摘要
将核主元分析(PCA)与支持向量机(SVM)相结合并将其应用到电子鼻模式识别单元中,实现了数据降维和改善分类器性能。实验结果表明与单纯的应用支持向量机方法进行分类相比,此方法具有更高的识别率。
This paper presents a pattern recognition method combining kernel-principal component analysis (PCA) and support vector machine (SVM) and its application to electronic nose technology. It can give data reduction and improve the performance of classification by combining the two methods used in complex electronic nose test environments. The experimental results show that the method has higher recognition compared with the simple application of SVM.
出处
《北京化工大学学报(自然科学版)》
CAS
CSCD
北大核心
2012年第2期106-109,共4页
Journal of Beijing University of Chemical Technology(Natural Science Edition)
关键词
电子鼻
核主元分析
支持向量机
electronic nose
kernel-principal component analysis (PCA)
support vector machine (SVM)