Formulation of a simple model to estimate road surface roughness condition from Android smartphone sensors

It is increasingly common to find many useful sensors on today's smartphones. Beside the use in the smartphones' user interface and features, many researchers and developers have also adopted the sensors for use in numerous applications in several fields and purposes. In this study, a simple model has been formulated to estimate road surface roughness condition from Android smartphone sensor data. The goal is to explore the use of smartphones, as a low cost and easy to implement approach, in the field of road maintenance management and continuous monitoring. The formulation of the model is based on an experiment and frequency domain analysis, in which it has been found that the sensor data, such as 3 axis acceleration and speed, has a linear relationship with road surface roughness condition. In our preliminary simulations on example road network with various settings, we have found that the performance and results of the model are very encouraging.