Recursive DBPSO for Computationally Efficient Electronic Nose System

Atiq ur Rehman, Amine Bermak

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Feature-rank-code based classifiers have been proposed recently in order to reduce the complexity for Electronic Nose System (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization (DBPSO), a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for identification of thirteen different industrial gases namely C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different datasets; two among these datasets are acquired experimentally in a laboratory setup, while one of these datasets is taken from the UCI machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17% is achieved by the proposed system with an average 69.04% reduction in memory requirement using only three to five features.

Original languageEnglish
JournalIEEE Sensors Journal
DOIs
Publication statusAccepted/In press - 8 Nov 2017

Fingerprint

Particle swarm optimization (PSO)
optimization
Gases
electronics
gases
classifiers
costs
set theory
Classifiers
Data storage equipment
Costs
requirements
machine learning
system identification
Learning systems
Identification (control systems)
Electronic nose

Keywords

  • Computational efficiency
  • Discrete Binary Particle Swarm optimization (DBPSO)
  • Electronic Nose
  • Feature extraction
  • Feature Selection
  • Gas detectors
  • Gases
  • Pattern Recognition
  • Sensor arrays

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Recursive DBPSO for Computationally Efficient Electronic Nose System. / Rehman, Atiq ur; Bermak, Amine.

In: IEEE Sensors Journal, 08.11.2017.

Research output: Contribution to journalArticle

@article{4bd9efbdeb914231b5236064d13e9f9e,
title = "Recursive DBPSO for Computationally Efficient Electronic Nose System",
abstract = "Feature-rank-code based classifiers have been proposed recently in order to reduce the complexity for Electronic Nose System (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization (DBPSO), a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for identification of thirteen different industrial gases namely C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different datasets; two among these datasets are acquired experimentally in a laboratory setup, while one of these datasets is taken from the UCI machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17{\%} is achieved by the proposed system with an average 69.04{\%} reduction in memory requirement using only three to five features.",
keywords = "Computational efficiency, Discrete Binary Particle Swarm optimization (DBPSO), Electronic Nose, Feature extraction, Feature Selection, Gas detectors, Gases, Pattern Recognition, Sensor arrays",
author = "Rehman, {Atiq ur} and Amine Bermak",
year = "2017",
month = "11",
day = "8",
doi = "10.1109/JSEN.2017.2771388",
language = "English",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Recursive DBPSO for Computationally Efficient Electronic Nose System

AU - Rehman, Atiq ur

AU - Bermak, Amine

PY - 2017/11/8

Y1 - 2017/11/8

N2 - Feature-rank-code based classifiers have been proposed recently in order to reduce the complexity for Electronic Nose System (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization (DBPSO), a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for identification of thirteen different industrial gases namely C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different datasets; two among these datasets are acquired experimentally in a laboratory setup, while one of these datasets is taken from the UCI machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17% is achieved by the proposed system with an average 69.04% reduction in memory requirement using only three to five features.

AB - Feature-rank-code based classifiers have been proposed recently in order to reduce the complexity for Electronic Nose System (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization (DBPSO), a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for identification of thirteen different industrial gases namely C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different datasets; two among these datasets are acquired experimentally in a laboratory setup, while one of these datasets is taken from the UCI machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17% is achieved by the proposed system with an average 69.04% reduction in memory requirement using only three to five features.

KW - Computational efficiency

KW - Discrete Binary Particle Swarm optimization (DBPSO)

KW - Electronic Nose

KW - Feature extraction

KW - Feature Selection

KW - Gas detectors

KW - Gases

KW - Pattern Recognition

KW - Sensor arrays

UR - http://www.scopus.com/inward/record.url?scp=85034265197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034265197&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2017.2771388

DO - 10.1109/JSEN.2017.2771388

M3 - Article

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

ER -