文献类型：期刊文献

英文题名：INTELLIGENT PEARL DISEASE DIAGNOSIS BASED ON ROUGH SET - NEURAL NETWORK

作者：Xu, Longqin[1];Liu, Shuangyin[1,2]

机构：[1]Guangdong Ocean Univ, Coll Informat, Zhanjiang 524025, Guangdong, Peoples R China;[2]China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China

年份：2012

卷号：18

期号：5

起止页码：469

外文期刊名：INTELLIGENT AUTOMATION AND SOFT COMPUTING

收录：SCI-EXPANDED(收录号：WOS:000314855700005)、、Scopus(收录号：2-s2.0-84876218100)、WOS

基金：This work was partially supported by the Country’s Spark Plan Project No.2007EA780068, Guangdong and Hong Kong Essential Domain Key Breakthrough Project No.2006A25007002, Guangdong Science and Technology Plan Project No. 2010B020315025 and Zhanjiang Science And Technology Plan Project No. 2010C3113011.

语种：英文

外文关键词：Intelligent Disease Diagnosis; rough set; neural network; reduction; pearl

外文摘要：In view of large amount of monitoring data for Pearl disease, complexity of network structure of the traditional diagnostic neural network method, validity of disease data issues and slow training, this paper introduces the rough set theory to intelligent Pearl disease diagnosis. A method for disease diagnostics is proposed based on rough set - neural network. The rough set is used to remove the redundant attributes of decision table in order to reduce the number of input neurons and optimize neural network topology. The experimental simulation shows that the proposed algorithm can effectively improve the diagnostic rate and diagnostic accuracy. The proposed algorithm is a new way of methods for the diagnosis aquaculture technology