Use of Machine Learning to Predict the Injuries of the Occupant of a Vehicle Involved in an Accident 2021-26-0003
As per the 2018 MoRTH accident report, there were 467,044 accidents, out of which 137,726 were fatal which resulted in 151,417 fatalities. In order to get an idea of the reasons for injuries and estimate the benefits of any intervention, a mathematical model should go a long way. This study is aimed at the development of such a model to predict the injuries sustained by the occupants of an M1 vehicle. We used a detailed accident database of 'Road Accident Sampling System India' (RASSI). RASSI, since 2011, has been collecting traffic accident data scientific across various locations in India. In the data, the occupant injuries are classified as No injury, Minor, Serious and Fatal We used the data of about 4700+ M1 occupants for the study & used almost 40 input parameters to determine the outcome. Based on the data, an algorithm was developed with an overall accuracy of about 67%. The parameters represented human, infrastructure, and environment. In 67% of the cases, the injuries were accurately predicted. In 14 % of the cases the predicted injuries were one level above than actual i.e. for example in case the actual injury was minor the model predicted it as serious we term this as +1 shift error. Likewise, 11% of the time the model predicted injury one level lower than the actual i.e. for example if the actual injury was of a serious nature, the model predicted it as minor. These can be termed as -1 shift errors. But if we combine ±1 shift errors and the 0 errors the accuracy increases to 92%. The model can be used as a first step towards accessing the effectiveness of an intervention. Post this more expensive field trials may be carried out
Citation: Howlader, A., "Use of Machine Learning to Predict the Injuries of the Occupant of a Vehicle Involved in an Accident," SAE Technical Paper 2021-26-0003, 2021, https://doi.org/10.4271/2021-26-0003. Download Citation
Author(s):
Ashim Howlader
Affiliated:
Maruti Suzuki India, Ltd.
Pages: 6
Event:
Symposium on International Automotive Technology
ISSN:
0148-7191
e-ISSN:
2688-3627
Related Topics:
Mathematical models
Crashes
Injuries
Machine learning
Fatal injuries
Vehicle occupants
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »