基于动态特征重要度的电子鼻传感器阵列优化方法  

An effective gas sensor array optimization method based on dynamic feature importance

作　　者：魏广芬[1] 赵捷 冯烟利[2] 何爱香[1] 余隽[3] 唐祯安[3] Guangfen WEI;Jie ZHAO;Yanli FENG;Aixiang HE;Jun YU;Zhen-An TANG(School of Information and Electronic Engineering,Shandong Technology and Business University,Yantai 264005,China;School of Computer Science and Technology,Shandong Technology and Business University,Yantai 264005,China;School of Biomedical Engineering,Dalian University of Technology,Dalian 116024,China)

机构地区：[1]山东工商学院信息与电子工程学院,烟台264005 [2]山东工商学院计算机科学与技术学院,烟台264005 [3]大连理工大学生物医学工程学院,大连116024

出　　处：《中国科学：信息科学》2020年第5期743-765,共23页Scientia Sinica(Informationis)

基　　金：国家自然科学基金(批准号:61174007);烟台市科技发展计划(批准号:2016ZH053,2017ZH063)资助项目。

摘　　要：气体传感器阵列的优化是电子鼻领域亟需解决的关键问题之一,同时也是一种特殊的特征选择问题.本文结合特征相关性和特征重要度,提出了一种有效的新型传感器(特征)重要性衡量方法--动态特征重要度,并在此基础上提出了一种新的基于动态特征重要度的电子鼻传感器阵列优化算法SAO DFI.通过对两种不同的气体环境下采集的数据进行分析,测试了重复传感器、传感器(特征)重要度、传感器(特征)相关性以及传感器特征参数对SAO DFI算法的影响,其优化结果证明了该阵列优化算法的有效性、鲁棒性和可解释性.Gas sensor array optimization is a key problem in the field of electronic noses,and it is also a special feature selection problem.In this paper,we propose a novel measure of sensor(or feature)importance,named dynamic feature importance,based on feature correlation and feature importance.Also,we propose an effective electronic nose sensor array optimization algorithm SAO DFI based on the dynamic feature importance.We analyze the effects of repeated sensors,sensor(or feature)importance,sensor(or feature)correlation,and sensor characteristic parameters,based on the proposed SAO DFI algorithm using data collected in two different gas environments.The optimization results demonstrate the effectiveness,robustness,and interpretability of the array optimization algorithm.

关 键 词：阵列优化 气体传感器 特征选择 特征相关性 电子鼻 动态特征重要度 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]