检索结果-内蒙古大学图书馆

Appearance and motion-based unusual crowd events detection using multiple moving objects

Multimedia Tools and Applications 2024年第42期83卷 90177-90189页

作者： Babu, K. Atlas, L. Godlin Sreeji, S. Arjun, K.P. Rasmi, A. Senthilvel, P. Gururama Computational Intelligence SRM Institute of Science & Technology Chengalpet Kattankulathur603203 India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gitam University Karnataka Bengaluru India Information Science and Engineering RRIT Bangalore India Saveetha University Chennai602 105 India

Unusual crowd analysis is an important problem in surveillance video due to their features cannot be extracted efficiently on the crowd scenes. To overcome this challenge, this paper introduced the appearance and motion based unusual events detection method by using multiple moving objects. This method includes appearance and motion based computation, and moving objects trajectory analysis. By using these all techniques, the unusual crowds and their activities can be obtained by analyzing moving objects size and the distance among multiple moving objects. Two benchmark datasets such as PETS 2009 and UMN are used for the experimental results. Also, several existing algorithms are compared with the proposed method to evaluate the effectiveness of the proposed work. The comparative analysis results proved that the proposed method achieved best accuracy for unusual crowd events. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： And trajectory analysis Appearance based analysis Distance based analysis Unusual crowd events detection

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Joint Service Caching and Load Balancing for MEC Blockchain Networks

引用

China Communications 2023年第1期20卷 125-139页

作者： Wenqian Zhang Wenya Fan Guanglin Zhang Shiwen Mao College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of EducationShanghai 201620China Department of Electrical and Computer Engineering Auburn UniversityAuburnAL 36849-5201USA

Integrating the blockchain technology into mobile-edge computing(MEC)networks with multiple cooperative MEC servers(MECS)providing a promising solution to improving resource utilization,and helping establish a secure reward mechanism that can facilitate load balancing among *** addition,intelligent management of service caching and load balancing can improve the network utility in MEC blockchain networks with multiple types of *** this paper,we investigate a learningbased joint service caching and load balancing policy for optimizing the communication and computation resources allocation,so as to improve the resource utilization of MEC blockchain *** formulate the problem as a challenging long-term network revenue maximization Markov decision process(MDP)*** address the highly dynamic and high dimension of system states,we design a joint service caching and load balancing algorithm based on the double-dueling Deep Q network(DQN)*** simulation results validate the feasibility and superior performance of our proposed algorithm over several baseline schemes.

关键词： cooperative mobile-edge computing blockchain workload offloading service caching load balancing deep reinforcement learning(DRL)

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 430-445页

作者： Jiawen Kang Junlong Chen Minrui Xu Zehui Xiong Yutao Jiao Luchao Han Dusit Niyato Yongju Tong Shengli Xie IEEE School of Automation Guangdong University of TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing based on IoT Technology Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingaporeSingapore College of Communication Engineering Army Engineering University of PLANanjing 210007China National Natural Science Foundation of China Beijing 100085China Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach

关键词： Avatar blockchain metaverses multi-agent deep reinforcement learning transformer UAVs

来源：评论

学校读者我要写书评

暂无评论

Zero Trust Networks: Evolution and Application from Concept to Practice

引用

computers, Materials & Continua 2025年第2期82卷 1593-1613页

作者： Yongjun Ren Zhiming Wang Pradip Kumar Sharma Fayez Alqahtani Amr Tolba Jin Wang School of Computer Science School of Cyber Science and EngineeringEngineering Research Center of Digital ForensicsMinistry of EducationNanjing University of Information Science and TechnologyNanjing210044China Department of Computing Science University of AberdeenAberdeenAB243FXUK Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Sanya Institute of Hunan University of Science and Technology Sanya572024China

In the context of an increasingly severe cybersecurity landscape and the growing complexity of offensive and defen-sive techniques,Zero Trust Networks(ZTN)have emerged as a widely recognized *** Trust not only addresses the shortcomings of traditional perimeter security models but also consistently follows the fundamental principle of“never trust,always verify.”Initially proposed by John Cortez in 2010 and subsequently promoted by Google,the Zero Trust model has become a key approach to addressing the ever-growing security threats in complex network *** paper systematically compares the current mainstream cybersecurity models,thoroughly explores the advantages and limitations of the Zero Trust model,and provides an in-depth review of its components and key ***,it analyzes the latest research achievements in the application of Zero Trust technology across various fields,including network security,6G networks,the Internet of Things(IoT),and cloud computing,in the context of specific use *** paper also discusses the innovative contributions of the Zero Trust model in these fields,the challenges it faces,and proposes corresponding solutions and future research directions.

关键词： Zero trust cybersecurity software-defined perimeter micro-segmentation internet of things

来源：评论

学校读者我要写书评

暂无评论

Layer-Wise Learning Rate Optimization for Task-Dependent Fine-Tuning of Pre-Trained Models: An Evolutionary Approach

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-23页

作者： Bu, Chenyang Liu, Yuxin Huang, Manzong Shao, Jianxuan Ji, Shengwei Luo, Wenjian Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

The superior performance of large-scale pre-Trained models, such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-Trained Transformer (GPT), has received increasing attention in both academic and industrial research and has become one of the current research hotspots. A pre-Trained model refers to a model trained on large-scale unlabeled data, whose purpose is to learn general language representation or features for fine-Tuning or transfer learning in subsequent tasks. After pre-Training is complete, a small amount of labeled data can be used to fine-Tune the model for a specific task or domain. This two-stage method of "pre-Training+fine-Tuning"has achieved advanced results in natural language processing (NLP) tasks. Despite widespread adoption, existing fixed fine-Tuning schemes that adapt well to one NLP task may perform inconsistently on other NLP tasks given that different tasks have different latent semantic structures. In this article, we explore the effectiveness of automatic fine-Tuning pattern search for layer-wise learning rates from an evolutionary optimization perspective. Our goal is to use evolutionary algorithms to search for better task-dependent fine-Tuning patterns for specific NLP tasks than typical fixed fine-Tuning patterns. Experimental results on two real-world language benchmarks and three advanced pre-Training language models show the effectiveness and generality of the proposed framework. © 2024 held by the owner/author(s).

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unknown Category Malicious Traffic Detection Based on Contrastive Learning 6th

Unknown Category Malicious Traffic Detection Based on Contra...

引用

6th International Conference on Machine Learning for Cyber Security, ML4CS 2024

作者： Yan, Leiming Zhou, Tao Chen, Xianyi Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer Science and Cyber Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (纸本)9789819645657

In response to the continuous emergence of novel unknown malicious traffic and the limitations of traditional detection methods, this paper presents an unknown-category malicious traffic detection approach based on contrastive learning. The proposed method utilizes contrastive learning to train an encoder for distinguishing normal traffic and multiple types of known malicious traffic, thereby enhancing inter-class separability. Subsequently, the model is fine-tuned to optimize the representations of malicious traffic categories with limited samples, amplifying the separation between different classes in the feature space. This ensures that the distance between unknown malicious traffic and other categories exceeds a predefined threshold, thereby achieving effective detection. Experimental results on the CICIoT2023 and UNSW-NB15 datasets demonstrate the superior performance of the proposed method, achieving multi-class F1-scores of 93.23 and 89.93, respectively, outperforming traditional approaches. Additionally, the method achieves an accuracy of over 83% in simulated scenarios involving unknown-category malicious traffic detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-level glowworm swarm convolution neural networks for abnormal event detection in online surveillance video

引用

International Journal of information technology (Singapore) 2025年第2期17卷 1179-1187页

作者： Rao, M. Koteswara Ashok Kumar, P.M. Department of Information technology VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad 500090 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Guntur District Vaddeswaram 522502 India

A surveillance camera is one of the most important tools for observing people's movements and stopping unauthorized or unplanned activity. Security management experts now significantly rely on video surveillance to combat crime and avert incidents that have a detrimental influence on human civilization. To monitor public activities, the installation of numerous surveillance cameras has drastically increased in both the public and private sectors. Security may be ensured most effectively through video surveillance. Installing a surveillance camera merely provides security personnel with the recorded video. However, integrating intelligent technology to analyze the videos is the only way to spot irregular actions. As a result, the goal of this study is to construct an Intelligent Video Analytics Model (IVAM), also known as a Human Object Detection (HOD) approach, for analyzing and spotting unusual human activity and abundant objects in videos. The proposed IVAM is designed based on Multi-level glowworm swarm convolution neural networks (ML-GSCNN). The proposed approach consists of two stages namely, frame conversion, and abnormal event detection. The captured video is first divided into segments, and then each segment is changed into a frame. After that, abnormal event detection is performed. For abnormal event detection, a novel ML-GSCNN is designed. Here, the hyper-parameter of CNN and the architecture of CNN both are optimized by the glowworm swarm optimization (GSO) algorithm to improve the detection accuracy. The experimental results show that the proposed approach attained better results compared to existing works. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： And abnormal event detection Glowworm swarm optimization (GSO) Human object detection (HOD) IVAM ML-GSCNN

来源：评论

学校读者我要写书评

暂无评论

Analysis of CNN Models using Augmented Data in Tomato Diseases 18

Analysis of CNN Models using Augmented Data in Tomato Diseas...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sharma, Pavan Yadav, Rakesh Kumar Rawat, Sur Singh Iftm University Department of Computer Science and Engineering Moradabad India Maharishi University of Information Technology Department of Computer Science and Engineering Lucknow India Jss Academy of Technical Education Department of Computer Science and Engineering Noida India

ISBN: (纸本)9789380544519

A vital source of nourishment for millions of people, tomatoes are one of the most significant vegetables in the world. However, many diseases may substantially decrease the yield and quality of tomato plants. Early blight, Late blight and Powdery mildew are the three most destructive diseases in tomatoes that have the capacity to drastically lower tomato crop yields. A trusted and efficient automated approach for identifying diseases needs to be created in order to address this problem. To recognize the three primary disorders that impact tomato plants based on leaf images, we created a model using a convolution neural network (CNN) and data augmentation. We also compared the performance of different CNN models, and assessed its efficacy. With an average accuracy rate of -61.75% and average loss of 6.75%, theResNet50 model is a valuable tool that tomato growers can use to keep the diseases mentioned above from affecting their tomatoes during the harvesting process. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： augmentation CNN mobilenet resnet50 vgg16 xception

来源：评论

学校读者我要写书评

暂无评论

Histological Image Diagnosis of Breast Cancer Based on Multi-Attention Convolution Neural Network

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 91-106页

作者： XU Wangwang XU Liangfeng LIU Ninghui LU Na Key Laboratory of Knowledge Engineering with Big Data(Hefei University of Technology) Ministry of EducationHefei230601China School of Computer and Information Hefei University of TechnologyHefei230601China First Affiliated Hospital of Anhui Medical University Hefei230022China

Breast cancer is a serious and high morbidity disease in women,and it is the main cause of cancer death in ***,getting tested and diagnosed early can reduce the risk of *** present,there are clinical examinations,imaging screening and biopsies,among which histopathological examination is the gold ***,the process is complicated and time-consuming,and misdiagnosis may *** paper puts forward a classification framework based on deep learning,introducing multi-attention mechanism,selecting kernel convolution instead of ordinary convolution,and using different weights and combinations to pay attention to the accuracy index and growth rate of the *** addition,we also compared the learning rate *** function can fine-tune the learning rate to achieve good performance,using label softening to reduce the loss error caused by model error recognition in the label,and assigning different category weights in the loss function to balance the positive and negative *** used the BreakHis data set to automatically classify histological images into benign and malignant,four categories and eight *** results showed that the accuracy of binary classifications ranged from 98.23%to 98.83%,and that of multiple classifications ranged from 97.89%to 98.11%.

关键词： breast cancer deep learning attentional mechanism classification diagnosis

来源：评论

学校读者我要写书评

暂无评论

Optimizing VNF Service Provisioning in Mobile Edge Computing Networks Through PSO-RL 3

Optimizing VNF Service Provisioning in Mobile Edge Computing...

引用

3rd IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Abinaya, K. Dhanasekaran, S. Vasudevan, V. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Srivilliputtur India Kalasalingam Academy of Research and Education Department of Information Technology Tamilnadu Srivilliputtur India

ISBN: (纸本)9798350361186

This study deals with setting up Virtual Network Function (VNF) services in Mobile Edge Computing (MEC) networks. It aims to balance different user needs in the everchanging MEC environment. Leveraging Particle Swarm Optimization-Reinforcement Learning algorithms (PSO-RL), our proposed system offers a dynamic provisioning approach adept at accommodating user mobility patterns and service delay prerequisites. The system's sequential flow comprises distinct stages designed for optimal functionality. The Firefly Algorithm efficiently maximizes utility by simplifying intricate issues and approximating optimal solutions. Additionally, our system implements Stochastic Gradient Descent and Simulated Annealing techniques for real-time throughput optimization, ensuring adaptability to ever-changing network conditions. Experimental simulations form a critical component of our study, providing a robust assessment of our proposed methodologies. Results obtained demonstrate substantial enhancements across critical metrics such as Throughput, Resource Utilization Efficiency, and End-to-End Delay. Varied scenarios encompassing different quantities of IoT users and mobile edge servers were simulated, reaffirming the efficacy of the PSO-RL method. These simulations underscore the potential of our proposed approach in significantly bolstering the performance and responsiveness of MEC networks. Ultimately, this study showcases promising prospects in addressing the intricate challenges associated with provisioning VNF services to mobile users in dynamic MEC environments. © 2024 IEEE.

关键词： Simulated annealing

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：