检索结果-内蒙古大学图书馆

Multi-modal visual tracking:Review and experimental comparison

Computational Visual Media 2024年第2期10卷 193-214页

作者： Pengyu Zhang Dong Wang Huchuan Lu Faculty of Electronic Information and Electrical Engineering Dalian University of TechnologyDalian 116024Chin

Visual object tracking has been drawing increasing attention in recent years,as a fundamental task in computer *** extend the range of tracking applications,researchers have been introducing information from multiple modalities to handle specific scenes,with promising research prospects for emerging methods and *** provide a thorough review of multi-modal tracking,different aspects of multi-modal tracking algorithms are summarized under a unified taxonomy,with specific focus on visibledepth(RGB-D)and visible-thermal(RGB-T)***,a detailed description of the related benchmarks and challenges is *** experiments were conducted to analyze the effectiveness of trackers on five datasets:PTB,VOT19-RGBD,GTOT,RGBT234,and ***,various future directions,including model design and dataset construction,are discussed from different perspectives for further research.

关键词： visual tracking object tracking multi-modal fusion RGB-T tracking RGB-D trackin

来源：评论

学校读者我要写书评

暂无评论

Approximate Solutions of Hypersingular Integral Equations of the First Kind Using Chebyshev Polynomials of the Second Kind in Matrix-Vector Versions

引用

IAENG International Journal of Applied Mathematics 2025年第1期55卷 214-222页

作者： Shoukralla, E.S. Ahmed, B.M. Faculty of Electronic Engineering Menofia University Egypt Faculty of Engineering and Technology Future University in Egypt Cairo Egypt

In this study, we focus on obtaining approximate solutions to hypersingular Fredholm integral equations of the first kind that appear in water wave dynamics, elasticity, acoustics, fluid mechanics, and others. The proposed method is based on Chebyshev polynomials of the second kind in matrix-vector forms. The analytical method was used to remove the singularity of the unknown function, whereas the asymptotic recurrence formula was used to remove the singularity of the hypersingular integral. A matrix equation whose solution is equivalent to the solution of the integral equation was obtained. Without using the collocation approach, this equivalent matrix equation has been transformed into a linear system of algebraic equations. A square coefficient matrix necessary for the algebraic system's solution has been extracted from the matrix equation. The solutions to four examples with tables and figures were provided. As it turns out, the derived approximate vector-matrix polynomials solutions significantly converge to the exact ones. The absolute errors were uniform and symmetric, and they also demonstrated proximity to zero as the degree of approximation was increased. The presented method included only a few simple steps and was highly accurate and innovative. © (2025), (International Association of Engineers). All rights reserved.

关键词： Chebyshev polynomials

来源：评论

学校读者我要写书评

暂无评论

Food ingredient recognition model via image and textual feature extraction and hybrid classification strategy

引用

International Journal of Reasoning-based Intelligent Systems 2024年第1期16卷 74-90页

作者： Madival, Sharanabasappa A. Jawaligi, Shivkumar S. Department of Computer Science and Engineering Faculty of Engineering and Technology Sharnbasva University India Department of Electronic and Communication Engineering Faculty of Engineering and Technology Sharnbasva University Karanataka Kalburgi India

This research work focuses on food recognition, especially, the identification of the ingredients from food images. Here, the developed model includes two stages namely: 1) feature extraction;2) classification. Initially, the image features and textual features will be extracted, where image features like SIFT and improved CNN-based deep features, textural features are extracted. Then, the hybrid classifier is used for the identification of food ingredients that combines the models like neural network (NN) as well as long short-term memory (LSTM). In order to make the accurate results, the weights of NN and LSTM are fine-tuned via the Chebyshev map evaluated teamwork optimisation (CME-TWO) algorithm. At the final stage, the primacy of the offered scheme is proven concerning varied metrics. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Cooperative Target Node Localization with Optimization Strategy Based on RSS for Wireless Sensor Networks

引用

Computers, Materials & Continua 2025年第3期82卷 5079-5095页

作者： Xinrong Zhang Bo Chang Faculty of Automation Huaiyin Institute of TechnologyHuaian223003China Faculty of Electronic Engineering Huaiyin Institute of TechnologyHuaian223003China

In the RSSI-based positioning algorithm,regarding the problem of a great conflict between precision and cost,a low-power and low-cost synergic localization algorithm is proposed,where effective methods are adopted in each phase of the localization process and fully use the detective information in the network to improve the positioning precision and *** the ranging period,the power attenuation factor is obtained through the wireless channel modeling,and the RSSI value is transformed into *** the positioning period,the preferred reference nodes are used to calculate *** the position optimization period,Taylor expansion and least-squared iterative update algorithms are used to further improve the location *** the positioning,the notion of cooperative localization is introduced,in which the located node satisfying certain demands will be upgraded to a reference node so that it can participate in the positioning of other nodes,and improve the coverage and positioning *** results show that on the same network conditions,the proposed algorithm in this paper is similar to the Taylor series expansion algorithm based on the actual coordinates,but much higher than the basic least square algorithm,and the positioning precision is improved rapidly with the reduce of the range error.

关键词： Wireless sensor networks received signal strength(RSS) optimization algorithm cooperative localiza-tion weighted least squares

来源：评论

学校读者我要写书评

暂无评论

Lithium-Ion Battery Pack Based on Fuzzy Logic Control Research on Multi-Layer Equilibrium Circuits

引用

Energy engineering 2024年第8期121卷 2231-2255页

作者： Tiezhou Wu Yukan Zhang Faculty of Electrical and Electronic Engineering Hubei University of TechnologyWuhanChina

In order to solve the problem of inconsistent energy in the charging and discharging cycles of lithium-ion battery packs,a new multilayer equilibrium topology is designed in this *** structure adopts a hierarchical structure design,which includes intra-group equilibrium,primary inter-group equilibrium and secondary inter-group *** structure greatly increases the number of equilibrium paths for lithium-ion batteries,thus shortening the time required for equilibrium,and improving the overall *** terms of control strategy,fuzzy logic control(FLC)is chosen to control the size of the equilibrium current during the equilibrium *** performed rigorous modeling and simulation of the proposed system by MATLAB and Simulink *** show that the multilayer equilibrium circuit structure greatly exceeds the traditional single-layer equilibrium circuit in terms of efficacy,specifically,the Li-ion battery equilibrium speed is improved by 12.71%in static equilibrium,14.48%in charge equilibrium,and 11.19%in discharge *** addition,compared with the maximum value algorithm,the use of the FLC algorithm reduces the equalization time by about 3.27%and improves the energy transfer efficiency by about 66.49%under the stationary condition,which verifies the feasibility of the equalization scheme.

关键词： Lithium-ion battery for new energy vehicles lithium-ion battery equilibrium fuzzy logic control

来源：评论

学校读者我要写书评

暂无评论

Brain tumors classification using deep models and transfer learning

引用

Multimedia Tools and Applications 2024年 1-32页

作者： Mavaddati, Samira Electronic Department Faculty of Engineering and Technology University of Mazandaran Babolsar Iran

Accurate brain tumor classification using magnetic resonance imaging (MRI) is crucial for guiding patient treatment decisions. However, differentiating tumor types can be challenging due to subtle variations in texture. This study investigates the potential of deep learning, specifically a 50-layer ResNet architecture, for improved brain tumor classification from MRI scans. The transfer learning technique is leveraged to enhance model performance and compare its effectiveness with other deep learning architectures such as CNN, RNN, and a dictionary learning-based classifier. The results demonstrate that the ResNet-50 model achieves superior performance in terms of accuracy, sensitivity, and robustness compared to the evaluated methods. This highlights the novelty of our work: combining a deep residual network (ResNet-50) with transfer learning for brain tumor classification. This approach offers a promising avenue for improved diagnostic accuracy and potentially better patient outcomes in a clinical setting with an accuracy rate of over 99.85%. The results of the experiments show that the proposed approach has significant potential in improving the accuracy of brain tumor classification using MRI and medical knowledge. Additionally, the use of deep learning structures combined with transfer learning yields a novel and effective solution for brain tumor classification. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Optimizing Rainforest Watershed Prediction Using Machine Learning for Disaster Response 10

Optimizing Rainforest Watershed Prediction Using Machine Lea...

引用

10th IEEE Asia-Pacific Conference on Applied Electromagnetics, APACE 2024

作者： Pupathy, Sabrina Azemi, Saidatul Norlyana Amir, Amiza Faculty of Electronic Engineering & Technology Perlis Malaysia Faculty of Electronic Engineering & Technology Perlis Malaysia

ISBN: (纸本)9798350364163

This study leverages advanced machine learning techniques to enhance disaster preparedness and watershed management in rainforest regions. This research developed a robust deep learning model using Convolutional Neural Networks (CNNs) to achieve accurate and timely detection of watershed areas, focusing on image analysis for effective monitoring and prediction. The model demonstrated a training accuracy of approximately 90% and validation accuracy stabilizing around 90% as well, indicating strong generalization capabilities. Additionally, the model achieved a low training and validation loss, each converging around 15%, showcasing reliable performance in handling watershed prediction. Our system incorporates an early warning mechanism, integrating CNN-based image segmentation with predictive analytics to facilitate proactive disaster prevention. By delivering consistent and accurate results, this research contributes to creating a comprehensive solution for the early detection and management of watershed-related events, aimed at reducing environmental and human impact. Findings from this study highlight the efficacy of machine learning in ecological monitoring and disaster preparedness, promoting sustainable management of rainforest ecosystems. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating transient behaviour of large-scale photovoltaic systems during lightning events using enhanced finite difference time domain method with variable cell size approach

引用

High Voltage 2024年第3期9卷 636-647页

作者： Ibrahim Hetita Diaa-Eldin A.Mansour Yang Han Ping Yang Congling Wang Mohamed M.F.Darwish Matti Lehtonen Amr S.Zalhaf School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China(UESTC)ChengduChina Electrical Power and Machines Engineering Department Faculty of EngineeringHelwan UniversityCairoEgypt Electrical Power and Machines Engineering Department Faculty of EngineeringTanta UniversityTantaEgypt Department of Electrical Power Engineering Faculty of EngineeringEgypt-Japan University of Science and TechnologyAlexandriaEgypt Department of Electrical Engineering Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of Electrical Engineering and Automation School of Electrical EngineeringAalto UniversityEspooFinland

Photovoltaic(PV)arrays are usually installed in open areas;hence,they are vulnerable to lightning strikes that can result in cell degradation,complete damage,service disruption,and increased maintenance *** a result,it is imperative to develop an effective and efficient lightning protection system by evaluating the transient behaviour of PV arrays during lightning *** aim is to evaluate the transient analysis of large-scale PV systems when subjected to lightning strikes using the finite difference time domain(FDTD)*** overvoltages are calculated at various points within the mounting *** optimise the FDTD method's execution time and make it more suitable for less powerful hardware,a variable cell size approach is ***,larger cell dimensions are used in the earthing system and smaller cell dimensions are used in the mounting *** FDTD method is utilised to calculate the temporal variation of transient overvoltages for large-scale PV systems under different scenarios,including variations in the striking point,soil resistivity,and the presence of a metal *** results indicate that the highest transient overvoltages occur at the striking point,and these values increase with the presence of a PV metal frame as well as with higher soil ***,a comparison is performed between the overvoltage results obtained from the FDTD approach and the partial element equivalent circuit(PEEC)method at the four corner points of the mounting systems to demonstrate the superior accuracy of the FDTD ***,a laboratory experiment is conducted on a small-scale PV system to validate the simulation *** calculated overvoltages obtained from the FDTD and PEEC methods are compared with the measured values,yielding a mean absolute error of 5%and 11%for the FDTD and PEEC methods,respectively,thereby confirming the accuracy of the FDTD simulation model.

关键词： transient behaviour finite

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Evaluation Method for Traffic Flow Data Quality Based on Grey Correlation Analysis and Particle Swarm Optimization

引用

Journal of Systems Science and Systems engineering 2024年第1期33卷 106-128页

作者： Wei Ba Baojun Chen Qi Li School of Automation and Electrical Engineering Dalian Jiaotong UniversityDalian116028China Faculty of Electronic Information and Electrical Engineering Dalian University of TechnologyDalian116023China

Nowadays,data are more and more used for intelligent modeling and prediction,and the comprehensive evaluation of data quality is getting more and more attention as a necessary means to measure whether the data are usable or ***,the comprehensive evaluation method of data quality mostly contains the subjective factors of the evaluator,so how to comprehensively and objectively evaluate the data has become a bottleneck that needs to be solved in the research of comprehensive evaluation *** order to evaluate the data more comprehensively,objectively and differentially,a novel comprehensive evaluation method based on particle swarm optimization(PSO)and grey correlation analysis(GCA)is presented in this *** first,an improved GCA evaluation model based on the technique for order preference by similarity to an ideal solution(TOPSIS)is ***,an objective function model of maximum difference of the comprehensive evaluation values is built,and the PSO algorithm is used to optimize the weights of the improved GCA evaluation model based on the objective function ***,the performance of the proposed method is investigated through parameter analysis.A performance comparison of traffic flow data is carried out,and the simulation results show that the maximum average difference between the evaluation results and its mean value(MDR)of the proposed comprehensive evaluation method is 33.24%higher than that of TOPSIS-GCA,and 6.86%higher than that of *** proposed method has better differentiation than other methods,which means that it objectively and comprehensively evaluates the data from both the relevance and differentiation of the data,and the results more effectively reflect the differences in data quality,which will provide more effective data support for intelligent modeling,prediction and other applications.

关键词： Data quality comprehensive evaluation particle swarm optimization grey correlation analysis traffic flow data

来源：评论

学校读者我要写书评

暂无评论

Effect of temperature and time on the precipitation ofκ-carbides in Fe-28Mn-10Al-0.8C low-density steels:Aging mechanism and its impact on material properties

引用

International Journal of Minerals,Metallurgy and Materials 2024年第10期31卷 2189-2198页

作者： Yulin Gao Min Zhang Rui Wang Xinxin Zhang Zhunli Tan Xiaoyu Chong School of Mechanical Electronic and Control EngineeringMaterials Science and Engineering Research CenterBeijing Jiaotong UniversityBeijing 100044China Faculty of Materials Science and Engineering Kunming University of Science and TechnologyKunming 650093China

In low-density steel,κ-carbides primarily precipitate in the form of nanoscale particles within austenite ***,their precipitation within ferrite matrix grains has not been comprehensively explored,and the second-phase evolution mechanism during aging remains *** this study,the crystallographic characteristics and morphological evolution ofκ-carbides in Fe-28Mn-10Al-0.8C(wt%)low-density steel at different aging temperatures and times and the impacts of these changes on the steels’microhardness and properties were comprehensively *** different heat treatment conditions,intragranularκ-carbides exhibited various morpho-logical and crystallographic characteristics,such as acicular,spherical,and short rod-like *** the initial stage of aging,acicularκ-carbides primarily precipitated,accompanied by a few spherical carbides.κ-Carbides grew and coarsened with aging time,the spherical carbides were considerably reduced,and rod-like carbides *** hardness testing demonstrated that the material’s hardness was affected by the volume fraction,morphology,and size ofκ-*** aging at higher temperatures led to an increase in carbide size and volume fraction,resulting in a gradual rise in *** deformation,the primary mechanisms for strengthening were dislocation strengthening and second-phase *** on these findings,potential strategies for improving material strength are proposed.

关键词： low-density steel κ-carbide solution-aging treatment hardness

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：