Road surface monitoring system through machine learning classification ensemble models

Abstract

The development of megacities is currently the scene of many problems; an important one to consider is the quality and efficiency of their mobility. An essential factor impacting this is the quality of their road networks, which can affect the durability and safety of ground transportation systems. Mexico City is a great example of such deficiencies. Therefore smart mobility strategies and planning in terms of logistics have been proposed, but few technological integrations have been implemented. In this work, a platform capable of monitoring surface defects in road pavement using Inertial Measurement Units and Machine Learning classification models was designed and developed. This was achieved by recording accelerometer and gyroscope measurements on a test vehicle's damped and undamped mass while driving on Mexico City streets. The measurements were labeled to identify and classify general and specific elements of road irregularities: smooth and uneven road segments, potholes, manholes, speed bumps, and patches. It is described as a methodology for preprocessing the data through time series analysis and feature extraction in the time and frequency domain. Four ensemble models were trained using the best classification models out of eight candidates; an exhaustive grid search methodology was used to select the best classification models per category and optimize the system's performance. Finally, the algorithms and models were loaded into a cloud instance to process incoming raw data; the resultant predictions were stored in a cloud database to be visualized on a web platform.