Title :
Research on the recognition of chemical odour information based on probabilistic neural networks
Author :
Zhou, Jianhui ; Lei, Wang ; Teng, Jionghua ; Tao, Zhou
Author_Institution :
Coll. of Electron. & Inf. Eng., TongJi Univ., Shanghai, China
Abstract :
An electronic nose is an intelligent instrument which identifies the chemical odours mimicking a human. Now the majority of electronic noses could only identify the specific species, however the human olfactory system is able to characterize and classify many different kinds of odours. This problem has prevented them from being used in wider commercial fields. The pattern recognition methods based on the probabilistic neural networks (PNN) are studied in the following experiments. The electronic nose systems designed could identify all the samples of beer, fruit juice and milk successfully in the experiments. The results of the experiments showed that the researched systems have a better classification and generalization capacity.
Keywords :
chemical technology; electronic noses; pattern recognition; chemical odour information recognition; electronic nose; human olfactory system; intelligent instrument; pattern recognition; probabilistic neural networks; Educational institutions; Gold; Pipelines; electronic nose; pattern recognition; probabilistic neural networks;
Conference_Titel :
Environmental Science and Information Application Technology (ESIAT), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-7387-8
DOI :
10.1109/ESIAT.2010.5567460