A Method of Pattern Classification for Faint Signals

摘要：

This paper proposes a faint signal processing approach combining AR model and BP neural network (NN), by which the faint signal is fitted with AR model, whose coefficient served as signal eigenvector, and then sent into a threetier BP NN for training and recognition classification. Classification tests on human pulse signals between drug users and nonusers show that this approach is characterized in high speed and high recognition rate.

关键词： pulsefaintsignal ARmodel orders LMalgorithm

作者: Li Zuojin Chen Liukui Wu Ying Xiang Yi

作者单位: Chongqing University of Science and TechnologyChongqing, China, 401331 Chongqing University of Science and Technology Chongqing, China, 401331

会议类型: 国际会议

会议名称: 2011 International Conference on Business Management and Electronic Information(2011商业管理与电子信息国际学术会议 BMEI2011)

会议地点: 广州

会议语种:英文

页码: 1-4

在线出版日期: 2011-05-13（万方平台首次上网日期，不代表论文的发表时间）