It is an established fact that malicious users in networks are able to mislead other users since the presence of herding behaviors, which will further amplify the hazards of these malicious behaviors. Due to the aforementioned scenarios in many practical applications, the study of decision fusion in the presence of such malicious users (often called Byzantines) is receiving increasing attention. In this paper, we propose an evolutionary game theoretical framework to model the human decision making process, which is based on the statistical signal processing framework. Specifically, we derive the analytical formulation of the evolutionary dynamics and the corresponding numerical evolutionary stable states, which can be utilized to infer the hazard of Byzantines on the network. Based on the above model and the Markov nature of the evolutionary dynamics, the fusion mechanism with maximum a posteriori estimation is proposed. Finally, simulation experiments are conducted to analyze the performance of the proposed human decision-∗
{"title":"Integrating Human Decisions in the Presence of Byzantines: An Evolutionary Game Theoretical Approach","authors":"Yiqing Lin, Hong Hu, H. V. Zhao, Yan Chen","doi":"10.1561/116.00000035","DOIUrl":"https://doi.org/10.1561/116.00000035","url":null,"abstract":"It is an established fact that malicious users in networks are able to mislead other users since the presence of herding behaviors, which will further amplify the hazards of these malicious behaviors. Due to the aforementioned scenarios in many practical applications, the study of decision fusion in the presence of such malicious users (often called Byzantines) is receiving increasing attention. In this paper, we propose an evolutionary game theoretical framework to model the human decision making process, which is based on the statistical signal processing framework. Specifically, we derive the analytical formulation of the evolutionary dynamics and the corresponding numerical evolutionary stable states, which can be utilized to infer the hazard of Byzantines on the network. Based on the above model and the Markov nature of the evolutionary dynamics, the fusion mechanism with maximum a posteriori estimation is proposed. Finally, simulation experiments are conducted to analyze the performance of the proposed human decision-∗","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yao Zhu, Xinyu Wang, Ronald Salloum, Hong-Shuo Chen, C. J. Kuo
{"title":"RGGID: A Robust and Green GAN-Fake Image Detector","authors":"Yao Zhu, Xinyu Wang, Ronald Salloum, Hong-Shuo Chen, C. J. Kuo","doi":"10.1561/116.00000005","DOIUrl":"https://doi.org/10.1561/116.00000005","url":null,"abstract":"","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67079931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pair programming is a model of collaborative learning. It has become a well-known pedagogical practice in teaching introductory programming courses because of its potential benefits to students. This study aims to investigate pair patterns in the context of pair program tracing and debugging to determine what characterizes collaboration and how these patterns relate to success, where success is measured in terms of performance task scores. This research used eye-tracking methodologies and techniques such as cross-recurrence quantification analysis. The potential indicators for pair success were used to create a model for predicting pair success. Findings suggest that it is possible to create a model capable of predicting pair success in the context of pair programming. The predictors for the pair success model that can obtain the best performance are the pairs’ proficiency level and degree of acquaintanceship. This was achieved using an ensemble algorithm such as Gradient Boosted Trees. The performance of the pairs is largely determined by the proficiency level of the individuals in the pairs; hence, it is recommended that the struggling students be paired with someone who is considered proficient in programming and with whom the struggling student is comfortable working with.
{"title":"Predicting Pair Success in a Pair Programming Eye Tracking Experiment Using Cross-Recurrence Quantification Analysis","authors":"Maureen M. Villamor, M. M. Rodrigo","doi":"10.1561/116.00000031","DOIUrl":"https://doi.org/10.1561/116.00000031","url":null,"abstract":"Pair programming is a model of collaborative learning. It has become a well-known pedagogical practice in teaching introductory programming courses because of its potential benefits to students. This study aims to investigate pair patterns in the context of pair program tracing and debugging to determine what characterizes collaboration and how these patterns relate to success, where success is measured in terms of performance task scores. This research used eye-tracking methodologies and techniques such as cross-recurrence quantification analysis. The potential indicators for pair success were used to create a model for predicting pair success. Findings suggest that it is possible to create a model capable of predicting pair success in the context of pair programming. The predictors for the pair success model that can obtain the best performance are the pairs’ proficiency level and degree of acquaintanceship. This was achieved using an ensemble algorithm such as Gradient Boosted Trees. The performance of the pairs is largely determined by the proficiency level of the individuals in the pairs; hence, it is recommended that the struggling students be paired with someone who is considered proficient in programming and with whom the struggling student is comfortable working with.","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jun Wang, Omran Alamayreh, B. Tondi, Andrea Costanzo, M. Barni
{"title":"Detecting Deepfake Videos in Data Scarcity Conditions by Means of Video Coding Features","authors":"Jun Wang, Omran Alamayreh, B. Tondi, Andrea Costanzo, M. Barni","doi":"10.1561/116.00000032","DOIUrl":"https://doi.org/10.1561/116.00000032","url":null,"abstract":"","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bayesian Multi-Temporal-Difference Learning","authors":"Jen-Tzung Chien, Y. Chiu","doi":"10.1561/116.00000037","DOIUrl":"https://doi.org/10.1561/116.00000037","url":null,"abstract":"","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Is Self-Rated Confidence a Predictor for Performance in Programming Comprehension Tasks?","authors":"Zubair Ahsan, U. Obaidellah, M. Danaee","doi":"10.1561/116.00000041","DOIUrl":"https://doi.org/10.1561/116.00000041","url":null,"abstract":"","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67081464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep neural networks (DNN) have solved many tasks, including image classification, object detection, and semantic segmentation. However, when there are huge parameters and high level of computation associated with a DNN model, it becomes difficult to deploy on mobile devices. To address this difficulty, we propose an efficient compression method that can be split into three parts. First, we propose a cross-layer matrix to extract more features from the teacher's model. Second, we adopt Kullback Leibler (KL) Divergence in an offline environment to make the student model find a wider robust minimum. Finally, we propose the offline ensemble pre-trained teachers to teach a student model. To address dimension mismatch between teacher and student models, we adopt a $1times 1$ convolution and two-stage knowledge distillation to release this constraint. We conducted experiments with VGG and ResNet models, using the CIFAR-100 dataset. With VGG-11 as the teacher's model and VGG-6 as the student's model, experimental results showed that the Top-1 accuracy increased by 3.57% with a $2.08times$ compression rate and 3.5x computation rate. With ResNet-32 as the teacher's model and ResNet-8 as the student's model, experimental results showed that Top-1 accuracy increased by 4.38% with a $6.11times$ compression rate and $5.27times$ computation rate. In addition, we conducted experiments using the ImageNet$64times 64$ dataset. With MobileNet-16 as the teacher's model and MobileNet-9 as the student's model, experimental results showed that the Top-1 accuracy increased by 3.98% with a $1.59times$ compression rate and $2.05times$ computation rate.
{"title":"Cross-layer knowledge distillation with KL divergence and offline ensemble for compressing deep neural network","authors":"Hsing-Hung Chou, Ching-Te Chiu, Yi-Ping Liao","doi":"10.1017/ATSIP.2021.16","DOIUrl":"https://doi.org/10.1017/ATSIP.2021.16","url":null,"abstract":"Deep neural networks (DNN) have solved many tasks, including image classification, object detection, and semantic segmentation. However, when there are huge parameters and high level of computation associated with a DNN model, it becomes difficult to deploy on mobile devices. To address this difficulty, we propose an efficient compression method that can be split into three parts. First, we propose a cross-layer matrix to extract more features from the teacher's model. Second, we adopt Kullback Leibler (KL) Divergence in an offline environment to make the student model find a wider robust minimum. Finally, we propose the offline ensemble pre-trained teachers to teach a student model. To address dimension mismatch between teacher and student models, we adopt a $1times 1$ convolution and two-stage knowledge distillation to release this constraint. We conducted experiments with VGG and ResNet models, using the CIFAR-100 dataset. With VGG-11 as the teacher's model and VGG-6 as the student's model, experimental results showed that the Top-1 accuracy increased by 3.57% with a $2.08times$ compression rate and 3.5x computation rate. With ResNet-32 as the teacher's model and ResNet-8 as the student's model, experimental results showed that Top-1 accuracy increased by 4.38% with a $6.11times$ compression rate and $5.27times$ computation rate. In addition, we conducted experiments using the ImageNet$64times 64$ dataset. With MobileNet-16 as the teacher's model and MobileNet-9 as the student's model, experimental results showed that the Top-1 accuracy increased by 3.98% with a $1.59times$ compression rate and $2.05times$ computation rate.","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46579651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
QAnon is an umbrella conspiracy theory that encompasses a wide spectrum of people. The COVID-19 pandemic has helped raise the QAnon conspiracy theory to a wide-spreading movement, especially in the US. Here, we study users' dynamics on Twitter related to the QAnon movement (i.e., pro-/anti-QAnon and less-leaning users) in the context of the COVID-19 infodemic and the topics involved using a simple network-based approach. We found that pro- and anti-leaning users show different population dynamics and that late less-leaning users were mostly anti-QAnon. These trends might have been affected by Twitter's suspension strategies. We also found that QAnon clusters include many bot users. Furthermore, our results suggest that QAnon continues to evolve amid the infodemic and does not limit itself to its original idea but instead extends its reach to create a much larger umbrella conspiracy theory. The network-based approach in this study is important for nowcasting the evolution of the QAnon movement.
{"title":"A Network-Based Approach to QAnon User Dynamics and Topic Diversity During the COVID-19 Infodemic","authors":"Wentao Xu, K. Sasahara","doi":"10.1561/116.00000055","DOIUrl":"https://doi.org/10.1561/116.00000055","url":null,"abstract":"QAnon is an umbrella conspiracy theory that encompasses a wide spectrum of people. The COVID-19 pandemic has helped raise the QAnon conspiracy theory to a wide-spreading movement, especially in the US. Here, we study users' dynamics on Twitter related to the QAnon movement (i.e., pro-/anti-QAnon and less-leaning users) in the context of the COVID-19 infodemic and the topics involved using a simple network-based approach. We found that pro- and anti-leaning users show different population dynamics and that late less-leaning users were mostly anti-QAnon. These trends might have been affected by Twitter's suspension strategies. We also found that QAnon clusters include many bot users. Furthermore, our results suggest that QAnon continues to evolve amid the infodemic and does not limit itself to its original idea but instead extends its reach to create a much larger umbrella conspiracy theory. The network-based approach in this study is important for nowcasting the evolution of the QAnon movement.","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2021-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48607737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social rhythms have been considered as relevant to mood disorders, but detailed analysis of social rhythms has been limited. Hence, we aim to assess social rhythms via social media use and predict users' psychiatric symptoms through their social rhythms. A two-wave survey was conducted in the Pigg Party, a popular Japanese avatar application. First and second waves of data were collected from 3504 and 658 Pigg Party users, respectively. The time stamps of their communication were sampled. Furthermore, the participants answered the General Health Questionnaire and perceived emotional support in the Pigg Party. The results indicated that social rhythms of users with many social supports were stable in a 24-h cycle. However, the rhythms of users with few social supports were disrupted. To predict psychiatric symptoms via social rhythms in the second-wave data, the first-wave data were used for training. We determined that fast Chirplet transformation was the optimal transformation for social rhythms, and the best accuracy scores on psychiatric symptoms and perceived emotional support in the second-wave data corresponded to 0.9231 and 0.7462, respectively. Hence, measurement of social rhythms via social media use enabled detailed understanding of emotional disturbance from the perspective of time-varying frequencies.
{"title":"Social rhythms measured via social media use for predicting psychiatric symptoms","authors":"K. Yokotani, Masanori Takano","doi":"10.1017/ATSIP.2021.17","DOIUrl":"https://doi.org/10.1017/ATSIP.2021.17","url":null,"abstract":"Social rhythms have been considered as relevant to mood disorders, but detailed analysis of social rhythms has been limited. Hence, we aim to assess social rhythms via social media use and predict users' psychiatric symptoms through their social rhythms. A two-wave survey was conducted in the Pigg Party, a popular Japanese avatar application. First and second waves of data were collected from 3504 and 658 Pigg Party users, respectively. The time stamps of their communication were sampled. Furthermore, the participants answered the General Health Questionnaire and perceived emotional support in the Pigg Party. The results indicated that social rhythms of users with many social supports were stable in a 24-h cycle. However, the rhythms of users with few social supports were disrupted. To predict psychiatric symptoms via social rhythms in the second-wave data, the first-wave data were used for training. We determined that fast Chirplet transformation was the optimal transformation for social rhythms, and the best accuracy scores on psychiatric symptoms and perceived emotional support in the second-wave data corresponded to 0.9231 and 0.7462, respectively. Hence, measurement of social rhythms via social media use enabled detailed understanding of emotional disturbance from the perspective of time-varying frequencies.","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"57024136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many approaches have been proposed in the literature to enhance the robustness of Convolutional Neural Network (CNN)-based architectures against image distortions. Attempts to combat various types of distortions can be made by combining multiple expert networks, each trained by a certain type of distorted images, which however lead to a large model with high complexity. In this paper, we propose a CNN-based architecture with a pre-processing unit in which only undistorted data are used for training. The pre-processing unit employs discrete cosine transform (DCT) and discrete wavelets transform (DWT) to remove high-frequency components while capturing prominent high-frequency features in the undistorted data by means of random selection. We further utilize the singular value decomposition (SVD) to extract features before feeding the preprocessed data into the CNN for training. During testing, distorted images directly enter the CNN for classification without having to go through the hybrid module. Five different types of distortions are produced in the SVHN dataset and the CIFAR-10/100 datasets. Experimental results show that the proposed DCT-DWT-SVD module built upon the CNN architecture provides a classifier robust to input image distortions, outperforming the state-of-the-art approaches in terms of accuracy under different types of distortions.
{"title":"Robust deep convolutional neural network against image distortions","authors":"Liang Wang, Sau-Gee Chen, Feng-Tsun Chien","doi":"10.1017/ATSIP.2021.14","DOIUrl":"https://doi.org/10.1017/ATSIP.2021.14","url":null,"abstract":"Many approaches have been proposed in the literature to enhance the robustness of Convolutional Neural Network (CNN)-based architectures against image distortions. Attempts to combat various types of distortions can be made by combining multiple expert networks, each trained by a certain type of distorted images, which however lead to a large model with high complexity. In this paper, we propose a CNN-based architecture with a pre-processing unit in which only undistorted data are used for training. The pre-processing unit employs discrete cosine transform (DCT) and discrete wavelets transform (DWT) to remove high-frequency components while capturing prominent high-frequency features in the undistorted data by means of random selection. We further utilize the singular value decomposition (SVD) to extract features before feeding the preprocessed data into the CNN for training. During testing, distorted images directly enter the CNN for classification without having to go through the hybrid module. Five different types of distortions are produced in the SVHN dataset and the CIFAR-10/100 datasets. Experimental results show that the proposed DCT-DWT-SVD module built upon the CNN architecture provides a classifier robust to input image distortions, outperforming the state-of-the-art approaches in terms of accuracy under different types of distortions.","PeriodicalId":44812,"journal":{"name":"APSIPA Transactions on Signal and Information Processing","volume":null,"pages":null},"PeriodicalIF":3.2,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48955187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：