In-Vehicle Alcohol Detection Using Low-Cost Sensors and Genetic Algorithms to Aid in the Drinking and Driving Detection
| Autor: | Carlos E. Galván-Tejada, José I. De la Rosa, Huizilopoztli Luna-García, Claudia Sifuentes-Gallardo, Nadia K. Gamboa-Rosales, Jonathan Samuel Romero-González, Antonio Martinez-Torteya, José M. Celaya-Padilla, Jorge I. Galván-Tejada, Jose G. Arceo-Olague, Hamurabi Gamboa-Rosales |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Automobile Driving
Computer science Feature selection Sample (statistics) smart vehicle TP1-1185 Biochemistry Article Analytical Chemistry Genetic algorithm In vehicle genetic algorithm Humans Sensitivity (control systems) Electrical and Electronic Engineering drinking and driving smart infotainment alcohol detection Child Instrumentation Driving Under the Influence business.industry Chemical technology Process (computing) Accidents Traffic Pattern recognition Atomic and Molecular Physics and Optics Support vector machine Motor Vehicles Artificial intelligence business Area under the roc curve Algorithms |
| Zdroj: | Sensors, Vol 21, Iss 7752, p 7752 (2021) Sensors (Basel, Switzerland) Sensors; Volume 21; Issue 22; Pages: 7752 |
| ISSN: | 1424-8220 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|