Abstract:
Millions of people are dying and billions of properties are damaged by road traffic accidents each
year worldwide. In the case of our country Ethiopia, the effect of traffic accidents is even more by
causing injuries, death, and property damage. Forecasting Road Traffic Accidents and Predicting
the severity of road traffic accidents contributes a role indirectly in reducing road traffic accidents.
This Study deals with forecasting the number of accident and predicting the severity of an accident
in the Oromia Special Zone using Deep Artificial Neural Network models. About 6170 road traffic
accidents data are collected from Oromia Police Commission Excel data and Oromia Special zone
Traffic Police Department hardcopy data. The dataset consists of accidents in the Special Zone of
Oromia Districts (Woredas) from 2005 to 2012 with 15 accidents attributes. About 4936 or (80%)
of the dataset was used for the training model and 1234 or (20%) of the dataset was used for the
testing model. This study proposed five different Neural Network architectures such as Back
Propagation Neural Network, Feed Forward Neural Network, Multi-Layer Perceptron Neural
Network, Recurrent Neural Network, and Radial Basis Function Neural Network for accident
severity prediction and The Long Short-Term Memory model for a time serious forecasting of
number accidents within specified years. The models will take input data, classify accidents, and
predicts the severity of an accident. Accident predictor Graphical User Interfaces has been created
using Python Tkinter library for easy accident severity prediction. According to the model
performance results, the Recurrent Neural Network model showed the best prediction accuracy of
97.18% whereas Multi-Layer Perceptron, Long Short-Term Memory, Radial Basis Function
Neural Network, Feed Forward Neural Network, and Back Propagation Neural Network models
showed the accuracy of 97.13%, 91.00%, 87.00%, 80.56%, 77.26%, respectively. The forecasted
accidents number for three years using Long Short-Term Memory model is 3555 whereas the
actual accident number is 3561 with Mean absolute error of 1.81, Root means squared error of
2.455, and Mean Percentage Error of -50.79. The prediction and forecast results obtained from the
model will be helpful in planning and management of road traffic accidents.
