Publication detail

Unveiling the Smell Inspector and Machine Learning Methods for Smell Recognition

KŘÍŽ, P. SIKORA, P. ŘÍHA, K. BURGET, R.

Original Title

Unveiling the Smell Inspector and Machine Learning Methods for Smell Recognition

Type

conference paper

Language

English

Original Abstract

This paper presents the implementation of an odor classifier that utilizes various machine learning algorithms, including MLP models, LSTM models, Random Forest and XGBoost. These algorithms are applied to a small training dataset obtained from the Smell Inspector sensor, developed by SmartNanotubes Technologies. Study focuses primarily on the classification of five distinct smell substances: air, chlorinated water, vinegar, rum, and coffee, into their respective classes. The best proposed approach achieves a maximum accuracy of 92 percent in this classification task. To further enhance the classification task, binary classifiers are specifically tested to distinguish between air and the remaining substances, representing normal versus abnormal smell conditions. The best binary classifier achieves an accuracy of 97 percent.

Keywords

smell recognition, e-nose implementation, Smell Inspector, decision tree algorithms, machine learning, deep learning

Authors

KŘÍŽ, P.; SIKORA, P.; ŘÍHA, K.; BURGET, R.

Released

5. 12. 2023

Publisher

IEEE Computer Society

Location

Ghent

ISBN

979-8-3503-9328-6

Book

2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

Pages from

182

Pages to

187

Pages count

6

URL

https://ieeexplore.ieee.org/document/10333105

BibTex

@inproceedings{BUT185660,
  author="Petr {Kříž} and Pavel {Sikora} and Kamil {Říha} and Radim {Burget}",
  title="Unveiling the Smell Inspector and Machine Learning Methods for Smell Recognition",
  booktitle="2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  year="2023",
  pages="182--187",
  publisher="IEEE Computer Society",
  address="Ghent",
  doi="10.1109/ICUMT61075.2023.10333105",
  isbn="979-8-3503-9328-6",
  url="https://ieeexplore.ieee.org/document/10333105"
}