Pub Date : 2025-03-03DOI: 10.26599/TST.2023.9010078
V. D. Ambeth Kumar;Venkatesan Ramachandran;Mamoon Rashid;Abdul Rehman Javed;Shayla Islam;Abdullah Al Hejaili
Unmanned Aerial Vehicles (UAVs) are enabled to be fast and flexible in managing traffic compared to the conventional methods. However, in emergencies, this system takes more time to identify and clear the traffic because of fixed time control. To overcome this problem, an automated intelligent traffic monitoring and controlling system is designed using YOLO V3 neural architecture and implemented to detect the emergency vehicles from video stream data from UAVs using deep Convolution Neural Network (CNN) along with rerouting algorithm to provide the safest alternate route from current position to destination, in a heavy traffic environment. The real-time visual data collected through UAV video cameras are trained using machine learning algorithms to produce statistical profiles that are used continuously as updated inputs to the existing traffic simulation models for improving predictions. The proposed automated system performs exemplary in recognizing emergency vehicles and diverting them to an alternate route for quick transportation in various scenarios.
{"title":"An Intelligent Traffic Monitoring System in Congested Regions with Prioritization for Emergency Vehicle Using UAV Networks","authors":"V. D. Ambeth Kumar;Venkatesan Ramachandran;Mamoon Rashid;Abdul Rehman Javed;Shayla Islam;Abdullah Al Hejaili","doi":"10.26599/TST.2023.9010078","DOIUrl":"https://doi.org/10.26599/TST.2023.9010078","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) are enabled to be fast and flexible in managing traffic compared to the conventional methods. However, in emergencies, this system takes more time to identify and clear the traffic because of fixed time control. To overcome this problem, an automated intelligent traffic monitoring and controlling system is designed using YOLO V3 neural architecture and implemented to detect the emergency vehicles from video stream data from UAVs using deep Convolution Neural Network (CNN) along with rerouting algorithm to provide the safest alternate route from current position to destination, in a heavy traffic environment. The real-time visual data collected through UAV video cameras are trained using machine learning algorithms to produce statistical profiles that are used continuously as updated inputs to the existing traffic simulation models for improving predictions. The proposed automated system performs exemplary in recognizing emergency vehicles and diverting them to an alternate route for quick transportation in various scenarios.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1387-1400"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908597","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.26599/TST.2024.9010021
Mostafa Jabari;Amin Rad
This paper demonstrates the application of optimization techniques, namely the Dung Beetle Optimizer (DBO) and the Ant-Lion Optimizer (ALO), to enhance the performance of cascaded Proportional Integral Derivative (PID) and Fractional Order PID (FOPID) controllers at the edge of an industrial network for Switched Reluctance Motor (SRM) speed control and torque ripple reduction. These techniques present notable advantages in terms of faster convergence and reduced computational complexity compared to existing optimization methods. Our research employs PID and FOPID controllers to regulate the speed and torque of the SRM, with a comparative analysis of other optimization approaches. In the domain of SRM control, we highlight the significance of the hysteresis band block in mitigating sudden state transitions, especially crucial for ensuring stable operation in the presence of noisy or slightly variable input signals requiring precise control. The results underscore the superior performance of the proposed optimization strategies, particularly showcasing the DBO-based cascaded PID and FOPID controllers, which exhibit reduced torque and current ripples along with improved speed response. Our investigation encompasses diverse loading conditions and is substantiated through time-domain simulations performed using MATLAB/SIMULINK.
{"title":"Optimization of Speed Control and Reduction of Torque Ripple in Switched Reluctance Motors Using Metaheuristic Algorithms Based PID and FOPID Controllers at the Edge","authors":"Mostafa Jabari;Amin Rad","doi":"10.26599/TST.2024.9010021","DOIUrl":"https://doi.org/10.26599/TST.2024.9010021","url":null,"abstract":"This paper demonstrates the application of optimization techniques, namely the Dung Beetle Optimizer (DBO) and the Ant-Lion Optimizer (ALO), to enhance the performance of cascaded Proportional Integral Derivative (PID) and Fractional Order PID (FOPID) controllers at the edge of an industrial network for Switched Reluctance Motor (SRM) speed control and torque ripple reduction. These techniques present notable advantages in terms of faster convergence and reduced computational complexity compared to existing optimization methods. Our research employs PID and FOPID controllers to regulate the speed and torque of the SRM, with a comparative analysis of other optimization approaches. In the domain of SRM control, we highlight the significance of the hysteresis band block in mitigating sudden state transitions, especially crucial for ensuring stable operation in the presence of noisy or slightly variable input signals requiring precise control. The results underscore the superior performance of the proposed optimization strategies, particularly showcasing the DBO-based cascaded PID and FOPID controllers, which exhibit reduced torque and current ripples along with improved speed response. Our investigation encompasses diverse loading conditions and is substantiated through time-domain simulations performed using MATLAB/SIMULINK.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1526-1538"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908595","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the Internet of Things (IoT) environment, user-service interaction data are often stored in multiple distributed platforms. In this situation, recommender systems need to integrate the distributed user-service interaction data across different platforms for making a comprehensive recommendation decision, during which user privacy is probably disclosed. Moreover, as user-service interaction records accumulate over time, they significantly reduce the efficiency of recommendations. To tackle these issues, we propose a lightweight and privacy-preserving service recommendation approach named SerRecL2H. In SerRecL2H, we employ Learning to Hash (L2H) to encapsulate sensitive user-service interaction data into less-sensitive user indices, which facilitates identifying users with similar preferences efficiently for accurate recommendations. We then validate the feasibility of our proposed SerRecL2H approach through massive experiments conducted on the popular WS-DREAM dataset. The comparative analysis with other competitive approaches demonstrates that our proposal surpasses other approaches in terms of recommendation accuracy and efficiency while protecting user privacy.
{"title":"Lightweight and Privacy-Preserving IoT Service Recommendation Based on Learning to Hash","authors":"Haoyang Wan;Yanping Wu;Yihong Yang;Chao Yan;Xiaoxiao Chi;Xuyun Zhang;Shigen Shen","doi":"10.26599/TST.2024.9010064","DOIUrl":"https://doi.org/10.26599/TST.2024.9010064","url":null,"abstract":"In the Internet of Things (IoT) environment, user-service interaction data are often stored in multiple distributed platforms. In this situation, recommender systems need to integrate the distributed user-service interaction data across different platforms for making a comprehensive recommendation decision, during which user privacy is probably disclosed. Moreover, as user-service interaction records accumulate over time, they significantly reduce the efficiency of recommendations. To tackle these issues, we propose a lightweight and privacy-preserving service recommendation approach named SerRec<inf>L2H</inf>. In SerRec<inf>L2H</inf>, we employ Learning to Hash (L2H) to encapsulate sensitive user-service interaction data into less-sensitive user indices, which facilitates identifying users with similar preferences efficiently for accurate recommendations. We then validate the feasibility of our proposed SerRec<inf>L2H</inf> approach through massive experiments conducted on the popular WS-DREAM dataset. The comparative analysis with other competitive approaches demonstrates that our proposal surpasses other approaches in terms of recommendation accuracy and efficiency while protecting user privacy.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1793-1807"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908664","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143535437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As the maritime industry continues to thrive and maritime services diversify, the demand for highly reliable maritime communication systems has become increasingly prominent. However, harsh marine conditions pose significant challenges to communication systems. In this work, we propose a Maritime AutoEncoder (MAE) communication system based on Attention Mechanisms (AMs) and DenseBlock (namely AM-Dense-MAE). AM-Dense-MAE utilizes DenseBlock and long short-term memory to extract deep features and capture spatio-temporal relationships, addressing the issue of “long-term dependency”. Furthermore, the decoder incorporates spatial attention modules and convolutional block attention module to enhance the preservation of crucial information and suppress irrelevant data. We employ the Rician fading channel model to simulate maritime communication channels. A substantial volume of data is utilized for model training and parameter optimization. Simulation results demonstrate that, in comparison to the benchmarks, the proposed AM-Dense-MAE exhibits better block error rate performance under various signal-to-noise ratio conditions and showcases generalization capabilities across diverse parameter settings.
{"title":"Design of a Maritime Autoencoder Communication System Based on Attention Mechanisms and DenseBlock","authors":"Xiaoling Han;Bin Lin;Shuai Shao;Nan Wu;Haocheng Wang;Liping Qian;Yuan Wu","doi":"10.26599/TST.2023.9010150","DOIUrl":"https://doi.org/10.26599/TST.2023.9010150","url":null,"abstract":"As the maritime industry continues to thrive and maritime services diversify, the demand for highly reliable maritime communication systems has become increasingly prominent. However, harsh marine conditions pose significant challenges to communication systems. In this work, we propose a Maritime AutoEncoder (MAE) communication system based on Attention Mechanisms (AMs) and DenseBlock (namely AM-Dense-MAE). AM-Dense-MAE utilizes DenseBlock and long short-term memory to extract deep features and capture spatio-temporal relationships, addressing the issue of “long-term dependency”. Furthermore, the decoder incorporates spatial attention modules and convolutional block attention module to enhance the preservation of crucial information and suppress irrelevant data. We employ the Rician fading channel model to simulate maritime communication channels. A substantial volume of data is utilized for model training and parameter optimization. Simulation results demonstrate that, in comparison to the benchmarks, the proposed AM-Dense-MAE exhibits better block error rate performance under various signal-to-noise ratio conditions and showcases generalization capabilities across diverse parameter settings.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1496-1510"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908674","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.26599/TST.2024.9010036
Xuefeng Su;Ru Li;Xiaoli Li;Zhichao Yan
Frame-Semantic Parsing (FSP) aims to extract frame-semantic structures from text. The task usually involves three subtasks sequentially: Target Identification (TI), Frame Identification (Fl), and Frame Semantic Role Labeling (FSRL). The three subtasks are closely related while most previous studies model them individually, encountering error propagation and running efficiency problems. Recently, an end-to-end graph-based model is proposed to jointly process three subtasks in one model. However, it still encounters three problems: insufficient semantic modeling between targets and arguments, span missing, and lacking knowledge incorporation of FrameNet. To address the mentioned problems, this paper presents an End-to-end FSP model with Table Encoder (EFSP-TE), which models FSP as two semantically dependent region classification problems and extracts frame-semantic structures from sentences in a one-step manner. Specifically, EFSP-TE incorporates lexical unit knowledge into context encoder via saliency embedding, and develops an effective table representation learning method based on Biaffine network and multi-layer ResNet-style-CNNs (Convolutional Neural Networks), which can fully exploit word-to-word interactions and capture the information of various levels of semantic relations between targets and arguments. In addition, it adopts two separate region-based modules to obtain potential targets and arguments, followed by two interactive classification modules to predict the frames and roles for the potential targets and arguments. Experiments on two public benchmarks show that the proposed approach achieves state-of-the-art performance in end-to-end setting.
{"title":"EFSP-TE: End-to-End Frame-Semantic Parsing with Table Encoder","authors":"Xuefeng Su;Ru Li;Xiaoli Li;Zhichao Yan","doi":"10.26599/TST.2024.9010036","DOIUrl":"https://doi.org/10.26599/TST.2024.9010036","url":null,"abstract":"Frame-Semantic Parsing (FSP) aims to extract frame-semantic structures from text. The task usually involves three subtasks sequentially: Target Identification (TI), Frame Identification (Fl), and Frame Semantic Role Labeling (FSRL). The three subtasks are closely related while most previous studies model them individually, encountering error propagation and running efficiency problems. Recently, an end-to-end graph-based model is proposed to jointly process three subtasks in one model. However, it still encounters three problems: insufficient semantic modeling between targets and arguments, span missing, and lacking knowledge incorporation of FrameNet. To address the mentioned problems, this paper presents an End-to-end FSP model with Table Encoder (EFSP-TE), which models FSP as two semantically dependent region classification problems and extracts frame-semantic structures from sentences in a one-step manner. Specifically, EFSP-TE incorporates lexical unit knowledge into context encoder via saliency embedding, and develops an effective table representation learning method based on Biaffine network and multi-layer ResNet-style-CNNs (Convolutional Neural Networks), which can fully exploit word-to-word interactions and capture the information of various levels of semantic relations between targets and arguments. In addition, it adopts two separate region-based modules to obtain potential targets and arguments, followed by two interactive classification modules to predict the frames and roles for the potential targets and arguments. Experiments on two public benchmarks show that the proposed approach achieves state-of-the-art performance in end-to-end setting.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1474-1495"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908675","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.26599/TST.2024.9010054
Haoling Meng;Jianguo Ding;Hongmei Wang;Zhimin Zhang;Xuanxia Yao;Huansheng Ning
The metaverse has gradually come into the public eye and has become a hotspot in cyberspace, but it still faces many technical difficulties to be solved. Blockchain is a key component of the metaverse, enhancing the development of the metaverse by connecting the real and virtual worlds seamlessly and solving some of the difficulties faced by the metaverse. Our paper comprehensively studies the development and application of blockchain technology in the metaverse. First, there is an introduction to blockchain and the metaverse, followed by a discussion of why blockchain should be integrated into the metaverse. Second, an overview of the main blockchain technologies is provided to evaluate blockchain's role in the metaverse and the value is summarized. Third, the development of future integration of blockchain and metaverse is presented from the perspective of social life and technology. For social life, how to use blockchain in the metaverse to enhance and improve social life is discussed. Then, from the technical perspective, it discusses how blockchain shapes the metaverse. Finally, challenges associated with the integration of blockchain into metaverses are analyzed and some promising research directions and solutions are proposed.
{"title":"Blockchain Enabled Metaverse: Development and Applications","authors":"Haoling Meng;Jianguo Ding;Hongmei Wang;Zhimin Zhang;Xuanxia Yao;Huansheng Ning","doi":"10.26599/TST.2024.9010054","DOIUrl":"https://doi.org/10.26599/TST.2024.9010054","url":null,"abstract":"The metaverse has gradually come into the public eye and has become a hotspot in cyberspace, but it still faces many technical difficulties to be solved. Blockchain is a key component of the metaverse, enhancing the development of the metaverse by connecting the real and virtual worlds seamlessly and solving some of the difficulties faced by the metaverse. Our paper comprehensively studies the development and application of blockchain technology in the metaverse. First, there is an introduction to blockchain and the metaverse, followed by a discussion of why blockchain should be integrated into the metaverse. Second, an overview of the main blockchain technologies is provided to evaluate blockchain's role in the metaverse and the value is summarized. Third, the development of future integration of blockchain and metaverse is presented from the perspective of social life and technology. For social life, how to use blockchain in the metaverse to enhance and improve social life is discussed. Then, from the technical perspective, it discusses how blockchain shapes the metaverse. Finally, challenges associated with the integration of blockchain into metaverses are analyzed and some promising research directions and solutions are proposed.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1552-1582"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908672","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.26599/TST.2024.9010061
Jie Pan;Qiang He;Guangming Cui;Yiwen Zhang;Yun Yang
Mobile Edge Computing (MEC) is a pivotal technology that provides agile-response services by deploying computation and storage resources in proximity to end-users. However, resource-constrained edge servers fall victim to Denial-of-Service (DoS) attacks easily. Failures to mitigate DoS attacks effectively hinder the delivery of reliable and sustainable edge services. Conventional DoS mitigation solutions in cloud computing environments are not directly applicable in MEC environments because their design did not factor in the unique characteristics of MEC environments, e.g., constrained resources on edge servers and requirements for low service latency. Existing solutions mitigate edge DoS attacks by transferring user requests from edge servers under attacks to others for processing. Furthermore, the heterogeneity in end-users' resource demands can cause resource fragmentation on edge servers and undermine the ability of these solutions to mitigate DoS attacks effectively. User requests often have to be transferred far away for processing, which increases the service latency. To tackle this challenge, this paper presents a fragmentation-aware gaming approach called HEDMGame that attempts to minimize service latency by matching user requests to edge servers' remaining resources while making request-transferring decisions. Through theoretical analysis and experimental evaluation, we validate the effectiveness and efficiency of HEDMGame, and demonstrate its superiority over the state-of-the-art solution.
{"title":"HEDMGame: Fragmentation-Aware Mitigation of Heterogeneous Edge DoS Attacks","authors":"Jie Pan;Qiang He;Guangming Cui;Yiwen Zhang;Yun Yang","doi":"10.26599/TST.2024.9010061","DOIUrl":"https://doi.org/10.26599/TST.2024.9010061","url":null,"abstract":"Mobile Edge Computing (MEC) is a pivotal technology that provides agile-response services by deploying computation and storage resources in proximity to end-users. However, resource-constrained edge servers fall victim to Denial-of-Service (DoS) attacks easily. Failures to mitigate DoS attacks effectively hinder the delivery of reliable and sustainable edge services. Conventional DoS mitigation solutions in cloud computing environments are not directly applicable in MEC environments because their design did not factor in the unique characteristics of MEC environments, e.g., constrained resources on edge servers and requirements for low service latency. Existing solutions mitigate edge DoS attacks by transferring user requests from edge servers under attacks to others for processing. Furthermore, the heterogeneity in end-users' resource demands can cause resource fragmentation on edge servers and undermine the ability of these solutions to mitigate DoS attacks effectively. User requests often have to be transferred far away for processing, which increases the service latency. To tackle this challenge, this paper presents a fragmentation-aware gaming approach called HEDMGame that attempts to minimize service latency by matching user requests to edge servers' remaining resources while making request-transferring decisions. Through theoretical analysis and experimental evaluation, we validate the effectiveness and efficiency of HEDMGame, and demonstrate its superiority over the state-of-the-art solution.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1724-1743"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908668","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.26599/TST.2024.9010066
Runyu Wang;Tun Lu;Peng Zhang;Ning Gu
Over the past few years, many efforts have been dedicated to studying cyberbullying in social edge computing devices, and most of them focus on three roles: victims, perpetrators, and bystanders. If we want to obtain a deep insight into the formation, evolution, and intervention of cyberbullying in devices at the edge of the Internet, it is necessary to explore more fine-grained roles. This paper presents a multi-level method for role feature modeling and proposes a differential evolution-assisted K-means (DEK) method to identify diverse roles. Our work aims to provide a role identification scheme for cyberbullying scenarios for social edge computing environments to alleviate the general safety issues that cyberbullying brings. The experiments on ten real-world datasets obtained from Weibo and five public datasets show that the proposed DEK outperforms the existing approaches on the method level. After clustering, we obtain nine roles and analyze the characteristics of each role and their evolution trends under different cyberbullying scenarios. Our work in this paper can be placed in devices at the edge of the Internet, leading to better real-time identification performance and adapting to the broad geographic location and high mobility of mobile devices.
{"title":"Role Identification Based Method for Cyberbullying Analysis in Social Edge Computing","authors":"Runyu Wang;Tun Lu;Peng Zhang;Ning Gu","doi":"10.26599/TST.2024.9010066","DOIUrl":"https://doi.org/10.26599/TST.2024.9010066","url":null,"abstract":"Over the past few years, many efforts have been dedicated to studying cyberbullying in social edge computing devices, and most of them focus on three roles: victims, perpetrators, and bystanders. If we want to obtain a deep insight into the formation, evolution, and intervention of cyberbullying in devices at the edge of the Internet, it is necessary to explore more fine-grained roles. This paper presents a multi-level method for role feature modeling and proposes a differential evolution-assisted K-means (DEK) method to identify diverse roles. Our work aims to provide a role identification scheme for cyberbullying scenarios for social edge computing environments to alleviate the general safety issues that cyberbullying brings. The experiments on ten real-world datasets obtained from Weibo and five public datasets show that the proposed DEK outperforms the existing approaches on the method level. After clustering, we obtain nine roles and analyze the characteristics of each role and their evolution trends under different cyberbullying scenarios. Our work in this paper can be placed in devices at the edge of the Internet, leading to better real-time identification performance and adapting to the broad geographic location and high mobility of mobile devices.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1659-1684"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908657","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the exponential growth of maritime wireless devices and the rapid development of maritime applications, traditional maritime communication networks encounter communication and computation limitations in supporting computation-intensive and latency-critical tasks. Edge computing and Intelligent Reflecting Surface (IRS) have emerged as promising techniques to improve communication and computation services for maritime devices with limited computation capabilities and battery capacity. This paper studies an IRS Mounted on Unmanned Aerial Vehicle (UIRS) assisted maritime edge computing network, in which the UIRS is deployed to assist the transmission from Unmanned Surface Vehicles (USVs) to the edge server via Non-Orthogonal Multiple Access (NOMA) protocol. We propose a resource management and trajectory optimization scheme by jointly optimizing subslot duration, offloading ratios, transmit power, edge computation capability allocation, UIRS phase shifts and UIRS trajectory, aiming at minimizing the overall energy consumption. Since the non-convex nature of the optimization problem, we propose a two-layered method by decomposing the original problem into two subproblems. The top-layered subproblem is solved by the Semi-Definite Relaxation (SDR) method and the underlying-layered subproblem is solved by the Deep Deterministic Policy Gradient (DDPG) algorithm. Numerical results demonstrate that our proposed scheme can effectively and efficiently reduce overall energy consumption.
{"title":"Resource Management and Trajectory Optimization for UAV-IRS Assisted Maritime Edge Computing Networks","authors":"Chaoyue Zhang;Bin Lin;Xu Hu;Shuang Qi;Liping Qian;Yuan Wu","doi":"10.26599/TST.2024.9010074","DOIUrl":"https://doi.org/10.26599/TST.2024.9010074","url":null,"abstract":"With the exponential growth of maritime wireless devices and the rapid development of maritime applications, traditional maritime communication networks encounter communication and computation limitations in supporting computation-intensive and latency-critical tasks. Edge computing and Intelligent Reflecting Surface (IRS) have emerged as promising techniques to improve communication and computation services for maritime devices with limited computation capabilities and battery capacity. This paper studies an IRS Mounted on Unmanned Aerial Vehicle (UIRS) assisted maritime edge computing network, in which the UIRS is deployed to assist the transmission from Unmanned Surface Vehicles (USVs) to the edge server via Non-Orthogonal Multiple Access (NOMA) protocol. We propose a resource management and trajectory optimization scheme by jointly optimizing subslot duration, offloading ratios, transmit power, edge computation capability allocation, UIRS phase shifts and UIRS trajectory, aiming at minimizing the overall energy consumption. Since the non-convex nature of the optimization problem, we propose a two-layered method by decomposing the original problem into two subproblems. The top-layered subproblem is solved by the Semi-Definite Relaxation (SDR) method and the underlying-layered subproblem is solved by the Deep Deterministic Policy Gradient (DDPG) algorithm. Numerical results demonstrate that our proposed scheme can effectively and efficiently reduce overall energy consumption.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1600-1616"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908662","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Graph neural networks (GNNs), grounded in spatial or spectral domains, have achieved remarkable success in learning graph representations in Euclidean space. Recent advances in spatial GNNs reveal that embedding graph nodes with hierarchical structures into hyperbolic space is more effective, reducing distortion compared to Euclidean embeddings. However, extending spectral GNNs to hyperbolic space remains several challenges, particularly in defining spectral graph convolution and enabling message passing within the hyperbolic geometry. To address these challenges, we propose the hyperbolic graph wavelet neural network (HGWNN), a novel approach for modeling spectral GNNs in hyperbolic space. Specifically, we first define feature transformation and spectral graph wavelet convolution on the hyperboloid manifold using exponential and logarithmic mappings, without increasing model parameter complexity. Moreover, we enable non-linear activation on the Poincaré manifold and efficient message passing via diffeomorphic transformations between the hyperboloid and Poincaré models. Experiments on four benchmark datasets demonstrate the effectiveness of our proposed HGWNN over baseline systems.
{"title":"Hyperbolic Graph Wavelet Neural Network","authors":"Wenjie Zheng;Guofeng Zhang;Xiaoran Zhao;Zhikang Feng;Lekang Song;Huaizhen Kou","doi":"10.26599/TST.2024.9010032","DOIUrl":"https://doi.org/10.26599/TST.2024.9010032","url":null,"abstract":"Graph neural networks (GNNs), grounded in spatial or spectral domains, have achieved remarkable success in learning graph representations in Euclidean space. Recent advances in spatial GNNs reveal that embedding graph nodes with hierarchical structures into hyperbolic space is more effective, reducing distortion compared to Euclidean embeddings. However, extending spectral GNNs to hyperbolic space remains several challenges, particularly in defining spectral graph convolution and enabling message passing within the hyperbolic geometry. To address these challenges, we propose the hyperbolic graph wavelet neural network (HGWNN), a novel approach for modeling spectral GNNs in hyperbolic space. Specifically, we first define feature transformation and spectral graph wavelet convolution on the hyperboloid manifold using exponential and logarithmic mappings, without increasing model parameter complexity. Moreover, we enable non-linear activation on the Poincaré manifold and efficient message passing via diffeomorphic transformations between the hyperboloid and Poincaré models. Experiments on four benchmark datasets demonstrate the effectiveness of our proposed HGWNN over baseline systems.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":"30 4","pages":"1511-1525"},"PeriodicalIF":6.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10908594","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：