检索结果-南通市图书馆

第24届中国控制与决策会议

作者： YAN Gao-wei, LI Chuang-qin, Lu Mu-chao Taiyuan University of Technology, Taiyuan, 030024

Social Force model is a dynamic model used to the simulation of crowd behaviors. The Social Force model explains the formation of self-organization from the dynamic. In this paper, a new swarm optimization algorithm based on Social Force model (SFSO) is proposed. The SFSO algorithm is a population based optimization technique which is inspired from the behaviors of pedestrian. In SFSO algorithm, the searching characteristics of the pedestrians, such as target selecting, information exchange, overtaking search and scene understanding, are the special abstraction to the pedestrians’ movement and psychology. The results on benchmark problems indicated that SFSO is a promising optimization method and an effective approach to solve multimodal numerical optimization problems.

关键词： Social Force Model swarm optimization SFSO algorithm Multimodal

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Exploring swarm optimization of Traffic flow in Cities

Exploring Swarm Optimization of Traffic flow in Cities

引用

2015 5th International Conference on Computer Sciences and Automation Engineering(ICCSAE 2015)

作者： Changbo Wang Yan Jiang Na Liu Hubei University of Medicine

With the acceleration of industrialization and urbanization in China, the development of the city is increasingly becoming saturated. There is no doubt that the city’s economic development and people’s travel life have brought a lot of pressure on the urban road traffic. Many research focus on the optimization of traffic flow in cities. Considering the accident, vehicles can avoid congestion point and change behavior, such as moving path of accidents before the vehicle driving rules in BML model was improved, closer to that of the actual vehicle driving behavior. On the basis of the improved model, the density of road network traffic flow must be respectively, the accident point number changes impact on the average speed of traffic flow;Accident number must be, a road network traffic flow density changes impact on the average speed of traffic flow;Accidents before the vehicle transition probability at each lattice point impact on the average speed of traffic flow;The vehicle before the accident point transfer probability distribution function of each lattice point is different effect the running state of the system simulation research on the four questions such as, the analysis of simulation results, a series of meaningful conclusions.

关键词： Traffic flow swarm optimization BML

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Metaheuristic optimization for Mobile Robot Navigation Based on Path Planning

引用

Computers, Materials & Continua 2022年第11期73卷 2241-2255页

作者： El-Sayed M.El-kenawy Zeeshan Shafi Khan Abdelhameed Ibrahim Bandar Abdullah Aloyaydi Hesham Arafat Ali Ali E.Takieldeen Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Computer Science Department College of Engineering and Computer ScienceMustaqbal UniversityBuraidahSaudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Mechanical Engineering Qassim UniversityBuraidah51452Saudi Arabia

Recently,the path planning problem may be considered one of the most interesting researched topics in autonomous *** is why finding a safe path in a cluttered environment for a mobile robot is a significant requisite.A promising route planning for mobile robots on one side saves time and,on the other side,reduces the wear and tear on the robot,saving the capital *** route planning methods for the mobile robot have been developed and *** to our best knowledge,no method offers an optimum solution among the existing *** swarm optimization(PSO),a numerical optimization method based on the mobility of virtual particles in a multidimensional space,is considered one of the best algorithms for route planning under constantly changing environmental *** the researchers,reactive methods are increasingly common and extensively used for the training of neural networks in order to have efficient route planning for mobile *** paper proposes a PSO Weighted Grey Wolf optimization(PSOWGWO)*** is a hybrid algorithm based on enhanced Grey Wolf optimization(GWO)with *** order to measure the statistical efficiency of the proposed algorithm,Wilcoxon rank-sum and ANOVA statistical tests are *** experimental results demonstrate a 25%to 45%enhancement in terms of Area Under Curve(AUC).Moreover,superior performance in terms of data size,path planning time,and accuracy is demonstrated over other state-of-the-art techniques.

关键词： Mobile robot swarm optimization robot route planning neural networks

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

LeafSpotNet:A deep learning framework for detecting leaf spot disease in jasmine plants

引用

Artificial Intelligence in Agriculture 2024年第2期12卷 1-18页

作者： Shwetha V Arnav Bhagwat Vijaya Laxmi Department of Electrical and Electronics Engineering Manipal Institute of TechnologyManipalManipal Academy of Higher EducationManipal 576104KarnatakaIndia

Leaf blight spot disease,caused by bacteria and fungi,poses a threat to plant health,leading to leaf discoloration and diminished agricultural *** response,we present a MobileNetV3 based classifier designed for the Jasmine plant,leveraging lightweight Convolutional Neural Networks(CNNs)to accurately identify disease *** model integrates depth wise convolution layers and max pool layers for enhanced feature extraction,focusing on crucial low level features indicative of the *** preprocessing techniques,including data augmentation with Conditional GAN and Particle swarm optimization for feature selection,the classifier achieves robust *** on curated datasets demonstrates an outstanding 97%training accuracy,highlighting its *** world testing with diverse conditions,such as extreme camera angles and varied lighting,attests to the model's resilience,yielding test accuracies between 94%and 96%.The dataset's tailored design for CNN based classification ensures result ***,the model's lightweight classification,marked by fast computation time and reduced size,positions it as an efficient solution for real time *** comprehensive approach underscores the proposed classifier's significance in addressing leaf blight spot dis-ease challenges in commercial crops.

关键词： CNN Detection Leaf CGAN Augmentation Classification swarm optimization Disease detection Tomato leaf Casava leaf

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Bio-Inspired Method for Breast Histopathology Image Classification Using Transfer Learning

引用

Journal of Artificial Intelligence and Technology 2024年第2期4卷 89-101页

作者： R.K.Chandana Mani J.Kamalakannan Y.Pandu Rangaiah Sesham Anand Vellore Institute of Technology VelloreTNIndia G.Pullaiah College of Engineering and Technology KurnoolAndhra PradeshIndia Maturi Venkata Subba Rao Engineering College HyderabadIndia

Breast cancer is one of the deadly cancer among the female population and still a developing area of research in the field of medical *** fatality rate is more in patients who are not early diagnosed and are given delayed ***,researchers are keeping their lot of efforts in developing breast cancer detection systems that could provide accurate diagnosis in the initial stages which are relied on medical *** learning is offering key solutions to overcome many image classification *** deep learning techniques have extended their root to many medical fields even it suffers from the problem of lack of sufficient *** neural networks are more preferred for medical image classification *** this paper,we propose a transfer learning method that overcomes the issue of insufficient *** use a familiar pre-trained network VGG-16(Visual Geometric Group)+with logistic regression as a binary *** hyper-parameters of every CNN have a closer impact on the performance of the entire deep learning model,our method focuses on optimizing hyper-parameters using particle swarm optimization which is a bio-inspired *** proposed model performs the classification of breast histopathology images into benign and malignant images and produce better *** use BreakHis Dataset to test our method and achieve an accuracy of around 96.9%.The experimental results show that this study has improved performance metrics when compared to other transfer learning methods.

关键词： bio-inspired algorithms breast cancer convolutional neural networks data augmentation swarm optimization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Modeling, Analysis and Simulation on Cloud optimization Algorithm

Modeling, Analysis and Simulation on Cloud Optimization Algo...

引用

第三十九届中国控制会议

作者： Jun Liu Xiaoning Ma Tianyun Shi Chang Bao Xin Li Guang Yang Institute of Computing Technologies China Academy of Railway Sciences

A new cloud optimization algorithm, which is mainly motivated by several swarm optimization methods and elastic computing in cloud computation, mainly tackles with the complicated optimization problem in few computational time. Some concepts of cloud optimization are provided to better illustrate the corresponding algorithm, while the velocity and position’s equations of cloud optimization algorithm, which are closely referred to as the topology, the delay time and key parameters,are also mathematically given and inspired by the existing swarm optimization methods and those improved methods. More importantly, the main steps of cloud optimization are also introduced to optimize the parameters. Numerical results, which are programmed by Java Language and executed in Spring Boot, show that cloud optimization including several PSO algorithms achieves good performance and has few computational time.

关键词： Cloud optimization swarm optimization virtual machine thread

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Parameters optimization Method for ADRC of Permanent Magnet Synchronous Motor Based on CMA-ES

Parameters Optimization Method for ADRC of Permanent Magnet ...

引用

第43届中国控制会议

作者： Tianjian Jiang Yang Yang Zhiyuan Li Tianqi Yang Xuwen Chen College of Automation and College of Aritifical Intelligence Nanjing University of Posts and Telecommunications College of Internet of Things Nanjing University of Posts and Telecommunications

Active disturbance rejection control(ADRC) is widely used to control permanent magnet synchronous motors(PMSM). However, the settings of gain parameters in ADRC is often dependent on engineers' experience. Also, it is difficult to design the parameters accurately by hand to achieve satisfactory results. A method based on evolution strategy with covariance matrix adaptation(CMA-ES) for optimizing the gain parameters of ADRC is proposed. By setting up some optimization tasks and using the CMA-ES algorithm, reinforcement learning is performed on the parameters of ADRC. In view of the high population size and complexity of CMA-ES, we adopt a parallel computation method to speed up the optimization *** method can effectively optimize the ADRC gain parameters to adapt to the specified application environment, and at the same time reduce the dependence of setting ADRC parameters on human experience as well as time consumption. Finally, we verify that this CMA-ES-based parameter optimization method can effectively improve the control performance of the motor by running simulations and comparing the motor speed changes before and after optimization.

关键词： Permanent-magnet Synchronous Motor Active Disturbance Rejection Control Field-oriented Control swarm optimization High Throughput Computing Modern Control

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：