检索结果-内蒙古大学图书馆

International Journal of Interactive Mobile Technologies 2023年第4期17卷 89-100页

作者： Sangeetha, M. Erna, G. Kannan, S. Rajes Salameh, Anas A. Kishore, Kakarla Hari Department of Data Science and Business Systems SRMIST KattankulathurChennai India Ongole India Computer Science and Engineering Chennai Institute of Technology Chennai India Department of Management Information Systems College of Business Administration Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Electronics and Communication Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh India

Mobile Ad-Hoc network is a distributed wireless network that is self-organized and self-maintained and it doesn’t require a fixed framework or central administration. Wireless nodes in a mobile ad hoc network are transient and have a short lifespan. They combine to form a self-configured, infrastructure-free network where routing is a significant difficulty. The wireless nodes in the network must synchronize in order to decide connectivity and routing. Ad hoc network synchronization includes activities including node organization, neighborhood detection, and routing. The predetermined framework resulted in an increase in network control overhead. If a node can link to every other node in the network, it is referred to as a dominating node, and a set of dominating nodes make up the dominating set. The main purpose of this article is to lessen routing overhead in the wireless network with the dominating set based routing (DSBR). In order to discover routes, shorten reroute establishment times, and increase packet delivery rates, this research presents an energy-efficient routing algorithm (EERA) that considerably increases the network performance. The effectiveness of this technique is demonstrated by the simulation analysis of the outcome. © 2023,International Journal of Interactive Mobile Technologies. All Rights Reserved.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-agency Collaboration Medical Images Analysis and Classification System based on Federated Learning 24

Research on Multi-agency Collaboration Medical Images Analys...

引用

2024 International Conference on Biomedicine and Intelligent Technology, ICBIT 2024

作者： Huang, Shijia Diao, Su Wan, Yajie Song, Chaoda Fu Foundation School of Engineering and Applied Science Columbia University United States Department of Industrial & Systems Engineering Auburn University United States Department of Computer Science Brown University United States School of Engineering Department of Computer and Data Sciences United States

ISBN: (纸本)9798400710063

In the field of medical image analysis, with the growth of data volume and the increasing demand for privacy protection, traditional centralized learning methods are facing the problems of data silos and privacy leakage. Therefore, federated learning, as an emerging distributed machine learning framework, provides a solution to protect data privacy while effectively utilizing decentralized data. The purpose of this study is to develop a federated learning-based medical image analysis and classification system to solve the data isolation and privacy problems existing in traditional methods. This study uses a distributed federated learning framework that allows multiple healthcare organizations to share updates to their models instead of raw data. data privacy protection is further enhanced through the use of differential privacy and secure multi-party computation techniques. In addition, a deep convolutional neural network (CNN) is used to improve the accuracy of feature extraction and classification of medical images. Experimental analysis shows that the system can significantly improve the classification accuracy of medical images. Specifically, our system achieved a 15% improvement in classification accuracy compared to traditional centralized methods. Additionally, the implementation of differential privacy and secure multi-party computation resulted in a privacy leakage reduction of 25%. These results verify the application potential of federated learning in the field of medical image processing, demonstrating superior performance and enhanced privacy protection compared to traditional centralized learning methods. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of the Imputing of Missing data on Air Pollution 2

A Comparative Analysis of the Imputing of Missing Data on Ai...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Gayathri, M. Kavitha, V. SRM Institute of Science and Technology Department of Computer Science and Engineering Kattankulathur Chennai India SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India

ISBN: (纸本)9798350365269

Air pollution is a significant environmental hazard in modern society because of its serious impact on human health and the environment. In point of fact, there has been a substantial rise in the levels of pollution in the environment over the course of the past few years. data analyst is commonly encountering the issue of data missing. It is crucial to handle them efficiently to get more accurate and dependable data analysis findings. This study aims to improve understanding of data missing mechanisms, data imputation techniques, and examine the efficacy of frequently utilized data imputation techniques on quantitative datasets. Analysts and data scientists frequently face the challenge of missing data in their investigations. Therefore, it is essential to handle them in an efficient manner so as to gain improved and more trustworthy results through the analysis of the data. The objective of this research is to enhance comprehension of data missing processes and data imputed methods, while also evaluating the effectiveness of data imputed approaches often employed in quantitative datasets. A complete comparison of 5 different data imputation methods is presented in this article. These approaches include mean imputation, median imputation, mode imputation, kNN imputation and Linear Regression. For the purpose of analysing and contrasting the efficacy of the various data imputation approaches, we have utilized five distinct numeric datasets that were gathered from several air pollution repositories. Standardized Root Mean Square Error (RMSE) is the technique for assessing the efficacy of data imputation techniques. According on the findings of the analysis, the kNN imputation approach offers superior performance than the other methods. There is no correlation between the length of the dataset or the number of values that are missing in the dataset and the accuracy of the data imputed approach. © 2024 IEEE.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

Unsupervised episode generation for graph meta-learning 24

Unsupervised episode generation for graph meta-learning

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jihyeong Jung Sangwoo Seo Sungwon Kim Chanyoung Park Department of Industrial & Systems Engineering KAIST Graduate School of Data Science KAIST Department of Industrial & Systems Engineering and Graduate School of Data Science KAIST

We propose Unsupervised Episode Generation method called Neighbors as Queries (NAQ) to solve the Few-Shot Node-Classification (FSNC) task by unsupervised Graph Meta-learning. Doing so enables full utilization of the information of all nodes in a graph, which is not possible in current supervised meta-learning methods for FSNC due to the label-scarcity problem. In addition, unlike unsupervised Graph Contrastive Learning (GCL) methods that overlook the downstream task to be solved at the training phase resulting in vulnerability to class imbalance of a graph, we adopt the episodic learning framework that allows the model to be aware of the downstream task format, i.e., FSNC. The proposed NAQ is a simple but effective unsupervised episode generation method that randomly samples nodes from a graph to make a support set, followed by similarity-based sampling of nodes to make the corresponding query set. Since NAQ is model-agnostic, any existing supervised graph meta-learning methods can be trained in an unsupervised manner, while not sacrificing much of their performance or sometimes even improving them. Extensive experimental results demonstrate the effectiveness of our proposed unsupervised episode generation method for graph meta-learning towards the FSNC task. Our code is available at: https://***/JhngJng/NaQ-PyTorch.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Multimodal AI Models for Enhanced Oral Cancer Detection and Diagnosis 2

Integrating Multimodal AI Models for Enhanced Oral Cancer De...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication systems, ICIICS 2024

作者： Shantha Kumari, K. Udhya shree, S. Calarany, C. Department of Data Science and Business Systems SRM Institue of Science and Technology Kattankulathur India Department of Computer Science and Engineering Rajiv Gandhi College of Engineering and Technology Pondicherry India Department of Computer Science and Engineering Tagore Government Arts and Science College Pondicherry India

ISBN: (纸本)9798331504960

Oral cancer is a major global health issue marked by high morbidity and mortality rates, primarily due to late-stage diagnosis. This work proposes the Advanced AI models that use multimodal data for early detection and diagnosis of oral cancer. Currently, traditional machine learning algorithms coupled with deep learning algorithms such as Convolutional neural networks (CNNs), focus on image-based analysis for detecting cancer. These works are delimited with minimal robustness and input data efficacy. Through the proposed multimodal AI model, histopathological images and clinical notes of the oral cancer patients are combinedly analyzed by which diagnostic accuracy is enhanced. This framework integrates CNNs for image analysis and Transformer-based models for text analysis, with a sophisticated fusion layer for data integration. Enhanced preprocessing techniques and performance optimization through Vision Transformers (ViTs) and BERT models significantly improve sensitivity, specificity, and F1-score. The multimodal AI model achieved a sensitivity of 0.90, specificity of 0.85, and an F1-score of 0.89, outperforming previous models like SVMs, RF, and CNNs. This indicates a high accuracy in identifying both positive and negative cases, ensuring reliable diagnoses. The results demonstrate a substantial improvement over traditional methods, that lays foundations for early diagnosis. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Distributed and Localized Model Predictive Control - Part II: Theoretical Guarantees

引用

IEEE Transactions on Control of Network systems 2023年第3期10卷 1113-1123页

作者： Alonso, Carmen Amo Li, Jing Shuang Matni, Nikolai Anderson, James California Institute of Technology Computing and Mathematical Sciences Department PasadenaCA91106 United States University of Pennsylvania Department of Electrical and Systems Engineering PhiladelphiaPA19104 United States Columbia University Department of Electrical Engineering and the Data Science Institute New YorkNY10027 United States

Engineered cyberphysical systems are growing increasingly large and complex. These systems require scalable controllers that robustly satisfy state and input constraints in the presence of additive noise: such controllers should also be accompanied by theoretical guarantees on feasibility and stability. In our companion paper, we introduced distributed and localized model predictive control (DLMPC) for large-scale linear systems;DLMPC is a scalable closed-loop MPC scheme in which subsystems need only exchange local information in order to synthesize and implement local controllers. In this article, we provide recursive feasibility and asymptotic stability guarantees for DLMPC. We leverage the system level synthesis framework to express the maximal positive robust invariant set for the closed-loop system and its corresponding Lyapunov function in terms of the closed-loop system responses. We use the invariant set as the terminal set for DLMPC, and show that this guarantees feasibility with minimal conservatism. We use the Lyapunov function as the terminal cost, and show that this guarantees stability. We provide fully distributed and localized algorithms to compute the terminal set offline, and also provide necessary additions to the online DLMPC algorithm to accommodate coupled terminal constraint and cost. In all algorithms, only local information exchange is necessary, and computational complexity is independent of the global system size: we demonstrate this analytically and experimentally. This is the first distributed MPC approach that provides minimally conservative yet fully distributed guarantees for recursive feasibility and asymptotic stability in the nominal and robust settings. © 2014 IEEE.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Coverage and Cell Capacity optimization in Private LTE network based on Position and Expected Channel Knowledge 5

Coverage and Cell Capacity optimization in Private LTE netwo...

引用

5th International Conference on Computer and Applications, ICCA 2023

作者： Kalakech, Ali Bakir, Mohamad Youssef, Riad Lebanese International University school of Engineering CCE Department Beirut Lebanon MindIT Telecoms and System Engineering Department Beirut Lebanon Midware Data Systems Network and security department Beirut Lebanon

ISBN: (纸本)9798350303254

This paper presents an innovative approach to maximize cell coverage and capacity in a private LTE network by optimizing resource block (RB) and power allocation. The proposed method decomposes the cell into sub-cells and employs two possible solutions: genetic algorithm (GA) and a water-filling based algorithm to find optimal resource distribution for each sub-cell. A priori knowledge of the expected channel gain is assumed. Both algorithms explore an efficient RB and power allocation, based on expected channel conditions and capacity requirements. The reported numerical results validate the effectiveness of the proposed approach, offering valuable insights for enhancing private LTE network performance through optimized resource allocation. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Rectification and converter control of the FPSLGs for energy storage applications

引用

IET Renewable Power Generation 2024年第9-10期18卷 1611-1625页

作者： Ali, Murad Haitao, Yu Mobayen, Saleh Zhang, Jiahui Zhilenkov, Anton Din, Zakiud School of Electrical Engineering Southeast University Nanjing China Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Douliou Taiwan Department of Cyber-Physical Systems St. Petersburg State Marine Technical University Saint-Petersburg Russia Department of Mechatronics Engineering College of Electrical and Mechanical Engineering National University of Sciences and Technology Islamabad Pakistan

This article presents two power converters with controllers attached to the Free-Piston Stirling Linear Generator (FPSLG) and energy storage system (ESS). The rectifier uses hysteresis-SVPWM current regulation and CB-SPWM, while the buck-boost converter utilizes the dual-loop PI control method. The storage battery receives energy from a linear-generator with a rectifier and converter. The FPSE and linear motors in the FPSLG convert thermal to electrical energy. A two-level electrical energy conversion technique using a three-phase AC signal to DC and DC-DC converter has been devised to reduce output electrical energy oscillation as well as stabilize the generating system's DC power. Initially, the FPSE's nonlinear model and the three-phase permanent magnet linear-motor's linear mathematical model were created and followed by the ESS and control mechanism simulation. The simulation shows that the ESS system and control approach can give stable power to the storage battery using linear-generator power. The PR controller replaces the PI controller in the position loop to improve frequency and displacement tracing. The control system design was simulated in MATLAB and the topology's feasibility and correctness were confirmed. Comparative analysis shows that, rectifier uses the H-SVPWM's unity power factor of AC and stability controllability of the DC-side voltage is better than the CB-SPWM approach. © 2024 The Author(s). IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

VeRB: Revolutionizing Vehicle Registration with Blockchain for Enhanced Security and Efficiency in RTO Processes 3

VeRB: Revolutionizing Vehicle Registration with Blockchain f...

引用

3rd IEEE International Conference on Blockchain and Distributed systems Security, ICBDS 2024

作者： Ramalingam, Gautham Praveen Pandian, Deepika Rajan, Deepak Syed Ammal Engineering College Department of Computer Science and Business Systems Tamilnadu Ramanathapuram India Syed Ammal Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Ramanathapuram India Syed Ammal Engineering College Tamilnadu Ramanathapuram India

ISBN: (纸本)9798350354348

The Vehicle-RTO-BlockChain (VeRB) system presents a pioneering solution to modernize the vehicle registration and re-registration process within Regional Transport Offices (RTOs) in India. Our work focuses on implementing blockchain technology to address challenges related to data security, administrative efficiency, and transparency in managing vehicle registration records. The VeRB system encompasses a user-friendly registration portal integrated with robust data verification modules and a permissioned blockchain infrastructure tailored to our specific needs. Through dynamic updating mechanisms and secure historical data storage, our system ensures the accuracy, integrity, and accessibility of registration records while mitigating risks associated with fraud and duplication. This abstract provides an overview of our research, highlighting the key components, benefits, and implications of the VeRB system in revolutionizing automotive registration practices and fostering safer, more streamlined transportation systems tailored to our organizational goals. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

An Anomaly Detection Algorithm for Estimating Interannual Variation in Crop Yields 5

An Anomaly Detection Algorithm for Estimating Interannual Va...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Vinoth Kumar, R. Malathy Manjula, M. Veerandeswari, J. Indumathy, M. Raghul, B.S. Rajiv Gandhi College of Engineering & Technology Information Technology Department Puduherry Kriumambakkam India Data Science and Business Systems Srm Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798350383522

Crop production is a vital aspect of human survival. Reducing global poverty heavily relies on increasing the robustness in crop yields. The quantity of crops harvested from a given agricultural land, also known as crop yields of that land is the important parameter that helps to increase the smartness in adopting novel agricultural plans. Measuring this parameter can be done through supervised machine learning techniques which helps with accurate predictions given the historical data of crop yield. This paper proposes an ideation, that uses Support Vector Machines (SVMs) because of its strength being accuracy, robust and flexible. SVM can predict reliable crop yield estimates that help to allocate resources and smart planning for agricultural activities. Also, SVMs are good enough to handle the imperfections in historical crop yield datasets, outliers, and inconsistencies. Furthermore, SVMs can bring out the relationships and any nonlinear patterns in the crop yields which are influenced by uncertain environmental factors over various seasons. This helps to identify the anomalies in the historical data. The anomalies could be exceptionally high yield or the failures which happen to be pinpointed as abnormal years. The identified outliers are excluded by the SVM, thus bringing out a prediction model that focusses on 'normal years'. By this, it is possible to represent more accurate inter-annual trends of crop yields avoiding the anomalies aiding the farmer to make better decisions for much more productivity in the crop yield. Based on the ideation, simulations are performed that showcase the success of the SVM in predicting good for the crop yields in inter-annual period. © 2024 IEEE.

关键词： Anomaly detection crop yield inter-annual variability SVM

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：