t-SNE+LDA算法在仿生嗅觉中的应用研究  

Research on bionic olfactory application using t-SNE+LDA

作　　者：郑首易 骆德汉[1] 温腾腾 何家峰[1] Zheng Shouyi;Luo Dehan;Wen Tengteng;He Jiafeng(School of Information Engineering,Guangdong University of Technology,Guangzhou 510006,China)

机构地区：[1]广东工业大学信息工程学院,广州510006

出　　处：《计算机应用研究》2018年第11期3315-3317,3321,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61571140);广东省科技计划资助项目(2016B030303011);广东省教育厅仪器重点培育项目(15ZK0130);广州市科技计划资助项目(201607010247)

摘　　要：将流形学习中的t-SNE算法引入仿生嗅觉领域中,提出一种基于t-SNE(t-分布邻域嵌入)与LDA(线性判别分析)算法相结合的气味分类鉴定新方法。由PEN3电子鼻获取物质气味特征信息,通过t-SNE算法将非线性、高维度的气味响应数据降维到低维空间,并利用LDA算法对低维数据进行分类和识别。利用五种不同成分的纺织品材料气味信息,通过t-SNE、PCA+LDA和t-SNE+LDA三种算法做对比实验。实验结果表明,相较于其他两种方法,t-SNE+LDA算法对常见的不同成分纺织品材料拥有更好的分类和识别效果,而且t-SNE+LDA算法得到的结果具有较小的类内离散度和较大的类间离散度。因此,t-SNE+LDA算法是仿生嗅觉中气味分类和识别的一个新方法。This paper introduced the t-SNE,a manifold learning algorithm,into the field of bionic olfaction,and proposed a method of odor classification and identification using t-SNE(t-distributed stochastic neighbor embedding)+LDA(linear discriminant analysis)technique.Odorant characteristic data were collected from PEN3 electronic nose.Then the method reduced these nonlinear and high-dimensional odorant response data to low-dimensional space by using t-SNE.Finally,it used LDA for classification and recognition in the low dimensional data.This paper implemented comparative experiments(t-SNE,PCA+LDA and t-SNE+LDA)of the classification and identification for five different ingredient textile material.The result shows that t-SNE+LDA has higher ability of distinguishing and recognizing common textile ingredient materials and according to the output t-SNE+LDA has smaller within-class scatter and larger between-class scatter.Consequently,t-SNE+LDA is supposed to be a new me-thod for odor classification and identification in bionic olfaction.

关 键 词：t-SNE+LDA算法 流形学习 仿生嗅觉 纺织品材料 特征提取 气味识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]