Abstract
Anomalies on road pavement cause discomfort to drivers and passengers, and may cause mechanical failure or even accidents. Governments spend millions of Euros every year on road maintenance, often causing traffic jams and congestion on urban roads on a daily basis. This paper analyses the difference between the deployment of a road anomalies detection and identification system in a “conditioned” and a real world setup, where the system performed worse compared to the “conditioned” setup. It also presents a system performance analysis based on the analysis of the training data sets; on the analysis of the attributes complexity, through the application of PCA techniques; and on the analysis of the attributes in the context of each anomaly type, using acceleration standard deviation attributes to observe how different anomalies classes are distributed in the Cartesian coordinates system. Overall, in this paper, we describe the main insights on road anomalies detection challenges to support the design and deployment of a new iteration of our system towards the deployment of a road anomaly detection service to provide information about roads condition to drivers and government entities.
Highlights
With the increase in number of vehicles on the roads and number of road networks, the issues related to road safety have become more pressing and complex
Road anomaly detection or road condition survey systems based on collaborative mobile sensing typically detect and automatically classify road anomalies using data-mining approaches on data collected by smartphones [11,12,13,14,15]
The objective was to evaluate a road anomalies detection system based on the data-mining approach described in a previous work [17], in a real world deployment, i.e., an environment in which data are collected during normal driving experience, which may originate some situations that were not perceived at the system design time
Summary
With the increase in number of vehicles on the roads and number of road networks, the issues related to road safety have become more pressing and complex. Road anomaly detection or road condition survey systems based on collaborative mobile sensing typically detect and automatically classify road anomalies using data-mining approaches on data collected by smartphones [11,12,13,14,15] This is a challenging task, especially when the data are collected in real-world deployments. The objective was to evaluate a road anomalies detection system based on the data-mining approach described in a previous work [17], in a real world deployment, i.e., an environment in which data are collected during normal driving experience, which may originate some situations that were not perceived at the system design time.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
