An Internet of Things Based system for Road Surface Condition Assessment Using Machine Learning

Road surface condition assessment is crucial for maintaining road safety and preserving road infrastructure. However, techniques for assessing road conditions employed in Tanzania are manual and labor-intensive, leading to slow and ineffective repair practices. To address these challenges, this project developed an Internet of Things-based system for Road Surface Condition Assessment using Machine Learning. The system collects real-time data on road surface conditions using camera and gyroscope sensors; processes the data using machine learning algorithms to detect defects on the road surface. The data is used for decision support by the maintenance authorities to ease their process by automation of road condition surveys. The effectiveness of the developed system was evaluated through a qualitative study that collected data on road condition assessment practices in Tanzania. The results indicate that the proposed system provides a more efficient, cost-effective, and comprehensive method for assessing road conditions in Tanzania. The study found that the proposed system facilitated efficient road maintenance. This project highlights the potential of IoT and machine learning in addressing road safety and labor requirement challenges faced by developing countries in the field of infrastructure management, it also offers a valuable contribution to the field of transportation and engineering.