文献类型：期刊文献

中文题名：改进的粒子群优化算法结合人工神经网络用于有机物毒性的QSAR研究

英文题名：QSAR for Toxicities of Organic Substance Using Improved PSO Algorithm Combined with BP Artificial Neural Network

作者：李绍军[1];奚玮君[1];钱锋[1]

机构：[1]华东理工大学自动化研究所,上海200237

年份：2007

卷号：33

期号：6

起止页码：865

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：CSTPCD;;EI(收录号：20080411059296);Scopus;北大核心:【北大核心2004】；CSCD:【CSCD2011_2012】；

基金：国家杰出青年科学基金(60625302);国家973计划基金(2002CB3122000);上海委科技攻关项目(05DJ14002);上海市自然科学基金(06ZR14027)

语种：中文

中文关键词：粒子群优化算法;Alopex-B算法;人工神经网络;QSAR

外文关键词：particle swarm optimization; Alopex-B; artificial neural network; QSAR

摘要：介绍了粒子群优化算法和Alopex-B算法的基本原理,提出了一种用Alopex-B算法改进的粒子群优化算法,并将其应用于函数优化和有机物毒性的QSAR研究。结果表明:改进型粒子群算法对复杂的测试函数搜索效率明显提高,应用于有机物毒性的QSAR研究能提高计算的精确度,降低预测误差。
Particle swarm optimization algorithm and Alopex-B algorithm are introduced. By combining Alopex-B with PSO algorithm, a new improved algorithm called PSO-Alopex B is presented. Compared with original PSO, lower failure rates and less error can be achieved when searching the minimum of test functions. It is also used to research QSAR for toxicities of organic substances. The results of both function optimization and QSAR researching show that the improved PSO algorithm is effective.