您好,欢迎来到三六零分类信息网!老站,搜索引擎当天收录,欢迎发信息

一种新颖的气味检测识别系统数据预处理方法

2025/8/7 2:37:13发布11次查看
a novel data pre-processing method for odour detection and identication system
一种新颖的气味检测识别系统数据预处理方法
wentian zhanga, taoping liua, lin yea, maiken uelandb, shari l. forbesb, steven w. sua,
afaculty of engineering and information technology, university of technology sydney, sydney, nsw 2007, australia.
bschool of mathematical and physical sciences, university of technology sydney, sydney, nsw 2007, australia
abstract
this paper presents a novel electronic nose (e-nose) data pre-processing method, based on a recently developed non-parametric kernel-based modelling (kbm) approach. the proposed method is tested by an automated odour detection and classication system, named nos.e, developed by the nos.e team in university of technology sydney. experimental results show that when extracting the derivative-related features from signals collected by the nos.e, the proposed non-parametric kbm odour data pre-processing method achieves more reliable and stable pre-processing results comparing with other pre-processing methods such as wavelet package correlation lter (wpcf), mean lter (mf), polynomial curve tting (pcf) and locally weighted regression (lwr). based on these derivative-related features, the nos.e can achieve a 96.23% accuracy of classication with the popular support vector machine (svm) classier.
本文提出了一种新的基于非参数核模型(kbm)的电子鼻数据预处理方法。该方法由悉尼理工大学团队开发的名为“nos.e”的自动气味检测和分类系统进行测试。实验结果表明,与小波包相关滤波器(wpcf)、均值滤波器(mf)、小波包相关滤波器(po)等预处理方法相比,该非参数kbm气味数据预处理方法在提取信号的导数相关特征时,获得了更加可靠、稳定的预处理结果。林氏曲线拟合(pcf)和局部加权回归(lwr)。基于这些与导数相关的特征,利用目前流行的支持向量机(svm)分类工具,能使分类精度达到96.23%。
keywords: electronic nose (e-nose), instrumentation, data pre-processing, non-parametric kernel-based modelling method
关键词:电子鼻,仪表,数据预处理,非参数核模型(kbm)
该用户其它信息

VIP推荐

免费发布信息,免费发布B2B信息网站平台 - 三六零分类信息网 沪ICP备09012988号-2
企业名录 Product