Abstract
We consider real-life smart parking systems where parking lot occupancy data are collected from field sensor devices and sent to backend servers for further processing and usage for applications. Our objective is to make these data useful to end users, such as parking managers, and, ultimately, to citizens. To this end, we concoct and validate an automated classification algorithm having two objectives: (1) outlier detection: to detect sensors with anomalous behavioral patterns, i.e., outliers; and (2) clustering: to group the parking sensors exhibiting similar patterns into distinct clusters. We first analyze the statistics of real parking data, obtaining suitable simulation models for parking traces. We then consider a simple classification algorithm based on the empirical complementary distribution function of occupancy times and show its limitations. Hence, we design a more sophisticated algorithm exploiting unsupervised learning techniques (self-organizing maps). These are tuned following a supervised approach using our trace generator and are compared against other clustering schemes, namely expectation maximization, k-means clustering and DBSCAN, considering six months of data from a real sensor deployment. Our approach is found to be superior in terms of classification accuracy, while also being capable of identifying all of the outliers in the dataset.
Highlights
Large-scale Internet of Things (IoT) deployments are being massively installed within smart cities [1], and alongside their adoption, there is a concurrent need for advanced processing functionalities to handle the vast amount of data generated by sensor devices and, more importantly, to make these data useful for public administrations and citizens
We found that k-means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Expectation Maximization (EM)-clustering all show classification problems and fail to separate outliers from the other clusters, whereas our Self-Organizing Maps (SOM)-based scheme performs satisfactorily, reaching the highest classification performance when tested on synthetically-generated parking events and reliably detecting all outliers when applied to real data
Outliers are generally defined as data points that globally have the least degree of similarity to the dataset they belong to, and for our classification task, a data point corresponds to the time series generated by a certain sensor, which represents the behavior of the associated parking space
Summary
Large-scale Internet of Things (IoT) deployments are being massively installed within smart cities [1], and alongside their adoption, there is a concurrent need for advanced processing functionalities to handle the vast amount of data generated by sensor devices and, more importantly, to make these data useful for public administrations and citizens. Our focus in this paper is on data analysis tools for smart parking systems, and for our designs, tests and considerations, we use data from a large commercial smart parking deployment installed and maintained by Worldsensing (http://www.worldsensing.com/) in a town in Northern Italy. This deployment features 370 wireless sensor nodes that are placed underneath parking spaces to Sensors 2016, 16, 1575; doi:10.3390/s16101575 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary 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.
