An Experiment on Measurement of Pavement Roughness via Android-Based Smartphones
This work addresses road maintenance monitoring for transportation agencies, but it is incremental as it builds on existing smartphone-based sensing methods with limited new insights.
The study tested using Android smartphones to measure pavement roughness by collecting vibration acceleration data on a 9 km expressway in Thailand, comparing results to a laser-based inertial profiler (IRI), and found that machine learning methods performed better than RMS but showed little relationship between smartphone data and IRI.
The study focuses on the experiment of using three different smartphones to collect acceleration data from vibration for the road roughness detection. The Android operating system is used in the application. The study takes place on asphaltic pavement of the expressway system of Thailand, with 9 km distance. The run vehicle has an inertial profiler with laser line sensors to record road roughness according to the IRI. The RMS and Machine Learning (ML) methods are used in this study. There is different ability of each smartphone to detect the vibration, thus different detected values are obtained. The results are compared to the IRI observation. ML method gives better result compared to RMS. This study finds little relationship between IRI and acceleration data from vibration collected from smartphones.