Discriminative metrics for gas classification with spike latency coding

Muhammad Hassan, Amine Bermak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A multi-sensor array of the gas sensors is used in order to improve the selectivity of a single sensor and obtain a unique signature. Typically, pattern recognition algorithms are used to find a relationship between the multi-sensor array response and odor class. Theses methods usually accompanied with high computational requirement. Recent results reveal that time of first spike coding exhibits fast and efficient odor identification with reduced computational cost. The objective of this paper is two fold. Firstly, we propose a new probabilistic discriminative metric for assigning an odor class to observed test pattern of first spikes of the sensors in the array. Secondly, we propose the decision boundary criteria for the spike distance algorithm that assesses the spike pattern by comparing its relative distance with training gases. The performance evaluation of these metrics is carried out through experimental data of three different gases. The results show that our proposed metrics display excellent performance as compared to existing pattern recognition algorithms.

Original languageEnglish
Title of host publication13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479939428
DOIs
Publication statusPublished - 30 Sep 2014
Externally publishedYes
Event13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Kota Kinabalu, Malaysia
Duration: 15 Jan 201418 Jan 2014

Other

Other13th International Conference on Electronics, Information, and Communication, ICEIC 2014
CountryMalaysia
CityKota Kinabalu
Period15/1/1418/1/14

Fingerprint

Odors
Sensor arrays
Pattern recognition
Gases
Sensors
Chemical sensors
Costs

Keywords

  • discriminative metric
  • Electronic nose
  • gas sensors
  • spike sequence
  • time of first spike

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Hassan, M., & Bermak, A. (2014). Discriminative metrics for gas classification with spike latency coding. In 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings [6914375] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ELINFOCOM.2014.6914375

Discriminative metrics for gas classification with spike latency coding. / Hassan, Muhammad; Bermak, Amine.

13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. 6914375.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hassan, M & Bermak, A 2014, Discriminative metrics for gas classification with spike latency coding. in 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings., 6914375, Institute of Electrical and Electronics Engineers Inc., 13th International Conference on Electronics, Information, and Communication, ICEIC 2014, Kota Kinabalu, Malaysia, 15/1/14. https://doi.org/10.1109/ELINFOCOM.2014.6914375
Hassan M, Bermak A. Discriminative metrics for gas classification with spike latency coding. In 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. 6914375 https://doi.org/10.1109/ELINFOCOM.2014.6914375
Hassan, Muhammad ; Bermak, Amine. / Discriminative metrics for gas classification with spike latency coding. 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{e2b1541483de4bb886d05942da4d2d0d,
title = "Discriminative metrics for gas classification with spike latency coding",
abstract = "A multi-sensor array of the gas sensors is used in order to improve the selectivity of a single sensor and obtain a unique signature. Typically, pattern recognition algorithms are used to find a relationship between the multi-sensor array response and odor class. Theses methods usually accompanied with high computational requirement. Recent results reveal that time of first spike coding exhibits fast and efficient odor identification with reduced computational cost. The objective of this paper is two fold. Firstly, we propose a new probabilistic discriminative metric for assigning an odor class to observed test pattern of first spikes of the sensors in the array. Secondly, we propose the decision boundary criteria for the spike distance algorithm that assesses the spike pattern by comparing its relative distance with training gases. The performance evaluation of these metrics is carried out through experimental data of three different gases. The results show that our proposed metrics display excellent performance as compared to existing pattern recognition algorithms.",
keywords = "discriminative metric, Electronic nose, gas sensors, spike sequence, time of first spike",
author = "Muhammad Hassan and Amine Bermak",
year = "2014",
month = "9",
day = "30",
doi = "10.1109/ELINFOCOM.2014.6914375",
language = "English",
booktitle = "13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Discriminative metrics for gas classification with spike latency coding

AU - Hassan, Muhammad

AU - Bermak, Amine

PY - 2014/9/30

Y1 - 2014/9/30

N2 - A multi-sensor array of the gas sensors is used in order to improve the selectivity of a single sensor and obtain a unique signature. Typically, pattern recognition algorithms are used to find a relationship between the multi-sensor array response and odor class. Theses methods usually accompanied with high computational requirement. Recent results reveal that time of first spike coding exhibits fast and efficient odor identification with reduced computational cost. The objective of this paper is two fold. Firstly, we propose a new probabilistic discriminative metric for assigning an odor class to observed test pattern of first spikes of the sensors in the array. Secondly, we propose the decision boundary criteria for the spike distance algorithm that assesses the spike pattern by comparing its relative distance with training gases. The performance evaluation of these metrics is carried out through experimental data of three different gases. The results show that our proposed metrics display excellent performance as compared to existing pattern recognition algorithms.

AB - A multi-sensor array of the gas sensors is used in order to improve the selectivity of a single sensor and obtain a unique signature. Typically, pattern recognition algorithms are used to find a relationship between the multi-sensor array response and odor class. Theses methods usually accompanied with high computational requirement. Recent results reveal that time of first spike coding exhibits fast and efficient odor identification with reduced computational cost. The objective of this paper is two fold. Firstly, we propose a new probabilistic discriminative metric for assigning an odor class to observed test pattern of first spikes of the sensors in the array. Secondly, we propose the decision boundary criteria for the spike distance algorithm that assesses the spike pattern by comparing its relative distance with training gases. The performance evaluation of these metrics is carried out through experimental data of three different gases. The results show that our proposed metrics display excellent performance as compared to existing pattern recognition algorithms.

KW - discriminative metric

KW - Electronic nose

KW - gas sensors

KW - spike sequence

KW - time of first spike

UR - http://www.scopus.com/inward/record.url?scp=84910049043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84910049043&partnerID=8YFLogxK

U2 - 10.1109/ELINFOCOM.2014.6914375

DO - 10.1109/ELINFOCOM.2014.6914375

M3 - Conference contribution

BT - 13th International Conference on Electronics, Information, and Communication, ICEIC 2014 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -