ABSTRACT
Pavements are major roadway infrastructure assets, and pavement maintenance to the preferred level of serviceability comprises one of the most challenging problems faced by civil and transportation engineers. Presented herein is a study on the utilization of low-cost technology for the data collection and classification of roadway pavement anomalies, by using sensors from smartphones and from automobiles’ On-Board Diagnostic (OBD-II) devices while vehicles are in movement. The smartphone-based data collection is com-plimented with artificial neural network techniques, various algorithms and classification models for the clas-sification of detected roadway anomalies. The proposed system architecture and methodology utilize nine metrics in the analysis, are checked against three types of roadway anomalies, and are validated against hun-dreds of roadway runs (relating to several thousands of data points) with an accuracy rate of about 90%. The study’s results confirm the value of smartphone sensors in the low-cost (and eventually crowd-sourced) detection of roadway anomalies.