检索结果-内蒙古大学图书馆

Contrastive Learning Based Human Activity Recognition Using Body Sensors 9

学校读者我要写书评

暂无评论

Contrastive Learning Based Human Activity Recognition Using ...

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Xie, Chuanshi Zhou, Yu Yu, Dandan Sun, Shilong Zhang, Xiao Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The First Affiliated Hospital of Dalian Medical University Information Center Dalian China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China South-Central Minzu University Department of Computer Science China South-Central Minzu University Key Laboratory of Cyber-Physical Fusion Intelligent Computing State Ethnic Affairs Commission Wuhan430074 China

ISBN: (纸本)9798350331240

Pervasive sensing and wearable sensor techniques have been increasingly employed to monitor and recognize human activities through body sensors in areas of smart healthcare and manufacturing. However, conventional machine learning or deep learning based human activity recognition (HAR) requires a large amount of labeled data, which is cost-expensive in real-world scenarios. To tackle this issue, we propose a contrastive learning framework for HAR (CL-HAR), which utilizes the generated unlabeled data as the input and explores the supervised features of the unlabeled data under the principle of self-supervised learning. A simple yet effective backbone network as a feature extractor for subsequent activity recognition is proposed. By using a small portion of the labeled samples as the training set which is fed into our learned feature extractor, we build a classifier and use the rest of the data to verify the feasibility and effectiveness of our CL method. Extensive experiments on three benchamark datasets and one real-world dataset demonstrate that CL-HAR can achieve better classification accuracy than compared supervised and semi-supervised methods with less labelled samples, which is of practical use. © 2023 IEEE.

关键词： Wearable sensors

FedTC: Enabling Communication-Efficient Federated Learning via Transform Coding

学校读者我要写书评

暂无评论

FedTC: Enabling Communication-Efficient Federated Learning v...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yixuan Guan Xuefeng Liu Jianwei Niu Tao Ren State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Federated learning (FL) enables distributed training via periodically synchronizing model updates among participants. Communication overhead becomes a dominant constraint of FL since participating clients usually suffer from limited bandwidth. To tackle this issue, top-k based gradient compression techniques are broadly explored in FL context, manifesting powerful capabilities in reducing gradient volumes via picking significant entries. However, previous studies are primarily conducted on the raw gradients where massive spatial redundancies exist and positions of non-zero (top-k) entries vary greatly between gradients, which both impede the achievement of deeper compressions. Top-k may also degrade the performance of trained models due to biased gradient estimations. Targeting the above issues, we propose FedTC, a novel transform coding based compression framework. FedTC transforms gradients into a new domain with more compact energy distributions, which facilitates reducing spatial redundancies and biases in subsequent sparsification. Furthermore, non-zero entries across clients from different rounds become highly aligned in the transform domain, motivating us to partition the gradients into smaller entry blocks with various alignment levels to better exploit these alignments. Lastly, positions and values of non-zero entries are independently compressed in a block-wise manner with our customized designs, through which a higher compression ratio is achieved. Theoretical analysis and extensive experiments consistently demonstrate the effectiveness of our approach.

关键词： Training Quantization (signal) Costs Federated learning Redundancy Transform coding Estimation

PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yuwei Jin, Zhi Xing, Ying Li, Ge Liu, Fang Zhu, Jiaxin Dou, Wensheng Wei, Jun Affiliated with Nanjing Institute of Software Technology University of Chinese Academy of Sciences Nanjing China Key Laboratory of System Software Chinese Academy of Sciences Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Computer Science Wuhan University Wuhan China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a noticeable gap in existing approaches lies in the oversight of collaborative facets intrinsic to bug resolution, treating the process as a single-stage endeavor. Moreover, most approaches solely take the buggy code snippet as input for LLMs during the patch generation stage. To mitigate the aforementioned limitations, we introduce a novel stage-wise framework named PATCH. Specifically, we first augment the buggy code snippet with corresponding dependence context and intent information to better guide LLMs in generating the correct candidate patches. Additionally, by taking inspiration from bug management practices, we decompose the bug-fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to simulate the collaborative behavior of programmers during the resolution of software bugs. By harnessing these collective contributions, PATCH effectively enhances the bug-fixing capability of LLMs. We implement PATCH by employing the powerful dialogue-based LLM ChatGPT. Our evaluation on the widely used bug-fixing benchmark BFP demonstrates that PATCH has achieved better performance than state-of-the-art LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： computer software maintenance

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

Approximation Methods for Simulation and Equivalence Checking of Noisy Quantum Circuits

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Mingyu Guan, Ji Fang, Wang Ying, Mingsheng Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing101408 China School of Informatics University of Edinburgh EdinburghEH8 9UR United Kingdom Centre for Quantum Software and Information University of Technology Sydney UltimoNSW2007 Australia

In the current NISQ (Noisy Intermediate-Scale Quantum) era, simulating and verifying noisy quantum circuits is crucial but faces challenges such as quantum state explosion and complex noise representations, constraining simulation, and equivalence checking to circuits with a limited number of qubits. This paper introduces an approximation algorithm for simulating and assessing the equivalence of noisy quantum circuits, specifically designed to improve scalability under low-noise conditions. The approach utilizes a novel tensor network diagram combined with singular value decomposition to approximate the tensors of quantum noises. The implementation is based on Google’s TensorNetwork Python package for contraction. Experimental results on realistic quantum circuits with realistic hardware noise models indicate that our algorithm can simulate and check the equivalence of QAOA (Quantum Approximate Optimization Algorithm) circuits with around 200 qubits, surpassing the state-of-the-art methods by noise number and execution time. © 2025, CC BY.

关键词： Qubits

Reply with Sticker: New Dataset and Model for Sticker Retrieval

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liang, Bin Wang, Bingbing Bai, Zhixin Lang, Qiwei Sun, Mingwei Hou, Kaiheng Zhou, Lanjun Xu, Ruifeng Wong, Kam-Fai Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Computer Science and Artificial Intelligence Foshan University Foshan China

Using stickers in online chatting is very prevalent on social media platforms, where the stickers used in the conversation can express someone’s intention/emotion/attitude in a vivid, tactful, and intuitive way. Existing sticker retrieval research typically retrieves stickers based on context and the current utterance delivered by the user. That is, the stickers serve as a supplement to the current utterance. However, in the real-world scenario, using stickers to express what we want to say rather than as a supplement to our words only is also important. Therefore, in this paper, we create a new dataset for sticker retrieval in conversation, called StickerInt, where stickers are used to reply to previous conversations or supplement our words1. Based on the created dataset, we present a simple yet effective framework for sticker retrieval in conversation based on the learning of intention and the cross-modal relationships between conversation context and stickers, coined as Int-RA. Specifically, we first devise a knowledge-enhanced intention predictor to introduce the intention information into the conversation representations. Subsequently, a relation-aware sticker selector is devised to retrieve the response sticker via cross-modal relationships. Extensive experiments on the created dataset show that the proposed model achieves state-of-the-art performance in sticker retrieval2 © 2024, CC BY-NC-ND.

关键词：

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Gene Mutation

学校读者我要写书评

暂无评论

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Ge...

IEEE Conference on Global Communications (GLOBECOM)

作者： Runfeng Lu Yuzhu Sun Haofeng Sun Xiao Fu Bin Luo Xiaojiang Du Jin Shi Nadjib Aitsaadi Mohsen Guizani State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA School of Information Management Nanjing University Nanjing China DAVID UVSQ Université Paris-Saclay France Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

With the rapid expansion of mobile internet usage, the prevalence of the Android operating system on smartphones is steadily growing. However, improper utilization of the Intent mechanism within Android applications can result in security vulnerabilities. Presently, the majority of Android security testing methods, which rely heavily on fuzzing, are predominantly focused on UI interactions, lacking sufficient testing capabilities for Intents. The motivation of this paper is to find a more effective testing method to improve the security detection capabilities of Intents. This paper introduces an Intent fuzzing method based on genetic mutation principles. Initially, we establish an Intent seed library using a text classification model, followed by employing Jaccard distance and minimum edit distance to refine high-quality seeds. Subsequently, we augment the seeds through extensive mutation using genetic algorithms, generating numerous test cases that exhibit structural similarity but contain varied content. During testing, we compare the state before and after Intent testing using image similarity to detect anomalies. Experimental results demonstrate that this method effectively enhances test coverage and identifies potential issues in edge cases. This approach offers an efficient means of conducting Intent security testing and enhances Android app robustness and security.

关键词： Operating systems Image edge detection Genetic mutations Text categorization Fuzzing Libraries Robustness Security Smart phones Testing

Joint Edge Aggregation and Association for Cost-Efficient Multi-Cell Federated Learning

学校读者我要写书评

暂无评论

Joint Edge Aggregation and Association for Cost-Efficient Mu...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Tao Wu Yuben Qu Chunsheng Liu Yuqian Jing Feiyu Wu Haipeng Dai Chao Dong Jiannong Cao National University of Defense Technology China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Federated learning (FL) has been proposed as a promising distributed learning paradigm to realize edge artificial intelligence (AI) without revealing the raw data. Nevertheless, it would incur inevitable costs in terms of training latency and energy consumption, due to periodical communication between user equipments (UEs) and the geographically remote central parameter server. Thus motivated, we study the joint edge aggregation and association problem to minimize the total cost, where the model aggregation over multiple cells just happens at the network edge. After proving its hardness with complex coupled variables, we transform it into a set function optimization problem and prove the objective function is neither submodular nor supermodular, which further complicates the problem. To tackle this difficulty, we first split it into multiple edge association subproblems, where the optimal solution to the computation resource allocation can be efficiently obtained in the closed form. We then construct a substitute function with the supermodularity and provable upper bound. On this basis, we reformulate an equivalent set function minimization problem under a matroid base constraint. We then propose an approximation algorithm to the original problem based on the two-stage search strategy with theoretical performance guarantee. Both extensive simulations and field experiments are conducted to validate the effectiveness of our proposed solution.

关键词：

Photonic integrated spiking neuron chip based on a self-pulsating DFB laser with a saturable absorber

学校读者我要写书评

暂无评论

Photonics Research 2023年第8期11卷 1382-1389页

作者： YUECHUN SHI SHUIYING XIANG XINGXING GUO YAHUI ZHANG HONGJI WANG DIANZHUANG ZHENG YUNA ZHANG YANAN HAN YONG ZHAO XIAOJUN ZHU XIANGFEI CHEN XUN LI YUE HAO Yongjiang Laboratory Ningbo 315202China State Key Laboratory of Integrated Service Networks State Key Discipline Laboratory of Wide Bandgap Semiconductor TechnologyXidian UniversityXi’an 710071China Key Laboratory of Intelligent Optical Sensing and Manipulation Ministry of EducationNational Laboratory of Solid State MicrostructuresCollege of Engineering and Applied SciencesInstitute of Optical Communication EngineeringNanjing UniversityNanjing 210023China School of Science Jiangnan UniversityWuxi 214122China School of Information Science and Technology Nantong UniversityNantong 226019China Department of Electrical and Computer Engineering McMaster UniversityHamiltonOantario L8S 4K1Canada

We proposed and experimentally demonstrated a simple and novel photonic spiking neuron based on a distributed feedback(DFB)laser chip with an intracavity saturable absorber(SA).The DFB laser with an intracavity SA(DFBSA)contains a gain region and an SA *** gain region is designed and fabricated by the asymmetric equivalentπ-phase shift based on the reconstruction-equivalent-chirp *** properly injected current in the gain region and reversely biased voltage in the SA region,periodic self-pulsation was experimentally observed due to the Q-switching *** self-pulsation frequency increases with the increase of the bias current and is within the range of several *** the bias current is below the self-pulsation threshold,neuronlike spiking responses appear when external optical stimulus pulses are *** results show that the spike threshold,temporal integration,and refractory period can all be observed in the fabricated DFB-SA *** numerically verify the experimental findings,a time-dependent coupled-wave equation model was developed,which described the physics processes inside the gain and SA *** numerical results agree well with the experimental *** further experimentally demonstrated that the weighted sum output can readily be encoded into the self-pulsation frequency of the DFB-SA *** also benchmarked the handwritten digit classification task with a simple single-layer fully connected neural *** using the experimentally measured dependence of the self-pulsation frequency on the bias current in the gain region as an activation function,we can achieve a recognition accuracy of 92.2%,which bridges the gap between the continuous valued artificial neural networks and spike-based neuromorphic *** the best of our knowledge,this is the first experimental demonstration of a photonic integrated spiking neuron based on a DFB-SA,which shows great potential to realizing large-scale mult

关键词： technique laser saturable