Shuffled frog-leaping and weighted cosine similarity for drift correction in gas sensors

Atiq Ur Rehman, Amine Bermak, Mounir Hamdi

Research output: Contribution to journalArticle

Abstract

Artificial Olfactory Systems (AOS) mimic the Biological Olfaction (BO) using sensors and artificial intelligence algorithms. The performance of an AOS is based on the sensitivity and the selectivity of the sensors against the sensed odors. Long term sensors drift is a major problem that brings distortion in the sensitivity of the sensors. Traditional methods to compensate drift, like sensors replacement, successive recalibration or domain transformations are either expensive or not always feasible to use. In order to overcome the issues related to traditional approaches, a novel method based on a sequential classification approach is proposed in this paper, with following contributions: (i) A Tree Structured Cosine Similarity (TSCS) based classification approach is proposed to handle long term sensors drift. (ii) The classifier is embedded within a memetic metaheuristic Shuffled Frog Leaping Optimization (SFLO) approach to optimize the features space. (iii) The proposed approach works as a combinatorial optimization problem that recursively reduces the number of features and increases the classification accuracy of the system, while compensating the drift. (iv) Only median values of optimized features are enough to train the classifier which reduces the computational cost and the memory requirement of the classifier. (v) The proposed approach is purely based on the feature subset selection process for drift compensation without requiring any data samples from target domain or system recalibration, making it suitable for the real life applications. The proposed approach is compared with the existing state-of-The-Art approaches using an extensive experimental dataset and a significant increase in the classification accuracy is observed.

Original languageEnglish
Article number8808894
Pages (from-to)12126-12136
Number of pages11
JournalIEEE Sensors Journal
Volume19
Issue number24
DOIs
Publication statusPublished - 15 Dec 2019

Fingerprint

frogs
Chemical sensors
sensors
Sensors
classifiers
gases
Classifiers
odors
artificial intelligence
optimization
intelligence
sensitivity
Combinatorial optimization
Odors
set theory
Artificial intelligence
selectivity
costs
Data storage equipment
requirements

Keywords

  • Artificial olfaction
  • Cosine similarity
  • Electronic nose
  • Metaheuristics
  • Sensors drift
  • Shuffled frog leaping

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Shuffled frog-leaping and weighted cosine similarity for drift correction in gas sensors. / Rehman, Atiq Ur; Bermak, Amine; Hamdi, Mounir.

In: IEEE Sensors Journal, Vol. 19, No. 24, 8808894, 15.12.2019, p. 12126-12136.

Research output: Contribution to journalArticle

Rehman, Atiq Ur ; Bermak, Amine ; Hamdi, Mounir. / Shuffled frog-leaping and weighted cosine similarity for drift correction in gas sensors. In: IEEE Sensors Journal. 2019 ; Vol. 19, No. 24. pp. 12126-12136.
@article{e309c8e23baf41c4baf47bffd3b6ef5c,
title = "Shuffled frog-leaping and weighted cosine similarity for drift correction in gas sensors",
abstract = "Artificial Olfactory Systems (AOS) mimic the Biological Olfaction (BO) using sensors and artificial intelligence algorithms. The performance of an AOS is based on the sensitivity and the selectivity of the sensors against the sensed odors. Long term sensors drift is a major problem that brings distortion in the sensitivity of the sensors. Traditional methods to compensate drift, like sensors replacement, successive recalibration or domain transformations are either expensive or not always feasible to use. In order to overcome the issues related to traditional approaches, a novel method based on a sequential classification approach is proposed in this paper, with following contributions: (i) A Tree Structured Cosine Similarity (TSCS) based classification approach is proposed to handle long term sensors drift. (ii) The classifier is embedded within a memetic metaheuristic Shuffled Frog Leaping Optimization (SFLO) approach to optimize the features space. (iii) The proposed approach works as a combinatorial optimization problem that recursively reduces the number of features and increases the classification accuracy of the system, while compensating the drift. (iv) Only median values of optimized features are enough to train the classifier which reduces the computational cost and the memory requirement of the classifier. (v) The proposed approach is purely based on the feature subset selection process for drift compensation without requiring any data samples from target domain or system recalibration, making it suitable for the real life applications. The proposed approach is compared with the existing state-of-The-Art approaches using an extensive experimental dataset and a significant increase in the classification accuracy is observed.",
keywords = "Artificial olfaction, Cosine similarity, Electronic nose, Metaheuristics, Sensors drift, Shuffled frog leaping",
author = "Rehman, {Atiq Ur} and Amine Bermak and Mounir Hamdi",
year = "2019",
month = "12",
day = "15",
doi = "10.1109/JSEN.2019.2936602",
language = "English",
volume = "19",
pages = "12126--12136",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "24",

}

TY - JOUR

T1 - Shuffled frog-leaping and weighted cosine similarity for drift correction in gas sensors

AU - Rehman, Atiq Ur

AU - Bermak, Amine

AU - Hamdi, Mounir

PY - 2019/12/15

Y1 - 2019/12/15

N2 - Artificial Olfactory Systems (AOS) mimic the Biological Olfaction (BO) using sensors and artificial intelligence algorithms. The performance of an AOS is based on the sensitivity and the selectivity of the sensors against the sensed odors. Long term sensors drift is a major problem that brings distortion in the sensitivity of the sensors. Traditional methods to compensate drift, like sensors replacement, successive recalibration or domain transformations are either expensive or not always feasible to use. In order to overcome the issues related to traditional approaches, a novel method based on a sequential classification approach is proposed in this paper, with following contributions: (i) A Tree Structured Cosine Similarity (TSCS) based classification approach is proposed to handle long term sensors drift. (ii) The classifier is embedded within a memetic metaheuristic Shuffled Frog Leaping Optimization (SFLO) approach to optimize the features space. (iii) The proposed approach works as a combinatorial optimization problem that recursively reduces the number of features and increases the classification accuracy of the system, while compensating the drift. (iv) Only median values of optimized features are enough to train the classifier which reduces the computational cost and the memory requirement of the classifier. (v) The proposed approach is purely based on the feature subset selection process for drift compensation without requiring any data samples from target domain or system recalibration, making it suitable for the real life applications. The proposed approach is compared with the existing state-of-The-Art approaches using an extensive experimental dataset and a significant increase in the classification accuracy is observed.

AB - Artificial Olfactory Systems (AOS) mimic the Biological Olfaction (BO) using sensors and artificial intelligence algorithms. The performance of an AOS is based on the sensitivity and the selectivity of the sensors against the sensed odors. Long term sensors drift is a major problem that brings distortion in the sensitivity of the sensors. Traditional methods to compensate drift, like sensors replacement, successive recalibration or domain transformations are either expensive or not always feasible to use. In order to overcome the issues related to traditional approaches, a novel method based on a sequential classification approach is proposed in this paper, with following contributions: (i) A Tree Structured Cosine Similarity (TSCS) based classification approach is proposed to handle long term sensors drift. (ii) The classifier is embedded within a memetic metaheuristic Shuffled Frog Leaping Optimization (SFLO) approach to optimize the features space. (iii) The proposed approach works as a combinatorial optimization problem that recursively reduces the number of features and increases the classification accuracy of the system, while compensating the drift. (iv) Only median values of optimized features are enough to train the classifier which reduces the computational cost and the memory requirement of the classifier. (v) The proposed approach is purely based on the feature subset selection process for drift compensation without requiring any data samples from target domain or system recalibration, making it suitable for the real life applications. The proposed approach is compared with the existing state-of-The-Art approaches using an extensive experimental dataset and a significant increase in the classification accuracy is observed.

KW - Artificial olfaction

KW - Cosine similarity

KW - Electronic nose

KW - Metaheuristics

KW - Sensors drift

KW - Shuffled frog leaping

UR - http://www.scopus.com/inward/record.url?scp=85076410040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076410040&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2019.2936602

DO - 10.1109/JSEN.2019.2936602

M3 - Article

AN - SCOPUS:85076410040

VL - 19

SP - 12126

EP - 12136

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 24

M1 - 8808894

ER -