检索结果-内蒙古大学图书馆

Reverse engineering module networks by PSO-RNN hybrid modeling

BMC GENOMICS 2009年第Sup1期10卷 S15-S15页

作者： Zhang, Yuji Xuan, Jianhua de los Reyes, Benildo G. Clarke, Robert Ressom, Habtom W. Virginia Polytech Inst & State Univ Dept Elect & Comp Engn Arlington VA USA Georgetown Univ Lombardi Comprehens Canc Ctr Washington DC USA Univ Maine Sch Biol & Ecol Orono ME 04469 USA

Background: Inferring a gene regulatory network (GRN) from high throughput biological data is often an under-determined problem and is a challenging task due to the following reasons: (1) thousands of genes are involved in one living cell;(2) complex dynamic and nonlinear relationships exist among genes;(3) a substantial amount of noise is involved in the data, and (4) the typical small sample size is very small compared to the number of genes. We hypothesize we can enhance our understanding of gene interactions in important biological processes (differentiation, cell cycle, and development, etc) and improve the inference accuracy of a GRN by (1) incorporating prior biological knowledge into the inference scheme, (2) integrating multiple biological data sources, and (3) decomposing the inference problem into smaller network modules. Results: This study presents a novel GRN inference method by integrating gene expression data and gene functional category information. The inference is based on module network model that consists of two parts: the module selection part and the network inference part. The former determines the optimal modules through fuzzy c-mean (FCM) clustering and by incorporating gene functional category information, while the latter uses a hybrid of particle swarm optimization and recurrent neural network (PSO-RNN) methods to infer the underlying network between modules. Our method is tested on real data from two studies: the development of rat central nervous system (CNS) and the yeast cell cycle process. The results are evaluated by comparing them to previously published results and gene ontology annotation information. Conclusion: The reverse engineering of GRNs in time course gene expression data is a major obstacle in system biology due to the limited number of time points. Our experiments demonstrate that the proposed method can address this challenge by: (1) preprocessing gene expression data (e. g. normalization and missing value imputation)

关键词： particle swarm optimization Gene Expression Data Gene Regulatory Network particle swarm optimization algorithm Relative Entropy

来源：评论

学校读者我要写书评

暂无评论

particle swarm optimization-based Clustering and Classification algorithms for Analyzing DNA Chip data

Particle Swarm Optimization-based Clustering and Classificat...

引用

International Multi-Conference on Engineering and Technological Innovation

作者： Lee, Yoonkyung Meang, Boyeon Choi, Ok-ju Lee, Minsoo Yoon, Kyong Oh Choi, Hye Yeon Kim, Dae Hyun Lee, Keun Il Ewha Womans Univ Dept Comp Sci & Engn 11-1 Daehyun Dong Seoul 120750 South Korea Macrogen World Meridian Venture Ctr Bioinformat Lab Seoul 153023 South Korea

ISBN: (纸本)9781934272442

DNA chips are used for experiments on genes and provide useful information that could be further analyzed. Instead of experimenting with real genes which are expensive, DNA chips are increasingly being used for biological experiments. The data provided by the DNA chips could be represented as a two dimensional matrix, in which one axis represent genes and the other represent samples. Extracting data from the DNA chips with high accuracy and finding out the patterns or useful information from such data has become a very important issue. Some commonly used methods to find meaningful information from the data are clustering and classification. In this paper, we propose clustering and classification mechanisms that are based on the particle swarm optimization algorithm. Considering that DNA chip data is extremely large and has a fuzzy characteristic, an algorithm that imitates the ecosystem such as the particle swarm optimization algorithm is suitable to be used for analyzing such data. Experiments show that the algorithms can efficiently cluster and classify DNA chip data.

关键词： particle swarm optimization algorithm Clustering Classification DNA Chip Analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic Scheduling of Multi-task for Hybrid Flow-shop Based on Idle Time Windows

Dynamic Scheduling of Multi-task for Hybrid Flow-shop Based ...

引用

2009中国控制与决策会议

作者： Zeng Ling-li,Zou Feng-xing,Gao Zheng,Xu Xiao-hong Department of Automatic Control,College of Mechatronics and Automation,National University of Defense Technology, 410073,Changsha,P.R.China

This paper presents an approach based on idle time windows(ITWs) and particle swarm optimization(PSO) algorithm to solve dynamic scheduling of multi-task for hybrid *** idea of ITW is introduced,then the dynamic updating rules of the sets of ITWs are explained in *** the sets of ITWs of machines as constraints, the mathematical model is presented for dynamic scheduling of multi-task for hybrid *** PSO algorithm is proposed in order to solve this *** results of simulation indicate that this approach satisfies the demand of dynamic scheduling of multi-task.

关键词： Idle Time Window Hybrid Flow-shop Multi-task Dynamic Scheduling particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

particle swarm optimization Based Multi-Robot Task Allocation Using Wireless Sensor Network

Particle Swarm Optimization Based Multi-Robot Task Allocatio...

引用

IEEE International Conference on Information and Automation

作者： Li Xun Ma Hong-xu Natl Univ Def Technol Coll Electromech Engn & Automat Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781424421831

To solve the multi-robot task allocation (MRTA) especially in unknown complex environment, a novel dynamic algorithm was put forward with the advantages of wireless sensor network (WSN). The architecture and sensor fusion of WSN were discussed. particle swarm optimization (PSO) algorithm based on bionic swarm intelligence was used for solution of the multi-objective optimization. A practical implementation with real WSN and real mobile robots were carried out. The successful implementation of tasks validates the efficiency, stability and accuracy of the proposed algorithm.

关键词： particle swarm optimization algorithm Multi-Robot Task Allocation Multi-Robot System Wireless Sensor Network swarm Intelligence

来源：评论

学校读者我要写书评

暂无评论

A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training

引用

APPLIED MATHEMATICS AND COMPUTATION 2007年第2期185卷 1026-1037页

作者： Zhang, Jing-Ru Zhang, Jun Lok, Tat-Ming Lyu, Michael R. Chinese Acad Sci Hefei Inst Intelligent Machines Intelligent Comp Lab Hefei 230031 Anhui Peoples R China Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China Chinese Univ Hong Kong Informat Engn Dept Shatin Hong Kong Peoples R China Chinese Univ Hong Kong Comp Sci & Engn Dept Shatin Hong Kong Peoples R China

The particle swarm optimization algorithm was showed to converge rapidly during the initial stages of a global search, but around global optimum, the search process will become very slow. On the contrary, the gradient descending method can achieve faster convergent speed around global optimum, and at the same time, the convergent accuracy can be higher. So in this paper, a hybrid algorithm combining particle swarm optimization (PSO) algorithm with back-propagation (BP) algorithm, also referred to as PSO-BP algorithm, is proposed to train the weights of feedforward neural network (FNN), the hybrid algorithm can make use of not only strong global searching ability of the PSOA, but also strong local searching ability of the BP algorithm. In this paper, a novel selection strategy of the inertial weight is introduced to the PSO algorithm. In the proposed PSO-BP algorithm, we adopt a heuristic way to give a transition from particle swarm search to gradient descending search. In this paper, we also give three kind of encoding strategy of particles, and give the different problem area in which every encoding strategy is used. The experimental results show that the proposed hybrid PSO-BP algorithm is better than the Adaptive particle swarm optimization algorithm (APSOA) and BP algorithm in convergent speed and convergent accuracy. (c) 2006 Elsevier Inc. All rights reserved.

关键词： particle swarm optimization algorithm feedforward neural network BP algorithm adaptive particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Acoustic radiation optimization using the particle swarm optimization algorithm

引用

JSME INTERNATIONAL JOURNAL SERIES C-MECHANICAL SYSTEMS MACHINE ELEMENTS AND MANUFACTURING 2004年第2期47卷 560-567页

作者： Jeon, JY Okuma, M Tokyo Inst Technol Dept Mech & Aerosp Engn Meguro Ku Tokyo 1528552 Japan

The present paper describes a fundamental study on structural bending design to reduce noise using a new evolutionary population-based heuristic algorithm called the particle swarm optimization algorithm (PSOA). The particle swarm optimization algorithm is a parallel evolutionary computation technique proposed by Kennedy and Eberhart in 1995. This algorithm is based on the social behavior models for bird flocking, fish schooling and other models investigated by zoologists. Optimal structural design problems to reduce noise are highly nonlinear, so that most conventional methods are difficult to apply. The present paper investigates the applicability of PSOA to such problems. Optimal bending design of a vibrating plate using PSOA is performed in order to minimize noise radiation. PSOA can be effectively applied to such nonlinear acoustic radiation optimization.

关键词： acoustics noise reduction particle swarm optimization algorithm finite element method Rayleigh integral method sound power level modal analysis genetic algorithm noise

来源：评论

学校读者我要写书评

暂无评论

Multi-objective design optimization of reconfigurable machine tools: a modified fuzzy-Chebyshev programming approach

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2008年第6期46卷 1587-1618页

作者： Liu, Wei Liang, Ming Univ Ottawa Dept Mech Engn Ottawa ON K1N 6N5 Canada

A reconfigurable manufacturing system (RMS) is designed for rapid adjustment of functionalities in response to market changes. A RMS consists of a number of reconfigurable machine tools (RMTs) for processing different jobs using different processing modules. The potential benefits of a RMS may not be materialized if not properly designed. This paper focuses on RMT design optimization considering three important yet conflicting factors: configurability, cost and process accuracy. The problem is formulated as a multi-objective model. A mechanism is developed to generate and evaluate alternative designs. A modified fuzzy-Chebyshev programming (MFCP) method is proposed to achieve a preferred compromise of the design objectives. Unlike the original fuzzy-Chebyshev programming (FCP) method which imposes an identical satisfaction level for all objectives regardless of their relative importance, the MFCP respects their priority order. This method also features an adaptive satisfaction-level-dependent process to dynamically adjust objective weights in the search process. A particle swarm optimization algorithm (PSOA) is developed to provide quick solutions. The application of the proposed approach is demonstrated using a reconfigurable boring machine. Our computational results have shown that the combined MFCP and PSOA algorithm is efficient and robust. The advantages of the MFCP over the original FCP are also illustrated based on the results.

关键词： reconfigurable manufacturing design optimization multi-objective optimization modified fuzzy-Chebyshev programming modeling particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Singularity-free trajectory planning of platform-type parallel manipulators for minimum actuating effort and reactions

引用

ROBOTICA 2008年第3期26卷 371-384页

作者： Chen, Chun-Ta Chi, Hua-Wei Da Yeh Univ Dept Mech & Automat Engn Da Tsuen 515 Changhwa Taiwan

Due to the existence of singular configurations within the workspace for a platform-type parallel manipulator (PPM), the actuating force demands increase drastically as the PPM approaches or crosses singular points. Therefore, in this report, a numerical technique is presented to plan a singularity-free trajectory of the PPM for minimum actuating effort and reactions. By using the parametric trajectory representation, the singularity-free trajectory planning problem can be cast to the determination of undetermined control points, after which a particle swarm optimization algorithm is employed to find the optimal control points. This algorithm ensures that the obtained trajectories can avoid singular points within the workspace and that the PPM has the minimum actuating effort and reactions. Simulations and discussions are presented to demonstrate the effectiveness of the algorithm.

关键词： platform-type parallel manipulator singularity-free trajectory particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved particle swarm optimization algorithm for optimum charge plan for steelmaking-continuous casting production scheduling

Improved particle swarm optimization algorithm for optimum c...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Jian, W Xuc, YC Huang, J Hubei Automot Ind Inst Dept Elect Engn Shiyan Peoples R China

ISBN: (纸本)0780386620

An optimum furnace charge plan model for steelmaking continuous casting planning and scheduling is presented. An improved particle swarm optimization is presented to solve the optimum charge plan problem. Simulations have been carried and the results show that the improved PSO has good performance than the standard PSO. This improved PSO has been used to solve the optimum charge plan problem. The computation with practical data shows that the model and the solving method are very effective.

关键词： particle swarm optimization algorithm charge plan steelmaking process modeling simulation

来源：评论

学校读者我要写书评

暂无评论

Mechanical Property Prediction of Strip Model Based on PSO-BP Neural Network

引用

Journal of Iron and Steel Research International 2008年第3期15卷 87-91页

作者： WANG Ping HUANG Zhen-yi ZHANG Ming-ya ZHAO Xue-wu School of Metallurgy and Materials Anhui University of Technology Ma＇anshan 243002 Anhui China Anhui Key Laboratory of Metal Materials and Processing Ma＇anshan 243002 Anhui China Zhangjiagang Pohang Stainless Steel Co Ltd Zhangjiagang 215000 Jiangsu China

Mechanical property prediction of hot rolled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimization algorithm-particle swarm optimization （PSO） is adopted. The algorithm is combined with the BP rapid training algorithm, and then, a kind of new neural network （NN） called PSO-BP NN is established. With the advantages of global optimization ability and the rapid constringency of the BP rapid training algorithm, the new algorithm fully shows the ability of nonlinear approach of multilayer feedforward network, improves the performance of NN, and provides a favorable basis for further online application of a comprehensive model.

关键词： particle swarm optimization algorithm BP neural network hot continuous rolling strip mechanical property prediction

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：