Modular neural networks for map-matched GPS positioning

This paper provides an overview of work undertaken over the past year to develop artificial neural network (ANN) techniques to improve the accuracy and reliability of road selection during map-matching computation. Map matching positions provided by low-cost GPS receivers have great potential when integrated with hand-held or in-vehicle geographical information system (GIS) applications, especially those used for tracking and navigation, on path and road networks. Initial results indicate that improvements in map-matching and positional accuracy can indeed be achieved by using simple ANNs over traditional methods. This earlier work is extended to incorporate more complex procedures and, hopefully, produce further improvements. Recent results are presented, and planned research is explained. Further results and conclusions of this on-going research are published in due course.