Millions of people get injured, disabled or die in automotive accidents each year. Knowledge about the type of road accident is invaluable to the emergency medical services providers for optimal planning and execution of the rescue operation. An IoT based system has been developed in this work to report the occurrence, location as well as the type of road accident. The system uses in-built sensors of passenger smartphone to detect and classify the accident as head-on collision, rollover or fall-off. The accuracy of the proposed system, which uses Naïve Bayes classifier for classification, has been evaluated using precision, recall, F1 score and ROC curve. © 2020 IEEE.

Divya Lohani

Computer Science and Engineering

(SoE) School of Engineering

Kumar N.

Barthwal A.

Acharya D.

<p>Shiv Nadar University is a comprehensive, multidisciplinary, research-focused, and student-centric University offering a full range of academic programs at the undergraduate, postgraduate and doctoral level. With state-of-the-art infrastructure, the University comprises of academic wings, sophisticated labs, international standard sports facilities, amphitheaters, auditorium, conference rooms and smart classrooms. The University&rsquo;s goal is to become internationally recognized for the quality of its research and creative endeavors and their applicability to improving quality of life, generating new insights and expanding the boundaries of human knowledge creativity. Committed to excellence in teaching, research and service, the University aims to serve the higher education needs of India and the world beyond.</p>

Shiv Nadar University

Modeling IoT Enabled Automotive System for Accident Detection and Classification

2020 IEEE Sensors Applications Symposium, SAS 2020 - Proceedings

Road accidents are a leading cause of death and disability among youth. Contemporary research on accident detection systems is focused on either decreasing the reporting time or improving the accuracy of accident detection. Internet-of-Things (IoT) platforms have been utilized considerably in recent times to reduce the time required for rescue after an accident. This work presents an IoT-based automotive accident detection and classification (ADC) system, which uses the fusion of smartphone's built-in and connected sensors not only to detect but also to report the type of accident. This novel technique improves the rescue efficacy of various emergency services, such as emergency medical services (EMSs), fire stations, towing services, etc., as knowledge about the type of accident is extremely valuable in planning and executing rescue and relief operations. The emergency assistance providers can better equip themselves according to the situation after making an inference about the injuries sustained by the victims and the damage to the vehicle. In this work, three machine learning models based on Naïve Bayes (NB), Gaussian mixture model (GMM), and decision tree (DT) techniques are compared to identify the best ADC model. Five physical parameters related to vehicle movement, i.e., speed, absolute linear acceleration (ALA), change-in-altitude, pitch, and roll, have been used to train and test each candidate ADC model to identify the correct class of accident among collision, rollover, falloff, and no accident. NB-based ADC model is found to be highly accurate with 0.95 mean F1-score. © 2014 IEEE.

IEEE Internet of Things Journal

An IoT-Based Vehicle Accident Detection and Classification System Using Sensor Fusion

Vehicle Indoor Air Quality (VIAQ) is a very important parameter that we often tend to ignore in our daily driving. VIAQ can worsen due to build-up of carbon dioxide (CO2), carbon monoxide (CO) and other harmful gases emitted by vehicles. Poor VIAQ can lead to short term health conditions like drowsiness, breathlessness, discomfort and headache. Drowsiness while driving is a predominant health condition that leads to large number of accidents and deaths all over the world. Standard equipment of air intake and recirculation in both low end and high end cars do not completely support pervasive maintenance of VIAQ. Due to unavailability of miniaturized sensors, a general purpose solution to this problem was rarely studied and addressed. In this work, we propose a novel mobile sensing system to monitor and understand change in VIAQ. Our mobile sensing system is general purpose, built by using an Android Smartphone and a mobile sensor, is independent of car age and model, and monitors VIAQ at all times. © 2016 IEEE.

2016 IEEE Annual India Conference, INDICON 2016

Real time in-vehicle air quality monitoring using mobile sensing

Accident Analysis & Prevention

Real-time accident detection: Coping with imbalanced data

Sensors

A Novel Internet of Things-Enabled Accident Detection and Reporting System for Smart City Environments

Information Sciences

Noisy values detection and correction of traffic accident data

IEEE Access

Delay-Aware Accident Detection and Response System Using Fog Computing