Predicting Car Park Occupancy Rates in Smart Cities

Abstract

In this article we address the study of parking occupancy data published by the Birmingham city council with the aim of testing several prediction strategies (polynomial fitting, Fourier series, k -means clustering, and time series) and analyzing their results. We have used cross validation to train the predictors and then tested them on unseen occupancy data. Additionally, we present a web page prototype to visualize the current and historical parking data on a map, allowing users to consult the occupancy rate forecast to satisfy their parking needs up to one day in advance. We think that the combination of accurate intelligent techniques plus final user services for citizens is the direction to follow for knowledge-based real smart cities.

IoT in Smart Cities: A Survey of Technologies, Practices and Challenges

“…Solutions to this problem have been formulated both as a regression problem as well as a classification one, both utilizing imaging and/or other occupancy sensing modalities. Regression solutions [205][206][207] are typically used to predict a parking lots occupancy levels in the future whereas classification systems [208][209][210] involve guiding drivers according to the shortest distance as well as used for user localization purposes within such lots. In addition to cloud based approaches, edge computing systems for smart parking have also been devised as suggested in [211,212] who deploy CNNs on edge devices for occupancy detection and user localization, respectively.…”

Forecasting Parking Lots Availability: Analysis from a Real-World Deployment

“…We have chosen the data set Parking in Birmingham. This data set has some flaws that has been addressed using the same approach described in [13]. One specific parking area, named Others-CCCPS202, has been chosen for conducting experiments.…”

BiPred: A Bilevel Evolutionary Algorithm for Prediction in Smart Mobility

“…In recent years, different techniques of Artificial Intelligence (AI), such as neural networks (NN), support vector machines (SVM), pattern recognition (PR), and adhoc heuristics have been used for the analysis of time series and the prediction of events. The NN approaches to time-series prediction have been widely used [4,22].…”

“…Indeed, the speed at which new challenges in mobility in cities is larger than the services given by city councils and collaborating companies. With the new concept of smart cities [1,2,3,4,5,6], countless new problems have been appearing in mobility [7,8,9], including: parking, optimized routes, car sharing, smart systems in buses, private models of mobility, signaling, lane decisions, social implications of mobility, energy consumption, and environmental implications.…”