Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·

Applying Neural-Symbolic Cognitive Agents in Intelligent Transport Systems to reduce CO2 emissions

Publication files not online:

Author: Penning, L. de · Avila Garcez, A.S. d · Lamb, L.C. · Stuiver, A. · Meyer, J.J.C.
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source:2014 International Joint Conference on Neural Networks, IJCNN 2014, 6 July 2014 through 11 July 2014, 55-62
Proceedings of the International Joint Conference on Neural Networks
Identifier: 519615
doi: doi:10.1109/IJCNN.2014.6889788
ISBN: 9781479914845
Article number: 6889788
Keywords: Training · Deep Learning · Driver modelling · Neural-Symbolic Learning and Reasoning · Restricted Boltzmann Machines (RBM) · Human Performances · TPI - Training & Performance Innovations · ELSS - Earth, Life and Social Sciences


Providing personalized feedback in Intelligent Transport Systems is a powerful tool for instigating a change in driving behaviour and the reduction of CO2 emissions. This requires a system that is capable of detecting driver characteristics from real-time vehicle data. In this paper, we apply the architecture and theory of a Neural-Symbolic Cognitive Agent (NSCA) to effectively learn and reason about observed driving behaviour and related driver characteristics. The NSCA architecture combines neural learning and reasoning with symbolic temporal knowledge representation and is capable of encoding background knowledge, learning new hypotheses from observed data, and inferring new beliefs based on these hypotheses. Furthermore, it deals with uncertainty and errors in the data using a Bayesian inference model, and it scales well to hundreds of thousands of data samples as in the application reported in this paper. We have applied the NSCA in an Intelligent Transport System to reduce CO2 emissions as part of an European Union project, called EcoDriver. Results reported in this paper show that the NSCA outperforms the state-of-the-art in this application area, and is applicable to very large data.