An Improved Gas Classification Technique Using New Features and Support Vector Machines

Se-Jong Kang, Jae-Young Kim, In-Kyu Jeong, M. M. Manjurul Islam, Kichang Im, Jong-Myon Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, we propose a gas classification technique based on extracting new features and support vector machines (SVM) in a chemical plant. First, various gases are collected using semiconductor gas seniors, and then we calculate the composition ratio of these gasses, which are defined as features. These extracted features are highly discriminative and quantify the presence of gas. Moreover, these features are used as the SVM input for classifying gas types. In addition, we apply a grid search technique in SVM for tuning hyper-parameters such as misclassification rate, C, and kernel bandwidth, σ, to improve the classification performance. To verify the proposed technique, we collect various gases composition using a cost-effective self-designed test rig. The experimental results indicate that the proposed method is highly capable of classifying various hazardous gases with good accuracy.
Original languageEnglish
Title of host publicationProceedings of the Tenth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2018)
Pages158–166
Number of pages9
ISBN (Electronic)978-3-030-17065-3
DOIs
Publication statusPublished (in print/issue) - 10 Apr 2019
EventInternational Conference on Soft Computing and Pattern Recognition - Porto, Portugal
Duration: 13 Dec 201815 Dec 2018
Conference number: 2018
https://link.springer.com/conference/socpar

Publication series

NameAdvances in Intelligent systems and Computing
Volume942
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceInternational Conference on Soft Computing and Pattern Recognition
Abbreviated titleSoCPaR
Country/TerritoryPortugal
CityPorto
Period13/12/1815/12/18
Internet address

Keywords

  • Feature extraction
  • Gas sensor array
  • Gas classification
  • Support vector machine
  • Chemical plants

Fingerprint

Dive into the research topics of 'An Improved Gas Classification Technique Using New Features and Support Vector Machines'. Together they form a unique fingerprint.

Cite this