Selection of suitable sensors of the electronic nose used for classification of myocardial infarction, stable coronary artery disease and healthy individuals

Ahmet Yilmaz, Cemaleddin Simsek, Bilge Han Tozlu, Onder Aydemir, Yusuf Karavelioglu


In recent years, disease diagnosis support systems using various machine learning algorithms have become quite common. Electronic nose systems containing various chemical sensors have also been used and such systems generally focused on the diagnosis of lung-based diseases. Most of the chemical sensors used in such studies are of the type that detects volatile organic compounds rather than the type that detects a specific component. For this reason, general purpose electronic noses are mostly used in such studies, but this means processing a large amount of data and using unnecessary resources including extra gas sensors. In this study, we focused on without loss of performance the reduction of sensors used in the classification of myocardial infarction, stable coronary artery disease and healthy individuals' breaths taken with a general purpose electronic nose containing 19 gas sensors. In order to achieve the goal, we applied a standard genetic algorithm technique to a neural network classifier. The results show that instead of the 19 gas sensors used in the reference study, it is sufficient to use 5 sensors in the same general purpose electronic nose which seems promising when compared in terms of cost and complexity.


Classification; Electronic nose; Genetic algorithms; Myocardial infarction; Stable coronary artery disease

Full Text:


Article Metrics

Metrics Loading ...

Metrics powered by PLOS ALM


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Selcuk University Journal of Engineering Sciences (SUJES) ISSN:2757-8828

Abstracting and indexing

Index Copernicus International


Selcuk university journal of engineering sciences (Online)

ICI World of Journals


Eurasian Scientific Journal Index