检索结果-内蒙古大学图书馆

bayesian and Multi-Armed Contextual Meta-Optimization for Efficient Wireless Radio Resource Management

IEEE Transactions on Cognitive Communications and Networking 2023年第5期9卷 1282-1295页

作者： Zhang, Yunchuan simeone, Osvaldo Jose, sharu Theresa Maggi, Lorenzo valcarce, Alvaro King's College London Department of Engineering LondonWC2R 2LS United Kingdom University of Birmingham Department of Computer Science BirminghamB15 2TT United Kingdom Nokia Bell Labs France Department of Radio Systems and Ai Nozay91620 France

Optimal resource allocation in modern communication networks calls for the optimization of objective functions that are only accessible via costly separate evaluations for each candidate solution. The conventional approach carries out the optimization of resource-allocation parameters for each system configuration, characterized, e.g., by topology and traffic statistics, using global search methods such as bayesian optimization (bO). These methods tend to require a large number of iterations, and hence a large number of key performance indicator (KPI) evaluations. In this paper, we propose the use of meta-learning to transfer knowledge from data collected from related, but distinct, configurations in order to speed up optimization on new network configurations. specifically, we combine meta-learning with bO, as well as with multi-armed bandit (MAb) optimization, with the latter having the potential advantage of operating directly on a discrete search space. Furthermore, we introduce novel contextual meta-bO and meta-MAb algorithms, in which transfer of knowledge across configurations occurs at the level of a mapping from graph-based contextual information to resource-allocation parameters. Experiments for the problem of open loop power control (OLPC) parameter optimization for the uplink of multi-cell multi-antenna systems provide insights into the potential benefits of meta-learning and contextual optimization. © 2015 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

An extensive critique on advances in digital control techniques for smart grid and micro grid operation

An extensive critique on advances in digital control techniq...

引用

IEEE students' Conference on Electrical, Electronics and computer science (sCEECs)

作者： sarathkumar D K. bashkaran Murugesan Manivel T. Jayakumar R. sivakumar Anandhakumar C Department of Electrical and Electronics Engineering Kongu Engineering College Tamil Nadu India Department of Biomedical Engineering Kongunadu College of Engineering and Technology Thottiam Tamil Nadu Department of Electrical and Electronics Engineering Karpagam Institute of Technology Coimbatore Tamilnadu India Department of Electrical and Electronics Engineering Nandha Engineering College Tamil Nadu India Department of Electrical and Electronics Engineering V.S.B Engineering College Tamil Nadu India Department of Electrical and Electronic Engineering Sri Ramakrishna Institute of Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

The integration of digital control techniques within smart grids and microgrids represents a pivotal advancement in the optimization, reliability, and efficiency of modern electrical networks. This paper explores the latest developments in digital control strategies, focusing on their application to the operation of smart grids and microgrids. Key areas of discussion include the implementation of advanced algorithms for real-time monitoring and control, the role of artificial intelligence and machine learning in predictive maintenance and decision-making, and the impact of distributed control systems on grid stability and resilience. Furthermore, the paper examines the challenges and solutions associated with integrating renewable energy sources and energy storage systems into the grid, emphasizing the importance of adaptive and scalable control frameworks. Through a comprehensive review of recent research and case studies, this paper provides insights into the future trends and potential breakthroughs in digital control technologies, highlighting their critical role in the evolution of smart grid and microgrid infrastructures. The findings suggest that continued innovation in this field will significantly enhance the operational capabilities of electrical grids, paving the way for more sustainable and resilient energy systems.

关键词： Digital control Renewable energy sources Microgrids Machine learning Power system stability Real-time systems smart grids Reliability Optimization Resilience

来源：评论

学校读者我要写书评

暂无评论

video based Car Parking Management and Monitoring Using computer vision and Machine Learning

Video Based Car Parking Management and Monitoring Using Comp...

引用

2025 International Conference on Multi-Agent systems for Collaborative Intelligence, ICMsCI 2025

作者： sujitha, bulla Ponraj, Anitha Chakkarapani, v. Parabrahmachari, sriram Lakshmi, T.v. Hyma Annamani, T. V. R. Siddhartha Engineering College Department of Ece AP Vijayawada India Kalasalingam Academy of Research and Education Kalasalingam University Department of Computer Science and Engineering Tamil Nadu Krishnankoil India School of Electrical and Electronics Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Guru Nanak institutions Department of Cse Technical Campus Telangana Ibrahimpatnam India S.R.K.R. Engineering College Department of Ece A.P Bhimavaram India Anurag University Department of Ece Telangana Hyderabad India

ISBN: (纸本)9798331509828

Each day, countless individuals around the globe are affected by the extensive and complex problem of traffic congestion. This raising challenge is becoming increasingly substantial across the country, driven by factors such as rising population numbers, speedy urban development, insufficient infrastructure, and changing socioeconomic requirements. This paper depicts a novel global video-based parking approach designed to boost the supervising and management of parking spaces using real-time aerial statistics. Utilizing advanced image processing and computer vision procedures, the system essentially detects and examines the occupancy position of parking slots. In our realization, we assessed a total of 48 parking spaces, positively identifying 7 as unused while 41 were occupied. The application of Python, OpenCv, and machine learning assisted real-time monitoring, allowing precise counting and expose of parking availability. The procedure contained critical procedures, including Gaussian blur filtering to minimize noise and improve edge detection, followed by binary thresholding to describe vehicles and parking spots from the background. Furthermore, a median filter was utilized to boost the clarity of vehicle contours. These image enhancement methods significantly expanded detection accuracy and facilitated precise recognition of the Region of Interest (ROI). The results show the system's ability to provide reliable, real-time data for dynamic parking administration, thereby focusing the challenges of urban parking. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

An Efficient blockchain and Deep Learning-based Framework for secure Healthcare Data Management and Disease Prediction

An Efficient Blockchain and Deep Learning-Based Framework fo...

引用

International Conference on computer and Communications Technologies (ICCCT)

作者： syed Mohamed E soundarapandiyan K Dinesh Kumar s syed Abdul syed s Department of computer science Engineering B.S.A Crescent Institute of Science & Technology Chennai India Department of Commerce B.S. Abdur Rahman Institute of Science & Technology Chennai India Department of Management Studies Sri Sairam Engineering College Chennai Tamil Nadu India Department of computer science Engineering BS Abdur Rahman Crescent Institute of Science and Technology

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Healthcare data security is a pressing concern given the surge in data breaches, with over 750 incidents reported in 2021 alone, exposing more than 193 million personal records. This paper introduces an Efficient Data security system that leverages smart contracts, WEb 3.0 deep learning algorithms, and blockchain technology to address these challenges. The system provides robust data protection by eliminating the need for encryption keys, utilizing blockchain for tamper-proof storage, and incorporating advanced deep learning algorithms for predictive analytics. The framework of WEb 3.0 integrates blockchain at the backend, ensuring secure and immutable data storage. smart contracts enable automated and transparent data access without compromising security. Additionally, the system utilizes the InterPlanetary File system (IPFs) for efficient image storage and retrieval, enhancing data accessibility while maintaining cryptographic security. The integration of deep learning algorithms enables predictive analytics for medical conditions such as Alzheimer's disease and tumor detection, further enhancing the system's capabilities in healthcare data management and analysis.

关键词： semantic Web Deep learning smart contracts Prediction algorithms blockchains InterPlanetary File system Predictive analytics Alzheimer's disease biomedical imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

Deep-Q Classifier for Predicting balanced and Imbalanced Features in Cartpole and Lunarlander Dataset

Deep-Q Classifier for Predicting Balanced and Imbalanced Fea...

引用

Data science, Agents & Artificial Intelligence (ICDsAAI), International Conference on

作者： K veeramanikandan R Ponnusamy Department of Computer Science and Engineering V.R.S. College of Engineering and Technology Villupuram Tamilnadu India Department of Computer Science and Engineering Chennai Institute of Technology Chennai Tamilnadu India

The purpose of this paper is to investigate the impact of significant Q-Assignment (sQN) on the convenience of multiclass portrayal estimations. To create a framework that blends DQN with existing supervised multiclass classification algorithms, we will utilize a Kaggle benchmark dataset. The findings of this review will provide insight on how to utilize profound support learning methods to enhance multiclass order precision. They have been used in different fields, including picture affirmation, normal language processing, and bioinformatics. The specialist demonstrates one example at each time point, and the climate evaluates the order activity and gives the specialist a prize. The specialist is more attentive to the minority class due to the higher prize for minority class tests. The agent ultimately discovers the optimal classification policy in the data with imbalances, guided by a specific reward function and a beneficial learning environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Utilizing Hsv Color space for Real-Time Early Fire

A Novel Deep Learning Approach Utilizing HSV Color Space for...

引用

International Conference on Communication systems and Network Technologies (CsNT)

作者： Md. shoaib Alam Pankaj Rai Rajesh Kumar Tiwari sharafat Hussain biresh Kumar Abhishek Kumar Computer Science and Engineering Jharkhand University of Technology Ranchi India Electrical Engineering BIT Sindri Dhanbad India Computer Science and Engineering R.V.S College of Engg & Tech Jamshedput India Dubai International Academic City American University in the Emirates Dubai UAE Computer Science and Engineering Amity University Ranchi India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

This study proposes a novel fire detection system aimed at improving fire prevention and control efforts, particularly addressing the growing threat posed by fires in urban settings and the alarming frequency of wildfires. Early detection of fire plays a critical role in safeguarding lives and property in places such as shopping malls, offices, factories, and educational institutions. Existing systems for detecting fires, which rely mainly on alarm-based mechanisms, have limitations in their responsiveness. In this project, we developed a machine learning-based fire detection system using computer vision techniques. The proposed model integrates a webcam as part of the surveillance setup to continuously monitor indoor environments. by leveraging video feeds, the system processes the input using machine learning algorithms and the Hue, saturation, value (Hsv) color space to detect fire at an early stage. OpenCv is employed to handle real-time video processing, ensuring prompt fire detection and timely alerts. This approach demonstrates a significant advancement over traditional systems, offering real-time detection capabilities through the combination of deep learning and advanced color space techniques.

关键词： Deep learning computer vision Wildfires Webcams surveillance Prevention and mitigation Color streaming media Real-time systems Production facilities

来源：评论

学校读者我要写书评

暂无评论

Enhancing Railway safety with an IoT based system for Real Time Fault Detection and Crack Monitoring

Enhancing Railway Safety with an IoT Based System for Real T...

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Rajermani Thinakaran somasekar Jalari vikram Neerugatti Madhusudana Rao Nalluri santhaiah Chukka Ravindra Raman Cholla Faculty of Data Science and Information Technology INTI International University Malaysia Department of Computer Science and Engineering Faculty of Engineering and technology Jain (Deemed-to-be University) Bangalore India Department of Computer Science and Engineering ICFAI Foundation for Higher Education Hyderabad Telangana India Department of Computer Science and Engineering S V College of Engineering Tirupati Andhra Pradesh India

ISBN: (数字)9798331510732

ISBN: (纸本)9798331510749

safety of railway is the major problem worldwide. It has problems like cracks or any fault in the railway tracks. These problems can cause severe accidents if it is not detected regularly and early. In traditional fault finding and crack detecting method, the manual method is involved which is very slow and consist of many errors. by considering all these challenges and issues in track detection method, we have implemented an advanced IoT based railway crack and fault-finding system. It uses advanced sensors, microcontroller, GPs and GsM module which can detect and report faults of the railway track. The system uses real time mechanism. The system is implemented and tested on a prototype railway track to detect crack or any fault. The internet of things technology added modern and accurate fault-finding feature in the system. The IoT plays an important role in implementing advance technologies, as it uses sensors and advance microcontroller. The accuracy rate of fault and crack detection is around 97%, which is for 2 mm crack. Along with this GPs module accurately track fault location. GsM module successfully send the alert message quickly after detecting the fault in the track. Hence the response time is very less and accurate. This system is implemented in order to ensure safety for the railway track and prevent the accidents. Hence the system is useful for improving overall transport safety.

关键词： GsM Accuracy Microcontrollers Fault location Rail transportation Real-time systems sensors safety Internet of Things Global Positioning system

来源：评论

学校读者我要写书评

暂无评论

blockchain-based Privacy-Preserving system for Internet of Things (IoT)

Blockchain-based Privacy-Preserving System for Internet of T...

引用

International Conference on Communication and Electronics systems (ICCEs)

作者： C. N. Ravi s Dinesh Krishnan Manikannan Kaliyaperumal sumita Kumar A. v. s. Ram Prasad s. suma Christal Mary Computer Science & Engineering Department CMR Engineering College Hyderabad Telangana Department of Computer Science & Engineering B V Raju Institute of Technology Narsapur Computer Science & Engineering R.M.K Engineering College R.S.M Nagar Department of Engineering and Technologies Computer Science & Engineering Bharati Vidyapeeth Deemed to be University Navi Mumbai Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Guntur India Department of Information Technology Panimalar Engineering College Chennai Tamil Nadu

The shortcomings of conventional healthcare systems are becoming more apparent as the Internet of Things (IoT) becomes ever more pervasive in people's daily lives. The standard procedure for dealing with confidential data frequently results in unwanted public disclosure. blockchain's agreements make it possible to automate the safe transfer of patient data based on their individual authorization settings. To create a completely untraceable trading platform, blockchain technology is frequently implemented. To protect user data in the Internet of Things (IoT), a privacy-protecting protocol is developed using the blockchain. It is important to consider that the rogue cloud server might potentially develop a database of user behaviour profiles, which could be a serious breach of privacy. Confidentiality makes it more difficult to resolve disagreements about private data exchange transactions. When users of metadata are falsely accused, their rights are difficult to defend. Also, smart contracts are used to enforce security protocols and data privacy for multisharing adaptable access control. There is no reason to doubt the safety of the proposed work. The proposed work is efficient and applicable, as demonstrated by the efficiency evaluation and experimental findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

big Data Analytics-based Diabetes Prediction Model for Identifying Internal Factors for Diabetes Mellitus

Big Data Analytics-Based Diabetes Prediction Model for Ident...

引用

Delhi section Conference (DELCON), IEEE

作者： C. Mallika J. vanitha K. Kalaivani s. selvamuthukumaran Department of MCA E.G.S. Pillay Engineering College Nagapattinam Tamilnadu India School of Computer Science and Engineering VIT Vellore Vellore India A.V.C. College of Engineering Mayiladuthura India

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Diabetes mellitus (DM) is a serious global health concern. According to the International Diabetes Foundation, 537 million individuals are living with DM worldwide, and this figure is expected to reach 643 million by 2030 and 783 million by 2045. Therefore, there is a pressing need for timely prognosis, identification, and management of DM and its impediments. This research proposes an efficient model to identify DM using an optimized support vector Machine (svM) algorithm. The proposed model implements the stochastic Gradient Descent (sGD) optimization technique to fine-tune the svM algorithm by updating hyperparameter. Thus, the cohesive sGD-svM approach is more appropriate for big databases related to conventional svM algorithms. The sGD-svM algorithm can apprise the system progressively as new data arrives, which is beneficial for constantly growing databases. The performance of our OsvM model is meticulously analyzed using the Pima Indian database. To assess the hybrid sGD-svM model, its classification enactment is compared with existing state-of-the-art machine learning-based diagnosis systems in terms of designated evaluation measures. The extensive results of the experimental analysis demonstrate that sGD-svM is a more competent model with 95.7% accuracy, 84.2% sensitivity, 86.9% specificity, and 91.7% precision. Further, it realizes a minimal false alarm rate (i.e., 2.0% false positive rate (FPR) and 1.4% false negative rate (FNR)). Therefore, this study can conclude that sGD-svM is the improved diabetes analytic tool as compared with other existing models found in the literature.

关键词： support vector machines Analytical models Machine learning algorithms sensitivity Accuracy Databases vectors Diabetes Classification algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid Competitive swarm Optimization Algorithm based scheduling in the Cloud Computing Environment 5

Hybrid Competitive Swarm Optimization Algorithm Based Schedu...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： shrichandran, G.v. Narayana Tinnaluri, v.s. senthil Murugan, J. Meeradevi, T. Dwivedi, vijay Kumar suma Christal Mary, s. B.Sc -CS Programme Srm Institute of Science and Technology Department of Computer Science & Applications Ramapuram Chennai89 India Koneru Lakshmaiah Education Foundation Department of Computer Science Vaddeswaram522025 India Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Avadi Chennai India Kongu Engineering College Department of Ece Perundurai Erode India V.E.C. Ambikapur Dist Surguja497001 India Panimalar Engineering College Poonamalle Department of Information Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350321425

Cloud computing (CC) platform not only offers resource sharing for users and also provide many on-demand services. business procedures can be managed to utilize the workflow technology on the cloud which signifies most of the problems in employing the resources in an effectual approach because of the dependencies between the tasks. Task scheduling (Ts) in a CC platform applies to the procedure of effectively allocating resources computing to tasks or jobs submitted to the CC environment. In a cloud platform, tasks are separated as smaller subtasks that are applied in parallel on distinct machines. There are many features to consider if the Ts is in CC platform, comprising the kind of tasks like resources cost, resources required, and resources availability. Therefore, this study presents a Hybrid Competitive swarm Optimization Algorithm based Task scheduling (HCsOA-Ts) technique in the CC platform. The presented HCsOA-Ts technique schedules the tasks proficiently in such a way that maximum resource utilization and performance gets accomplished. In the design of HCsOA, Cauchy mutation operator is included in the CsO algorithm and thereby improves the overall performance. In addition, the derivation of the fitness function by the HCsOA-Ts technique undergoes optimal scheduling process and decreases energy usage. The experimental result analysis of the HCsOA-Ts technique is tested using a series of measures. The comprehensive comparison study highlighted the improvements of the HCsOA-Ts technique over recent approaches. © 2023 IEEE.

关键词： Cloud computing

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：