医用电子鼻气体传感器阵列优化方法  

Gas sensors array optimization for medical electronic noses

作　　者：胥勋涛[1] 田逢春[2] 杨先一[2] 

机构地区：[1]绵阳职业技术学院,四川绵阳621000 [2]重庆大学通信工程学院,重庆市400044

出　　处：《传感器世界》2009年第5期17-20,共4页Sensor World

基　　金：人事部2005年度留学回国人员科技活动择优资助项目(优秀类)基金资助

摘　　要：电子鼻气体传感器阵列存在冗余和相关,将对分类识别效果产生影响。提出并实现了一种新的医用电子鼻气体传感器阵列优化方法,利用改进遗传算法设定气体传感器的重要性系数,以去除传感器阵列的冗余和相关,提高系统的判别能力。新的方法分别用于五种乳癌特征气体和七种伤口病原菌检测,使正确识别率得到较大提高。Since there are some redundancy and correlation in gas sensor array, which will affect the discriminating ability of e-nose （electronic-nose）, a new method for gas sensors array optimization for medical e-nose is designed and implemented. To reduce the redundancy and correlation of gas sensor array, and to enhance the discriminating ability of the e-nose system, the weight coefficient of each gas sensor is set by an improved genetic algorithm. The proposed new method is applied to five types of breast cancer biomarks and seven types of wound pathogens infections. The recognition accuracy can be significantly improved.

关 键 词：医用电子鼻 阵列优化 改进遗传算法 乳癌诊断 伤口病原菌检测 

分 类 号：TP212.2[自动化与计算机技术—检测技术与自动化装置]