检索结果-内蒙古大学图书馆

Journal of Shanghai Jiaotong university(science) 2024年第3期29卷 480-491页

作者：王丽张旭毅姚亚兵尉雪龙 Library Northwest Normal UniversityLanzhou 730070China Department of Criminal Science and Technology Henan Police CollegeZhengzhou 450046China School of Computer and Communication Lanzhou University of TechnologyLanzhou 730050China School of Computer Science and Engineering Northeastern UniversityShenyang 110169China

This study mainly focused on the dynamic self-similar k_(c)-center network as a result of information distribution through social *** attraction with various preferences was characterized in the model as a result of reciprocal attraction among individuals and human ***,the model incorporated the community network structure and network evolution mechanism,and a dynamic self-similar k_(c)-center network generation model was *** with the classical scale-free network generation algorithm,the generated network embodied not only the characteristics of the small-world and scale-free,but also the characteristics of dynamic self-similar k_(c)-center *** experimental results were verified by comparing the real data with the experimental *** results showed that there are dynamic self-similar k_(c)-center networks and their internal network relationship dynamics in the micro scale,meso scale and global perspective based on information dissemination.

关键词： edge state evolutionary network self-similarity ke-center network

来源：评论

学校读者我要写书评

暂无评论

An Integrated Long Short-Term Memory Based Online Log Anomaly Detection 9

An Integrated Long Short-Term Memory Based Online Log Anomal...

引用

9th International Conference on Systems and Informatics, ICSAI 2023

作者： He, Shiming Zeng, Sikai Changsha University of Science and Technology College of Computer and Communication Engineering China

ISBN: (纸本)9798350383706

System logs record noteworthy information and become a valuable resource for tracking and investigating the status of a system. Detecting anomalies from logs as fast as possible can enhance quality of service. Although many deep learning algorithms have achieved good results in the field of log anomaly detection, we find that they assume that data is acquired and trained in bulk and may have high training time, while in reality log data streams are constantly arriving. Facing these challenges, this paper proposes a Long Short-Term Memory network (LSTM) based online log anomaly detection. We use transfer learning to train weak learners and integrate weak learners as strong learners for the constantly arriving log. We compare the performance of the methods using a public log dataset and experimentally validate the effectiveness of each module. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A comprehensive examination of load balancing algorithms in cloud environments: a systematic literature review, comparative analysis, taxonomy, open challenges, and future trends

引用

Iran Journal of computer science 2024年第3期7卷 663-698页

作者： Prity, Farida Siddiqi Hossain, Md. Maruf Department of Information and Communication Engineering Noakhali Science and Technology University Noakhali 3814 Bangladesh Department of Information and Communication Engineering Pabna University of Science and Technology Pabna 6600 Bangladesh Department of Computer Science and Engineering Shanto-Mariam University of Creative Technology Dhaka 1230 Bangladesh

Cloud computing is a robust paradigm that empowers users and organizations to procure services tailored to their needs. This model encompasses many offerings, including storage solutions, platforms for seamless deployment, and convenient access to web services. Load balancing, a fundamental pillar in cloud computing, is crucial in distributing requests across multiple servers to optimize resource utilization and reduce response times. However, load balancing presents a common challenge in the cloud environment, as it hampers the ability to maintain optimal application performance while adhering to the stringent requirements of Quality of Service (QoS) measurements and Service Level Agreement (SLA) compliance mandated by cloud providers to enterprises. The equitable workload distribution across servers poses a significant challenge for cloud providers. Hence, an efficient load-balancing technique should optimize resource utilization in Virtual Machines (VMs) to ensure maximum user satisfaction and overall system efficiency. However, existing review papers on load balancing in cloud environments often exhibit limitations, lacking in-depth analyses, graphical representations, and comprehensive evaluations of performance metrics. This review paper aims to fill these gaps by providing a novel taxonomy of load balancing algorithms divided into four categories (types of algorithms, nature of problem, metrics, and simulation tools) and thoroughly examining their objectives, parameters, and operational flows. It evaluates the strengths and weaknesses of these algorithms, considering their nature and type, and employs qualitative QoS parameter-based criteria for effectiveness evaluation. The paper also includes a comparative analysis of simulation tools, visual representations, and experimental results. By offering valuable insights, open issues, recommendations, and future directions, this review paper equips researchers, practitioners, and cloud service providers with the k

关键词： Algorithms Cloud computing Load balancing Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Utilizing Different Edge Detection and Preprocessing Techniques to Improve the Accuracy of Durian Cultivar Detection using Convolutional Neural Networks 9

Utilizing Different Edge Detection and Preprocessing Techniq...

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Hussin, Amir Laalieff Bin Amir Muzammil, Harith Syazwan Bin Haril Shaharuddin, Muhammad Afiq A. Bin Ismail, Amelia Ritahani Binti Zainuddin, Ahmad Anwar Bin Kulliyyah of Information and Communication Technology Department of Computer Science Gombak Malaysia

ISBN: (纸本)9798350370126

Using machine learning to recognize images of fruits or plants is a very practical and focused application. When using machine learning principles to classify specific fruit varieties, as opposed to traditional approaches, a higher level of accuracy is promised but also requiring more training data. Particularly in situations where different cultivars of the same fruit family are valued differently, the capacity to recognize and classify diverse cultivars of a fruit family is crucial. The objective of this study is to develop a practical method for classifying the many cultivars of Durio zibethinus, also known as Durian, based on the visual traits of the crop using Convolution Neural Networks (CNNs) to improve the accuracy and speed of cultivar recognition. Utilizing a database of images with tagged Durian cultivars. Images from two high-value classes of Durian cultivars are utilized to train the neural network. The first phases in the research project involve pre-processing and converting the images using Canny, Laplacian, Sobel on X-axis, and image binarization. Next up are model training, model validation, and network architecture development. Finally, they were combined as an ensemble machine learning method using majority voting to examine the potential for enhancing prediction performance. Laplacian edge detection was found to yield the best results of the four studied approaches, while ensemble methods gave more accurate results than a single method. © 2023 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Improved encoding structure and decoding algorithms for spinal codes

引用

Journal of Systems Engineering and Electronics 2022年第4期33卷 856-866页

作者： HUANG Wensha WANG Lina School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Shunde Graduate School University of Science and Technology BeijingBeijing 100083China

To improve the error correction performance, an innovative encoding structure with tail-biting for spinal codes is designed. Furthermore, an adaptive forward stack decoding(A-FSD) algorithm with lower complexity for spinal codes is proposed. In the A-FSD algorithm, a flexible threshold parameter is set by a variable channel state to narrow the scale of nodes accessed. On this basis, a new decoding method of AFSD with early termination(AFSD-ET) is further proposed. The AFSD-ET decoder not only has the ability of dynamically modifying the number of stored nodes, but also adopts the early termination criterion to curtail complexity. The complexity and related parameters are verified through a series of simulations. The simulation results show that the proposed spinal codes with tail-biting and the AFSD-ET decoding algorithms can reduce the complexity and improve the decoding rate without sacrificing correct decoding performance.

关键词： spinal code tail-biting encoding lower decoding complexity early termination strategy

来源：评论

学校读者我要写书评

暂无评论

Lightweight Website Fingerprinting Defense Method Based on Distribution Distance Padding 25

Lightweight Website Fingerprinting Defense Method Based on D...

引用

25th IEEE International Conferences on High Performance Computing and communications, 9th International Conference on Data science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Lu, Tong Zhou, Qiang Zhu, Huijuan School of Computer Science and Communication Technology Jiangsu University Zhenjiang China

ISBN: (纸本)9798350330014

Website fingerprinting (WF) attackers passively collect anonymous traffic traces and employ machine learning methods to identify the target website visited by anonymous network users, which poses a threat to user privacy. To address this issue and protect users' privacy, a lightweight website fingerprinting defense based on distribution distance padding method is proposed, named WFD3p. The method focuses on selecting the target trace with the largest distribution distance, which is significantly different from the source trace. By padding dummy packets into the normal trace based on the transmission characteristics of the target trace, we effectively alter the distribution of the source trace. The dummy packet padding method introduces changes to the traffic features during traffic bursts, thereby confusing the classifier used by WF attackers. This approach enables us to defend against WF attacks. To evaluate the effectiveness of our proposed method, we conducted extensive experiments using open-source data sets under both closed-world and open-world settings. In the closed-world setting, our method reduces the accuracy of WF attacks from 98 % to 75% while only resulting in a 36 % increase in bandwidth consumption. Furthermore, our defense mechanism outperforms WTF-PAD, a defense method developed by the Tor project, in terms of defense performance. By employing our WFD3P, we aim to address the privacy concerns associated with WF attacks and provide users with enhanced protection. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Detection of Diabetic Retinopathy from Retinal Images Using DenseNet Models

引用

computer Systems science & Engineering 2023年第4期45卷 279-292页

作者： R.Nandakumar P.Saranya Vijayakumar Ponnusamy Subhashree Hazra Antara Gupta Department of ECE K S R Institute for Engineering and TechnologyTiruchengode637215India Department of Computer Science and Engineering SRM Institute of Science and TechnologyChennai603203India Department of Electronics and Communication and Engineering SRM Institute of Science and TechnologyChennai603203India

A prevalent diabetic complication is Diabetic Retinopathy(DR),which can damage the retina’s veins,leading to a severe loss of *** treated in the early stage,it can help to prevent vision *** since its diagnosis takes time and there is a shortage of ophthalmologists,patients suffer vision loss even before ***,early detection of DR is the necessity of the *** primary purpose of the work is to apply the data fusion/feature fusion technique,which combines more than one relevant feature to predict diabetic retinopathy at an early stage with greater *** procedures for diabetic retinopathy analysis are fundamental in taking care of these *** profound learning for parallel characterization has accomplished high approval exactness’s,multi-stage order results are less noteworthy,especially during beginning phase *** Connected Convolutional Networks are suggested to detect of Diabetic Retinopathy on retinal *** presented model is trained on a Diabetic Retinopathy Dataset having 3,662 images given by *** results suggest that the training accuracy of 93.51%0.98 precision,0.98 recall and 0.98 F1-score has been achieved through the best one out of the three models in the proposed *** same model is tested on 550 images of the Kaggle 2015 dataset where the proposed model was able to detect No DR images with 96%accuracy,Mild DR images with 90%accuracy,Moderate DR images with 89%accuracy,Severe DR images with 87%accuracy and Proliferative DR images with 93%accuracy.

关键词： Convolutional Neural Networks vision loss pathogenic blood vessels DenseNet AlexNet ResNet

来源：评论

学校读者我要写书评

暂无评论

Optimized Convolutional Neural Network at the IoT edge for image detection using pruning and quantization

引用

Multimedia Tools and Applications 2025年第9期84卷 5435-5455页

作者： Naveen, Soumyalatha Kounte, Manjunath R Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India School of Electronics and Communication Engineering REVA University Bangalore India

Most real-time computer vision applications heavily rely on Convolutional Neural Network (CNN) based models, for image classification and recognition. Due to the computationally and memory-intensive nature of the CNN model, it’s challenging to deploy on resource-constrained Internet of Things (IoT) devices to enable Edge intelligence for real-time decision-making. Edge intelligence requires minimum inference latency, memory footprint, and energy-efficient model. This work aims to develop an energy-efficient deep learning accelerator using a 3-stage pipeline: Training, Weight-pruning, and Quantization to reduce the model size and optimize the resources. First, we employ YOLOv3, a CNN architecture to detect objects in an image on the trained data. In addition, a sparse network of YOLO has been created by using pruning, which helps to improve the network’s performance and efficiency by reducing the computational requirements. Finally, we utilize 8-bit quantization to reduce the precision of the weights and activations, in a neural network. The evaluation of our proposed model shows that combining pruning and 8-bit quantization improves the efficiency and performance of the model. While pruning shows a decline of 80.39% in model parameters. The combination of 8-bit quantization results in an improvement in inference latency by 22.72% compared to existing SQuantization approach and a reduction of energy consumption by 29.41%. © The Author(s) 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A new intelligent cross-domain routing method in SDN based on a proposed multiagent reinforcement learning algorithm

引用

International Journal of Intelligent Computing and Cybernetics 2024年第2期17卷 330-362页

作者： Miao Ye Lin Qiang Huang Xiao Li Wang Yong Wang Qiu Xiang Jiang Hong Bing Qiu School of Information and Communication Guilin University of Electronic TechnologyGuilinChina School of Computer and Information Security Guilin University of Electronic TechnologyGuilinChina School of Computer Science and Technology Xidian UniversityXianChina School of Optoelectronic Egineering Guilin University of Electronic TechnologyGuilinChina

Purpose–A cross-domain intelligent software-defined network(SDN)routing method based on a proposed multiagent deep reinforcement learning(MDRL)method is ***/methodology/approach–First,the network is divided into multiple subdomains managed by multiple local controllers,and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement ***,a cooperative communication module is designed to realize message transmission and message synchronization between the root and local controllers,and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to acquire global network state information in real ***,after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers,a network traffic state prediction mechanism is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real ***–Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and open shortest path first(OSPF)routing methods Originality/value–Message transmission and message synchronization for multicontroller interdomain routing in SDN have long adaptation times and slow convergence speeds,coupled with the shortcomings of traditional interdomain routing methods,such as cumbersome configuration and inflexible acquisition of network state *** drawbacks make it difficult to obtain global state information about the network,and the optimal routing decision cannot be made in real time,affecting network *** paper proposes a cross-domain intelligent SDN routing method based on a proposed MDRL ***,the network

关键词： Reinforcement learning Cross-domain intelligent routing Network traffic state prediction Software-defined network

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Multi-Frame Integration Detection Method for Weak Target with Coherent MIMO Radar

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 6518-6536页

作者： Gao, Longji Li, Xiaolong Wang, Mingxing Sun, Zhi Cui, Guolong Yeo, Tat Soon University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China National University of Singapore Department of Electrical and Computer Engineering Singapore119077 Singapore

Coherent multiple-input multiple-output (MIMO) radar could significantly improve the weak moving target detection ability by accumulating multi-channel and multi-frame echo signal. However, due to the target motion and the geometric configuration differences of each node relative to the target, the multi-channel multi-frame accumulation of target echoes by coherent MIMO radar faces several difficulties, i.e., range migration (RM) and Doppler frequency migration (DFM) issues within each channel, spatial variations of target signal envelope and phase across different channels, time variations of target signal envelope and phase across different frames. To tackle these problems, two contributions are made in this paper. Firstly, by applying the generalized Radon Fourier transform (GRFT) to correct the RM/DFM and obtain the signal integration within each channel, we propose a multi-channel accumulation algorithm to compensate the spatial variations of target signal and realize the target energy accumulation across different channels, which takes full advantage of the GRFT output characteristics and the radar system topological structure. Secondly, a multi-frame accumulation algorithm is developed to compensate the time variations of target signal and achieve the further integration of target energy distributed in different frames. We also provide explicit expressions and analysis for performance metrics, including the output response, SNR improvement performance. The proposed method's effectiveness is confirmed through simulation experiments. © 1965-2011 IEEE.

关键词： Topology

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：