Data Analytics for Smart Parking Applications

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.

Clustering Analysis of the Spatio-Temporal On-Street Parking Occupancy Data: A Case Study in Hong Kong

“…The study from Gomari et al [41] used parking events to model the parking behaviors in Munich. Different clustering methods can be applied to the smart parking data, and a comparative analysis is conducted by Piovesan et al [42]. By contrast, this study focuses on new parking meter data in Hong Kong, rarely studied in the existing literature.…”

Smart cities: potential and challenges

“…For example, in Cenedese et al (2014) and Zanella, Bui, Castellani, Vangelista, & Zorzi (2014), it is shown how malfunctioning street lights can be easily identified by simply comparing the standard deviation of the values read by the light sensors applied to the different light poles during nighttime. More advanced techniques can be used to extract interesting correlations among different signals and build advanced services (Piovesan, Turi, Toigo, Martinez, & Rossi, 2016).…”

Analytics for the Internet of Things

“…The parking process is modelled as a birth-death stochastic process which allows prediction and optimisation of parking availability. Piovesan et al [155] describe the application of their unsupervised form of self-organising maps (SOM) clustering to the classification of parking spaces according to spatio-temporal patterns. This type of analytics automatically discovers outliers for sensor maintenance and usage anomalies.…”