期刊：
International Conference on Challenges in Environmental Science and Computer Engineering, CESCE 2010,2010年1:287-290
通讯作者：
Shen, X.(xjshen@mail.ccnu.edu.cn)
作者机构：
[Yang, Jincai; Chi, Zhifeng; Chen, Caixia; Shen, Xianjun] Department of Computer Science, Central China Normal University, 430079 Wuhan, China;[Chi, Zhifeng] Department of Urban and Environmental Science, Xinyang Normal University, 464000 Xinyang, China
摘要：
This paper introduced a stochastic disturbance and an attractive operator into the standard particle swarm optimization (SPSO) algorithm to improve its performance in a predefined number of generations. It termed as stochastic disturbance particle swarm optimization based on attractive operator (SDPSO). In this paper, the concept of attractive operator is recommended that every particle has its own flight direction during the process of optimization, thus it increase the possibility of finding out a potential optimum, moreover, a stochastic disturbance is presented that aim to prevent the particles trapping into local optimum. The experiment results show that the SDPSO algorithm provides better solutions than the SPSO algorithm.
期刊：
Proceedings of 2009 4th International Conference on Computer Science and Education, ICCSE 2009,2009年:1699-1703
通讯作者：
Xianjun, S.(xjshen@mail.ccnu.edu.cn)
作者机构：
[Yang, Jincai; He, Tingting; Shen, Xianjun; Chen, Caixia] Cent China Normal Univ, Dept Comp Sci, Wuhan, Peoples R China.
会议名称：
第四届国际计算机新科技与教育学术会议(2009 4th International Conference on Computer Science & Education)
会议时间：
2009-07-25
会议地点：
南京
会议论文集名称：
第四届国际计算机新科技与教育学术会议(2009 4th International Conference on Computer Science & Education)论文集
关键词：
particle swam optimization;BP neural network;postgraduate entrant and employment forecasting
摘要：
It is hard to train the influence variables and to forecast the complex problems due to the time series. Recently the neural network method has been successfully employed to solve the forecasting problem. In this paper, an approach that integrate modified BP neural network optimized with particle swarm optimization algorithm (MBPPSO) is proposed which applied to forecast postgraduate entrant and employment problem. It introduces particle swarm optimization algorithm to optimize the initial weights of the BP neural network, which effectively improve velocity of convergence BP neural network. Moreover, the adaptive adjust learn strategy is introduced to avoid acutely shake of train and decrease the bias error. The experiment results show MBPPSO can achieve reasonable forecast result.
摘要：
A method named PMMR (previously merging for masking repeats) Is proposed In this paper for masking repeats in DNA fragment assembly. The method firstly identifies and counts the fragments including a same k-mer substring by scanning the shotgun data set. Then, it merges these fragments by the same k-mer substring. Based on merging, the method can not only mark the position of the repeats, but also reduce the scale of shotgun data set. The computer simulations show that the rate of repeats recognition Is enhanced in this method, and the CPU time of DNA fragment assembly will be reduced.
作者机构：
[Yang Jin-cai; Hu Jin-zhu; Liu Xiao-jiao; Zhao Sen] Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.
通讯机构：
[Yang Jin-cai] C;Cent China Normal Univ, Dept Comp Sci, Wuhan 430079, Peoples R China.
关键词：
mobile database;multi-mobile-agent;data broadcast;query optimization
摘要：
Because of the mobile database system with mobility, frequent disconnection, asymmetry of network and limited resource, the traditional query optimization has no longer applicable. Based on analyses on the characteristics of mobile database and mobile agent, a multi-mobile-agent technology is introduced into the mobile database and a model of query optimization based on multi-mobile-agent is proposed. Cooperation of multi-mobile-agent, query decomposition and data broadcast can reduce the times of query and network flow, improve the efficiency of query.
期刊：
2008 INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION, VOL III, PROCEEDINGS,2008年:526-+
通讯作者：
Shen, Xianjun
作者机构：
[Yang, Jincai; Shen, Xianjun; Chi, Zhifeng] Huazhong Normal Univ, Dept Comp Sci, Wuhan 430079, Hubei, Peoples R China.;[Chi, Zhifeng] Xinyang Normal Univ, Dept Urban & Environm Sci, Xinyang 464000, Peoples R China.;[Zheng, Bojin] South Cent Univ Nationaalities, Coll Comp Sci, Wuhan 430074, Peoples R China.
通讯机构：
[Shen, Xianjun] H;Huazhong Normal Univ, Dept Comp Sci, Wuhan 430079, Hubei, Peoples R China.
摘要：
Neural network has been widely used in the field of data mining, but the traditional neural network has some defects, such as convergence in the local optimal solution, learning a long time, etc. The genetic algorithm is a global optimization search algorithm, and can effectively overcome these shortcomings. Therefore, based on the comparative analysis of the standard BP algorithm and genetic algorithms, the hybrid algorithm G-BP algorithm that this paper presents not only retains the original merits of the neural network, but also overcomes these shortcomings. Through specific application it has been proved that the algorithm is practical in data mining, and is a good method of data mining.
