A Perera

Learn More
In this paper we propose a new technique for feature extraction/selection based on the projection of sensor features in class space and taking into account the sensor variance. The proposed technique is inspired by the organization of the early stages in the biological olfactory system, and proves to be highly suitable for high-dimensional feature vectors(More)
  • R Gutierrez-Osuna, S Korah, A Perera
  • 2001
This article presents an empirical study of temperature modulation for metal-oxide gas sensors at multiple frequencies ranging from 0.125Hz to 4Hz. Commercial metal-oxide sensors from two manufacturers were exposed to analyte concentrations below their isothermal discrimination threshold over a period of ten days. The results reported in this article(More)
Two dimensionality reduction techniques are widely used to analyze data from chemical sensor arrays: Fisher's Linear Discriminants Analysis (LDA) and Principal Components Analysis (PCA). LDA finds the directions of maximum discrimination in classification problems, but has a tendency to overfit when the ratio of training samples to dimensionality is low, as(More)
This article presents a novel dimensionality-reduction technique, Regularized Non-negative Matrix Factorization (RNMF), which combines the non-negativity constraint of NMF with a regularization term. In contrast with NMF, which degrades to holistic representations with decreasing amount of data, RNMF is able to extract parts of objects even in the(More)
+ + Most electronic noses need a computer and special software in order to analyze data from sensors. In the case of portable electronic noses, most of them are operated by microcontrollers with limited data storage (usually feature vectors) and simple signal processing capabilities. Here we suggest the integration of a small form factor computer inside the(More)
  • 1