Mortality Prediction of Victims in Road Traffic Accidents (RTAs) in India using Opposite Population SGO-DE based Prediction Model

Jena, Junali Jasmine; Satapathy, Suresh Chandra

Abstract

Getting immediate and appropriate care for the victims of Road Traffic Accidents (RTAs) in countries like India with huge population is a challenging job. In this paper a new hybridized evolutionary algorithm has been proposed for hyper-parameter tuning of the hyper-parameters of the prediction models using which mortality prediction of victims of RTAs in India have been performed. The proposed methodology Opp-SGO-DE has been used for parameter tuning in prediction algorithms like Random Forest (RF) and Support Vector Machine (SVM) and promising results were found from the experimentation. In RF, accuracy was increased from 0.75 to 0.82 and F1-score was increased from 0.66 to 0.77 in dataset-1 and accuracy was increased from 0.66 to 0.75 and F1-score was increased from 0.62 to 0.65 in dataset-2. In SVM, accuracy was increased from 0.63 to 0.74 and F1-score was increased from 0.58 to 0.67 in dataset-1 and accuracy was increased from 0.56 to 0.62 and F1-score was increased from 0.54 to 0.575 in dataset-2.


Keyword(s)

Opp-SGO-DE, Parameter Tuning, Random Forest, Support Vector Machine


Full Text: PDF (downloaded 191 times)

Refbacks

  • There are currently no refbacks.
This abstract viewed 266 times