Detail publikace

Unveiling the Smell Inspector and Machine Learning Methods for Smell Recognition

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

Originální název

Unveiling the Smell Inspector and Machine Learning Methods for Smell Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

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

Vydáno

5. 12. 2023

Nakladatel

IEEE Computer Society

Místo

Ghent

ISBN

979-8-3503-9328-6

Kniha

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

Strany od

182

Strany do

187

Strany počet

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"
}