Abstract
Currently, the popularity of smartphones with networking capabilities equipped with various sensors and the low cost of the Internet have opened up great opportunities for the use of smartphones for sensing systems. One of the most popular applications is the monitoring and the detection of anomalies in the environment. In this article, we propose to enhance classic road anomaly detection methods using the Grubbs test on a sliding window to make it adaptive to the local characteristics of the road. This allows more precision in the detection of potholes and also building algorithms that consume less resources on smartphones and adapt better to real conditions by applying statistical outlier tests on current threshold-based anomaly detection methods. We also include a clustering algorithm and a mean shift-based algorithm to aggregate reported anomalies on data to the server. Experiments and simulations allow us to confirm the effectiveness of the proposed methods.
Highlights
The mobile phone sensor system is promising great potential for applications
We propose to enhance classic road anomaly detection methods using the Grubbs test on a sliding window to make it adaptive to the local characteristics of the road
We found that the current methods were less adaptable to real conditions such as the flatness of the road, the type of vehicle, the speed of travel, the quality of the suspension, and smartphone type
Summary
The mobile phone sensor system is promising great potential for applications. For the past few years, smartphones have become more popular and powerful. There will be many other applications that can be exploited from monitoring and anomaly detection systems based on data from sensors such as ambient light sensors, magnetometers, barometers, air humidity sensors, and thermometers. The basic processing of monitoring and anomaly detection systems is as follows: Data from sensors are collected regularly in time. These data on smartphones are comprised of Sensors 2019, 19, 3834; doi:10.3390/s19183834 www.mdpi.com/journal/sensors. This paper presents the overall architecture of the system we developed for the monitoring and the detection of anomalies With this model, we propose lightweight algorithms to identify anomalies on smartphones and an algorithm to aggregate these anomalies and the associated data on the server.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
