Improving Machine Learning Identification of Unsafe Driver Behavior by Means of Sensor Fusion

Abstract

Most road accidents occur due to human fatigue, inattention, or drowsiness. Recently, machine learning technology has been successfully applied to identifying driving styles and recognizing unsafe behaviors starting from in-vehicle sensors signals such as vehicle and engine speed, throttle position, and engine load. In this work, we investigated the fusion of different external sensors, such as a gyroscope and a magnetometer, with in-vehicle sensors, to increase machine learning identification of unsafe driver behavior. Starting from those signals, we computed a set of features capable to accurately describe the behavior of the driver. A support vector machine and an artificial neural network were then trained and tested using several features calculated over more than 200 km of travel. The ground truth used to evaluate classification performances was obtained by means of an objective methodology based on the relationship between speed, and lateral and longitudinal acceleration of the vehicle. The classification results showed an average accuracy of about 88% using the SVM classifier and of about 90% using the neural network demonstrating the potential capability of the proposed methodology to identify unsafe driver behaviors.

Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach

“…The article [10] discusses a research study that aims to enhance the identification of hazardous driver behavior using sensor fusion and machine learning. The study employed an Android smartphone to collect motion data using accelerometers, gyroscopes, and magnetometers.…”

“…Technique Performance Accuracy (%) [10] 2020 Accelerometers, gyroscopes, and magnetometer data. The investigation [13] suggests utilizing smartphone sensors to accumulate data on driver behavior and classify it into four categories normal, intermediate, aggressive, and dangerous in various external conditions such as speed limits, weather conditions, and traffic signs.…”

“…Performance Accuracy (%) [11] 2019 Neural network 96.1 [12] 2019 DeepConvLSTM 95.7 [10] 2020 Neural network 90.0 [13] 2022 LightGBM 88.0 [23] 2022 ConvLSTM 79.5 [36] 2022 CNN-LSTM 91.9 [14] 2023 RF 95.0 [15] 2023 CNN-LSTM 97.6 Our 2023 RF 99.9…”

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

“…However, there were 10 drivers whose faces were occluded or far away from the camera, and the expression data could not be well recognized, thus a total of 12 drivers were finally employed. Considering the long test time and high sampling frequency, a dataset with the test results from 12 drivers should already be sufficient [ 32 , 33 , 34 ]. Due to the specificity of this occupation, the 12 drivers were all male, with an average age of 36 years old, and they all had three or more years’ driving experience.…”

Analysis of driving style using self-organizing maps to analyze driver behavior

“…+ Classification method based on support vectors [13], [18], [19] + + [17]/- [18], [19] + + Classification method based on neural network multi-layer perceptron (MLP) [14],…”