Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-2, 107-114, 2014
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-2/107/2014/
doi:10.5194/isprsarchives-XL-2-107-2014
© Author(s) 2014. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
11 Nov 2014
An Intelligent Spatial Proximity System Using Neurofuzzy Classifiers and Contextual Information
F. Barouni and B. Moulin Laval University, Computer Science Department, Pavi llon Pouliot, 1065, rue de la Médecine Quebec City QC G1V 0A6, Canada
Keywords: GIS, Decision Support, Reasoning, Artificial Intelligence, Contextual, Analysis Abstract. In this paper, we propose a novel approach to reason with spatial proximity. The approach is based on contextual information and uses a neurofuzzy classifier to handle the uncertainty aspect of proximity. Neurofuzzy systems are a combination of neural networks and fuzzy systems and incorporate the advantages of both techniques. Although fuzzy systems are focused on knowledge representation, they do not allow the estimation of membership functions. Conversely, neuronal networks use powerful learning techniques but they are not able to explain how results are obtained. Neurofuzzy systems benefit from both techniques by using training data to generate membership functions and by using fuzzy rules to represent expert knowledge. Moreover, contextual information is collected from a knowledge base. The complete solution that we propose is integrated in a GIS, enhancing it with proximity reasoning. From an application perspective, the proposed approach was used in the telecommunication domain and particularly in fiber optic monitoring systems. In such systems, a user needs to qualify the distance between a fiber break and the surrounding objects of the environment to optimize the assignment of emergency crews. The neurofuzzy classifier has been used to compute the membership function parameters of the contextual information inputs using a training data set and fuzzy rules.
Conference paper (PDF, 1394 KB)


Citation: Barouni, F. and Moulin, B.: An Intelligent Spatial Proximity System Using Neurofuzzy Classifiers and Contextual Information, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-2, 107-114, doi:10.5194/isprsarchives-XL-2-107-2014, 2014.

BibTeX EndNote Reference Manager XML