检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Two-stage Vehicle Pair Dispatch in Multi-hop Ridesharing 26

Two-stage Vehicle Pair Dispatch in Multi-hop Ridesharing

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wei, Xiaobo Li, Peng Huang, Weiyi Liu, Zhiyuan Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Ridesharing benefits the economy and the environment. In multi-hop ridesharing, passengers are permitted to switch vehicles within a single trip, extending the flexibility of conventional ridesharing. Nonetheless, vehicle dispatch is a difficult issue in multi-hop ridesharing. We subdivide the vehicle dispatching problem into the vehicle pairing problem and the request selection problem within a vehicle pair. To address these subproblems, we propose a two-stage framework for vehicle pair dispatching. In the initial stage, we model the vehicle pairing problem as a maximum vehicle-vehicle matching problem in a general graph, which differs from the conventional vehicle-request matching problem in a bipartite graph. The vehicle pairing algorithm is proposed to efficiently solve the vehicle pairing problem. In the second stage, we model the request selection problem as a multidimensional knapsack problem (d-KP) and propose an LP-relaxation request selection algorithm with an approximation ratio 1/5. Experiments conducted on a real-world dataset demonstrate the economic benefit of our proposed two-stage framework. © 2023 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

On Privacy-Preserving Task Assignment for Heterogeneous Users in Mobile Crowdsensing 26

On Privacy-Preserving Task Assignment for Heterogeneous User...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Ji Li, Peng Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350331684

Task assignment is a key challenge in mobile crowd-sensing because of the varying capabilities of crowd users. Location-based task assignment schemes require users to upload their location to an untrusted platform, which raises many privacy concerns. However, stronger privacy preservation may lead to lower system utility. It is challenging to maximize system utility under privacy preservation for users. In this paper, we propose a privacy-preserving task assignment for heterogeneous users (PTAH) problem in mobile crowdsensing. Specifically, we divide users into two groups: private users with location privacy requirements and public users without location privacy requirements. We first design a privacy-preserving mechanism to obfuscate the actual location of private users. Then we construct a relationship graph based on the locations between users and tasks. We prove that the PTAH problem is an NP-hard problem, so to maximize the system utility, we propose an approximation algorithm based on the greedy algorithm. Then we propose a multi-thread cooperative simulated annealing algorithm to search for a better approximate solution. Finally, we conducted simulations based on the widely-used real-world Roma dataset. The results show that our proposed algorithm consistently outperforms other baseline algorithms. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

An FPGA-based QDI Asynchronous Circuits Design Methodology

An FPGA-based QDI Asynchronous Circuits Design Methodology

引用

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Guangyao Lin Jinghai Wang Zeyang Xu Zhiyi Yu Shanlin Xiao School of Microelectronics Science and Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems

ISBN: (数字)9798331530723

ISBN: (纸本)9798331530730

Quasi delay insensitive (QDI) circuits, as a type of asynchronous circuits, have unique advantages such as high robustness, low power consumption, and event driven, so they have the potential to be applied in fields such as Network-on-Chip (NoC). However, due to the lack of supporting EDA tools, designing QDI circuits is difficult, resulting in limited application. This article proposes a systematic FPGA-based QDI circuit design methodology based on existing EDA tools, and designs a QDI router according to the proposed methodology. The designed QDI router reduces power consumption by 52.1% and latency by 19.7% compared to synchronous router with similar structure.

关键词： Integrated circuit technology Power demand Systematics Design methodology Network-on-chip Throughput Robustness Delays Field programmable gate arrays Asynchronous circuits

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Arbitration Circuit Optimization for Multicore Neuromorphic Processors

Asynchronous Arbitration Circuit Optimization for Multicore ...

引用

International Conference on Solid-State and Integrated Circuit technology

作者： Jiajie Guo Guangyao Lin Bohan Wang Zhiyi Yu Shanlin Xiao School of Microelectronics Science and Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems

ISBN: (数字)9798350361834

ISBN: (纸本)9798350361841

Spiking Neural Networks (SNNs), with their significant advantages of low power consumption and low latency, are a promising approach for edge computing and have attracted considerable attention in the scientific community. Multicore neuromorphic processors have been demonstrated as an effective solution for constructing large-scale SNN models. However, as the scale of these networks increases, the resource and power demands of inter-core communication escalate significantly. The inter-core arbiter represents an important component of the Power-Performance-Area (PPA) bottleneck. Compared to synchronous circuits, asynchronous circuits feature lower power consumption and enhanced robustness, making them more suitable for inter-core communication. We propose an asynchronous Quasi-Delay Insensitive (QDI) arbitration circuit based on hybrid encoding method and the NCL_X pipeline architecture, achieving a 22% improvement in speed and a 23% reduction in power consumption.

关键词： Power demand Program processors Neuromorphics Multicore processing Circuits Pipelines computer architecture Spiking neural networks Encoding Robustness

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Fault-Tolerant Sparse Coding for Spiking Neural Networks Accelerator

Energy-Efficient and Fault-Tolerant Sparse Coding for Spikin...

引用

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Bo Li Wei Liu Yue Liu Xiao Huang Zhiyi Yu Shanlin Xiao School of Microelectronics Science and Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems

ISBN: (数字)9798331530723

ISBN: (纸本)9798331530730

Spiking Neural Networks (SNNs) exhibit superior energy efficiency and fault tolerance compared to Artificial Neural Networks (ANNs). Due to their spike-based nature, input signals must be encoded into spike trains. However, traditional spiking coding schemes often encounter a trade-off between energy efficiency and fault tolerance. To overcome this limitation, we propose a novel coding scheme, Spiking Sparse Coding (SSC), which achieves both high sparsity and enhanced fault tolerance. SSC not only improves network performance but also reduces the number of spikes by 93.69%, resulting in a 76.47% increase in energy efficiency. Additionally, SSC enhances network fault tolerance, with accuracy improvements of up to 12.06% under identical noise interference conditions. We deployed the network on the ZCU102 FPGA platform, operating at a frequency of 200 MHz with a power consumption of 409 mW. On the MNIST dataset, we achieved a classification accuracy of 95.84%. The training speed and energy consumption were 12656 frames per second and 0.032 mJ per image, the inference speed and energy consumption were 19279 frames per second and 0.021 mJ per image.

关键词： Training Fault tolerance Energy consumption Accuracy Power demand Fault tolerant systems Noise Spiking neural networks Encoding Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Thermally tunable high Q-factor and low-power silicon resonators using Graphene transparent electrodes

Thermally tunable high Q-factor and low-power silicon resona...

引用

2023 Applied Optics and Photonics China: Laser technology and Applications;and Optoelectronic Devices and Integration, AOPC 2023

作者： Hong, Qilin Xu, Ping Xu, Wei Zhu, Zhihong College of Advanced Interdisciplinary Studies Hunan Provincial Key Laboratory of Novel Nano Optoelectronic Information Materials and Devices National University of Defense Technology Changsha410073 China Nanhu Laser Laboratory National University of Defense Technology Changsha410073 China Institute for Quantum Information State Key Laboratory of High-Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha410073 China

ISBN: (纸本)9781510672246

Tunable and low-power microcavities play a vital role in facilitating the development of large-scale photonic integrated circuits. Among various tuning methods, thermal tuning has gained significant popularity due to its convenience and stability, especially in the fields of optical neural networks and quantum information processing. In recent years, graphene thermal tuning has emerged as a promising technique, offering both tunability and power efficiency by eliminating the need for thick spacers to prevent light absorption. In this study, we propose and fabricate a silicon-based on-chip Fano resonator with graphene nano-heaters. This innovative Fano structure incorporates a scattering block and can be easily manufactured in large quantities. Experimental results demonstrate that the resonator exhibits desirable characteristics, including a high quality factor of approximately 31000 and a low state-switching power consumption of around 1 mW. The temporal responses of the microcavity exhibit satisfactory modulation speed, with a rise time of 9.8 µs and a fall time of 16.6 µs. The findings of this research offer an alternative solution for the future development of large-scale tunable and low-power-consumption optical networks, with potential applications in optical filters and switches. © 2023 SPIE.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Overview of the SIGHAN 2024 Shared Task for Chinese Dimensional Aspect-Based Sentiment Analysis 10

Overview of the SIGHAN 2024 Shared Task for Chinese Dimensio...

引用

10th SIGHAN Workshop on Chinese Language processing, SIGHAN 2024

作者： Lee, Lung-Hao Yu, Liang-Chih Wang, Suge Liao, Jian Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Taiwan Department of Information Management Yuan Ze University Taiwan School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9798891761551

This paper describes the SIGHAN-2024 shared task for Chinese dimensional aspect-based sentiment analysis (ABSA), including task description, data preparation, performance metrics, and evaluation results. Compared to representing affective states as several discrete classes (i.e., sentiment polarity), the dimensional approach represents affective states as continuous numerical values (called sentiment intensity) in the valence-arousal space, providing more fine-grained affective states. Therefore, we organized a dimensional ABSA (shorted dimABSA) shared task, comprising three subtasks: 1) intensity prediction, 2) triplet extraction, and 3) quadruple extraction, receiving a total of 214 submissions from 61 registered participants during evaluation phase. A total of eleven teams provided selected submissions for each subtask and seven teams submitted technical reports for the subtasks. This shared task demonstrates current NLP techniques for dealing with Chinese dimensional ABSA. All data sets with gold standards and evaluation scripts used in this shared task are publicly available for future research. © 2024 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

PUMTD:Privacy-Preserving User-Profile Matching Protocol in Social Networks

引用

China Communications 2022年第6期19卷 77-90页

作者： Jianhong Zhang Haoting Han Hongwei Su Zhengtao Jiang Changgen Peng School of Information Sciences and Technology North China University of TechnologyBeijing 100043China Key Laboratory of Cryptography of Zhejiang Province Hangzhou Normal UniversityHangzhou 311121China Guizhou Provincial Key Laboratory of Public Big Data Guizhou UniversityGuiyang 550025China School of Computer and Cyber Sciences Communication University of ChinaBeijing 100025China

User profile matching can establish social relationships between different users in the social *** the user profile is matched in plaintext,the user's privacy might face a security *** there exist some schemes realizing privacypreserving user profile matching,the resource-limited users or social service providers in these schemes need to take higher computational complexity to ensure the privacy or matching of the *** overcome the problems,a novel privacy-preserving user profile matching protocol in social networks is proposed by using t-out-of n servers and the bloom filter technique,in which the computational complexity of a user is reduced by applying the Chinese Remainder Theorem,the matching users can be found with the help of any t matching servers,and the privacy of the user profile is not ***,if at most t-1 servers are allowed to collude,our scheme can still fulfill user profile privacy and user query ***,the performance of the proposed scheme is compared with the other two schemes,and the results show that our scheme is superior to them.

关键词： user profile matching Chinese remainder theorem privacy-preserving query privacy

来源：评论

学校读者我要写书评

暂无评论

HighlightRemover: Spatially Valid Pixel Learning for Image Specular Highlight Removal 24

HighlightRemover: Spatially Valid Pixel Learning for Image S...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Ling Ma, Yidong Jiang, Zhi He, Weilei Bao, Zhongyun Fu, Gang Xu, Wenju Xiao, Chunxia School of Computer Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Realtime Industrial Systems Wuhan University of Science and Technology Wuhan China School of Computer Science Wuhan University Wuhan China Department of Computing Hong Kong Polytechnic University Hong Kong Amazon Palo Alto United States

ISBN: (纸本)9798400706868

Recently, learning-based methods have made significant progress for image specular highlight removal. However, many of these approaches treat all the image pixels uniformly, overlooking the negative impact of invalid pixels on feature reconstruction. This oversight often leads to undesirable outcomes, such as color distortion or residual highlights. In this paper, we propose a novel image specular highlight removal network called HighlightRNet, which utilizes valid pixels as references to reconstruct the highlight-free image. To achieve this, we introduce a context-aware fusion block (CFBlock) that aggregates information in four directions, effectively capturing global contextual information. Additionally, we introduce a location-aware feature transformation module (LFTModule) to adaptively learn the valid pixels for feature reconstruction, thereby avoiding information errors caused by invalid pixels. With these modules, our method can produce high-quality highlight-free results without color distortion and highlight residual. Furthermore, we develop a multiple light image-capturing system to construct a large-scale highlight dataset called NSH, which exhibits minimal misalignment in image pairs and minimal brightness variation in non-highlight regions. Experimental results on various datasets demonstrate the superiority of our method over state-of-the-art methods, both qualitatively and quantitatively. © 2024 ACM.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：