检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Xiang, Axin Gao, Hongfeng Tian, Youliang Wang, Linjie Xiong, Jinbo State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guizhou Guiyang550025 China Guizhou Provincial Key Laboratory of Cryptography and Blockchain Technology Guizhou University Guizhou Guiyang550025 China Network and Information Management Center Guizhou University Guizhou Guiyang550025 China School of Data Science Tongren University Guizhou Tongren554300 China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou350117 China

Internet of Medical Things (IoMT) provides real-time data collection and access services to medical entities by connecting their devices to Internet. However, within such a complex architecture, achieving patient-centric data access still presents trustworthiness challenges. Ciphertext-policy attribute-based encryption (CP-ABE) and blockchain are both the promising cryptographic technologies that support patients with secure and fine-grained access control over their data. Nevertheless, both have their unique key management issues. In this paper, we propose a novel patient-centric and trusted data access (PCT-DA) system in blockchain-enabled IoMT. Firstly, we develop an online/offline encryption and verifiable outsourced decryption CP-ABE scheme to relieves the computation pressure on patients/users. Secondly, we design a flexible attribute-based key management mechanism to overcome the security drawbacks of data encryption keys and user attribute keys. Finally, we build a trusted integrity audit contract to guarantee the incentive fairness of patients/users, allowing them to release/access medical data honestly. Moreover, theoretical analyses prove that the PCT-DA system not only achieves confidentiality, integrity, auditability and forward/backward security, but also guarantees static security under random oracles. Simulation experiments indicate that our proposal reduces the time cost by approximately 14.14 seconds over state-of-the-art and is more flexible in BE-IoMT. © 2023, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

OAA: An Abstraction for Efficient Accelerator Adaptation in Deep Learning Frameworks

OAA: An Abstraction for Efficient Accelerator Adaptation in ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Zhengxian Lu Chengkun Du Xueshuo Xie Qiankun Dong Cheng Gong Tao Li College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Huawei Technologies Zhejiang China Haihe Lab of ITAI Tianjin China College of Software Nankai University Tianjin China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Deep learning frameworks rely on specific runtime and computation libraries to rewrite the backend for the adaptation of specialized accelerators, which is inefficient and hard to guarantee performance. This paper solves the issue by proposing an Operator Adaptation Abstraction (OAA) that lies between the framework and the libraries. In addition, this paper optimizes training performance based on the hardware characteristics of the accelerator. We designed experiments based on Ascend 910 and OneFlow to verify the effectiveness of OAA. Our adaptation includes more than 50 Ascend operators, achieving up to 2.0x throughput compared to the official adaptation version of PyTorch. The experiments validate that the adaptation method proposed in this paper can effectively retain the advantages of both the framework and the accelerator.

关键词： Deep learning Training Runtime Neural networks Throughput Libraries Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Semantic and Emotional Dual Channel for Emotion Recognition in Conversation

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Zhenyu Zhang, Zhibo Cheng, Yuhu Zhang, Tong Wang, Xuesong Jinan250353 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China China University of Mining and Technology Engineering Research Center of Intelligent Control for Underground Space Ministry of Education Xuzhou Key Laboratory of Artificial Intelligence and Big Data School of Information and Control Engineering Xuzhou221116 China South China University of Technology Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information School of Computer Science and Engineering Guangzhou510006 China Pazhou Lab Guangzhou510335 China Engineering Research Center Ministry of Education on Health Intelligent Perception and Paralleled Digital-Human Guangzhou China

Emotion recognition in conversation (ERC) aims at accurately identifying emotional states expressed in conversational content. Existing ERC methods, although relying on semantic understanding, often encounter challenges when confronted with incomplete or misleading semantic information. In addition, when dealing with the interaction between emotional and semantic information, existing methods are often difficult to effectively distinguish the complex relationship between the two, which affects the accuracy of emotion recognition. To address the problems of semantic misdirection and emotional cross-talk encountered by traditional models when confronted with complex conversational data, we propose a semantic and emotional dual channel (SEDC) strategy for emotion recognition in conversations to process emotional and semantic information independently. Under this strategy, emotion information provides an auxiliary recognition function when the semantics are unclear or lacking, enhancing the accuracy of the model. Our model consists of two modules: the emotion processing module accurately captures the emotional features of each utterance through contrastive learning, and then constructs a dialogue emotion propagation map to simulate the emotional information conveyed in the dialogue;the semantic processing module combines an external knowledge base to enhance the semantic expression of the dialogue through knowledge enhancement strategies. This divide-and-conquer approach allows us to more deeply analyze the emotional and semantic dimensions of complex dialogues. Experimental results on the IEMOCAP, EmoryNLP, MELD, and DailyDialog datasets show that our approach significantly outperforms existing techniques and effectively improves the accuracy of dialogue emotion recognition. Our code is available at https://***/r/SEDC-FCF1. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Secure key-Aggregate keyword Retrieval Scheme Over Encrypted data in Cloud Computing

引用

IEEE Access 2024年 1-1页

作者： Lou, Chunwei Cao, Mingsheng Luo, Yaohua Xu, Hua Gao, Yuan Wang, Weiwei Wang, Dong University of Electronic Science and Technology of China Chengdu 611731 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu 611731 China School of Information Science and Technology Chengdu University of Technology Chengdu 610059 China School of Physics and Electronic Engineering Yancheng Teachers University Yancheng 224007 China China Academy of Railway Sciences Beijing 100081 China School of Computer Science and Engineering and the Center for Cyber Security University of Electronic Science and Technology of China Chengdu 611731 China

key-aggregate keyword retrieval primitive enables a cloud server on behalf of delegated users to securely perform a keyword search over the data encrypted with various public keys. However, existing key-aggregate searchable encryption schemes are insecure against keyword guessing attacks, which result in the privacy leakage of keyword ciphertext and trapdoor. In this paper, we for the first time formulate a secure and efficient key-aggregate searchable encryption for cloud-assisted IoT applications, which not only enables a data owner to securely share the selected documents to multiple users, but also supports data users in delegating the capability of keyword search to a cloud server for searching the desired documents without leaking any privacy of keyword ciphertext and trapdoor. Then, the security of the proposed scheme is formally defined and proven to be secure against the indistinguishable selective-file chosen keyword attacks. The flexibility and practicability of the formulated scheme is also demonstrated by theoretical evaluations and experimental simulations. Author

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Robust Dynamic Broadcasting for Multi-Hop Wireless networks Under Time-Varying Connectivity and Dynamic SINR

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tian, Xiang Yu, Jiguo Luo, Chuanwen Yu, Dongxiao Wang, Guijuan Feng, Bin Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Taishan University School of Information Science and Technology 271000 China

Throughput-optimal dynamic broadcasting is an essential cornerstone for the efficient operation of Multi-hop Wireless networks (MWNs). Most existing algorithms for this problem were developed assuming static interference environments and network connectivity. However, wireless interference environments and network connectivity are inherently time-varying in real-world scenarios, primarily due to uncontrollable interference sources and unreliable links. Such time-varying characteristics make these existing algorithms less robust. In this paper, we study the robust throughput-optimal dynamic broadcasting for MWNs with multi-dimensional time-varying characteristics in terms of interference environments, network connectivity, and data arrival. We model the time-varying link existence states using a random process and characterize the time-varying interference environments through a dynamic variant of the classical Signal-to-Interference-plus-Noise-Ratio (SINR) model. In this variant, the SINR model parameters are dynamically adjusted over time by an adversary. Based on this, we first design a Robust Throughput-optimal Dynamic Broadcast (RTDB) algorithm which makes efficient slot-based max-weight link scheduling, power allocation, and data forwarding decisions in each time slot. We then prove its throughput-optimality in time-varying acyclic directed MWNs under the dynamic SINR model. The effectiveness of RTDB is validated via numerous simulations. © 2002-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Prediction Method Based on MODWT-EMD for Time Series in Wireless Sensor networks 16

A Hybrid Prediction Method Based on MODWT-EMD for Time Serie...

引用

16th IEEE International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2021

作者： Wang, Zhongmin Jia, Jingwen Gao, Cong Chen, Yanping Xia, Hong Xi'an University of Posts and Telecommunications Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an China Xi'an University of Posts and Telecommunications School of Computer Science Technology Xi'an China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China

ISBN: (纸本)9781665405539

Time series is the main form of sensor data. Time series prediction is conducive to reduce the energy consumption of sensor nodes and increase the service life. As time cost and computation cost of the existing hybrid prediction methods for time series are not good, this paper proposes a hybrid prediction method based on MODWT-EMD for time series. Firstly, the original time series is decomposed into multiple frequency components by Maximal Overlapping Discrete Wavelet Transform (MODWT). Secondly, the multiple frequency components are decomposed successively by Empirical Mode Decomposition (EMD) to obtain IMF components and residuals. IMFs and residuals contain the feature information of time series. Then, the importance of the extracted feature information is scored and sorted by random forest. We select feature information with a higher score. Finally, the selected feature information is input into Bi-GRU for training. We predicted the original time series by the trained Bi-GRU and obtained the prediction results. The experimental results show that the method proposed in this paper can predict the time series effectively. © 2021 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

TSdetector: Temporal-Spatial Self-correction Collaborative Learning for Colonoscopy Video Detection

arXiv

引用

arXiv 2024年

作者： Wang, Kai-Ni Wang, Haolin Zhou, Guang-Quan Wang, Yangang Yang, Ling Chen, Yang Li, Shuo School of Biological Science and Medical Engineering Southeast University Nanjing China Jiangsu Key Laboratory of Biomaterials and Devices Southeast University Nanjing China Laboratory of Image Science and Technology Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China TUGE Healthcare Nanjing China Institute of Medical Technology Peking University Health Science Center China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

CNN-based object detection models that strike a balance between performance and speed have been gradually used in polyp detection tasks. Nevertheless, accurately locating polyps within complex colonoscopy video scenes remains challenging since existing methods ignore two key issues: intra-sequence distribution heterogeneity and precision-confidence discrepancy. To address these challenges, we propose a novel Temporal-Spatial self-correction detector (TSdetector), which first integrates temporal-level consistency learning and spatial-level reliability learning to detect objects continuously. Technically, we first propose a global temporal-aware convolution, assembling the preceding information to dynamically guide the current convolution kernel to focus on global features between sequences. In addition, we designed a hierarchical queue integration mechanism to combine multi-temporal features through a progressive accumulation manner, fully leveraging contextual consistency information together with retaining long-sequence-dependency features. Meanwhile, at the spatial level, we advance a position-aware clustering to explore the spatial relationships among candidate boxes for recalibrating prediction confidence adaptively, thus eliminating redundant bounding boxes efficiently. The experimental results on three publicly available polyp video dataset show that TSdetector achieves the highest polyp detection rate and outperforms other state-of-the-art methods. The code can be available at https://***/soleilssss/TSdetector. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Energy-time entanglement coexisting with fiber-optical communication in the telecom C band

引用

Physical Review A 2023年第2期108卷 L020601-L020601页

作者： Yun-Ru Fan Yue Luo Zi-Chang Zhang Yun-Bo Li Sheng Liu Dong Wang De-Chao Zhang Guang-Wei Deng You Wang Hai-Zhi Song Zhen Wang Li-Xing You Chen-Zhi Yuan Guang-Can Guo Qiang Zhou Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu 610054 China Department of Fundamental Network Technology China Mobile Research Institute Beijing 100053 China Southwest Institute of Technical Physics Chengdu 610041 China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai 200050 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei 230026 China

We study the coexistence of energy-time entanglement with fiber-optical communication in the telecom C band. The property of noise from wavelength-multiplexed classical channels is characterized with different wavelength settings. With the largest noise, i.e., the worst case, we measure the entanglement property of the distributed energy-time entangled photon pairs at different data rates of fiber-optical communication. After being distributed over 40-km spooled fiber coexisting with a bidirectional data rate of 20 Gbps, a visibility of 82.01±1.10% is obtained by measuring the Franson interference. With the Bennett-Brassard-Mermin 1992 (BBM92) protocol, a secret key rate of 343 bits per second is reached over the 40-km spooled fiber coexisting with a bidirectional data rate of 10 Gbps. Our result paves the way for developing a cost-effective quantum entanglement network compatible with fiber communication systems.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective

arXiv

引用

arXiv 2025年

作者： Zheng, Guanhua Sang, Jitao Xu, Changsheng The University of Science and Technology of China Hefei230026 China The School of Computer and Information Technology The Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China The National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China The University of Chinese Academy of Sciences China

Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original gradients. However, these methods lack a solid theoretical foundation and exhibit perplexing behaviors, such as reduced sensitivity to parameter randomization, raising concerns about their reliability and highlighting the need for theoretical justification. In this work, we present a unified theoretical framework for methods like GBP, RectGrad, LRP, and DTD, demonstrating that they achieve input alignment by combining the weights of activated neurons. This alignment improves the visualization quality and reduces sensitivity to weight randomization. Our contributions include: (1) Providing a unified explanation for multiple behaviors, rather than focusing on just one. (2) Accurately predicting novel behaviors. (3) Offering insights into decision-making processes, including layer-wise information changes and the relationship between attributions and model decisions. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interaction-induced inversion of chiral transports

arXiv

引用

arXiv 2024年

作者： Pan, Li Liang, Qian Yang, Chang-An Huang, Yu Liu, Pengjie Xi, Fanying Yi, Wei Zhou, Xiaofan Pan, Jian-Song College of Physics Sichuan University Chengdu610065 China Zhejiang Province Key Laboratory of Quantum Technology and Device School of Physics State Key Laboratory for Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Optical Science and Engineering Zhejiang University Hangzhou310027 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China Anhui Province Key Laboratory of Quantum Network University of Science and Technology of China Hefei230026 China CAS Center For Excellence in Quantum Information and Quantum Physics Hefei230026 China Hefei National Laboratory University of Science and Technology of China Hefei230088 China State Key Laboratory of Quantum Optics and Quantum Optics Devices Institute of Laser spectroscopy Shanxi University Taiyuan030006 China Collaborative Innovation Center of Extreme Optics Shanxi University Shanxi Taiyuan030006 China Key Laboratory of High Energy Density Physics and Technology Ministry of Education Sichuan University Chengdu610065 China

We study the chiral transport of interacting bosons in a two-leg flux ladder with on-site interactions. Focusing on the flux-induced chiral current along the two legs, we show that, counter-intuitively, on-site interactions can reverse the direction of the chiral flow. For a Bose-Einstein condensate whose dynamical evolution is driven by the Gross-Pitaevskii equation under the mean-field approximation, this reversal can be understood as an interaction-induced dynamic occupation inversion, under which single-particle band with opposing chirality becomes heavily populated in the dynamics. This chirality inversion also persists in the two-body dynamics with strong quantum fluctuations beyond the mean-field regime, as demonstrated through time-dependent density-matrix renormalization group and exact diagonalization analyses. Herein, besides the band-occupation-inversion mechanism, we find that the formation of two-body bound states with opposite chirality contributes significantly to the reversed chiral transport. Our discovery highlights the significance of correlation effects in quantum transport, and can be readily demonstrated using cold atoms. © 2024, CC BY-NC-ND.

关键词： Chirality

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：