CAJ | 학술논문

具有模仿人的嗅觉系统的电子鼻在过去十年中发展迅速,大部分成果开始商业应用,主要应用于食品和化妆品行业.用于电子鼻系统的信号处理方法主要包括静特征分析法和动态特征处理方法.静态特征分析法包括主成分分析法,判别函数分析法,类聚分析法和基于网络的多层感知器.动态特征分析法包括传统的参数法和非参数法,非参数法是借助于传统的系统识别方式及线性滤波器、时间序列神经网络系统.
구유모방인적후각계통적전자비재과거십년중발전신속,대부분성과개시상업응용,주요응용우식품화화장품행업.용우전자비계통적신호처리방법주요포괄정특정분석법화동태특정처리방법.정태특정분석법포괄주성분분석법,판별함수분석법,류취분석법화기우망락적다층감지기.동태특정분석법포괄전통적삼수법화비삼수법,비삼수법시차조우전통적계통식별방식급선성려파기、시간서렬신경망락계통.
The field of electronic noses,electronic instruments capable of mimicking the human olfactory system,has developed rapidly in the past ten years.Most of the work published to date and commercial applications,which are mainly employed in the food and cosmetics industries.The signal processing techniques in electronic relate to the use of wel established static and dynamic pattern analysis techniques such as principal components analysis,discriminant function analysis,cluster analysis and multilayer perceptron based neural networks.Dynamic signal processing techniques reported so far include traditional parametric and nonparametlic ones borrowed from the traditional field of system identification as wel as linear filters,time series neural networks and others.