Maintaining and Managing Road Quality:Using MLP and DNN
Makgotso Jacqueline Maotwana
TL;DR
The study tackles automatic road quality assessment by classifying road surface images into four categories using a Kaggle dataset. It benchmarks an MLP baseline against a CNN-based DNN (implemented in Keras), along with mention of logistic regression and a feature-engineered KNN approach from the abstract, finding the DNN to deliver the highest accuracy (approximately 89.3% test) while the MLP lags at around 40% accuracy. Data augmentation and early stopping are shown to improve generalization, though some overfitting remains evident. The results demonstrate the practical potential of CNN-based road-condition monitoring for scalable maintenance and safety improvements, with future work aiming at larger, diversified datasets and real-time deployment in urban environments.
Abstract
Poor roads are a major issue for cars, drivers, and pedestrians since they are a major cause of vehicle damage and can occasionally be quite dangerous for both groups of people (pedestrians and drivers), this makes road surface condition monitoring systems essential for traffic safety, reducing accident rates ad also protecting vehicles from getting damaged. The primary objective is to develop and evaluate machine learning models that can accurately classify road conditions into four categories: good, satisfactory, poor, and very poor, using a Kaggle dataset of road images. To address this, we implemented a variety of machine learning approaches. Firstly, a baseline model was created using a Multilayer Perceptron (MLP) implemented from scratch. Secondly, a more sophisticated Deep Neural Network (DNN) was constructed using Keras. Additionally, we developed a Logistic Regression model from scratch to compare performance. Finally, a wide model incorporating extensive feature engineering was built using the K-Nearest Neighbors (KNN) algorithm with sklearn.The study compared different models for image-based road quality assessment. Deep learning models, the DNN with Keras achieved the best accuracy, while the baseline MLP provided a solid foundation. The Logistic Regression although it is simpler, but it provided interpretability and insights into important features. The KNN model, with the help of feature engineering, achieved the best results. The research shows that machine learning can automate road condition monitoring, saving time and money on maintenance. The next step is to improve these models and test them in real cities, which will make our cities better managed and safer.