Font Size: a A A

Research On Method And Theory Of Electronic Nose In Human Odor Detection

Posted on:2008-12-17Degree:MasterType:Thesis
Country:ChinaCandidate:K CengFull Text:PDF
GTID:2178360215971317Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
Nowadays, the study of disaster emergency and rescue techniques are drawing more and more attention all over the world. This paper "Research on Method and Theory of Electronic Nose in Human Odor Detection" is funded by Sichuan province research project "The Theory and Method Study on Disaster Life Search and Rescue" and the Minister of Education fundamental Doctor's Degree research subject "Research on the Theory of new kind of Disaster Search and Rescue Methods". It's an important question in disaster rescue that how to find and rescue people in danger after the disaster. The means of rescue based on sense, touch, and vision have been well developed, such as sonic vibration life detector, infra life detector, optics life detector, low frequency electromagnetic life detector and rescue robot. In the field of olfactory sense, we don't have better means than the sensitive dog nose. The electronic nose has been widely used in our life, but it's a unsolved problem that weather it can be used in life rescue.The following are discussed in this paper:1. Why the electronic nose are used in the life rescue.2. The nature and main components of human odor are summarized, as well as the differences in kinds of racial.3. Fifty group of human odor data, which are from people at different ages and form different genders are collected by the electronic nose PEN3, and the human odor parameter model are established with the collected data.4. Firstly, the control rules are established based on expert's experience and the result of human odor detection, and grammar rules of fuzzy system is established. By means of the FIS in the Matlab, fuzzy inference system is established, and the probability of confirming the people is given. Secondly, combining with the fuzzy system, the ANFIS is established. Using the ANFIS editor in the Matlab and BP algorithm, the SUGENO type fuzzy inference system's parameter is optimized5. The differences between fuzzy system and the ANFIS is compared, as well as their advantage and disadvantage. The possibility of the electronic nose using in human odor detection is validated through the experiment and its data.
Keywords/Search Tags:electronic nose, disaster rescue, human odor, sensor array
PDF Full Text Request
Related items