Comparison of Machine Learning Algorithm's Performance Based on Decision making in Autonomous Car
Ittikon Thammachantuek, Somkiat Kosolsomnbat, Mahasak Ketcham · 2018
This paper presents the performance comparison of popular supervised learning algorithms: SVM, MLP, CNN, DT, and RF. These algorithms are used for road images recognition. All images are collected by our model car. They are labeled with four different classes: left, right, forward and stop. We use 90% of them for training and use 10% for testing each model. The result shows that, CNN has the best accuracy about 83.45%.