In the dynamic landscape of online social networks, recognizing sensitive content is essential for safeguarding user privacy, fostering inclusivity, and enhancing diversity awareness. Building on prior research, this ...
详细信息
Sentiment analysis, a critical branch of Natural Language Processing (NLP), is pivotal for uncovering the emotional undertones within textual data, thereby revealing public sentiments on diverse topics. This study con...
详细信息
Emotion recognition in text has become an essential research area within artificial intelligence and natural language processing due to its applications in sentiment analysis, human-computer interaction, and social me...
详细信息
Integration of inverter-based resources (IBRs) which lack the intrinsic characteristics such as the inertial response of the traditional synchronous-generator (SG)-based sources presents a new challenge in the form of...
详细信息
Stochastic computing(SC)has a substantial amount of study on application-specific integrated circuit(ASIC)design for artificial intelligence(AI)edge computing,especially the convolutional neural network(CNN)***,SC has...
详细信息
Stochastic computing(SC)has a substantial amount of study on application-specific integrated circuit(ASIC)design for artificial intelligence(AI)edge computing,especially the convolutional neural network(CNN)***,SC has little to no optimization on field-programmable gate array(FPGA).Scaling up the ASIC logic without FPGA-oriented designs is inefficient,while aggregating thousands of bitstreams is still challenging in the conventional *** research has reinvented several FPGA-efficient 8-bit SC CNN computing architectures,i.e.,SC multiplexer multiply-accumulate,multiply-accumulate function generator,and binary rectified linear unit,and successfully scaled and implemented a fully parallel CNN model on Kintex7 *** proposed SC hardware only compromises 0.14%accuracy compared to binary computing on the handwriting Modified National Institute of Standards and Technology classification task and achieved at least 99.72%energy saving per image feedforward and 31?more data throughput than modern *** to SC,early decision termination pushed the performance baseline exponentially with minimum accuracy loss,making SC CNN extremely lucrative for AI edge computing but limited to classification *** SC's inherent noise heavily penalizes CNN regression performance,rendering SC unsuitable for regression tasks.
This work presents an accelerator that performs blind deblurring based on the dark channel prior. The alternating minimization algorithm is leveraged for latent image and blur kernel estimation. A 2-D Laplace equation...
详细信息
Graph convolutional neural networks(GCNs)have emerged as an effective approach to extending deep learning for graph data analytics,but they are computationally challenging given the irregular graphs and the large num-...
详细信息
Graph convolutional neural networks(GCNs)have emerged as an effective approach to extending deep learning for graph data analytics,but they are computationally challenging given the irregular graphs and the large num-ber of nodes in a *** involve chain sparse-dense matrix multiplications with six loops,which results in a large de-sign space for GCN *** work on GCN acceleration either employs limited loop optimization techniques,or determines the design variables based on random sampling,which can hardly exploit data reuse efficiently,thus degrading system *** overcome this limitation,this paper proposes GShuttle,a GCN acceleration scheme that maximizes memory access efficiency to achieve high performance and energy *** systematically explores loop opti-mization techniques for GCN acceleration,and quantitatively analyzes the design objectives(e.g.,required DRAM access-es and SRAM accesses)by analytical calculation based on multiple design *** further employs two ap-proaches,pruned search space sweeping and greedy search,to find the optimal design variables under certain design *** demonstrated the efficacy of GShuttle by evaluation on five widely used graph *** experimental simulations show that GShuttle reduces the number of DRAM accesses by a factor of 1.5 and saves energy by a factor of 1.7 compared with the state-of-the-art approaches.
Topology is usually perceived intrinsically immutable for a given *** argue that optical topologies do not immediately enjoy such ***'optical skyrmions'as an example,we show that they will exhibit varying text...
详细信息
Topology is usually perceived intrinsically immutable for a given *** argue that optical topologies do not immediately enjoy such ***'optical skyrmions'as an example,we show that they will exhibit varying textures and topological invariants(skyrmion numbers),depending on how to construct the skyrmion vector when projecting from real to parameter *** demonstrate the fragility of optical skyrmions under a ubiquitous scenario-simple reflection off an optical *** topology is not without benefit,but it must not be assumed.
As big data,Artificial Intelligence,and Vehicle-to-Everything(V2X)communication have advanced,Intelligent Transportation Systems(ITS)are being developed to enable efficient and safe transportation *** Toll Collection(...
详细信息
As big data,Artificial Intelligence,and Vehicle-to-Everything(V2X)communication have advanced,Intelligent Transportation Systems(ITS)are being developed to enable efficient and safe transportation *** Toll Collection(ETC),which is one of the services included in ITS systems,is an automated system that allows vehicles to pass through toll plazas without stopping for manual *** ETC system is widely deployed on highways due to its contribution to stabilizing the overall traffic system *** ensure secure and efficient toll payments,designing a distributed model for sharing toll payment information among untrusted toll service providers is ***,the current ETC system operates under a centralized ***,both toll service providers and toll plazas know the toll usage history of *** raises concerns about revealing the entire driving routes and patterns of *** address these issues,blockchain technology,suitable for secure data management and data sharing in distributed systems,is being applied to the ETC *** enables efficient and transparent management of ETC ***,the public nature of blockchain poses a challenge where users’usage records are exposed to all *** tackle this,we propose a blockchain-based toll ticket model named AnonymousTollPass that considers the privacy of *** proposed model utilizes traceable ring signatures to provide unlinkability between tickets used by a vehicle and prevent the identity of the vehicle using the ticket from being identified among the ring members for the ***,malicious vehicles’identities can be traced when they attempt to reuse *** conducting simulations,we show the effectiveness of the proposed model and demonstrate that gas fees required for executing the proposed smart contracts are only 10%(when the ring size is 50)of the fees required in previous studies.
Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distri...
详细信息
Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.
暂无评论