021-11-14},
urldate = {2021-01-01},
abstract = {We present CrissCross, a self-supervised framework for learning audio-visual representations. A novel notion is introduced in our framework whereby in addition to learning the intra-modal and standard 'synchronous' cross-modal relations, CrissCross also learns 'asynchronous' cross-modal relationships. We show that by relaxing the temporal synchronicity between the audio and visual modalities, the network learns strong time-invariant representations. Our experiments show that strong augmentations for both audio and visual modalities with relaxation of cross-modal temporal synchronicity optimize performance. To pretrain our proposed framework, we use 3 different datasets with varying sizes, Kinetics-Sound, Kinetics-400, and AudioSet. The learned representations are evaluated on a number of downstream tasks namely action recognition, sound classification, and retrieval. CrissCross shows state-of-the-art performances on action recognition (UCF101 and HMDB51) and sound classification (ESC50). The codes and pretrained models will be made publicly available. },
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
We present CrissCross, a self-supervised framework for learning audio-visual representations. A novel notion is introduced in our framework whereby in addition to learning the intra-modal and standard 'synchronous' cross-modal relations, CrissCross also learns 'asynchronous' cross-modal relationships. We show that by relaxing the temporal synchronicity between the audio and visual modalities, the network learns strong time-invariant representations. Our experiments show that strong augmentations for both audio and visual modalities with relaxation of cross-modal temporal synchronicity optimize performance. To pretrain our proposed framework, we use 3 different datasets with varying sizes, Kinetics-Sound, Kinetics-400, and AudioSet. The learned representations are evaluated on a number of downstream tasks namely action recognition, sound classification, and retrieval. CrissCross shows state-of-the-art performances on action recognition (UCF101 and HMDB51) and sound classification (ESC50). The codes and pretrained models will be made publicly available.
Phinnemore, Rachel; Cimolino, Gabriele; Sarkar, Pritam; Etemad, Ali; Graham, T. C. Nicholas
Happy Driver: Investigating the Effect of Mood on Preferred Style of Driving in Self-Driving Cars Inproceedings
In: Proceedings of the 9th International Conference on Human-Agent Interaction, pp. 139–147, Association for Computing Machinery, Virtual Event, Japan, 2021, ISBN: 9781450386203.
Abstract | Links | BibTeX | Tags: driver mood, driving styles, Self-driving cars, user experience.
@inproceedings{10.1145/3472307.3484169,
title = {Happy Driver: Investigating the Effect of Mood on Preferred Style of Driving in Self-Driving Cars},
author = {Rachel Phinnemore and Gabriele Cimolino and Pritam Sarkar and Ali Etemad and T. C. Nicholas Graham},
url = {https://doi.org/10.1145/3472307.3484169},
doi = {10.1145/3472307.3484169},
isbn = {9781450386203},
year = {2021},
date = {2021-11-09},
urldate = {2021-01-01},
booktitle = {Proceedings of the 9th International Conference on Human-Agent Interaction},
pages = {139–147},
publisher = {Association for Computing Machinery},
address = {Virtual Event, Japan},
series = {HAI '21},
abstract = {Self-driving cars are around the corner, yet little is known about how users of self-driving cars will react to the car’s driving style, and whether the driver’s mood affects their driving style preference. This paper explores the impact of users’ mood on driving style preference in self-driving cars. An experiment was conducted online (N=182) to investigate participants’ preference for three driving styles (conservative, moderate, aggressive) under three induced moods (calm, neutral, excited). Measures of arousal, valence, and driving satisfaction were recorded. Overall, participants scored the aggressive driving style lowest, irrespective of driver mood. Participants’ mood impacted preference, where a mismatch between driving style and mood induced prior to the driving style predicted lower driver satisfaction scores. We conclude with the design recommendation that driving styles in self-driving cars should not be overly aggressive, and drivers’ mood should be taken into consideration when designing driving styles.},
keywords = {driver mood, driving styles, Self-driving cars, user experience.},
pubstate = {published},
tppubtype = {inproceedings}
}
Self-driving cars are around the corner, yet little is known about how users of self-driving cars will react to the car’s driving style, and whether the driver’s mood affects their driving style preference. This paper explores the impact of users’ mood on driving style preference in self-driving cars. An experiment was conducted online (N=182) to investigate participants’ preference for three driving styles (conservative, moderate, aggressive) under three induced moods (calm, neutral, excited). Measures of arousal, valence, and driving satisfaction were recorded. Overall, participants scored the aggressive driving style lowest, irrespective of driver mood. Participants’ mood impacted preference, where a mismatch between driving style and mood induced prior to the driving style predicted lower driver satisfaction scores. We conclude with the design recommendation that driving styles in self-driving cars should not be overly aggressive, and drivers’ mood should be taken into consideration when designing driving styles.
Li, Dayu; Zhu, Xiaodan; Li, Yang; Wang, Suge; Li, Deyu; Liao, Jian; Zheng, Jianxing
Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy Inproceedings
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3935–3941, Ässociation for Computational Linguistics, Önline and Punta Cana, Dominican Republic, 2021.
Abstract | Links | BibTeX | Tags:
@inproceedings{li-etal-2021-emotion,
title = {Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy},
author = {Dayu Li and Xiaodan Zhu and Yang Li and Suge Wang and Deyu Li and Jian Liao and Jianxing Zheng},
url = {https://aclanthology.org/2021.emnlp-main.320},
year = {2021},
date = {2021-11-01},
urldate = {2021-11-01},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
pages = {3935--3941},
publisher = {Ässociation for Computational Linguistics},
address = {Önline and Punta Cana, Dominican Republic},
abstract = {Emotion inference in multi-turn conversations aims to predict the participant's emotion in the next upcoming turn without knowing the participant's response yet, and is a necessary step for applications such as dialogue planning. However, it is a severe challenge to perceive and reason about the future feelings of participants, due to the lack of utterance information from the future. Moreover, it is crucial for emotion inference to capture the characteristics of emotional propagation in conversations, such as persistence and contagiousness. In this study, we focus on investigating the task of emotion inference in multi-turn conversations by modeling the propagation of emotional states among participants in the conversation history, and propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn. In addition, we propose an ensemble strategy to further enhance the model performance. Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Emotion inference in multi-turn conversations aims to predict the participant's emotion in the next upcoming turn without knowing the participant's response yet, and is a necessary step for applications such as dialogue planning. However, it is a severe challenge to perceive and reason about the future feelings of participants, due to the lack of utterance information from the future. Moreover, it is crucial for emotion inference to capture the characteristics of emotional propagation in conversations, such as persistence and contagiousness. In this study, we focus on investigating the task of emotion inference in multi-turn conversations by modeling the propagation of emotional states among participants in the conversation history, and propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn. In addition, we propose an ensemble strategy to further enhance the model performance. Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines.
Shi, Zhan; Liu, Hui; Min, Martin Renqiang; Malon, Christopher; Li, Li Erran; Zhu, Xiaodan
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning Inproceedings
In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 1990–2000, Ässociation for Computational Linguistics, Punta Cana, Dominican Republic, 2021.
Abstract | Links | BibTeX | Tags:
@inproceedings{shi-etal-2021-retrieval-analogy,
title = {Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning},
author = {Zhan Shi and Hui Liu and Martin Renqiang Min and Christopher Malon and Li Erran Li and Xiaodan Zhu},
url = {https://aclanthology.org/2021.findings-emnlp.171},
year = {2021},
date = {2021-11-01},
urldate = {2021-11-01},
booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
pages = {1990--2000},
publisher = {Ässociation for Computational Linguistics},
address = {Punta Cana, Dominican Republic},
abstract = {Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the autoregressive generation framework, current approaches fail to generalize well to novel concept combinations. We propose a new framework that revolves around probing several similar image caption training instances (retrieval), performing analogical reasoning over relevant entities in retrieved prototypes (analogy), and enhancing the generation process with reasoning outcomes (composition). Our method augments the generation model by referring to the neighboring instances in the training set to produce novel concept combinations in generated captions. We perform experiments on the widely used image captioning benchmarks. The proposed models achieve substantial improvement over the compared baselines on both composition-related evaluation metrics and conventional image captioning metrics.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training. In spite of significant progress in image captioning with the help of the autoregressive generation framework, current approaches fail to generalize well to novel concept combinations. We propose a new framework that revolves around probing several similar image caption training instances (retrieval), performing analogical reasoning over relevant entities in retrieved prototypes (analogy), and enhancing the generation process with reasoning outcomes (composition). Our method augments the generation model by referring to the neighboring instances in the training set to produce novel concept combinations in generated captions. We perform experiments on the widely used image captioning benchmarks. The proposed models achieve substantial improvement over the compared baselines on both composition-related evaluation metrics and conventional image captioning metrics.
He, Weinan; Huang, Canming; Liu, Yongmei; Zhu, Xiaodan
WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge Inproceedings
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3779–3789, Ässociation for Computational Linguistics, Önline and Punta Cana, Dominican Republic, 2021.
Abstract | Links | BibTeX | Tags:
@inproceedings{he-etal-2021-winologic,
title = {WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge},
author = {Weinan He and Canming Huang and Yongmei Liu and Xiaodan Zhu},
url = {https://aclanthology.org/2021.emnlp-main.307},
year = {2021},
date = {2021-11-01},
urldate = {2021-11-01},
booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
pages = {3779--3789},
publisher = {Ässociation for Computational Linguistics},
address = {Önline and Punta Cana, Dominican Republic},
abstract = {The recent success of neural language models (NLMs) on the Winograd Schema Challenge has called for further investigation of the commonsense reasoning ability of these models. Previous diagnostic datasets rely on crowd-sourcing which fails to provide coherent commonsense crucial for solving WSC problems. To better evaluate NLMs, we propose a logic-based framework that focuses on high-quality commonsense knowledge. Specifically, we identify and collect formal knowledge formulas verified by theorem provers and translate such formulas into natural language sentences. Based on these true knowledge sentences, adversarial false ones are generated. We propose a new dataset named WinoLogic with these sentences. Given a problem in WinoLogic, NLMs need to decide whether the plausible knowledge sentences could correctly solve the corresponding WSC problems in a zero-shot setting. We also ask human annotators to validate WinoLogic to ensure it is human-agreeable. Experiments show that NLMs still struggle to comprehend commonsense knowledge as humans do, indicating that their reasoning ability could have been overestimated.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The recent success of neural language models (NLMs) on the Winograd Schema Challenge has called for further investigation of the commonsense reasoning ability of these models. Previous diagnostic datasets rely on crowd-sourcing which fails to provide coherent commonsense crucial for solving WSC problems. To better evaluate NLMs, we propose a logic-based framework that focuses on high-quality commonsense knowledge. Specifically, we identify and collect formal knowledge formulas verified by theorem provers and translate such formulas into natural language sentences. Based on these true knowledge sentences, adversarial false ones are generated. We propose a new dataset named WinoLogic with these sentences. Given a problem in WinoLogic, NLMs need to decide whether the plausible knowledge sentences could correctly solve the corresponding WSC problems in a zero-shot setting. We also ask human annotators to validate WinoLogic to ensure it is human-agreeable. Experiments show that NLMs still struggle to comprehend commonsense knowledge as humans do, indicating that their reasoning ability could have been overestimated.