检索结果-内蒙古大学图书馆

6th IEEE International Conference and Workshop Obuda on electrical and Power engineering, CANDO-EPE 2023

作者： Kamoona, Mustafa A. Saleh, Ameer L. Szamel, Laszlo Mauricio, Juan Manuel University of Seville Department of Electrical Power Systems Maysan Iraq Budapest University of Technology and Economics Department of Electric Power Engineering Budapest Hungary University of Misan Department of Electrical Engineering Misan Iraq University of Seville Department of Electrical Power Systems Seville Spain

ISBN: (纸本)9798350328752

One of the key parts of overhead transmission lines that support and insulate the power transmission line is the string insulator discs. This need involves a meticulous design of string insulators for achieving high string efficiency, this is necessary for efficient power transmission. This paper has two aims, first improving and developing the efficiency of string insulators of overhead transmission lines 33kV and 132kV to be efficient, properly insulated and safe. Based on an optimum value of the capacitance (self-capacitance) which can be achieved via the proposed algorithm named Modified Particle Swarm Optimization (MPSO) technique which is the second aim of this paper. The MPSO algorithm tuned the self-capacitance (Cnew) as well as operating the model at the high efficiency of the string insulators with respect to its mechanical effectiveness. Moreover, analysis and evaluations of the systems (33kV and 132kV) as a classic model, proposed model and the MPSO have been carried out by MATLAB/Simulink R2022b environment. On the basis of the simulation findings, this paper produced a specific theoretical design for two transmission line systems 33kV and 132kV;where remarkable that the string efficiencies of 33kV and 132kV systems increased by 14.24% and 64.54% respectively. Also, compared the results between the proposed MPSO and conventional PSO. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Individual Consumer Load Forecasting

引用

CSEE Journal of Power and Energy systems 2023年第1期9卷 326-330页

作者： Yi Wang Ning Gao Gabriela Hug Department of Electrical and Electronic Engineering The University of Hong KongHong KongChinaare also with ETH ZurichZurichSwitzerland Power Systems Laboratory ETH Zurich8092 ZurichSwitzerland

Installation of smart meters enables electricity retailers or consumers to implement individual load forecasting for demand *** individual load forecasting model can be trained either on each consumer’s own smart meter data or the smart meter data of multiple *** former practice may suffer from overfitting if a complex model is trained because the dataset is limited;the latter practice cannot protect the privacy of individual *** paper tackles the dilemma by proposing a personalized federated approach for individual consumer load ***,a group of consumers first jointly train a federated forecasting model on the shared smart meter data pool,and then each consumer personalizes the federated forecasting model on their own *** case studies are conducted on an open dataset of 100 *** verify the proposed method can enhance forecasting accuracy by making full use of data from other consumers with privacy protection.

关键词： Federated learning load forecasting personalization privacy-preserving smart meter

来源：评论

学校读者我要写书评

暂无评论

Enhancing Early Detection of Lung Cancer through Advanced Image Processing Techniques and Deep Learning Architectures for CT Scans

引用

Computers, Materials & Continua 2024年第10期81卷 271-307页

作者： Nahed Tawfik Heba M.Emara Walid El-Shafai Naglaa F.Soliman Abeer D.Algarni Fathi EAbd El-Samie Computers and Systems Department Electronics Research InstituteEl NozhaHuckstep Cairo12622Egypt Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Lung cancer remains a major concern in modern oncology due to its high mortality rates and multifaceted origins,including hereditary factors and various clinical *** stands as the deadliest type of cancer and a significant cause of cancer-related deaths *** diagnosis enables healthcare providers to administer appropriate treatment measures promptly and accurately,leading to improved prognosis and higher survival *** significant increase in both the incidence and mortality rates of lung cancer,particularly its ranking as the second most prevalent cancer among women worldwide,underscores the need for comprehensive research into efficient screening *** in diagnostic techniques,particularly the use of computed tomography(CT)scans,have revolutionized the identification of lung *** scans are renowned for their ability to provide high-resolution images and are particularly effective in detecting small,calcified areas,crucial for identifying earlystage lung ***,there is growing interest in enhancing computer-aided detection(CAD)*** algorithms assist radiologists by reducing false-positive interpretations and improving the accuracy of early cancer *** study aims to enhance the effectiveness of CAD systems through various ***,the Contrast Limited Adaptive Histogram Equalization(CLAHE)algorithm is employed to preprocess CT scan images,thereby improving their visual *** refinement is achieved by integrating different optimization strategies with the CLAHE *** CutMix data augmentation technique is applied to boost the performance of the proposed model.A comparative analysis is conducted using deep learning architectures such as InceptionV3,ResNet101,Xception,and *** study evaluates the performance of these architectures in image classification tasks,both with and without the implementation of the CLAHE *** empirical findings of the study demonst

关键词： Lung cancer detection CLAHE algorithm optimization deep learning classification feature extraction healthcare applications

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence for Wildlife Conservation: Real-Time Hornbill Call Classification Using TinyML 2nd

Edge Intelligence for Wildlife Conservation: Real-Time Hornb...

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Hing, Kong Ka Behjati, Mehran Saleh, Vala Meng, Yap Kian Majeed, Anwar P. P. Abdul Zheng, Yufan Department of Computing and Information Systems School of Engineering and Technology Sunway University Petaling Jaya47500 Malaysia Department of Computing and Information Systems School of Engineering and Technology Sunway University Petaling Jaya47500 Malaysia Department of Electrical Engineering Shiraz University of Technology Shiraz Iran Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

Hornbills, an iconic species of Malaysia's biodiversity, face threats from habitat loss, poaching, and environmental changes, necessitating accurate and real-time population monitoring that is traditionally challenging and resource intensive. The emergence of Tiny Machine Learning (TinyML) offers a chance to transform wildlife monitoring by enabling efficient, real-time data analysis directly on edge devices. Addressing the challenge of wildlife conservation, this research paper explores the pivotal role of machine learning, specifically TinyML, in the classification and monitoring of hornbill calls in Malaysia. Leveraging audio data from the Xeno-canto database, the study aims to develop a speech recognition system capable of identifying and classifying hornbill vocalizations. The proposed methodology involves preprocessing the audio data, extracting features using Mel-Frequency Energy (MFE), and deploying the model on an Arduino Nano 33 BLE, which is adept at edge computing. The research encompasses foundational work, including a comprehensive introduction, literature review, and methodology. The model is trained using Edge Impulse and validated through real-world tests, achieving high accuracy in hornbill species identification. The project underscores the potential of TinyML for environmental monitoring and its broader application in ecological conservation efforts, contributing to both the field of TinyML and wildlife conservation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

TraiNDSim: A Simulation Framework for Comprehensive Performance Evaluation of Neuromorphic Devices for On-Chip Training 24

TraiNDSim: A Simulation Framework for Comprehensive Performa...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Heo, Donghyeok Bang, Hyeonsu Ko, Jong Hwan Department of Ai Systems Engineering Sungkyunkwan University Suwon Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of College of Information and Communication Engineering Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9798400706011

The advancement of neuromorphic devices (NDs) for processing deep neural networks has narrowed the accuracy gap with software-trained models. To accurately assess ND performance, reliable simulation frameworks for on-chip training are crucial. However, existing frameworks encounter difficulties accurately reflecting the characteristics of NDs in training simulations. Consequently, we introduce TraiNDSim, a novel framework that comprehensively evaluates the performance of NDs to address these difficulties. Specifically, we propose an advanced conductance normalization strategy called layer-wise normalization, which limits the weight range by taking the initial weight distribution into account. Additionally, our framework integrates three conductance models, notably refining one of the conventional models to depend solely on nonlinearity. Moreover, it features a bi-directional weight representation method with a unique conductance compensation technique. Our comprehensive analysis using TraiNDSim demonstrates its effectiveness in accurately reflecting the impact of ND parameters on training, promising more precise device performance evaluations. Our framework is available at https://***/donghyeokheo/TraiNDSim. © 2024 Copyright held by the owner/author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs

Graphon Pooling for Reducing Dimensionality of Signals and C...

引用

作者： Parada-Mayorga, Alejandro Wang, Zhiyang Ribeiro, Alejandro University of Pennsylvania Department of Electrical and Systems Engineering PhiladelphiaPA19104 United States

In this article we propose a pooling approach for convolutional information processing on graphs relying on the theory of graphons and limits of dense graph sequences. We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0,1]2 in the graphon space. As a result we derive low dimensional representations of the convolutional operators, while a dimensionality reduction of the signals is achieved by simple local interpolation of functions in L2([0,1]). We prove that those low dimensional representations constitute a convergent sequence of graphs and graph signals, respectively. The methods proposed and the theoretical guarantees that we provide show that the reduced graphs and signals inherit spectral-structural properties of the original quantities. We evaluate our approach with a set of numerical experiments performed on graph neural networks (GNNs) that rely on graphon pooling. We observe that graphon pooling performs significantly better than other approaches proposed in the literature when dimensionality reduction ratios between layers are large. We also observe that when graphon pooling is used we have, in general, less overfitting and lower computational cost. © 1991-2012 IEEE.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

A Multisensorial Socially Assistive Robot for Therapies with Children with Autism Spectrum Disorder and Down Syndrome Using Serious Games 9th

A Multisensorial Socially Assistive Robot for Therapies wit...

引用

9th Latin American Congress on Biomedical engineering, CLAIB 2022 and 28th Brazilian Congress on Biomedical engineering, CBEB 2022

作者： Panceri, J.A.C. Freitas, E.V.S. Schreider, S.L. Souza, J.C. Caldeira, E.M.O. Bastos-Filho, T.F. Postgraduate Program in Electrical Engineering Federal University of Espirito Santo Vitória Brazil Automation and Control Engineering Department Federal Institute of Espirito Santo Linhares Brazil Electrical Engineering Department Federal University of Espirito Santo Vitória Brazil Postgraduate Program in Biotechnology Federal University of Espirito Santo Vitória Brazil

ISBN: (纸本)9783031494062

Much of the data obtained by health professionals for diagnosis and therapies applied to children with Autistic Spectrum Disorder (ASD) and Down Syndrome (DS) depend on visual observations and interviews with family members and clinical assessments. Therefore, the use of sensors has the potential of complementing this process by generating quantitative data. This work demonstrates that the use of sensors embedded in a Socially Assistive Robot (SAR) developed at UFES/Brazil, termed Mobile Autonomous Robot for Interaction with Autistics and Trisomy 21 (MARIA T21), can be used as a centralized tool to quantify more objective measures of children’s spatial, postural and social behavior during the interaction with the robot through Serious Games (SG) projected on the floor by the robot. The information generated can help therapists in the application of more efficient therapies, as well as monitor the evolution of the children submitted to the protocol with the robot. The results demonstrates the feasibility of using these sensors and evidence the requirements to be evolved. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Exploring Player's Body as a Game Controller for Fitness Activity Promotion 6

Exploring Player's Body as a Game Controller for Fitness Act...

引用

6th Experiment at International Conference, exp.at 2023

作者： Simoes, Diogo Menezes, Paulo University of Coimbra Institute of Systems and Robotics Electrical and Computer Engineering Department Coimbra Portugal

ISBN: (纸本)9798350314403

In recent years, there has been a tendency for people to resort to a more sedentary lifestyle, which has only been aggravated by the COVID-19 pandemic and the evermore common remote work policies. This lack of physical activity brings negative health outcomes and can generally be difficult to overcome due to how challenging it can be for a person to find the motivation to adopt a more physically active routine. To address this issue, we propose the use of serious games as an engaging, fun, and highly motivational tool that can aid people in their quest for a healthier lifestyle. We focus on three problem areas: motor control improvement and rehabilitation, post-stroke rehabilitation, and physical activity for general health. There exist multiple solutions for these problems which often require specific equipment that may not be available to the common user. Therefore, we propose a different approach requiring solely a laptop equipped with a camera, thus making it more practical and accessible to the wider public. © 2023 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Efficient Safety Verification of Discrete Event systems 19

Efficient Safety Verification of Discrete Event Systems

引用

19th IEEE International Conference on Automation Science and engineering, CASE 2023

作者： Lennartson, Bengt Chalmers University of Technology Division of Systems and Control Department of Electrical Engineering Gothenburg Sweden

ISBN: (纸本)9798350320695

Formal verification of safety properties is critical in many application areas. In this paper a survey of the most common and efficient methods is given. The different methods are compared for some typical scalable examples, both modeled by transition systems and Petri nets. The methods are based on symbolic computations and logic representations of both sets and transition relations. Reachability analysis is performed not only from the initial states to any forbidden states, but also in the opposite backward direction. The reason is that a system is also safe when no initial state is backward reachable from the set of forbidden states. For safe systems the number of backward reachable states from forbidden states is often much less than the forward reachable states from the initial states. The backward strategy is shown to be very efficient and often even better than the most efficient methods that are specialized on safety analysis. © 2023 IEEE.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Ni–B alloy electroplated with different anionic groups

引用

Journal of Materials Research and Technology 2023年 27卷 8360-8371页

作者： Cheng, An-Yu Pu, Nen-Wen Liu, Yih-Ming Hsieh, Min-Syuan Ger, Ming-Der Department of Chemistry & Materials Engineering Chung Cheng Institute of Technology National Defense University Taiwan Taoyuan Taiwan Department of Electrical Engineering Yuan Ze University Zhongli Taiwan Taoyuan320 Taiwan System Engineering and Technology Program National Chiao Tung University Hsinchu Taiwan

In order to study the effects of the main nickel salt on the electroplated nanocrystalline Ni–B alloy coating, the deposition rates, surface morphology, crystallinity, grain sizes, hardness, and corrosion resistance of the Ni–B films electrodeposited with plating baths containing separately nickel sulfate (NS) and nickel sulfamate (NSA) under various temperatures and current densities were compared. Under all conditions, the NSA bath system offered higher deposition rates and lower B contents than the NS counterpart because of the formation of Ni-ammonium complex, which can be adsorbed faster than nickel ions. These two groups of coatings had similar surface morphology and crystallinity under all plating conditions except for those plated with the NS bath system at 60 °C, wherein significant changes in surface texture and preferred crystal orientation as well as an abrupt increase in grain size occurred. The coating hardness was optimized by reducing the grain size and increasing the boron content because of the combined effects of grain refinement strengthening and solid solution strengthening. The differences between the two main salt systems can be explained by the presence of ammonium ions in the NSA bath, which not only increased the deposition rate but also maintained the preferred orientation in Ni (111) at high temperature. Our results indicate that, under high current density and high temperature operation conditions, the NSA main salt plating system is a more favorable option for obtaining higher quality Ni–B alloy coatings. © 2023 The Authors

关键词： Sulfur compounds

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：