Swarm Intelligence and Similarity Measures for Memory Efficient Electronic Nose System

Atiq Ur Rehman, Amine Bermak

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Recursive discrete binary particle swarm optimization (RDBPSO) with Euclidean distance as a fitness function was recently proposed for the electronic nose system (ENS). It demonstrated a significant reduction in the memory requirement and the response time of the system using optimum subset of features. To further enhance the memory requirement and response time of the ENS, this paper proposes some new fitness functions for RDBPSO with following merits: 1) a novel approach based on different similarity measures is proposed with improved memory efficiency and response time of the ENS; 2) feature augmentation strategy that combines the original sensors response and some extracted features is incorporated, which enhances the learning process; 3) the proposed algorithm utilizes only the median values of the training data, which makes the system memory efficient and feasible for portable use; and 4) optimization of features vector using RDBPSO maintains the classification accuracy high, even with a reduced number of features. The proposed algorithm is validated against four different data sets of gases and mixtures of gases. Two of these data sets are experimentally acquired from a laboratory setup, while other two are publically available on the University of California, Irvine machine learning online repository. Validation results reveal an average of 96.77% decrease in the memory requirement, while an average classification accuracy of 98.73% is achieved for all the four data sets.

Original languageEnglish
Pages (from-to)2471-2482
Number of pages12
JournalIEEE Sensors Journal
Volume18
Issue number6
DOIs
Publication statusPublished - 15 Mar 2018

Fingerprint

intelligence
Response time (computer systems)
Data storage equipment
Particle swarm optimization (PSO)
electronics
optimization
fitness
requirements
machine learning
Gases
gases
learning
set theory
Learning systems
Computer systems
education
Swarm intelligence
Electronic nose
augmentation
sensors

Keywords

  • Electronic nose
  • fitness functions
  • gas discrimination
  • gas sensors
  • RDBPSO
  • swarm intelligence

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Swarm Intelligence and Similarity Measures for Memory Efficient Electronic Nose System. / Ur Rehman, Atiq; Bermak, Amine.

In: IEEE Sensors Journal, Vol. 18, No. 6, 15.03.2018, p. 2471-2482.

Research output: Contribution to journalArticle

@article{f42645c453f24159ba5d3ceb8362c803,
title = "Swarm Intelligence and Similarity Measures for Memory Efficient Electronic Nose System",
abstract = "Recursive discrete binary particle swarm optimization (RDBPSO) with Euclidean distance as a fitness function was recently proposed for the electronic nose system (ENS). It demonstrated a significant reduction in the memory requirement and the response time of the system using optimum subset of features. To further enhance the memory requirement and response time of the ENS, this paper proposes some new fitness functions for RDBPSO with following merits: 1) a novel approach based on different similarity measures is proposed with improved memory efficiency and response time of the ENS; 2) feature augmentation strategy that combines the original sensors response and some extracted features is incorporated, which enhances the learning process; 3) the proposed algorithm utilizes only the median values of the training data, which makes the system memory efficient and feasible for portable use; and 4) optimization of features vector using RDBPSO maintains the classification accuracy high, even with a reduced number of features. The proposed algorithm is validated against four different data sets of gases and mixtures of gases. Two of these data sets are experimentally acquired from a laboratory setup, while other two are publically available on the University of California, Irvine machine learning online repository. Validation results reveal an average of 96.77{\%} decrease in the memory requirement, while an average classification accuracy of 98.73{\%} is achieved for all the four data sets.",
keywords = "Electronic nose, fitness functions, gas discrimination, gas sensors, RDBPSO, swarm intelligence",
author = "{Ur Rehman}, Atiq and Amine Bermak",
year = "2018",
month = "3",
day = "15",
doi = "10.1109/JSEN.2018.2799611",
language = "English",
volume = "18",
pages = "2471--2482",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Swarm Intelligence and Similarity Measures for Memory Efficient Electronic Nose System

AU - Ur Rehman, Atiq

AU - Bermak, Amine

PY - 2018/3/15

Y1 - 2018/3/15

N2 - Recursive discrete binary particle swarm optimization (RDBPSO) with Euclidean distance as a fitness function was recently proposed for the electronic nose system (ENS). It demonstrated a significant reduction in the memory requirement and the response time of the system using optimum subset of features. To further enhance the memory requirement and response time of the ENS, this paper proposes some new fitness functions for RDBPSO with following merits: 1) a novel approach based on different similarity measures is proposed with improved memory efficiency and response time of the ENS; 2) feature augmentation strategy that combines the original sensors response and some extracted features is incorporated, which enhances the learning process; 3) the proposed algorithm utilizes only the median values of the training data, which makes the system memory efficient and feasible for portable use; and 4) optimization of features vector using RDBPSO maintains the classification accuracy high, even with a reduced number of features. The proposed algorithm is validated against four different data sets of gases and mixtures of gases. Two of these data sets are experimentally acquired from a laboratory setup, while other two are publically available on the University of California, Irvine machine learning online repository. Validation results reveal an average of 96.77% decrease in the memory requirement, while an average classification accuracy of 98.73% is achieved for all the four data sets.

AB - Recursive discrete binary particle swarm optimization (RDBPSO) with Euclidean distance as a fitness function was recently proposed for the electronic nose system (ENS). It demonstrated a significant reduction in the memory requirement and the response time of the system using optimum subset of features. To further enhance the memory requirement and response time of the ENS, this paper proposes some new fitness functions for RDBPSO with following merits: 1) a novel approach based on different similarity measures is proposed with improved memory efficiency and response time of the ENS; 2) feature augmentation strategy that combines the original sensors response and some extracted features is incorporated, which enhances the learning process; 3) the proposed algorithm utilizes only the median values of the training data, which makes the system memory efficient and feasible for portable use; and 4) optimization of features vector using RDBPSO maintains the classification accuracy high, even with a reduced number of features. The proposed algorithm is validated against four different data sets of gases and mixtures of gases. Two of these data sets are experimentally acquired from a laboratory setup, while other two are publically available on the University of California, Irvine machine learning online repository. Validation results reveal an average of 96.77% decrease in the memory requirement, while an average classification accuracy of 98.73% is achieved for all the four data sets.

KW - Electronic nose

KW - fitness functions

KW - gas discrimination

KW - gas sensors

KW - RDBPSO

KW - swarm intelligence

UR - http://www.scopus.com/inward/record.url?scp=85041392969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041392969&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2018.2799611

DO - 10.1109/JSEN.2018.2799611

M3 - Article

VL - 18

SP - 2471

EP - 2482

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 6

ER -