Electrotechnical and Computer Engineering
Vol. 37 No. 04 (2022): Proceedings of the Faculty of Technical Sciences
SENSOR FAULT CLASSIFICATION USING MACHINE LEARNING METHODS
Abstract
This paper describes temperature sensors and the most common faults on sensors. Three machine learning methods for clasification are also described. Methods that has beed used are: K Nearest Neighbors, Support Vector Machines and Neural Networks. The analysis of the mentioned clasification methods of the sensor fault is presented and a comparison of the obtained results is given.
References
[1] M. Popović „Senzori u robotici “, Viša elektrotehnička škola, Beograd, 1996
[2] S. U. Jan, I. Koo, „A Novel Feature Selection Scheme and a Diversified-Input SVM-Based Classifier for Sensor Fault Classification “
[3] S. U. Jan, Y. D. Lee, I. S. Koo, „A distributed sensor-fault detection and diagnosis framework using machine learning“
[4] S. U. Jan, Y.-D. Lee, J. Shin, and I. Koo, „Sensor fault classification based on support vector machine and statistical time-domain features “
[5] B. Nikolić, D. Drašković „Nastavni materijali iz predmeta Inteligentni sistemi “, ETF, Beograd 2021.
[6] M. Nikolić, A. Zečević „Mašinsko učenje “, Matematički fakultet, Beograd 2019.
[7] Y. Zhang „Support Vector Machine Classification Algorithm and Its Application “