In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection

Worldwide, motor vehicle accidents are one of the leading causes of death, with alcohol-related accidents playing a significant role, particularly in child death. Aiming to aid in the prevention of this type of accidents, a novel non-invasive method capable of detecting the presence of alcohol insid...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jose M. Celaya-Padilla, Jonathan S. Romero-González, Carlos E. Galvan-Tejada, Jorge I. Galvan-Tejada, Huizilopoztli Luna-García, Jose G. Arceo-Olague, Nadia K. Gamboa-Rosales, Claudia Sifuentes-Gallardo, Antonio Martinez-Torteya, José I. De la Rosa, Hamurabi Gamboa-Rosales
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	drinking and driving smart vehicle smart infotainment alcohol detection genetic algorithm Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/5aa60ce12c2e480ca05592dafedccbfb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5aa60ce12c2e480ca05592dafedccbfb
record_format	dspace
spelling	oai:doaj.org-article:5aa60ce12c2e480ca05592dafedccbfb2021-11-25T18:59:00ZIn-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection10.3390/s212277521424-8220https://doaj.org/article/5aa60ce12c2e480ca05592dafedccbfb2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7752https://doaj.org/toc/1424-8220Worldwide, motor vehicle accidents are one of the leading causes of death, with alcohol-related accidents playing a significant role, particularly in child death. Aiming to aid in the prevention of this type of accidents, a novel non-invasive method capable of detecting the presence of alcohol inside a motor vehicle is presented. The proposed methodology uses a series of low-cost alcohol MQ3 sensors located inside the vehicle, whose signals are stored, standardized, time-adjusted, and transformed into 5 s window samples. Statistical features are extracted from each sample and a feature selection strategy is carried out using a genetic algorithm, and a forward selection and backwards elimination methodology. The four features derived from this process were used to construct an SVM classification model that detects presence of alcohol. The experiments yielded 7200 samples, 80% of which were used to train the model. The rest were used to evaluate the performance of the model, which obtained an area under the ROC curve of 0.98 and a sensitivity of 0.979. These results suggest that the proposed methodology can be used to detect the presence of alcohol and enforce prevention actions.Jose M. Celaya-PadillaJonathan S. Romero-GonzálezCarlos E. Galvan-TejadaJorge I. Galvan-TejadaHuizilopoztli Luna-GarcíaJose G. Arceo-OlagueNadia K. Gamboa-RosalesClaudia Sifuentes-GallardoAntonio Martinez-TorteyaJosé I. De la RosaHamurabi Gamboa-RosalesMDPI AGarticledrinking and drivingsmart vehiclesmart infotainmentalcohol detectiongenetic algorithmChemical technologyTP1-1185ENSensors, Vol 21, Iss 7752, p 7752 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	drinking and driving smart vehicle smart infotainment alcohol detection genetic algorithm Chemical technology TP1-1185
spellingShingle	drinking and driving smart vehicle smart infotainment alcohol detection genetic algorithm Chemical technology TP1-1185 Jose M. Celaya-Padilla Jonathan S. Romero-González Carlos E. Galvan-Tejada Jorge I. Galvan-Tejada Huizilopoztli Luna-García Jose G. Arceo-Olague Nadia K. Gamboa-Rosales Claudia Sifuentes-Gallardo Antonio Martinez-Torteya José I. De la Rosa Hamurabi Gamboa-Rosales In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
description	Worldwide, motor vehicle accidents are one of the leading causes of death, with alcohol-related accidents playing a significant role, particularly in child death. Aiming to aid in the prevention of this type of accidents, a novel non-invasive method capable of detecting the presence of alcohol inside a motor vehicle is presented. The proposed methodology uses a series of low-cost alcohol MQ3 sensors located inside the vehicle, whose signals are stored, standardized, time-adjusted, and transformed into 5 s window samples. Statistical features are extracted from each sample and a feature selection strategy is carried out using a genetic algorithm, and a forward selection and backwards elimination methodology. The four features derived from this process were used to construct an SVM classification model that detects presence of alcohol. The experiments yielded 7200 samples, 80% of which were used to train the model. The rest were used to evaluate the performance of the model, which obtained an area under the ROC curve of 0.98 and a sensitivity of 0.979. These results suggest that the proposed methodology can be used to detect the presence of alcohol and enforce prevention actions.
format	article
author	Jose M. Celaya-Padilla Jonathan S. Romero-González Carlos E. Galvan-Tejada Jorge I. Galvan-Tejada Huizilopoztli Luna-García Jose G. Arceo-Olague Nadia K. Gamboa-Rosales Claudia Sifuentes-Gallardo Antonio Martinez-Torteya José I. De la Rosa Hamurabi Gamboa-Rosales
author_facet	Jose M. Celaya-Padilla Jonathan S. Romero-González Carlos E. Galvan-Tejada Jorge I. Galvan-Tejada Huizilopoztli Luna-García Jose G. Arceo-Olague Nadia K. Gamboa-Rosales Claudia Sifuentes-Gallardo Antonio Martinez-Torteya José I. De la Rosa Hamurabi Gamboa-Rosales
author_sort	Jose M. Celaya-Padilla
title	In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
title_short	In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
title_full	In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
title_fullStr	In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
title_full_unstemmed	In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
title_sort	in-vehicle alcohol detection using low-cost sensors and genetic algorithms to aid in the drinking and driving detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/5aa60ce12c2e480ca05592dafedccbfb
work_keys_str_mv	AT josemcelayapadilla invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT jonathansromerogonzalez invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT carlosegalvantejada invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT jorgeigalvantejada invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT huizilopoztlilunagarcia invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT josegarceoolague invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT nadiakgamboarosales invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT claudiasifuentesgallardo invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT antoniomartineztorteya invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT joseidelarosa invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection AT hamurabigamboarosales invehiclealcoholdetectionusinglowcostsensorsandgeneticalgorithmstoaidinthedrinkinganddrivingdetection
_version_	1718410463482478592

In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection

Ejemplares similares