Heuristic Random Forests (HRF) for Drift Compensation in Electronic Nose Applications

Atiq ur Rehman, Amine Bermak

Research output: Contribution to journalArticle

Abstract

Electronic nose is an instrument equipped with chemical gas sensors and is used to sense, identify and measure different odors. The problem arises when these sensors incorporate drift by the passage of time. The effect of drift is so adverse that the pattern recognition algorithms used for identification and measurement of odors fail to respond accurately. To overcome the challenge of drift in sensors, one of the most widely used techniques is system re-calibration, which is a cumbersome process. Keeping in mind the challenges of drift and issues of system re-calibration for real life applications, this paper proposes a novel method to compensate drift in gas sensors with following contributions: (i) The fitness function of a recursive metaheuristic optimization method is modified by embedding Random Forests learning for quantification of six different gases under drift, (ii) The proposed approach is able to compensate the long term sensors drift without requiring any system re-calibration, (iii) The feature vector exploitation using Particle Swarm Optimization (PSO) reduces the computational complexity and increases the prediction accuracy of the system. A comparison is provided with different state-of-the-art approaches and the proposed approach is found better in terms of prediction accuracy when tested on a benchmark dataset publically available.

Original languageEnglish
JournalIEEE Sensors Journal
DOIs
Publication statusAccepted/In press - 1 Jan 2018

Fingerprint

Chemical sensors
Odors
Calibration
Sensors
electronics
sensors
odors
Particle swarm optimization (PSO)
Pattern recognition
Computational complexity
gases
optimization
fitness
Gases
exploitation
predictions
Electronic nose
Compensation and Redress
pattern recognition
embedding

Keywords

  • Concentration estimation
  • Electronic Nose
  • Feature extraction
  • Forestry
  • Gas detectors
  • Heuristic Random Forest
  • Industrial Gases
  • Machine learning
  • Sensor arrays
  • Sensor Drift
  • Sensor phenomena and characterization
  • Volatile Organic Compounds

ASJC Scopus subject areas

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Heuristic Random Forests (HRF) for Drift Compensation in Electronic Nose Applications. / Rehman, Atiq ur; Bermak, Amine.

In: IEEE Sensors Journal, 01.01.2018.

Research output: Contribution to journalArticle

@article{96b7a10080b349c7b44066098df66d30,
title = "Heuristic Random Forests (HRF) for Drift Compensation in Electronic Nose Applications",
abstract = "Electronic nose is an instrument equipped with chemical gas sensors and is used to sense, identify and measure different odors. The problem arises when these sensors incorporate drift by the passage of time. The effect of drift is so adverse that the pattern recognition algorithms used for identification and measurement of odors fail to respond accurately. To overcome the challenge of drift in sensors, one of the most widely used techniques is system re-calibration, which is a cumbersome process. Keeping in mind the challenges of drift and issues of system re-calibration for real life applications, this paper proposes a novel method to compensate drift in gas sensors with following contributions: (i) The fitness function of a recursive metaheuristic optimization method is modified by embedding Random Forests learning for quantification of six different gases under drift, (ii) The proposed approach is able to compensate the long term sensors drift without requiring any system re-calibration, (iii) The feature vector exploitation using Particle Swarm Optimization (PSO) reduces the computational complexity and increases the prediction accuracy of the system. A comparison is provided with different state-of-the-art approaches and the proposed approach is found better in terms of prediction accuracy when tested on a benchmark dataset publically available.",
keywords = "Concentration estimation, Electronic Nose, Feature extraction, Forestry, Gas detectors, Heuristic Random Forest, Industrial Gases, Machine learning, Sensor arrays, Sensor Drift, Sensor phenomena and characterization, Volatile Organic Compounds",
author = "Rehman, {Atiq ur} and Amine Bermak",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/JSEN.2018.2881745",
language = "English",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Heuristic Random Forests (HRF) for Drift Compensation in Electronic Nose Applications

AU - Rehman, Atiq ur

AU - Bermak, Amine

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Electronic nose is an instrument equipped with chemical gas sensors and is used to sense, identify and measure different odors. The problem arises when these sensors incorporate drift by the passage of time. The effect of drift is so adverse that the pattern recognition algorithms used for identification and measurement of odors fail to respond accurately. To overcome the challenge of drift in sensors, one of the most widely used techniques is system re-calibration, which is a cumbersome process. Keeping in mind the challenges of drift and issues of system re-calibration for real life applications, this paper proposes a novel method to compensate drift in gas sensors with following contributions: (i) The fitness function of a recursive metaheuristic optimization method is modified by embedding Random Forests learning for quantification of six different gases under drift, (ii) The proposed approach is able to compensate the long term sensors drift without requiring any system re-calibration, (iii) The feature vector exploitation using Particle Swarm Optimization (PSO) reduces the computational complexity and increases the prediction accuracy of the system. A comparison is provided with different state-of-the-art approaches and the proposed approach is found better in terms of prediction accuracy when tested on a benchmark dataset publically available.

AB - Electronic nose is an instrument equipped with chemical gas sensors and is used to sense, identify and measure different odors. The problem arises when these sensors incorporate drift by the passage of time. The effect of drift is so adverse that the pattern recognition algorithms used for identification and measurement of odors fail to respond accurately. To overcome the challenge of drift in sensors, one of the most widely used techniques is system re-calibration, which is a cumbersome process. Keeping in mind the challenges of drift and issues of system re-calibration for real life applications, this paper proposes a novel method to compensate drift in gas sensors with following contributions: (i) The fitness function of a recursive metaheuristic optimization method is modified by embedding Random Forests learning for quantification of six different gases under drift, (ii) The proposed approach is able to compensate the long term sensors drift without requiring any system re-calibration, (iii) The feature vector exploitation using Particle Swarm Optimization (PSO) reduces the computational complexity and increases the prediction accuracy of the system. A comparison is provided with different state-of-the-art approaches and the proposed approach is found better in terms of prediction accuracy when tested on a benchmark dataset publically available.

KW - Concentration estimation

KW - Electronic Nose

KW - Feature extraction

KW - Forestry

KW - Gas detectors

KW - Heuristic Random Forest

KW - Industrial Gases

KW - Machine learning

KW - Sensor arrays

KW - Sensor Drift

KW - Sensor phenomena and characterization

KW - Volatile Organic Compounds

UR - http://www.scopus.com/inward/record.url?scp=85056719234&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056719234&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2018.2881745

DO - 10.1109/JSEN.2018.2881745

M3 - Article

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

ER -