English Abstract
Abstract:
Despite the benefits of Intelligent Transportation Systems (ITS) in enhancing the
performance of the transportation mechanize and facilitate the fast rhythm of the
citizens' lifestyle, still there is a suffer from the traffic congestion. As with the increase
in population and urban growth, the traffic congestion is increased as well. Therefore,
this study is conducted to mitigate the traffic congestion using Machine Learning (ML)
approaches. It is aimed to mitigate the traffic congestion in Kingdom of Bahrain by
predicting the solution needed from construction and traffic engineering perspective.
This research used a primary data, which is collected by the author from the reports and
documents provided by the Ministry of Works who is responsible of the roads'
construction in Bahrain. The extracted dataset has five class labels and were imbalanced
classed, therefore, three oversampling methods were applied on the dataset. After that,
three datasets result from each oversampling methods; Synthetic Minority
Oversampling Technique (SMOTE), Adaptive Synthetic (ADASYN), Random
Oversampling (ROS) and the fourth one is the hybrid and the combination of the three
datasets. The models are built using five ML approaches; Decision Tree, Random
Forest, k-Nearest Neighbours, Support Vector Machine and Multilayer Perceptron. All
the models applied five times; one before applying oversampling and one for each
oversampling method including the hybrid. The hybrid dataset produced the high
accuracy among all the ML models. K-Nearest Neighbours and Random Forest resulted
the best accuracy 100% and 99.9%. This study proved that the ML approaches are
empowering the decision making in taking the suitable solution for road construction
to mitigate the traffic congestion.
