FPGA based run time reconfigurable gas discrimination system

M. Shi, S. Chandrasekaran, Amine Bermak, A. Amira

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

1 Citation (Scopus)

Abstract

In this paper a gas discrimination system based Analon five classification algorithms including K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RBF), Gaussian Mixture Model (GMM) and Probabilistic Principal Component Analysis (PPCA) has been presented. A Committee Machine (CM) is used in which the results from each classifier are first transformed to confidences and then a weighted combination rule is used to generate the final decision result. In order to overcome the problem of very high computational complexity of the CM requiring large amount of hardware resources, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable Field Programmable Gate Array (FPGA) platform. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

Original languageEnglish
Title of host publication2007 International Symposium on Integrated Circuits, ISIC
Pages180-183
Number of pages4
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 International Symposium on Integrated Circuits, ISIC - Singapore, Singapore
Duration: 26 Sep 200728 Sep 2007

Other

Other2007 International Symposium on Integrated Circuits, ISIC
CountrySingapore
CitySingapore
Period26/9/0728/9/07

Fingerprint

Field programmable gate arrays (FPGA)
Hardware
Multilayer neural networks
Tin oxides
Chemical sensors
Gases
Multiplexing
Principal component analysis
Computational complexity
Classifiers

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Shi, M., Chandrasekaran, S., Bermak, A., & Amira, A. (2007). FPGA based run time reconfigurable gas discrimination system. In 2007 International Symposium on Integrated Circuits, ISIC (pp. 180-183). [4441827] https://doi.org/10.1109/ISICIR.2007.4441827

FPGA based run time reconfigurable gas discrimination system. / Shi, M.; Chandrasekaran, S.; Bermak, Amine; Amira, A.

2007 International Symposium on Integrated Circuits, ISIC. 2007. p. 180-183 4441827.

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

Shi, M, Chandrasekaran, S, Bermak, A & Amira, A 2007, FPGA based run time reconfigurable gas discrimination system. in 2007 International Symposium on Integrated Circuits, ISIC., 4441827, pp. 180-183, 2007 International Symposium on Integrated Circuits, ISIC, Singapore, Singapore, 26/9/07. https://doi.org/10.1109/ISICIR.2007.4441827
Shi M, Chandrasekaran S, Bermak A, Amira A. FPGA based run time reconfigurable gas discrimination system. In 2007 International Symposium on Integrated Circuits, ISIC. 2007. p. 180-183. 4441827 https://doi.org/10.1109/ISICIR.2007.4441827
Shi, M. ; Chandrasekaran, S. ; Bermak, Amine ; Amira, A. / FPGA based run time reconfigurable gas discrimination system. 2007 International Symposium on Integrated Circuits, ISIC. 2007. pp. 180-183
@inproceedings{a76a0acd51fa46819463c7df128b5c82,
title = "FPGA based run time reconfigurable gas discrimination system",
abstract = "In this paper a gas discrimination system based Analon five classification algorithms including K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RBF), Gaussian Mixture Model (GMM) and Probabilistic Principal Component Analysis (PPCA) has been presented. A Committee Machine (CM) is used in which the results from each classifier are first transformed to confidences and then a weighted combination rule is used to generate the final decision result. In order to overcome the problem of very high computational complexity of the CM requiring large amount of hardware resources, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable Field Programmable Gate Array (FPGA) platform. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.",
author = "M. Shi and S. Chandrasekaran and Amine Bermak and A. Amira",
year = "2007",
doi = "10.1109/ISICIR.2007.4441827",
language = "English",
isbn = "1424407974",
pages = "180--183",
booktitle = "2007 International Symposium on Integrated Circuits, ISIC",

}

TY - GEN

T1 - FPGA based run time reconfigurable gas discrimination system

AU - Shi, M.

AU - Chandrasekaran, S.

AU - Bermak, Amine

AU - Amira, A.

PY - 2007

Y1 - 2007

N2 - In this paper a gas discrimination system based Analon five classification algorithms including K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RBF), Gaussian Mixture Model (GMM) and Probabilistic Principal Component Analysis (PPCA) has been presented. A Committee Machine (CM) is used in which the results from each classifier are first transformed to confidences and then a weighted combination rule is used to generate the final decision result. In order to overcome the problem of very high computational complexity of the CM requiring large amount of hardware resources, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable Field Programmable Gate Array (FPGA) platform. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

AB - In this paper a gas discrimination system based Analon five classification algorithms including K Nearest Neighbors (KNN), Multi-layer Perceptron (MLP), Radial Basis Function (RBF), Gaussian Mixture Model (GMM) and Probabilistic Principal Component Analysis (PPCA) has been presented. A Committee Machine (CM) is used in which the results from each classifier are first transformed to confidences and then a weighted combination rule is used to generate the final decision result. In order to overcome the problem of very high computational complexity of the CM requiring large amount of hardware resources, we propose a novel time multiplexing hardware implementation using a dynamically reconfigurable Field Programmable Gate Array (FPGA) platform. The system is successfully tested for combustible gas identification application using our in-house tin-oxide gas sensors.

UR - http://www.scopus.com/inward/record.url?scp=51549087349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51549087349&partnerID=8YFLogxK

U2 - 10.1109/ISICIR.2007.4441827

DO - 10.1109/ISICIR.2007.4441827

M3 - Conference contribution

AN - SCOPUS:51549087349

SN - 1424407974

SN - 9781424407972

SP - 180

EP - 183

BT - 2007 International Symposium on Integrated Circuits, ISIC

ER -