Multi-Single-Class Support Vector Machine Classifier for Artificial Olfaction Signals

摘要：

Signal processing and pattern recognition are important parts of electronic nose. Considering the same sensor in electronic nose have different response to different odor, a multi-Single-Class Support Vector Machine (MSCSVM) classifier was designed based on the selected features for each kind of odor. Through the measurement and recognition of three kinds of odor, the value of the classifier for artificial olfaction signals was verified.

关键词： Artificial olfaction Pattern recognition Multi-Class-Single SVM Classifier

作者: QIN Guojun SUN Hai HU Niaoqing

作者单位: School of Mechatronics Engineering and Automation, National University ofDefense Technology, Changsha, Hunan, 410073, China

会议类型: 国际会议

会议名称: 第八届国际测试技术研讨会(8th International Symposium on Test and Measurement)

会议地点: 重庆

会议语种:英文

页码: 2109-2112

在线出版日期: 2009-08-01（万方平台首次上网日期，不代表论文的发表时间）