检索结果-内蒙古大学图书馆

Probabilistic Reliability via Subsystem Structures of Arrangement Graph Networks

IEEE Transactions on Reliability 2024年第1期73卷 279-289页

作者： Huang, Yanze Lin, Limei Xu, Li Hsieh, Sun-Yuan Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Fujian Normal University College of Computer and Cyber Security Key Laboratory of Network Security and Cryptology Fuzhou350117 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701 Taiwan

With the rapid growth of the number of processors in a multiprocessor system, faulty processors occur in it with a probability that rises quickly. The probability of a subsystem with an appropriate size being fault-free in a definite time interval is a significant and practical measure of the reliability for a multiprocessor system, which characterizes the functionality of a multiprocessor system well. Motivated by the study of subgraph reliability, as well as the attractive structure and fault tolerance properties of (n, k)-arrangement graph A n, k, we focus on the subgraph reliability for A n, k under the probabilistic fault model in this article. First, we investigate intersections of no more than four subgraphs in A n, k, and classify all the intersecting modes. Second, we focus on the probability P(q, A n, k n-1, k-1) with which at least one (n-1, k-1)-subarrangement graph is fault-free in A n, k, when given a uniform probability q with which a single vertex is fault-free, and we establish the P(q, A n, kn-1, k-1) by adopting the principle of inclusion-exclusion under the probabilistic fault model. Finally, we study the probabilistic fault model involving a nonuniform probability with which a single vertex is fault-free, and we prove that the P(q, A n, kn-1, k-1) under both models is very close to the asymptotic value by both theoretical arguments and experimental results. © 1963-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A fractional-order multivariable grey model and its application in predicting pollution emissions 4

A fractional-order multivariable grey model and its applicat...

引用

4th IEEE International Conference on Electronic technology, Communication and information, ICETCI 2024

作者： Zhang, Meng Cheng, Chonglv Wuhan College of Arts and Science Institute of Information and Computer Wuhan China Dalian University of Technology School of Energy and Power Engineering Dalian China

ISBN: (纸本)9798350361643

The dissemination and utilization of information has been facilitated by the rapid development of the Internet. Pollution emissions should be attracted attention, and information technology can promote the effective analysis of pollution discharge. A novel enhanced model is proposed by incorporating fractional order, power exponential, linear correction, and random disturbance terms into the GM (1,N) model. By introducing the fractional-order accumulation, the model is able to capture the dynamic changes in the raw data, thereby enhancing the accuracy of models. In addition, the unknown informations in the raw data can be taken into account. The uncertainties can also be addressed in the system, which making the predictions more reliable. At last, the FMGM (1, N) model achieved high accuracy in predicting pollution emissions for Beijing and Hubei Province. © 2024 IEEE.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

Adaptive residual convolutional neural network for moiré image restoration

引用

International Journal of information technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the Zebra Optimization Algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure Zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Smart Waste Management System Using IoT

Smart Waste Management System Using IoT

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Dhar, Mainak Roy, Alak Mandal, Purnendu Icfai University Dept. of Computer Science and Engineering Tripura Agartala India Tripura University Dept. of Information Technology Agartala India

ISBN: (纸本)9798331540821

It is thereby noticed that the rapid rate of urbanization has increased the quantum of waste generation manifold, which imposes significant challenges in waste management for traditional systems. In this paper, a Smart Waste Management System (SWMS) is proposed at a time when Internet of Things (IoT) and Artificial Intelligence (AI) technologies are about to reach the mainstream. The SWMS will reduce operations costs and its impact on the environment with its architecture, which provides real-time monitoring, data analytics, and intelligent decision-making methods to enhance efficiency. The IoT part of SWMS involves setting up sensor nodes in the waste bins to observe fill levels and other environmental parameters. The sensors transmit the data without wires to a central cloud platform for storage and analysis. AI algorithms on the cloud process this information to produce optimized disposal schedules, fill-level predictions, and anomaly detection, like fires or spills. Moreover, by using techniques of machine learning, system performance will be improved further by available historical data and real-time feedback. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Memristive Chaotic 5D System with 3D Offset Boosting

A Memristive Chaotic 5D System with 3D Offset Boosting

引用

2023 IEEE International Conference on Memristive Computing and Applications, ICMCA 2023

作者： Zhang, Xin Li, Chunbiao Cen, Xiaoliang Akgul, Akif Gao, Yikai School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China Hitit University Department of Computer Engineering Corum19030 Turkey

ISBN: (纸本)9798350316230

In this article, a 5D memristive chaotic system with three 3D offset boosting is designed and analyzed. By introducing three independent offset constants in the system equation, different regimes of offset boosting are defined by the external constants including various combinations of reverse control and differential control. Furthermore, the offset boosting is also influenced by the coefficient of the linear terms, which is a bifurcation parameter. Finally, the memristive 5D chaotic circuit is designed based on the software of Multisim. Circuit simulation validates the function of offset boosting from the separated three constants. © 2023 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

DS-YOLO:A dense small object detection algorithm based on inverted bottleneck and multi-scale fusion network

引用

Biomimetic Intelligence & Robotics 2024年第4期4卷 64-75页

作者： Hongyu Zhang Guoliang Li Dapeng Wan Ziyue Wang Jinshun Dong Shoujun Lin Lixia Deng Haiying Liua School of Information and Automation Engineering Qilu University of TechnologyJinan 250353China Unimation Intelligent Technology Co. Jinan 250101China School of Computer Science University of St AndrewsSt Andrews KY169AJUnited Kingdom

In the field of security,intelligent surveillance tasks often involve a large number of dense and small objects,with severe occlusion between them,making detection particularly *** address this significant challenge,Dense and Small YOLO(DS-YOLO),a dense small object detection algorithm based on YOLOv8s,is proposed in this ***,to enhance the dense small objects'feature extraction capability of backbone network,the paper proposes a lightweight *** improved C2fUIB is employed to create a lightweight model and expand the receptive field,enabling the capture of richer contextual information and reducing the impact of occlusion on detection ***,to enhance the feature fusion capability of model,a multi-scale feature fusion network,Light-weight Full Scale PAFPN(LFS-PAFPN),combined with the DO-C2f module,is *** new module successfully reduces the miss rate of dense small objects while ensuring the accuracy of detecting large ***,to minimize feature loss of dense objects during network transmission,a dynamic upsampling module,DySample,is ***-YOLO was trained and tested on the CrowdHuman and VisDrone2019 datasets,which contain a large number of densely populated pedestrians,vehicles and other *** evaluations demonstrated that Ds-YOLO has advantages in dense small object detection *** with YOLOv8s,the Recall and mAP@0.5 are increased by 4.9%and 4.2%on CrowdHuman dataset,4.6%and 5%on VisDrone2019,***,DS-YOLO does not introduce a substantial amount of computing overhead,maintaining low hardware requirements.

关键词： Denseobjects detection LFS-PAFPN DOConv C2fUIB YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Kernel Based Fuzzy Simulation Model for Early Detection of Cancer to Avoid Metastasis 3

Kernel Based Fuzzy Simulation Model for Early Detection of C...

引用

3rd IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2024

作者： Santra, Soumen Majumdar, Dipankar Mandal, Surajit Deyasi, Arpan Techno International New Town Department of Computer Application Kolkata India RCC Institute of information Technology Department of Computer Science and Engineering Kolkata India B. P. Poddar Institute of Management & Technology Department of Electronics and Communication Engineering Kolkata India RCC Institute of Information Technology Department of Electronics and Communication Engineering Kolkata India

ISBN: (纸本)9798350374643

In this paper, novel cancer detection method using Kernel Based Fuzzy Simulation Model (KBFSM) represented with enhanced accuracy of 12%, considering MRI based breast cancer images. Developed framework, as suggested in this paper, Effectiveness and superiority of the suggested approach are proven by thorough testing on a variety of datasets and thorough assessment metrics, highlighting its capacity to produce accurate and nuanced segmentation results. Fuzzification and defuzzification of images using Fuzzy C means algorithm, speaks in favor of the proposed analysis, as tested over several dataset, owing to minute pixel intensity modification when associated with malignant tissues. Result is supported by histogram analysis, which paves the way of future research in the field of lung cancer using the same technique. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

NLP-Enhanced Long Document Summarization: A Comprehensive Approach for information Condensation 2

NLP-Enhanced Long Document Summarization: A Comprehensive Ap...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Maurya, Karan Guru Prasad, M.S. Gupta, Shubham Ameta, Hardik Negi, Abhijeet Singh Amrutha, P.V. Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Reva University School of computing & Information Technology Bengaluru India

ISBN: (纸本)9798350371314

The present era is characterized by information overload, making the ability to distil multitude of data into concise and meaningful summaries very important. The response to ever-increasing challenge is this revolutionary NLP based model called text Summarizer that will redefine the interactions with information. Text Summarizer aims at providing users with quick, accurate and coherent summaries of lengthy texts so to promote their understanding. The cutting-edge methods harnessed by the Text Summarizer enable it to assimilate given text context, identify major themes and provide brief summaries that capture the essence of source content. To build this text summarizer advanced NLP algorithms are used. Modern deep learning models are mainly based on transformer architectures like BERT (Bidirectional Encoder Representations from Transformers) or GPT (Generative Pre-trained Transformer);they are used because they have the capacity to capture complicated language patterns and nuances. Transformer is a sequence-to-sequence model which uses attention technique to process text sequentially. It is made up of encoders and decoders interconnection. This transformer takes in the text input and provide the summary as output. Transformer discussed in this paper has an accuracy of around 98% which is trained over cnn-dailymail dataset. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Frequency Hopping Scheme for Cognitive Radio Networks using Reinforcement Learning 3

An Adaptive Frequency Hopping Scheme for Cognitive Radio Net...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Meena, Y.R. Acharjya, Kalyan Upadhyay, Ramakant JAIN School of Engineering and Technology Department of Civil Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Sanskriti University Department of Computer Science Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350354171

Adaptive Frequency Hopping (AFH) is an essential generation for Cognitive Radio Networks (CRNs). It no longer bests improves spectral efficiency and quality of service of CRNs but also prevents interference amongst customers. However, traditional AFH schemes need help with essential problems. First, they require a large amount of previous expertise approximately the surroundings. 2d, they remain highly static and inflexible, situation to adjustments in the external environment. This paper presents an Adaptive AFH scheme using Reinforcement to gain knowledge of (RL) for CRNs. First off, an environment-conscious AFH approach based on the user-described frequency occupancy possibility is proposed. The method is composed of a probabilistic hopping sequence generator and an intra-frequency hopping detector. Secondly, an adaptive AFH scheme with temporal-spatial getting to know is proposed, which incorporates an actor-critic-based RL controller and recreation-theoretic modeled surroundings. The RL controller generates a dynamic hopping sequence with low hopping frequency collisions at the same time as the sport-theoretic surroundings fashion the temporal-spatial modifications of the wireless medium. Sooner or later, the proposed scheme is proven in a simulated CRN environment. © 2024 IEEE.

关键词： Frequency hopping

来源：评论

学校读者我要写书评

暂无评论

Double Mutational Salp Swarm Algorithm:From Optimal Performance Design to Analysis

引用

Journal of Bionic engineering 2023年第1期20卷 184-211页

作者： Chao Lin Pengjun Wang Xuehua Zhao Huiling Chen College of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou325035China College of Electrical and Electronic Engineering Wenzhou UniversityWenzhou325035China School of Digital Media Shenzhen Institute of Information TechnologyShenzhen518172China

The Salp Swarm Algorithm(SSA)is a population-based Meta-heuristic Algorithm(MA)that simulates the behavior of a group of salps foraging in the *** the basic SSA has stable exploration capability and convergence speed,it still can fall into local optimum when solving complex optimization problems,which may be due to low utilization of population information and unbalanced exploration-to-exploitation ***,this study proposes a Double Mutation Salp Swarm Algorithm(DMSSA).In this study,a Cuckoo Mutation Strategy(CMS)and an Adaptive DE Mutation Strategy(ADMS)are introduced into the structure of the original *** former mutation strategy is summarized as three basic operations:judgment,shuffling,and *** purpose is to fully consider the information among search agents and use the differences between different search agents to participate in the update of positions,making the optimization process both diverse in exploration and minor in *** latter strategy employs three basic operations:selection,mutation,and *** the follower part,some individuals do not blindly adopt the original follow ***,the global optimal position and differences are considered,and the variation factor is adjusted adaptively,allowing the new algorithm to balance exploration,exploitation,and convergence *** evaluate the performance of DMSSA,comparisons are made with numerous algorithms on 30 IEEE CEC2014 benchmark *** statistical results confirm the better performance and significant difference of DMSSA in solving benchmark function ***,the applicability and scalability of DMSSA to optimization problems with constraints are further confirmed in three experiments on classical engineering design optimization *** source code of the proposed algorithm will be available at:https://***/ncjsq/Double-Mutational-Salp-Swarm-Algorithm.

关键词： Salp swarm algorithm Meta-heuristic algorithm Global optimization-Exploration Exploitation Bionic

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：