检索结果-内蒙古大学图书馆

A Study on Learning of Ensemble Classification Model Based on Radial Basis Function Neural Networks

Transactions of the Korean Institute of electrical Engineers 2024年第8期73卷 1429-1436页

作者： Roh, Seok-Beom Oh, Sung-Kwun Dept. of Electrical and Electronic Engineering University of Suwon Korea Republic of Dept. of Electronics and Computer Engineering Seokyeong University Korea Republic of

In this study, we introduce an ensemble model that leverages a radial basis function neural network as the base model to enhance the classification performance of a pattern classifier. While existing ensemble models use the majority vote technique for aggregation, we proposes a new aggregation method that combines a simple linear function and a softmax function, using the outputs of the base model as input variables. This aggregation approach linearly combines the class prediction probabilities from each base model to calculate the class-specific probability for the ensemble model. To evaluate the performance of the proposed pattern classifier, we used 14 datasets to optimize the parameters of the linear function and compared the performance with existing pattern classifiers. Our method achieved better results on 10 out of the 14 datasets compared to other pattern classifiers. Additionally, when compared with a recently reported ensemble model, our method also demonstrated superior performance. Copyright © The Korean Institute of electrical Engineers.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Voltage Sag Investigation for Induction Motor Startup in Distribution Systems using Solid State Transformer 15

Voltage Sag Investigation for Induction Motor Startup in Dis...

引用

15th International Renewable Energy Congress, IREC 2025

作者： Ghambirlou, Khaled Abosnina, Adel Ali Moschopoulos, Gerry Western University Dept. Electrical and Computer Engineering London Canada College of Electrical and Electronics Technology Benghazi Libya

ISBN: (纸本)9798331516772

Dealing with voltage sags during motor startup is crucial because they can delay power restoration and lead to widespread failures for industrial loads and distribution systems. A novel approach is introduced to investigate voltage sag in distribution networks using solid-state transformers (SSTs) instead of traditional ones. The induction motor startup model is employed to simulate voltage sags, accurately representing the characteristics influenced by conventional industrial loads. The inherent capabilities of SSTs are leveraged to mitigate these voltage sag issues effectively. This study focuses on analyzing voltage sags caused by the activation of induction motors in power systems, with particular emphasis on SST technology, which actively regulates voltage during motor starting by controlling reactive power. The selected distribution system is implemented and tested using MATLAB/Simulink. The results will be compared with previous research on voltage sag during motor startup, demonstrating the improvements and effectiveness of using SSTs in managing power quality issues. This study emphasizes the potential of SSTs to improve the stability and reliability of power systems during the challenging conditions of motor startup. © 2025 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Power Quality in Distribution Systems through Bi-directional Solid-State Transformers 3

Enhancing Power Quality in Distribution Systems through Bi-d...

引用

3rd IEEE Industrial electronics Society Annual On-Line Conference, ONCON 2024

作者： Ghambirlou, Khaled Esamil SH Abosnina, Adel Ali Moschopoulos, Gerry Engineering Western University Dept. Electrical and Computer London Canada College of Electrical and Electronics Technology Benghazi Libya

ISBN: (纸本)9798331540319

Power quality issues, including voltage sags, swells, harmonic distortion, oscillatory voltage transients, etc. can degrade equipment performance, leading to inefficiencies and costly disruptions. Studying these issues and introducing solutions are essential for maintaining the reliability and efficiency of modern distribution systems. This paper examines and contrasts the benefits of a bidirectional three-stage solid-state transformer (SST) in mitigating power quality issues to traditional transformers. SST introduces reactive power support to improve the system quality by controlling active and reactive power. This paper investigates key power quality issues-voltage sag, swell, harmonic distortion, and oscillatory transients-arising from capacitor bank energizing, focusing on the novel application of solid-state transformers (SSTs) in mitigating these effects. Additionally, it examines SST-based fault isolation across various fault types (three-phase, double line-to-ground, and line-to-ground). Several simulations have been performed using the MATLAB/Simulink platform to highlight the benefits of the Solid-State Transformer (SST) over conventional transformers and cascade multiple-active-bridge SST (CMABSST) types. The proposed SST employs active and reactive power control to alleviate these effects, allowing the SST controller to manage reactive power effectively and provide the required support that makes the system stable and reliable. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Empirical Validation of Fuzzy Logic Based Predictive Load Scheduling in Mimic Home Energy Management System

引用

Journal of Internet Technology 2023年第7期24卷 1429-1436页

作者： Jegadeesan, Nirmala Balasubramanian, G. Hemavathi, N. Chen, Yu-Chi School of Electrical and Electronics Engineering SASTRA Deemed University India Dept. Computer Science and Information Engineering National Taipei University of Technology Taiwan

Load scheduling plays a vital role in the home energy management systems. The main objective of this load scheduling is to balance the power demand and supply power without degrading the performance of the loads and consumers tolerance. Though many research works concentrate on load scheduling, very few works concentrated on real time scenario. On the other hand, research work concentrated on optimal load scheduling through fuzzy logic requires incorporation of fuzzy based system in either simulated or real-time home energy management system. Hence, the proposal aims to schedule the loads in a simulated home energy management system through fuzzy logic controller using MATLAB Simscape with required subsystems. The proposed simulated environment considers four different resistive loads. Intelligent scheduling is aimed to achieve efficient load scheduling. A fuzzy controller has three inputs namely integrated source, state of charge of battery, and power demand whereas probability of scheduling is considered as output. The efficiency of the proposed fuzzy-based load scheduling scheme is evaluated under various load conditions for different sub-systems with varying input power. The results exhibit the efficacy of the proposed scheme. © 2023 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Single-Phase Single-Stage Isolated Buck-Boost Inverters

Single-Phase Single-Stage Isolated Buck-Boost Inverters

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Khan, Usman Ali Khan, Ashraf Ali Jang, Won-Yong Jung, Hyeonwoo Park, Jung-Wook Yonsei University Dept of Electrical and Electronics Engineering Seoul Korea Republic of Memorial University of Newfoundland Dept of Electrical and Computer Engineering St John De Canada

ISBN: (纸本)9798350376067

This paper presents a single-stage single-phase high-frequency isolated buck-boost inverter. The proposed inverter is capable of efficiently converting and controlling the voltage from a single-phase DC source to a desired AC output buck and boost voltages with isolation. It utilizes a solitary output inductor, a high frequency transformer for isolation and operates with only one switch working at a high frequency. The proposed inverter eliminates the necessity for low frequency transformers operating at 50/60 Hz. The operation principles and control strategy of the inverter is thoroughly investigated, and a detailed analysis of the topology performance is presented. Simulation results validate the effectiveness and feasibility of the proposed topology. Experimental results are presented to confirm the practicality and reliability of the proposed work. © 2024 IEEE.

关键词： Buck converter

来源：评论

学校读者我要写书评

暂无评论

MOPO-HBT: A movie poster dataset for title extraction and recognition

引用

Multimedia Tools and Applications 2024年第18期83卷 54545-54568页

作者： Ghosh, Mridul Roy, Sayan Saha Banik, Bivan Mukherjee, Himadri Obaidullah, Sk Md Roy, Kaushik Dept. of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah India Dept. of Computer Science & Engineering Aliah University Kolkata India Dept. of Electronics & Electrical Communication Engineering IIT Kharagpur Kharagpur India TISA Lab Dept. of Computer Science West Bengal State University Barasat India

Real-world images often encompass embedded texts that adhere to disparate disciplines like business, education, and amusement, to name a few. Such images are graphically rich in terms of font attributes, color distribution, foreground-background similarity, and component organization. This aggravates the difficulty of recognizing texts from these images. Such characteristics are very prominent in the case of movie posters. One of the first pieces of information on movie posters is the title. Automatic recognition of movie titles from images can aid in efficient indexing as well as information conveyance. However, it is accompanied by other texts like the names of actors, producers, taglines, dates, etc. Though the organization of components is somewhat similar across different film industries like Tollywood (West Bengal), Bollywood (Mumbai), and Hollywood (Los Angeles), the graffiti patterns differ in multifarious instances. To address the problem of movie title understanding, we propose a dataset named MOvie POsters-Hollywood Bollywood Tollywood (MOPO-HBT) that encompasses movie posters from the aforementioned industries. The entire dataset is publicly available (http://***/11564) for research purposes. The baseline results of title identification and recognition were obtained with a CNN-based (Convolutional Neural Network) approach, wherein the titles were extracted using the M-EAST (Modified-Efficient and Accurate Scene Text) detector model. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Joint Spectrum Sensing and Resource Allocation for OFDMA-based Underwater Acoustic Communications

引用

IEEE Communications Letters 2025年第6期29卷 1300-1304页

作者： Kim, Minwoo Choi, Youngchol Kim, Yeongjun Seo, Eojin Yang, Hyun Jong Dept. of Electrical Engineering Pohang Korea Republic of Daejeon Korea Republic of Samsung Electronics System LSI Modem Development Team Device Solutions Hwaseong Korea Republic of Seoul National University Dept. of Electrical and Computer Engineering Seoul Korea Republic of

Underwater acoustic (UWA) communications generally rely on cognitive radio (CR)-based ad-hoc networks due to challenges such as long propagation delay, limited channel resources, and high attenuation. To address the constraints of limited frequency resources, UWA communications have recently incorporated orthogonal frequency division multiple access (OFDMA), significantly enhancing spectral efficiency (SE) through multiplexing gains. Still, the low propagation speed of UWA signals, combined with the dynamic underwater environment, creates asynchrony in multiple access scenarios. This causes inaccurate spectrum sensing as inter-carrier interference (ICI) increases, which leads to difficulties in resource allocation. As efficient resource allocation is essential for achieving high-quality communication in OFDMA-based CR networks, these challenges degrade communication reliability in UWA systems. To resolve the issue, we propose an end-to-end sensing and resource optimization method using deep reinforcement learning (DRL) in an OFDMA-based UWA-CR network. Through extensive simulations, we confirm that the proposed method is superior to baseline schemes, outperforming other methods by 42.9 % in SE and 4.4 % in communication success rate. © 1997-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Alcohol Detection and Alert System for Vehicles 1

Design of Alcohol Detection and Alert System for Vehicles

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Bhardwaj, Indu Saravanan, D. Bhardwaj, Ajay Yadav, Daman Kumari, Vijeta Kumar, R Ramesh Galgotias University Dept. of Electrical Electronics and Communication Engineering Greater Noida India Madanapalle Institute of Technology and Science Dept. of Electrical and Electronics Engineering India Delhi Technological University Dept. of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350356816

Recent days accidents are increasing on an exponential basis due to drinking and drive. Driving after drinking alcohol is a major cause of the majority of the accidents due to which sometimes innocent people lose their lives. As the number of vehicles is increasing day by day, accidents are also occurring due to many reasons but alcohol consumption is a major factor in many of the accidents. To avoid these accidents, an alcohol detection and alert system for vehicles is proposed in this paper that is based on MQ3 sensor. The proposed system gives a coherent solution to control injuries because of consumption of alcohol while driving. The alcohol detected by the MQ-3 sensor is processed via an ATmega328P Microcontroller that collate it with a fixed threshold for compliance. The device will nonstop monitor concentration of alcohol by the alcohol recognition sensor and consequently flip off the working of automobile's engine if the alcohol concentration is exceeding threshold value. The replica can even send the alert of locality of the car via SIM900A (GSM module). The model presents an adequate answer to regulate injuries by the influence of alcohol driving. The LCD module is used to show that alcohol has been identified. The proposed system is cost effective, less bulky and more reliable. © 2024 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Robust decentralized plug and play voltage tracker of islanded microgrids under loads and lines uncertainties by the invariant ellipsoids

引用

Journal of King Saud University - engineering Sciences 2024年第6期36卷 409-419页

作者： Bayoumi, Ehab H.E. Soliman, Hisham M. El-Sheikhi, Farag Ali Shafiq, M. Awad, Hilmy Energy and Renewable Energy Department Egyptian Chinese University Cairo Egypt Dept. of Electrical Power Eng. Faculty of Eng Cairo University Cairo Egypt Dept. of Electrical and Electronics Engineering Istanbul Esenyurt University Istanbul Turkey Dept. of Electrical and Computer Engineering Sultan Qaboos University Muscat Oman Dept. of Electrical Technology Faculty of Technology and Education Helwan University Egypt

Microgrids (MGs) comprising of distributed generation units (DGs) are subjected to plug-and-play operation (PnP), lines (connecting the DGs) parameters uncertainty, and load changes. Robust stability and an authentic operation for islanded microgrids can be guaranteed through a robust decentralized voltage tracker developed in this paper. The proposed controller design has the following merits: 1) fully decentralized, 2) scalable, and 3) maintains robust stability against PnP of DGs, load changes, and lines parameters’ uncertainties. A sufficient condition is developed by linear matrix inequality convex optimization is exploited to solve the problem. The MGs’ changes in load and the line's parameters are modelled as norm-bounded uncertainties. The suggested controller uses local measurements from DGs, i.e., decentralized by the decomposition of the global system into subsystems. For each subsystem, the rest of the system's impact is considered disturbances, whose influence must be minimized. The proposed disturbance rejection control algorithm is based on the method of invariant-ellipsoids. Several time-domain scenarios such as connecting and disconnecting a number of DGs, local load changes, and variation of transmission line parameters are executed to assess the suggested controller's effectiveness, using MATLAB /Sim PowerSystems Toolbox. © 2021 The Authors

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

RenalNet: An End-to-End Hybrid Deep Learning and Ensemble Model for Accurate Kidney Disorder Classification 3

RenalNet: An End-to-End Hybrid Deep Learning and Ensemble Mo...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Haque, Fariha Siddique, Md Abu Ismail Shojol, Md. Shojeb Hossain Rajshahi University of Engineering & Technology Dept. of Electronics & Telecommunication Engineering Rajshahi Bangladesh Rajshahi University of Engineering & Technology Dept. of Electrical & Computer Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350388282

Kidney disorders are a major public health issue affecting millions worldwide. Renal calculi and cancer are prevalent, causing chronic kidney disease(CKD). Artificial intelligence can assist in the precise diagnosis of kidney *** developed an end-to-end system using a custom CNN model to extract informative features from kidney images. Multiple ML classifiers provide complementary perspectives. A High-Performance Filter(HPF) selects the top classifiers for an ensemble model. The interactive web interface enables real-time prediction. Our approach achieves excellent performance metrics with an accuracy of 99.98%. Overall, We demonstrate an automated system combining deep learning and ensembling for the accurate characterization of diverse kidney abnormalities, which can aid in the early detection and treatment of CKD. © 2024 IEEE.

关键词： Classification (of information)

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：