Using Supervised Machine Learning to Predict the Status of Road Signs

There is no data collected and saved about road signs in Sweden and the status for these signs is unknown. Furthermore, the status of the sign colors, the quality of the sign, the type of the retroreflection material, and age of the road signs are unknown. Therefore, the status of a road sign (approved or not), which depends on these parameters, is unknown.The aim of this study is to predict the status of the road signs mounted on the Swedish roads by using supervised machine learning. This study investigates the effect of using principal component analysis (PCA) and data scaling on the accuracy of the prediction. The data were prepared before using then scaled using two methods which are the normalization and the standardization.The three algorithms that tested in this study are Random Forest, Artificial Neural Network (ANN), and Support Vector Machines (SVM). They are invoked to predict the status of the road signs. The algorithms exhibited overall high predicting accuracy (98%), high precision (98%), high recall (98%), and high F1 scores (98%).Random forest showed the best performance with 4 PC components on the normalized data with a highest accuracy of 98%.Using PCA showed different impacts on the performance of different techniques. In the case of ANN, invoking PCA improves the accuracy, while for SVM the accuracy decreases when PCA is used. On other hand, PCA has no effect on the accuracy of the random forest model when scaling is invoked.The effect of the data scaling using normalization and standardization is also investigated in this study, and it is noticed that scaling of the data increases the accuracy of the prediction for all the three models (ANN, SVM and Random Forest). Furthermore, better accuracy is achieved when the standardization is invoked compared with normalization.