A recommender system is a tool designed to suggest relevant items to users based on their preferences and behaviors.Collaborative filtering,a popular technique within recommender systems,predicts user interests by ana...A recommender system is a tool designed to suggest relevant items to users based on their preferences and behaviors.Collaborative filtering,a popular technique within recommender systems,predicts user interests by analyzing patterns in interactions and similarities between users,leveraging past behavior data to make personalized recommendations.Despite its popularity,collaborative filtering faces notable challenges,and one of them is the issue of grey-sheep users who have unusual tastes in the system.Surprisingly,existing research has not extensively explored outlier detection techniques to address the grey-sheep problem.To fill this research gap,this study conducts a comprehensive comparison of 12 outlier detectionmethods(such as LOF,ABOD,HBOS,etc.)and introduces innovative user representations aimed at improving the identification of outliers within recommender systems.More specifically,we proposed and examined three types of user representations:1)the distribution statistics of user-user similarities,where similarities were calculated based on users’rating vectors;2)the distribution statistics of user-user similarities,but with similarities derived from users represented by latent factors;and 3)latent-factor vector representations.Our experiments on the Movie Lens and Yahoo!Movie datasets demonstrate that user representations based on latent-factor vectors consistently facilitate the identification of more grey-sheep users when applying outlier detection methods.展开更多
With increasing awareness of environmental protection and rising carbon emission costs,participation in electricity and carbon markets for energy-intensive industrial users will become an effective way to reduce opera...With increasing awareness of environmental protection and rising carbon emission costs,participation in electricity and carbon markets for energy-intensive industrial users will become an effective way to reduce operating costs and carbon emissions.In this regard,a novel Stackelberg game framework is developed in this study for coordinated participation in coupled electricity‒carbon markets.Specifically,generalized carbon emission models and electricity consumption models for different energy-intensive industrial users are established,and a Stackelberg game-based interactive operation strategy is proposed for load aggregators(LAs)and energy-intensive industrial users in joint electricity‒carbon markets,where the LA works as a leader who chooses proper interactive prices to maximize the comprehensive benefit,whereas energy-intensive industrial users serve as followers who minimize the total energy costs in response to the interactive prices set by the LA.Then,the existence and uniqueness of the Stackelberg equilibrium(SE)are analyzed,and a decentralized solution algorithm is suggested to reach the SE.Finally,the simulation results demonstrate that the proposed interactive operation strategy can not only increase the profit of the LA but also reduce the cost of energy-intensive industrial users,which achieves a win-win result.展开更多
This study introduces an advanced recommender system for technology enhanced learning(TEL)that synergizes neural collaborative filtering,sentiment analysis,and an adaptive learning rate to address the limitations of t...This study introduces an advanced recommender system for technology enhanced learning(TEL)that synergizes neural collaborative filtering,sentiment analysis,and an adaptive learning rate to address the limitations of traditional TEL systems.Recognizing the critical gap in existing approaches—primarily their neglect of user emotional feedback and static learning paths—our model innovatively incorporates sentiment analysis to capture and respond to nuanced emotional feedback from users.Utilizing bidirectional encoder representations from Transformers for sentiment analysis,our system not only understands but also respects user privacy by processing feedback without revealing sensitive information.The adaptive learning rate,inspired by AdaGrad,allows our model to adjust its learning trajectory based on the sentiment scores associated with user feedback,ensuring a dynamic response to both positive and negative sentiments.This dual approach enhances the system’s adapt-ability to changing user preferences and improves its contentment understanding.Our methodology involves a comprehensive analysis of both the content of learning materials and the behaviors and preferences of learners,facilitating a more personalized learning experience.By dynamically adjusting recommendations based on real-time user data and behavioral analysis,our system leverages the collective insights of similar users and rele-vant content.We validated our approach against three datasets-MovieLens,Amazon,and a proprietary TEL dataset—and saw significant improvements in recommendation precision,F-score,and mean absolute error.The results indicate the potential of integrating sentiment analysis and adaptive learning rates into TEL recommender systems,marking a step forward in developing more responsive and user-centric educational technologies.This study paves the way for future advancements in TEL systems,emphasizing the importance of emotional intelli-gence and adaptability in enhancing the learning experience.展开更多
In the upcoming B5G/6G era,Virtual Reality(VR)over wireless has become a typical application,which is an inevitable trend in the development of video.However,in immersive and interactive VR experiences,VR services typ...In the upcoming B5G/6G era,Virtual Reality(VR)over wireless has become a typical application,which is an inevitable trend in the development of video.However,in immersive and interactive VR experiences,VR services typically exhibit high delay,while simultaneously posing challenges for the energy consumption of local devices.To address these issues,this paper aims to improve the performance of VR service in the edge-terminal cooperative system.Specifically,we formulate a joint Caching,Computing,and Communication(3C)VR service policy problem by optimizing the weighted sum of the total VR delivery delay and the energy consumption of local devices.To design the optimal VR service policy,the optimization problem is decoupled into three independent subproblems to be solved separately.To improve the caching efficiency within the network,a Bert-based user interest analysis method is first proposed to accurately characterize the content request behavior.Based on this,a service cost minimum-maximization problem is formulated under the consideration of performance fairness among users.Then,the joint caching and computing scheme is derived for each user with a given allocation of communication resources while a bisection-based communication scheme is acquired with the given information on the joint caching and computing policy.With alternative optimization,an optimal policy for joint 3C based on user interest can be finally obtained.Simulation results are presented to demonstrate the superiority of the proposed user interest-aware caching scheme and the effectiveness of the joint 3C optimization policy while considering user fairness.Our code is available at https://github.com/mrfuqaq1108/Interest-Aware-Joint-3C-Optimization.展开更多
Identifying influential users in social networks is of great significance in areas such as public opinion monitoring and commercial promotion.Existing identification methods based on Graph Neural Networks(GNNs)often l...Identifying influential users in social networks is of great significance in areas such as public opinion monitoring and commercial promotion.Existing identification methods based on Graph Neural Networks(GNNs)often lead to yield inaccurate features of influential users due to neighborhood aggregation,and require a large substantial amount of labeled data for training,making them difficult and challenging to apply in practice.To address this issue,we propose a semi-supervised contrastive learning method for identifying influential users.First,the proposed method constructs positive and negative samples for contrastive learning based on multiple node centrality metrics related to influence;then,contrastive learning is employed to guide the encoder to generate various influence-related features for users;finally,with only a small amount of labeled data,an attention-based user classifier is trained to accurately identify influential users.Experiments conducted on three public social network datasets demonstrate that the proposed method,using only 20%of the labeled data as the training set,achieves F1 values that are 5.9%,5.8%,and 8.7%higher than those unsupervised EVC method,and it matches the performance of GNN-based methods such as DeepInf,InfGCN and OlapGN,which require 80%of labeled data as the training set.展开更多
Objective： To understand the prevalence and behavioral risk factors of HIV infection among injection drug users in the Pearl River Delta Region （PRDR） of Guangdong province, and to provide evidence for establishing...Objective： To understand the prevalence and behavioral risk factors of HIV infection among injection drug users in the Pearl River Delta Region （PRDR） of Guangdong province, and to provide evidence for establishing effective intervention strategies. Methods： Face to face interviews were conducted and serum samples from injection drug users from detoxification centers and the community were collected for HIV screening. Results： 655 drug users were recruited and interviewed. The HIV seropositive rate was 29.0%. 99.5 % of subjects were injection drug users （IDUs）, of whom,75.4% reported sharing injection equipment. Conclusion： HIV prevalence among injection drug users is high in the PRDR of Guangdong. Injection drug use is the principal behavioral risk factor for HIV transmission. Pragmatic harm reduction programs should be implemented to prevent the spread of HIV infection.展开更多
New idea studying urban parks was opened up by "Reflection on Urban Park:Public Space and Multi-culture". By introducing anthropology into planning and design methodology of urban public space, it provided a...New idea studying urban parks was opened up by "Reflection on Urban Park:Public Space and Multi-culture". By introducing anthropology into planning and design methodology of urban public space, it provided a new research method for the planning of urban park in our country. Through introduction and assessment of the book, existing problems and suggestions of the construction of our urban parks were proposed. In the perspective of urban parks' users, by the method of ethnology and anthropology, cultural diversity of urban public space would be investigated, paying attention to the usage behavior and different cultural characteristics, thinking about how to respect ecology and environmental construction of parks and coordinate the relation between culture and ecology while cultural diversity was respected. What should be considered in the construction of urban parks was not only culture but also ecological environment protection when culture was respected and citizens' interests during environment construction. These were also the fundamental problems needed to be considered and solved in parks' planning, construction and operation.展开更多
The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-gener...The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.展开更多
文摘A recommender system is a tool designed to suggest relevant items to users based on their preferences and behaviors.Collaborative filtering,a popular technique within recommender systems,predicts user interests by analyzing patterns in interactions and similarities between users,leveraging past behavior data to make personalized recommendations.Despite its popularity,collaborative filtering faces notable challenges,and one of them is the issue of grey-sheep users who have unusual tastes in the system.Surprisingly,existing research has not extensively explored outlier detection techniques to address the grey-sheep problem.To fill this research gap,this study conducts a comprehensive comparison of 12 outlier detectionmethods(such as LOF,ABOD,HBOS,etc.)and introduces innovative user representations aimed at improving the identification of outliers within recommender systems.More specifically,we proposed and examined three types of user representations:1)the distribution statistics of user-user similarities,where similarities were calculated based on users’rating vectors;2)the distribution statistics of user-user similarities,but with similarities derived from users represented by latent factors;and 3)latent-factor vector representations.Our experiments on the Movie Lens and Yahoo!Movie datasets demonstrate that user representations based on latent-factor vectors consistently facilitate the identification of more grey-sheep users when applying outlier detection methods.
基金grateful for the financial support from the National Key R&D Program of China(2023YFB2407300).
文摘With increasing awareness of environmental protection and rising carbon emission costs,participation in electricity and carbon markets for energy-intensive industrial users will become an effective way to reduce operating costs and carbon emissions.In this regard,a novel Stackelberg game framework is developed in this study for coordinated participation in coupled electricity‒carbon markets.Specifically,generalized carbon emission models and electricity consumption models for different energy-intensive industrial users are established,and a Stackelberg game-based interactive operation strategy is proposed for load aggregators(LAs)and energy-intensive industrial users in joint electricity‒carbon markets,where the LA works as a leader who chooses proper interactive prices to maximize the comprehensive benefit,whereas energy-intensive industrial users serve as followers who minimize the total energy costs in response to the interactive prices set by the LA.Then,the existence and uniqueness of the Stackelberg equilibrium(SE)are analyzed,and a decentralized solution algorithm is suggested to reach the SE.Finally,the simulation results demonstrate that the proposed interactive operation strategy can not only increase the profit of the LA but also reduce the cost of energy-intensive industrial users,which achieves a win-win result.
文摘This study introduces an advanced recommender system for technology enhanced learning(TEL)that synergizes neural collaborative filtering,sentiment analysis,and an adaptive learning rate to address the limitations of traditional TEL systems.Recognizing the critical gap in existing approaches—primarily their neglect of user emotional feedback and static learning paths—our model innovatively incorporates sentiment analysis to capture and respond to nuanced emotional feedback from users.Utilizing bidirectional encoder representations from Transformers for sentiment analysis,our system not only understands but also respects user privacy by processing feedback without revealing sensitive information.The adaptive learning rate,inspired by AdaGrad,allows our model to adjust its learning trajectory based on the sentiment scores associated with user feedback,ensuring a dynamic response to both positive and negative sentiments.This dual approach enhances the system’s adapt-ability to changing user preferences and improves its contentment understanding.Our methodology involves a comprehensive analysis of both the content of learning materials and the behaviors and preferences of learners,facilitating a more personalized learning experience.By dynamically adjusting recommendations based on real-time user data and behavioral analysis,our system leverages the collective insights of similar users and rele-vant content.We validated our approach against three datasets-MovieLens,Amazon,and a proprietary TEL dataset—and saw significant improvements in recommendation precision,F-score,and mean absolute error.The results indicate the potential of integrating sentiment analysis and adaptive learning rates into TEL recommender systems,marking a step forward in developing more responsive and user-centric educational technologies.This study paves the way for future advancements in TEL systems,emphasizing the importance of emotional intelli-gence and adaptability in enhancing the learning experience.
基金supported in part by the Graduate Research Innovation Project of Chongqing under grant CYB23237in part by the Doctoral Candidate Innovative Talent Program of CQUPT under grant BYJS202201+3 种基金in part by the National Natural Science Foundation of China(62271096,U20A20157)in part by the Natural Science Foundation of Chongqing,China(cstc2020jcyjzdxmX0024)in part by the University Innovation Research Group of Chongqing(CXQT20017)in part by the Youth Innovation Group Support Program of ICE Discipline of CQUPT(SCIE-QN-2022-04).
文摘In the upcoming B5G/6G era,Virtual Reality(VR)over wireless has become a typical application,which is an inevitable trend in the development of video.However,in immersive and interactive VR experiences,VR services typically exhibit high delay,while simultaneously posing challenges for the energy consumption of local devices.To address these issues,this paper aims to improve the performance of VR service in the edge-terminal cooperative system.Specifically,we formulate a joint Caching,Computing,and Communication(3C)VR service policy problem by optimizing the weighted sum of the total VR delivery delay and the energy consumption of local devices.To design the optimal VR service policy,the optimization problem is decoupled into three independent subproblems to be solved separately.To improve the caching efficiency within the network,a Bert-based user interest analysis method is first proposed to accurately characterize the content request behavior.Based on this,a service cost minimum-maximization problem is formulated under the consideration of performance fairness among users.Then,the joint caching and computing scheme is derived for each user with a given allocation of communication resources while a bisection-based communication scheme is acquired with the given information on the joint caching and computing policy.With alternative optimization,an optimal policy for joint 3C based on user interest can be finally obtained.Simulation results are presented to demonstrate the superiority of the proposed user interest-aware caching scheme and the effectiveness of the joint 3C optimization policy while considering user fairness.Our code is available at https://github.com/mrfuqaq1108/Interest-Aware-Joint-3C-Optimization.
基金supported by the National Key Project of the National Natural Science Foundation of China under Grant No.U23A20305.
文摘Identifying influential users in social networks is of great significance in areas such as public opinion monitoring and commercial promotion.Existing identification methods based on Graph Neural Networks(GNNs)often lead to yield inaccurate features of influential users due to neighborhood aggregation,and require a large substantial amount of labeled data for training,making them difficult and challenging to apply in practice.To address this issue,we propose a semi-supervised contrastive learning method for identifying influential users.First,the proposed method constructs positive and negative samples for contrastive learning based on multiple node centrality metrics related to influence;then,contrastive learning is employed to guide the encoder to generate various influence-related features for users;finally,with only a small amount of labeled data,an attention-based user classifier is trained to accurately identify influential users.Experiments conducted on three public social network datasets demonstrate that the proposed method,using only 20%of the labeled data as the training set,achieves F1 values that are 5.9%,5.8%,and 8.7%higher than those unsupervised EVC method,and it matches the performance of GNN-based methods such as DeepInf,InfGCN and OlapGN,which require 80%of labeled data as the training set.
文摘Objective： To understand the prevalence and behavioral risk factors of HIV infection among injection drug users in the Pearl River Delta Region （PRDR） of Guangdong province, and to provide evidence for establishing effective intervention strategies. Methods： Face to face interviews were conducted and serum samples from injection drug users from detoxification centers and the community were collected for HIV screening. Results： 655 drug users were recruited and interviewed. The HIV seropositive rate was 29.0%. 99.5 % of subjects were injection drug users （IDUs）, of whom,75.4% reported sharing injection equipment. Conclusion： HIV prevalence among injection drug users is high in the PRDR of Guangdong. Injection drug use is the principal behavioral risk factor for HIV transmission. Pragmatic harm reduction programs should be implemented to prevent the spread of HIV infection.
文摘New idea studying urban parks was opened up by "Reflection on Urban Park:Public Space and Multi-culture". By introducing anthropology into planning and design methodology of urban public space, it provided a new research method for the planning of urban park in our country. Through introduction and assessment of the book, existing problems and suggestions of the construction of our urban parks were proposed. In the perspective of urban parks' users, by the method of ethnology and anthropology, cultural diversity of urban public space would be investigated, paying attention to the usage behavior and different cultural characteristics, thinking about how to respect ecology and environmental construction of parks and coordinate the relation between culture and ecology while cultural diversity was respected. What should be considered in the construction of urban parks was not only culture but also ecological environment protection when culture was respected and citizens' interests during environment construction. These were also the fundamental problems needed to be considered and solved in parks' planning, construction and operation.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(RS-2025-00559546)supported by the IITP(Institute of Information&Coummunications Technology Planning&Evaluation)-ITRC(Information Technology Research Center)grant funded by the Korea government(Ministry of Science and ICT)(IITP-2025-RS-2023-00259004).
文摘The advent of sixth-generation(6G)networks introduces unprecedented challenges in achieving seamless connectivity,ultra-low latency,and efficient resource management in highly dynamic environments.Although fifth-generation(5G)networks transformed mobile broadband and machine-type communications at massive scales,their properties of scaling,interference management,and latency remain a limitation in dense high mobility settings.To overcome these limitations,artificial intelligence(AI)and unmanned aerial vehicles(UAVs)have emerged as potential solutions to develop versatile,dynamic,and energy-efficient communication systems.The study proposes an AI-based UAV architecture that utilizes cooperative reinforcement learning(CoRL)to manage an autonomous network.The UAVs collaborate by sharing local observations and real-time state exchanges to optimize user connectivity,movement directions,allocate power,and resource distribution.Unlike conventional centralized or autonomous methods,CoRL involves joint state sharing and conflict-sensitive reward shaping,which ensures fair coverage,less interference,and enhanced adaptability in a dynamic urban environment.Simulations conducted in smart city scenarios with 10 UAVs and 50 ground users demonstrate that the proposed CoRL-based UAV system increases user coverage by up to 10%,achieves convergence 40%faster,and reduces latency and energy consumption by 30%compared with centralized and decentralized baselines.Furthermore,the distributed nature of the algorithm ensures scalability and flexibility,making it well-suited for future large-scale 6G deployments.The results highlighted that AI-enabled UAV systems enhance connectivity,support ultra-reliable low-latency communications(URLLC),and improve 6G network efficiency.Future work will extend the framework with adaptive modulation,beamforming-aware positioning,and real-world testbed deployment.
