Tutorial at the 

2017 International Joint Conference on Neural Networks (IJCNN 2017)

Anchorage, Alaska, USA, May 14-19, 2017

Tutorial title:
Time-Evolving Data Streams Learning and Short-Term Urban Traffic Flow Forecasting

Date: Sunday May 14th, 2017; Time 1:30 pm - 3:30 pm


Presenter: Prof. Francesco Masulli   email: francesco<dot>masulli<at>unige<at>it
DIBRIS - Dept of Informatics, Bioingengering, Robotics and Systems Engineering
, University of Genova (ITALY)
and
Center for Biotechnology of Temple University, Philadelphia (PA, USA)


Abstract: Data streams have arisen as a relevant topic during the last decade. In this tutorial we consider non-stationary data stream clustering using a possibilistic approach. The Graded Possibilistic Clustering model offers a way to evaluate “outlierness” through a natural measure, which is computed directly from the model. Both online and batch training approaches are considered, to provide different trade-offs between stability and speed of response to changes. The proposed approach is evaluated on a synthetic data set, for which the ground truth is available. Moreover, a real-time short-term urban traffic flow forecasting application is proposed, taking into account both spatial and temporal information. To this aim, we introduce a Layered Ensemble Model which combines Artificial Neural Networks and Graded Possibilistic Clustering models, obtaining in such a way an accurate forecaster of the traffic flow rates with outlier detection. Experimentation has been carried out on two different data sets. The former consists on real UK motorway data and the latter is obtained from simulated traffic flow on a street network in Genoa (Italy). The proposed model for short-term traffic forecasting provides promising results and given its characteristics of outlier detection, accuracy, and robustness, and can be fruitful integrated in traffic flow management systems.



Presenter's biography: Francesco Masulli is a Professor of Computer Science with the Department of Informatics, Bioingengering, Robotics and Systems Engineering (DIBRIS) of the University of Genoa (Italy) and Adjunct Professor at the Center for Biotechnology of Temple University-Philadelphia (PA, USA). He is lecturer of the courses on Fundamentals of Computer Science, Well-Being Technologies, Computational Intelligence and Machine Learning at the University of Genoa. He is the recipient of the 2008 Pattern Recognition Society Award for the paper "A survey of kernel and spectral methods for clustering". Author of more than 200 scientific papers in Clustering, Machine Learning, Neural Networks, Fuzzy Systems, Bioinformatics and Well-Being Technologies. He is also the President of Italian Chapter of the IEEE-CIS and a Co-Chair of the Special Interest Group on Bioinformatics and Intelligence of the International Neural Network Society.



Last updated  1 March 2017  by francesco<dot>masulli<at>unige<at>it