초록

용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

This paper describes a portable electronic nose (e-nose) system for use in the identification of synthesized gasoline, comprised of a single semiconductor type of gas sensor and pattern recognition NNs (neural networks). The designed e-nose system consists of a one-chip microcontroller, a pre-concen...

This paper describes a portable electronic nose (e-nose) system for use in the identification of synthesized gasoline, comprised of a single semiconductor type of gas sensor and pattern recognition NNs (neural networks). The designed e-nose system consists of a one-chip microcontroller, a pre-concentrator, and a gas sensor. A 20 dimensional data set was extracted using a temperature modulation method. A total of 50 measurements were taken, 30 of these measurement data were prepared for a training data set for a neural network and the remaining data was used for the testing data set. Two different NNs, a multi-layer perceptron (MLP) NN and a fuzzy ARTMAP NN were applied to discriminate synthesized gasoline from normal gasoline. The results of the classification showed 100% and 85% recognition rates for the training data set and testing data set, respectively. It was expected that the proposed e-nose system could be a prime candidate for testing due to its simple testing methods.

주제어