检索结果-内蒙古大学图书馆

Listen With Seeing: Cross-Modal Contrastive Learning for Audio-Visual Event Localization

IEEE Transactions on Multimedia 2025年 27卷 2650-2665页

作者： Sun, Chao Chen, Min Zhu, Chuanbo Zhang, Sheng Lu, Ping Chen, Jincai Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Wuhan430074 China South China University of Technology School of Computer Science and Engineering Guangzhou510640 China Pazhou Laboratory Guangzhou510640 China

In real-world physiological and psychological scenarios, there often exists a robust complementary correlation between audio and visual signals. Audio-Visual Event Localization (AVEL) aims to identify segments with Audio-Visual Events (AVEs) that contain both audio and visual tracks in unconstrained videos. Prior studies have predominantly focused on audio-visual cross-modal fusion methods, overlooking the fine-grained exploration of the cross-modal information fusion mechanism. Moreover, due to the inherent heterogeneity of multi-modal data, inevitable new noise is introduced during the audio-visual fusion process. To address these challenges, we propose a novel Cross-modal Contrastive Learning Network (CCLN) for AVEL, comprising a backbone network and a branch network. In the backbone network, drawing inspiration from physiological theories of sensory integration, we elucidate the process of audio-visual information fusion, interaction, and integration from an information-flow perspective. Notably, the Self-constrained Bi-modal Interaction (SBI) module is a bi-modal attention structure integrated with audio-visual fusion information, and through gated processing of the audio-visual correlation matrix, it effectively captures inter-modal correlation. The Foreground Event Enhancement (FEE) module emphasizes the significance of event-level boundaries by elongating the distance between scene events during training through adaptive weights. Furthermore, we introduce weak video-level labels to constrain the cross-modal semantic alignment of audio-visual events and design a weakly supervised cross-modal contrastive learning loss (WCCL Loss) function, which enhances the quality of fusion representation in the dual-branch contrastive learning framework. Extensive experiments conducted on the AVE dataset for both fully supervised and weakly supervised event localization, as well as Cross-Modal Localization (CML) tasks, demonstrate the superior performance of our model compa

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Machine learning for Internet of Things (IoT) device identification: a comparative study

引用

PeerJ computer science 2025年 11卷 1-34页

作者： Tahaei, Hamid Liu, Anqi Forooghikian, Hamid Gheisari, Mehdi Zaki, Faiz Anuar, Nor Badrul Fang, Zhaoxi Huang, Longjun Institute of Artificial Intelligence Shaoxing University Shaoxing China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia Department of Management Islamic Azad University of Kish Kish Iran Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Selangor Kuala Lumpur Malaysia Department of Computer Science and Engineering Shaoxing University Shaoxing China

The rapid deployment of millions of connected devices brings significant security challenges to the Internet of Things (IoT). IoT devices are typically resource-constrained and designed for specific tasks, from which new security challenges are introduced. As such, IoT device identification has garnered substantial attention and is regarded as an initial layer of cybersecurity. One of the major steps in distinguishing IoT devices involves leveraging machine learning (ML) techniques on device network flows known as device fingerprinting. Numerous studies have proposed various solutions that incorporate ML and feature selection (FS) algorithms with different degrees of accuracy. Yet, the domain needs a comparative analysis of the accuracy of different classifiers and FS algorithms to comprehend their true capabilities in various datasets. This article provides a comprehensive performance evaluation of several reputable classifiers being used in the literature. The study evaluates the efficacy of filter-and wrapper-based FS methods across various ML classifiers. Additionally, we implemented a Binary Green Wolf Optimizer (BGWO) and compared its performance with that of traditional ML classifiers to assess the potential of this binary meta-heuristic algorithm. To ensure the robustness of our findings, we evaluated the effectiveness of each classifier and FS method using two widely utilized datasets. Our experiments demonstrated that BGWO effectively reduced the feature set by 85.11% and 73.33% for datasets 1 and 2, respectively, while achieving classification accuracies of 98.51% and 99.8%, respectively. The findings of this study highlight the strong capabilities of BGWO in reducing both the feature dimensionality and accuracy gained through classification. Furthermore, it demonstrates the effectiveness of wrapper methods in the reduction of feature sets. 2025 Tahaei et al.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Single-Valued Neutrosophic Graph with Heptapartitioend Structure

引用

Neutrosophic Sets and systems 2025年 80卷 728-748页

作者： Fathi, Hanaa Myvizhi, M. Abdelhafeez, Ahmed Abdellah, Mohamed Refaat Eassa, Mohamed Sawah, Mohamed S. Elbehiery, Hussam College of Information Technology Amman Arab University Amman Jordan KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan The Department of Computer Science College of Information Technology Misr University for Science and Technology Cairo Egypt Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan

This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neutrosophic Graphs (SVHNG) and investigate their characteristics through comprehensive proofs and illustrative examples. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioend Neutrosophic Set Neutrosophic Graph Neutrosophic Sets SVHN-Graph

来源：评论

学校读者我要写书评

暂无评论

A Multi-Agent Garage Service Search and Recommendation with Hybrid MLs and LLMs

A Multi-Agent Garage Service Search and Recommendation with ...

引用

2025 International Conference on computer, Electrical and Communication engineering, ICCECE 2025

作者： Shuvo, Mahfuzur Rahman Rahman, Ashifur Akuthota, Vishwanath Paul, Tanay Islam, Mahfujul Ashraf, Md Sadi Roy, Prosenjit Reza, Md Tanzim International American University Department of Management Information System United States Chittagong University of Engineering and Technology Department of Computer Science and Engineering Bangladesh TechOptima Hyderabad India Brac University Department of Computer Science and Engineering Bangladesh Prairie View A & M University Department of Computer Science TX United States

ISBN: (纸本)9798331513894

The automobile service industry's explosive growth highlights the need for creative approaches to boost operational effectiveness and user experience. This study introduces a Hybrid Garage Assistance system, integrating Classical Machine Learning (ML) techniques with Generative AI to optimize garage service discovery and analysis. The system employs sophisticated data processing methods, including Term Frequency-Inverse Document Frequency (TF-IDF) vectorization and regex-based service detection, to extract actionable insights from unstructured garage *** to the system are machine learning models Random Forest (RF) and XGBoost (XGB) which achieve high precision and recall in classifying garage services. A hybrid search mechanism, combining cosine similarity with ML-driven predictions, ensures the delivery of highly personalized search results. To further refine decision-making, the system incorporates Generative AI models such as Perplexity for web-based research, Gemini for location-specific analysis, Mistral for email sending and GPT-4 for detailed service recommendations and dall-e for creating user specific parts images. These advanced tools provide users with comprehensive information that enables them to make well-informed decisions about garage *** evaluation of the system is conducted using robust metrics, including precision, recall, F1-score, and system latency. Experimental results reveal a precision of 85%, recall of 70.8%, and an F1-score of 77.2%, demonstrating the efficacy of integrating classical ML with generative AI. The system's average latency of 5.9 seconds ensures a seamless and responsive user *** hybrid framework highlights the potential of blending classical ML and Large Language Models (LLMs) to enhance search and recommendation functionalities, offering a scalable and robust blueprint for future advancements in the automotive service sector. The system's Propose a Multi-Agent system With high accuracy,

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A novel approach to identify parkinson’s disease and other similar neural stress by analysing keystrokes on modern active devices with ensemble classification

引用

Multimedia Tools and Applications 2025年 1-40页

作者： Roy, Soumen Roy, Utpal Sinha, Devadatta Pal, Rajat Kumar Department of Computer Science and Engineering University of Calcutta Acharya Prafulla Chandra Roy Siksha Prangan JD-2 Sector - III Saltlake City Kolkata700106 India Department of Computer and System Sciences Visva-Bharati University Santiniketan731235 India

Motor skills (related to the motor nerve) and neurocognitive disorders affect humans’ typing ability to an extent that is noticeable while using a keyboard, smartphone, or other electronic gadgets. These two medical conditions are Parkinson’s disease (PD), caused by malfunctions of the motor nerve, and neurocognitive disorder, caused by a deficiency of organismic responses to stimuli. A mild symptom of PD, change in fine motor skills during typing, is reflected heavily in keystroke patterns during the early stages. Similarly, Emotional stress (ES) expresses a neurocognitive disorder that affects cognitive abilities as well. Early symptoms of this disorder are reflected in the keystroke patterns according to their severity. As there is no such pathological examination, it is challenging to perceive and measure the development of such disorders already developed in human behaviour as a disease. Furthermore, early screening of these diseases is essential for future diagnosis and preventing fatal consequences, since both are progressive illnesses. A modest attempt is made here to detect two such neurodegenerative disorders in humans using the way they type, formally known as Keystroke dynamics (KD). In this study, a bootstrapped-based homogeneous ensemble classification method has been proposed to address the uncertain performance and uneven distribution of classes for the detection of such medical conditions using users’ typing tendencies. For this purpose, two recent benchmark datasets were used for the validation and confirmation of operational improvements of the proposed method, which have been validated qualitatively and quantitatively. As a result, sensitivity/specificity of 0.82/0.78 in detecting PD and 0.98/0.98 in ES have been achieved, which is robust and accurate in a more realistic evaluation. The proposed framework explores the possibilities of implementing it in web-based systems, which has significant benefits. A better diagnosis, early detection at home

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Compression Format and Systolic Array Structure Co-design for Accelerating Sparse Matrix Multiplication in DNNs 24th

Compression Format and Systolic Array Structure Co-design f...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Cao, Yongxiang Jiang, Jixiang Zhao, Guocheng Wang, Wei Jiang, Hongxu Song, Yanfei School of Computer Science and Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789819615445

The systolic array (SA) architecture is widely used in accelerator/AI chip design due to its excellent matrix multiplication acceleration effect. However, the mismatch between the traditional sparse matrix compression format and the SA architecture results in poor SA performance in computing sparse matrices. To solve the problem, we propose a method for co-designing the sparse compression format and SA architecture. This work proposes the Vector Group Compressed Coordinate (VGCC) data stream compression format and designs a sparse SA architecture based on hardware encoding and decoding. VGCC can handle data streams of any size without increasing the index bit width. The VGCC compression size is significantly smaller than general sparse compression formats such as COO/CSR. In a sparse matrix with a sparsity of 90%, it saves 67.13% of storage space compared to the state-of-the-art ECOO data stream compression format and achieves an average acceleration of 1.54 times. We also propose a VGCC-friendly SA architecture. Our SA architecture engine reduces logic consumption by 51.6% compared to Sparse TPU while achieving a 3.23x speedup. To mitigate the issue of high no-load rates in systolic arrays, we introduce a Data Transmission Priority (DTP) data matching algorithm. With sparsity levels ranging from 50% to 90%, the algorithm’s calculation speed is enhanced by 1.124x to 1.991x. We implemented a sparse DNN accelerator on an FPGA Zynq UltraScale+MPSoC ZCU102, utilizing the VGCC compression format proposed in this study for compressing input data. When compared to the S2 Engine, the accelerator achieved a 3.37x speed improvement in matrix multiplication with 75% sparsity, significantly enhancing the speed of sparse matrix multiplication. The accelerator achieved an average throughput of 1079.33GOP/s when inferencing DNNs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Systolic arrays

来源：评论

学校读者我要写书评

暂无评论

Assessment of Multilevel Intransitive Noninterference by Nonblocking Analysis

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 2902-2917页

作者： Zhong, Wenjing Zhao, Jinjing Hu, Hesuan Xidian University School of Electro-Mechanical Engineering Xi'an710071 China National Key Laboratory of Science and Technology on Information System Security Beijing100101 China Nanyang Technological University School of Computer Science and Engineering College of Engineering 639798 Singapore Xi'an Jiaotong University State Key Laboratory for Manufacturing Systems Engineering Xi'an710054 China

Security of system behavior is a kind of information flow security, which is achieved by confusing the intruders via the indistinguishability of system behaviors. Noninterference is a typical notion to describe information flow security, for which multilevel intransitive noninterference (MINI) is an advanced variant. Since there is a lack of rigorous approach to assessing MINI, this article achieves so via observability theory. For systems modeled by labeled Petri nets (LPNs), two MINI properties, i.e., positive MINI (PMINI) and bipolar MINI (BMINI), are considered. First, a necessary and sufficient condition for their assessment is established via language equivalence. Language equivalence analyses for PMINI and BMINI are based on the existing trace equivalence and the proposed INI bisimulation, respectively. INI bisimulation is more comprehensive to describe negative noninterference than bisimulation. Second, another necessary and sufficient condition is established after the transformation of MINI assessment problem to nonblocking analysis problem. The core of such a problem transformation is the stepwise construction of nonblocking analyzer. This stepwise construction allows MINI assessment to proceed online before terminating at an appropriate time. In addition, this stepwise construction fully employs the concurrency of LPNs so that MINI can be assessed in a multithreaded way. Both online and multithreaded MINI assessments can improve assessment efficiency. © 1963-2012 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Behaviour-diverse automatic penetration testing:a coverage-based deep reinforcement learning approach

引用

Frontiers of computer science 2025年第3期19卷 15-24页

作者： Yizhou YANG Longde CHEN Sha LIU Lanning WANG Haohuan FU Xin LIU Zuoning CHEN Zhongguancun Laboratory Beijing 100081China Zhejiang Lab Hangzhou 311121China National Research Centre of Parallel Computer Engineering and Technology Wuxi 214000China Faculty of Geographical Science Beijing Normal UniversityBeijing 100875China Department of Earth System Science Tsinghua UniversityBeijing 100084China

Reinforcement Learning(RL)is gaining importance in automating penetration testing as it reduces human effort and increases ***,given the rapidly expanding scale of modern network infrastructure,the limited testing scale and monotonous strategies of existing RLbased automated penetration testing methods make them less effective in practical *** this paper,we present CLAP(Coverage-Based Reinforcement Learning to Automate Penetration Testing),an RL penetration testing agent that provides comprehensive network security assessments with diverse adversary testing behaviours on a massive *** employs a novel neural network,namely the coverage mechanism,to address the enormous and growing action spaces in large *** also utilizes a Chebyshev decomposition critic to identify various adversary strategies and strike a balance between *** results across various scenarios demonstrate that CLAP outperforms state-of-the-art methods,by further reducing attack operations by nearly 35%.CLAP also provides enhanced training efficiency and stability and can effectively perform pen-testing over large-scale networks with up to 500 ***,the proposed agent is also able to discover pareto-dominant strategies that are both diverse and effective in achieving multiple objectives.

关键词： network security penetration testing reinforcement learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Privacy and Security Implications of Mobile Apps 8

Evaluating the Privacy and Security Implications of Mobile A...

引用

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Mazumder, Shafiul Islam Shovon, Sazzadul Islam Chowdhury, Md Tanvir Islam, Minhajul Raisa, Habiba Azad Rahman, Habibur Sumon, Monjurul Islam Khan, Md. Khalid Mahbub American International University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System Michigan United States East West University Department of Computer Science and Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331520762

The rapid growth of mobile applications, combined with an increasing reliance on these apps for a variety of purposes, has prompted serious concerns about user privacy and data security. This study aims to assess the privacy practices, data handling methods, and security vulnerabilities of mobile apps in a variety of categories, including social media, e-commerce, health and fitness, and financial management. This study identifies major privacy and security issues by examining privacy policies and terms of service, as well as how these apps handle sensitive data. The study also examines free and premium apps' privacy procedures, taking into account the implications for user data protection. The findings illustrate differences in data handling and security standards across different app categories, highlighting the importance of transparent privacy policies, strong security mechanisms, and limited data sharing to protect user information. The research helps to define standards and best practices for promoting secure app activity, increasing user confidence, and guaranteeing a safer digital environment. © 2025 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading 23

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Duan, Zhuohui Feng, Hao Liu, Haikun Liao, Xiaofei Jin, Hai Li, Bangyu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world application. In this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems. © 2025 FAST. All Rights Reserved.

关键词： Digital storage

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：