کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
751242 | 895212 | 2010 | 9 صفحه PDF | دانلود رایگان |
A gas-sensor optimization scheme for odor discrimination is introduced in this paper. We formulate the odor class separability in terms of a fundamental tool in information theory, namely the Kullback–Leibler distance (KL-distance), which gives a quantitative measure of the mutual difference between two probability distributions. We argue that maximizing this measure over a controllable operating parameter of a sensing element promotes robust odor discrimination. We demonstrate on a sample dataset that tuning the operating temperature of a metal oxide sensor based on the suggested criterion not only yields a substantial improvement in classification performance but also informs about those operating temperatures that cause a total confusion in the odor discrimination.
Journal: Sensors and Actuators B: Chemical - Volume 148, Issue 1, 30 June 2010, Pages 298–306