Last Thursday, February 11, Jamie Arjona, industrial doctoral student at inLab FIB, presented his thesis “Design smart its services through innovative date analsys modeling”, directed by Josep Casanovas and Ma Paz Linares, which obtained a final grade of excellent.

Jamie’s thesis is the product of the collaboration between the inLab FIB and the company Worldsensing S.L. with the aim of characterizing and modeling different parking systems around the world using advanced modeling techniques. Worldsensing S.L. are manufacturers of sensors for the industrial field and Smart Cities and also offer different software solutions for these fields. The sensors used provide data on the occupation status of the parking spaces in real time. This data is stored and is subsequently analyzed to create the models.

The chosen models are based on the methodology of neural networks, specifically the Multilayer Perceptron (MLP), Long Short Term Memory (LSTM) and United Recurrent Gated (GRU) models have been studied, and a comparison with classic models such as the Autoregresive Integrated Moving Average (ARIMA) has also been done.

In addition, a study has been carried out in which other data sources are used and their effect on parking processes is analyzed, and how this information improves the predictions of the models is quantified. These data are weather effects and calendar events.