Correlating Fatality Rate to Road Accidents in India: A Case Study using Big Data

Koley, Subha, Srivastava, Saket and Ghosal, Prasun (2018) Correlating Fatality Rate to Road Accidents in India: A Case Study using Big Data. In: IEEE International Symposium on Smart Electronic Systems, 17-19 Dec 2018, Hyderabad, India.

Correlating Fatality Rate to Road Accidents in India: A Case Study using Big Data
[img] PDF
iSES_2018_resume_89.pdf - Whole Document

Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive


Number of vehicles on Indian roads is increasing at a very high rate every year and the number of road accidents is rising at a similar rate. In 2016, around half a million (reported) people were injured in India due to different types of road accidents and out of them, around 150,000 people were killed. This leads to a very serious concern that there are some major flaws in emergency rescue services in the country. Big Data analysis and different statistical models can identify accident frequencies and patterns in a region, which may be useful to identify accident-prone regions in the country. A centralized database of all possible rescue authorities with their exact location and contact information can be a very important part of a smart accident reporting system and rescue operations. In this paper, we have studied the number of injuries in road accidents and deaths in most of the Indian states and proposed a model correlating them with the number of hospitals and police stations available in those states. This model will help not only to figure out critical accident-prone states in India but also to create a database for an emergency rescue system. The data used for this model has been generated using Google Radar Search and Reverse Geocoding API that can be very much useful to accelerate development f emergency rescue operations needed for Indian road systems and can be replicated easily for other countries.

Keywords:Big Data, Machine Learning, Road Accidents, Reverse Geocoding
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G790 Artificial Intelligence not elsewhere classified
G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Engineering
ID Code:34437
Deposited On:11 Dec 2018 16:12

Repository Staff Only: item control page