Underwater Sediments Echoes Recognition Based on KECCA + PLS
In order to solve the nonlinear feature fusion of underwater sediments echoes,the shortage of Enhanced Canonical Correlation Analysis (ECCA) was analyzed and made ECCA extend to Kernel ECCA (KECCA) in the nuclear space,a multi-feature nonlinear fusion classification model with KECCA combining with Partial Least-Square (PLS) was put forward.In the process of identifying four types of underwater sediment such as Basalt,Volcanic breccia,Cobalt crusts and Mudstone,the results showed that the recognition accuracy could be further improved for the KECCA + PLS model.
feature fusion ECCA nuclear space PLS Cobalt crusts
Bowen LUO Buyan WAN Weibin QIN Jiyu XU
Engineering Research Center of Advanced Mining Equipment under Ministry of Education, Hunan Universi Mechanical and Electrical Department, Shanxi Luan Environmental Energy Development Company Limited,
国际会议
石家庄
英文
629-633
2012-10-26（万方平台首次上网日期，不代表论文的发表时间）