[ Clasificación y Clustering de Series de Tiempo para Predicción del Comportamiento de Voltaje de Vehículos almacenados en Patios Automotrices ]
Volume 44, Issue 2, September 2019, Pages 123–130
Carolina Flores Peralta1, Perfecto M. Quintero F.2, and Rodolfo Eleazar Pérez Loaiza3
1 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
2 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
3 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
Original language: Spanish
Copyright © 2019 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
An Automotive Yard stores a big number of vehicles that stay in the site for different intervals of time (days, weeks or months), requering preventive maintenance during their stay. Through Internet of Things Sensors, the battery voltage of each vehicle is recorded every day generating a large data transformed into time series to analyze it. Classification and Clustering Algorithms based on K-Nearest Neighbors were developed using scikit-learn tool, for the extraction of knowledge from the IoT Data, specifically battery voltaje behavior patterns according to certain vehicle models. The performance of the algorithms was obtained making a comparison between them. The information founded will be of help for the planning of preventive maintenance carried out in the logistics processes of the automotive yard, minimizing the replacement of batteries and along with this the economic and ecological cost.
Author Keywords: Time Series, k-Nearest Neighbors, IoT Sensors, Clustering, Classification.
Volume 44, Issue 2, September 2019, Pages 123–130
Carolina Flores Peralta1, Perfecto M. Quintero F.2, and Rodolfo Eleazar Pérez Loaiza3
1 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
2 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
3 Departamento de Estudios de Posgrado, Tecnológico Nacional de México/I.T. Apizaco, Apizaco, Tlaxcala, México
Original language: Spanish
Copyright © 2019 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
An Automotive Yard stores a big number of vehicles that stay in the site for different intervals of time (days, weeks or months), requering preventive maintenance during their stay. Through Internet of Things Sensors, the battery voltage of each vehicle is recorded every day generating a large data transformed into time series to analyze it. Classification and Clustering Algorithms based on K-Nearest Neighbors were developed using scikit-learn tool, for the extraction of knowledge from the IoT Data, specifically battery voltaje behavior patterns according to certain vehicle models. The performance of the algorithms was obtained making a comparison between them. The information founded will be of help for the planning of preventive maintenance carried out in the logistics processes of the automotive yard, minimizing the replacement of batteries and along with this the economic and ecological cost.
Author Keywords: Time Series, k-Nearest Neighbors, IoT Sensors, Clustering, Classification.
How to Cite this Article
Carolina Flores Peralta, Perfecto M. Quintero F., and Rodolfo Eleazar Pérez Loaiza, “Time Series Classification and Clustering for Voltage Behaviour Prediction from Vehicles stored inside Automotive Yards,” International Journal of Innovation and Scientific Research, vol. 44, no. 2, pp. 123–130, September 2019.
