INESC TEC researchers receive IEEE award in the field of Intelligent Transportation Systems

João Gama (INESC TEC/FEP), João Mendes Moreira (INESC TEC/FEUP) and Luís Moreira-Matias, researchers from INESC TEC’s Artificial Intelligence and Decision Support Laboratory (LIAAD), received “The George N. Saridis Best Transactions Paper Award for Outstanding Research”, along with Luís Damas (Geolink, FCUP) and Michel Ferreira (Geolink, FCUP). They were the co-authors of the paper “Predicting taxi-passenger demand using streaming data,” published in the journal IEEE Transactions on Intelligent Transportation Systems, in September 2013.

Informed driving is increasingly becoming a key feature for increasing the sustainability of taxi companies. The sensors installed in each vehicle provide new opportunities for automatically discovering knowledge, thus providing information for real-time decision-making e.g., finding routes that allow saving time.

In this context, the award-winning paper presents a new methodology to predict the spatial distribution of taxi passengers for a short-term time horizon, resorting to streaming data. In this study, the information was initially aggregated into a histogram time series. Then, three time-series forecasting techniques were combined to generate a prediction. Finally, experimental tests were carried out using online data transmitted by 441 vehicles from a fleet operating in the city of Porto, Portugal. The results showed that the proposed framework could provide an effective insight into the spatiotemporal distribution of passengers’ demand, for a horizon of 30 minutes.

According to João Gama, João Mendes Moreira and Luís Moreira-Matias, this paper was groundbreaking, by anticipating the paradigm shift in transportation research that occurred over the last decade, covering several fields of knowledge. “We went from being ‘model-based’, and trying to draw mathematical models that explain the phenomena that occur around us manually, to being ‘data driven’, focusing on the design of algorithms to create these models automatically from large amounts of data describing historical occurrences of these same phenomena”, explained the authors.

This award owes its name to the Greek George N. Saridis (1931–2006), professor at Purdue University and the Rensselaer Polytechnic Institute, a well-known pioneer in intelligent control, robotics and intelligent transportation systems, who led the effort to start R&D in these areas in the 1960s and 1970s.

In 2015, the Board of Governors of the IEEE Intelligent Transportation Systems Society approved the proposal to name the Best Paper Award in IEEE Transactions on Intelligent Transportation Systems as the George N. Saridis Best Transactions Paper Award. After nearly six years of preparation and planning, the George N. Saridis Award for Best Transaction Article 2014–2017 was announced for papers published in IEEE Transactions on Intelligent Transportation Systems, which rewards the works with the greatest impact, as well as those most cited on Google Scholar.

The paper by the Portuguese authors was acknowledged in the category “Outstanding Research” in the year 2016. More information here.

The INESC TEC researchers mentioned in this news piece are associated with UP-FEUP and UP-FEP.