| Paper: | MLSP-P7.6 | ||
| Session: | Pattern Recognition and Classification II | ||
| Time: | Friday, May 21, 15:30 - 17:30 | ||
| Presentation: | Poster | ||
| Topic: | Machine Learning for Signal Processing: Signal detection, Pattern Recognition and Classification | ||
| Title: | GAS IDENTIFICATION WITH MICROELECTRONIC GAS SENSOR IN PRESENCE OF DRIFT USING ROBUST GMM | ||
| Authors: | Sofiane Brahim-Belhouari; Hong Kong University of Science and Technology | ||
| Amine Bermak; Hong Kong University of Science and Technology | |||
| Philip C. H. Chan; Hong Kong University of Science and Technology | |||
| Abstract: | The pattern recognition problem for real life applications of gasidentification is particularly challenging due to the small amountof data available and the temporal variability of the instrumentmainly caused by drift. In this paper we present a gasidentification approach based on class-conditional densityestimation using Gaussian mixture models (GMM). A driftcounteraction approach based on extracting robust feature using asimulated drift is proposed. The performance of the retrained GMMshows the effectiveness of the new approach in improving theclassification performance in the presence of artificial drift. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops