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

Abstract

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.

A Lightweight In-Vehicle Alcohol Detection using Smart Sensing and Supervised Learning

“…Subsequently, the table considers six distinct alcohol detection systems for the in-vehicle ecosystem developed during the last five years (from 2016 to 2021) alongside our proposed in-vehicle alcohol detection system which relies on the optimizable shallow neural networks (O-SNN) as the core learning model. The reported detection schemes incorporate the following supervised learning models: genetic algorithm with support vector machine/radial which has been used by [35], Ross-Quinlan decision trees known as (C4.5 DT), used in the development of alcohol detection system in [50], reduced error pruning tree (REPT-DT) decision tree, which has been employed in [36], the random forest classifier (RFC) model used in [37], support vector machine (SVM) utilized by author of [38], and finally, the k-nearest neighbors (kNN) learning model that is used in [39].…”

“…The authors of the article [35] proposed a non-invasive approach for detecting the presence of alcohol within a vehicle. The proposed technique relies on a set of MQ-3 alcohol sensors installed inside the car.…”

“…Year Learning Scheme Accuracy F-Score Kappa [35] 2021 GA+ SVM 97.60% 97.5% 97.90% [50] 2019 C4.5 DT 92.53% -- [36] 2018 REPT DT 87.70% 85.90% - [37] 2019 RFC 97.53% -- [38] 2021 SVM 86.00% 98.00% - [39] 2016 kNN 92.00% 87.50% -Proposed 2022 O-SNN 99.80% 99.70% 99.50%…”

Vehicle Accident and Alcohol Detection System using IoT Platform

“…So, the alert mechanism equipped with the vehicle will convert the conventional vehicle into a smart vehicle (1) . Installing Global positioning System (GPS) and global system for mobile communication (GSM) to the vehicle will add immediate attention of the health care persons and shipment process to intensive unit may save the human life and eventually decrease the death rate (2) . GPS System is more versatile device in all climate conditions.…”

From 0D to 2D: N-doped carbon nanosheets for detection of alcohol-based chemical vapours

“…Additionally, alcohol detection to ensure road safety protocols are obeyed, has also provided a large market for the detection of ethanol vapours. 5 As such, the search for portable, low-cost, low power usage, high response and easily operated sensing devices for VOC detection still continues, in particular for those devices that can operate satisfactorily under room temperature conditions. 6 Owing to this growing demand, several sensing techniques have been explored for the detection of VOCs.…”