Vehicle accident sub-classification modeling using stacked generalization: A multisensor fusion approach

Abstract

Road accidents caused by several factors are responsible for the deaths and injuries of people. The majority of deaths occur within first few hours of an accident. If in case of an accident the victim becomes incapacitated, and there is no onlooker to help, then an accurate automated accident reporting system can significantly reduce the number of such deaths. This paper reports an Android smartphone-based end-to-end Internet of Things (IoT) system that can transmit accident information to emergency services and affected families once a vehicle accident is detected. Along with the detection, the classification of vehicle accidents can be very helpful in identifying suitable life-saving medical-aid and appropriate rescue operation equipment. The main objective of this research work is to develop a machine learning (ML) model that can detect as well as classify vehicle accidents accurately into eight categories. To enhance the classification efficacy of the system, a multi-sensor fusion framework has been proposed that incorporates various sensor-fusion techniques at different levels of its implementation along with several preprocessing methods such as 10-ms moving maximum, complementary filters, and a 2-sec sliding window. The framework uses Logistic Regression (LR) based stacked generalization approach to combine the decisions of three ML classifiers, which are based on Decision Tree (DT), Naïve Bayes (NB), and Random Forest (RF) methods. The LR-based stacking classifier is found to be very accurate with an F1-score of 0.95, whose performance is significantly better than the performance of all individual base-classifiers.