检索结果-内蒙古大学图书馆

A Hybrid Convolutional Neural Network Model Based on Different evolution for Medical Image Classification

ENGINEERING LETTERS 2022年第1期30卷 168页

作者： Hu, Yinyin Zhang, Xiaoxia Yang, Jiao Fu, Shuai Univ Sci & Technol LiaoNing Sch Comp Sci & Software Engn Anshan 114051 Peoples R China

In clinical practice, the X-Ray image classification for the presence or absence of lesions by the medical auxiliary diagnosis system is the basic work, and the classification of lesion images and normal images can be completed by reading the medical X-Ray graphics. The actual process is the convolution and pooling layer of CNN to extract the features of medical images, and the full connection layer of CNN is used to classify the local information. The structure of CNN needs to be adjusted repeatedly. This paper focuses on utilizing differential evolution (DE) to automatically search for the optimal architecture of CNN. The research idea of this paper is to use the global optimization ability of differential evolution algorithm to regulate the structure of CNN. When the termination condition is satisfied, DE-CNN can automatically adjust the parameters and optimize the structure of the CNN. Among them, for mutation operation, we study a new mutation strategy in this paper, which inherits the vector that may solve the next generation, and appropriately accepts the basic elements of the inferior solution to increase the disturbance of the new species. The optimal individual is found through the optimization process of the DE algorithm, and the CNN model composed of all basic elements in the individual and trained on the medical X-Ray image data set is saved. The new mutation strategy generates mutation solution vector, through experimental verification which is beneficial to the optimization of CNN structure, and the accurate value of DE-CNN algorithm processing medical image classification is better than GoogLenet, ResNet34, VGGNet16, DenseNet, Lenet, AlexNet etc network structure.

关键词： differential evolution algorithm Convolution Neural Network GoogLenet ResNet34 VGGNet16 DenseNet

来源：评论

学校读者我要写书评

暂无评论

A novel ECG signal classification method using DEA-ELM

引用

MEDICAL HYPOTHESES 2020年第0期136卷 109515-000页

作者： Diker, Aykut Avci, Engin Tanyildizi, Erkan Gedikpinar, Mehmet Bitlis Eren Univ Dept Informat TR-13100 Bitlis Turkey Firat Univ Dept Software Engn TR-23100 Elazig Turkey Firat Univ Dept Elect Elect Engn TR-23100 Elazig Turkey

Electrocardiogram (ECG) signals represent the electrical mobility of the human heart. In recent years, computer-aided systems have helped to cardiologists in the detection, classification and diagnosis of ECG. The aim of this paper is to optimize the number hidden neurons of the traditional Extreme Learning Machine (ELM) using differential evolution algorithm (DEA) and contribute to the classification of ECG signals with a higher accuracy rate. In this paper, publicly ECG records in Physionet was utilized. Pan-Tompkins technique (PTT) and Discrete Wavelet Transform (DWT) approaches were implemented to obtain characteristic properties which are PR period, QT period, ST period and QRS wave of ECG signals. Then, ELM was executed to the ECG samples. Lastly, DEA on software ELM was developed for the assign of the number of hidden neurons, which were used in the ELM algorithm. The performance criterions were used in order to compare the performance of the classification exerted. Concordantly, it was realized that the highest classification achievement values were reached to Accuracy 97.5% and values 93 of number of hidden neurons, with the practice improved with the DEA compared to conventional ELM.

关键词： Electrocardiogram differential evolution algorithm Extreme Learning Machine Pan-Tompkins technique

来源：评论

学校读者我要写书评

暂无评论

Adaptive Constrained differential evolutionary algorithm Based on Interval Probability Mechanism

引用

ENGINEERING LETTERS 2021年第4期29卷 1414页

作者： Wei Yanting Feng Quanxi Yuan Sainan Guilin Univ Technol Sch Sci Guilin 541006 Peoples R China

This paper aims to improve premature convergence and low precision of the differential evolution algorithm. An adaptive constrained differential evolution algorithm based on a probability interval update mechanism (PIMDE) is proposed. First, the interval probability update mechanism is developed to adaptively generate the mutation probability value, and the hybrid mutation strategy is formulated by effectively selecting complementary mutation strategies based on the mutation probability. Subsequently, the adaptive mechanism is employed to dynamically adjust the mutation strategy and parameters;as a result, the global detection and local search ability of the algorithm can be balanced, and the search efficiency of the algorithm can be enhanced. To verify determine the performance of the proposed algorithm, ten standard constrained optimization problems and five engineering optimization problems are analyzed. As revealed from experimental results, PIMDE can effectively solve COPs with high precision and robustness.

关键词： Constrained optimization differential evolution algorithm parameter self-adaptive epsilon-constraint processing technique

来源：评论

学校读者我要写书评

暂无评论

Optimal strategy for distribution system with PV based on voltage violation regulation

引用

The Journal of Engineering 2017年第13期2017卷 1124-1128页

作者： Shanhong Jin Weiguo He Jingwei Zhang Xiang Zhu Haoming Liu State Grid Jiaxing Power Supply Company Jiaxing People's Republic of China China Electric Power Research Institute Nanjing People's Republic of China College of Energy and Electrical Engineering Hohai University Nanjing People's Republic of China

The high penetration of distributed photovoltaic (PV) can bring about huge economic and environmental benefits in the distribution network. While at the same time, it can result in the voltage violation in power system. Due to the two-quadrant power output characteristics of PV inverter, it is possible to regulate voltage violation via utilising the reactive power output of PV inverter instead of traditional reactive power compensation devices. In this study, a global voltage regulation strategy has been addressed by taking the indices of voltage violation regulation and active power loss of distribution network into consideration, and voltage limit violation is processed based on the concept of hard and soft voltage boundary constraints. differential evolution algorithm is introduced to solve the optimisation model. Finally, it was simulated in IEEE-33 node distribution system, results of example analysis confirm that the proposed strategy can optimise the reactive and active power of PV, which can not only regulate the voltage violation but also realise the economic operation of the distribution system.

关键词： photovoltaic power systems voltage control power distribution control power generation control power distribution economics power generation economics environmental factors invertors evolutionary computation optimisation reactive power control distribution network system distributed photovoltaic system economic benefit environmental benefit power system two-quadrant power output characteristics PV inverter optimisation model IEEE-33 node distribution system optimisation model differential evolution algorithm soft voltage boundary constraint reactive power compensation device global voltage violation regulation strategy active power loss hard voltage boundary constraint

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Tradeoffs in the Design Optimization of Synchronous Reluctance Machines for Electric Vehicle Application

Multi-Objective Tradeoffs in the Design Optimization of Sync...

引用

IEEE International Electric Machines and Drives Conference

作者： S. Guenther W. Hofmann Institute of Electrical Power Engineering Dresden University of Technology

ISBN: (纸本)9781479979424

The synchronous reluctance machine (SynRM) can be considered as a viable alternative to permanent-magnet synchronous machines and induction machines. The absence of permanent magnets or excitation windings are advantages. Additionally, higher efficiencies respectively torque densities are possible compared to induction machines. Lower power factors (typically less than 0.7-0.8) and therefore larger inverter currents are one of the major drawbacks of the SynRM. This paper presents a design optimization procedure for synchronous reluctance machines for electric vehicle application and discusses the tradeoffs between the most important design objectives. The optimization problem is solved using a multi-objective evolutionary algorithm (differential evolution) assisted by a surrogate model (Kriging). This work aims at presenting an approach which is more comprehensive than usual due to the consideration of electromagnetic, thermal and mechanical aspects.

关键词： AC Machines Synchronous Reluctance Machine Electric Vehicle Multi-Objective Optimization differential evolution algorithm Kriging Finite Element Analysis Driving Cycle Efficiency Pareto Optimization

来源：评论

学校读者我要写书评

暂无评论

Double-transfer learning-based least squares wavelet support vector machine for water quality classification

引用

DESALINATION AND WATER TREATMENT 2024年 320卷

作者： Wang, Le Huang, Yang Ren, Jian Zhou, Hengrui Chen, Lianghai Zhou, Hongbiao Huaiyin Inst Technol Fac Automat Huaian 223003 Peoples R China

In the context of intelligent wastewater interception systems, the enhancement of decision control capability heavily relies on precise water quality classification outcomes. Nonetheless, conventional classification techniques encounter challenges in attaining satisfactory accuracy because of the intricate interplay between feature parameters of water quality and the imbalanced distribution of samples across different classes. In this paper, a least squares wavelet support vector machine (LSWSVM) is proposed with a double-transfer learning (DTL) strategy and an enhanced adaptive differential evolution (EADE) algorithm, referred to as DTL-EADE-LSWSVM. Firstly, the radial basis function is replaced by a wavelet function with multiresolution analysis to enhance the generalization ability of the LSWSVM. Secondly, three adaptive adjustment strategies for mutation factor, crossover probability and population size are designed in the EADE algorithm. Then, the EADE algorithm is adopted to obtain the optimal penalty factor and the parameter of the wavelet kernel function of the LSWSVM. Thirdly, the DTL strategy is developed to transfer the classification labels and model knowledge of the LSWSVM as well as the optimal population and optimal parameters of the EADE in the source domain to the target domain to improve the optimization efficiency and classification performance of the model in the target domain. Finally, the classification accuracy of the class imbalance samples is improved by reshaping the objective function. The experimental results indicate that the accuracy of the proposed DTL-EADE-LSWSVM classification model on balanced and imbalanced datasets is 92.5 % and 92.4 %, respectively, which is better than that of neural networks, stochastic deep forests and classical SVMs. In addition, the proposed DTL strategy has a stronger knowledge transfer capability than the single transfer learning strategy. The proposed DTL-EADE-LSWSVM is fully capable of classifying water

关键词： Wastewater intercepting system Water quality classification Least squares support vector machine differential evolution algorithm Transfer learning strategy

来源：评论

学校读者我要写书评

暂无评论

Health estimation of fan based on belief-rule-base expert system in turbofan engine gas-path

引用

ADVANCES IN MECHANICAL ENGINEERING 2017年第3期9卷

作者： Yin, Xiaojing Wang, Zhanli Zhang, Bangcheng Zhou, Zhijie Gao, Zhi Changchun Univ Technol Sch Mechatron Engn Changchun 130012 Peoples R China High Tech Inst Xian Xian Peoples R China Changchun Univ Technol Sch Appl Technol Changchun Peoples R China

Fan is an important rotating part in turbofan engine gas-path. The health condition of fan has a great impact on the health status of the whole aero-engine. Based on belief-rule-base, a novel health estimation model is proposed for fan in turbofan engine gas-path. In this model, the health condition of fan is reflected by the observable information which can represent the system health. In the process of health estimation, the expert knowledge is used fully to improve the precision and speed of the estimation. In the initial health estimation model, some parameters given by expert may not be accurate. To obtain the accurate estimation result, an algorithm for updating the parameters is proposed based on differential evolution algorithm. In order to verify the feasibility and accuracy of the proposed model, back-propagation neural network is applied to comparison. The newly proposed model is applied to an actual test in the aero-engine test bed, which is used to testify the validity of the health estimation model. This model can also provide a reference for the health estimation of turbofan engine gas-path.

关键词： Health estimation belief-rule-base expert knowledge differential evolution algorithm fan aero-engine

来源：评论

学校读者我要写书评

暂无评论

An Optimized Coverage Robot SLAM algorithm Based on Improved Particle Filter for WSN Nodes

引用

INTERNATIONAL JOURNAL OF GRID AND HIGH PERFORMANCE COMPUTING 2020年第4期12卷 76-88页

作者： Zhang, Wei Du, Yanli Bai, Qinghua Beihua Univ Jilin Jilin Peoples R China

In order to realize the positioning and creation of the environment of mobile robots, this article proposes an optimized coverage robot SLAM algorithm based on an improved particle filter for WSN nodes. The algorithm overcomes the disadvantages of the standard particle filter SLAM algorithm in the simultaneous positioning of robot poses and creation of environmental maps. By constructing the sensor node to cover the high coverage of the SLAM positioning information node of the robot, the algorithm can search for the ideal result under the existing information, and the local optimization is performed to obtain the ideal result in another local state. Thus, the global accurate robot SLAM information is finally obtained. Simulation experiments show that the influence of the time delay parameter for simultaneous positioning of the robot SLAM is almost zero at different speeds, which shows the superior positioning stability of the new algorithm.

关键词： Delay Estimation differential evolution algorithm Particle Filter Robot SLAM algorithm

来源：评论

学校读者我要写书评

暂无评论

UNCREWED BOAT PATH PLANNING algorithm BASED ON evolutionARY POTENTIAL FIELD MODEL IN DENSE OBSTACLE ENVIRONMENT

引用

SCALABLE COMPUTING-PRACTICE AND EXPERIENCE 2024年第3期25卷 1773-1780页

作者： Zheng, Wei Huang, Xin Nanyang Normal Univ Sch Comp Sci & Technol Nanyang 473061 Henan Peoples R China Henan Res Ctr Serv & Guarantee Intelligent Emergen Nanyang 473061 Henan Peoples R China

In the trajectory planning of crewless ships, the artificial potential field method is commonly used. The results obtained using the classic potential field model for path design are not optimal and cannot fully meet the trajectory design requirements of uncrewed ships. This paper uses the evolutionary potential field model for trajectory planning. The evaluation formula of the potential path is combined with the differential evolution algorithm to evaluate and optimize the potential. A quadratic optimization smoothing algorithm is designed to limit the maximum turning angle of the uncrewed ship. Simulation experiments show that this method is effective and reliable.

关键词： Uncrewed boat Path planning Potential modeling differential evolution algorithm Track optimization Maxi- mum turning angle limit

来源：评论

学校读者我要写书评

暂无评论

Operation Loop Based Optimization Model for Resource Allocation in Defense

Operation Loop Based Optimization Model for Resource Allocat...

引用

第30届中国控制与决策会议

作者： Chunqi Wan Weitao Xiong Qingsong Zhao Kewei Yang Wenying Chen National University of Defense Technology Beijing Special Vehicle Institute

Weapons development planning is an unstructured, complex multi-criteria decision problem, especially in antagonistic environments. In this paper, the decision in terms of the defender is modeled as a non-linear optimization problem with high complexity under limited resource constraints. More specifically, the operation loop is used to model the relationship among all weapons in the defense system. Considering the opponent, this paper uses accumulative threat to measure different development planning solutions. Then, the differential evolution algorithm combined with special constraints-handling mechanism is designed to find the optimal planning solution. Finally, the feasibility and validity of the proposed model are verified by an illustrative example.

关键词： Weapon development planning Resource constraint Threat differential evolution algorithm

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：