Fuzzy sets and membership functions based on probabilities
Information Sciences: an International Journal
Automatically determine the membership function based on the maximum entropy principle
Information Sciences: an International Journal
Fuzzy c-means approach to tissue classification in multimodal medical imaging
Information Sciences: an International Journal
Information combination operators for data fusion: a comparative review with classification
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
| Hi-index | 0.00 |
Information fusion plays an important role in decision support support systems as this procedure can provide a wealth of information by integrating data obtained from multiple sources. However, this data fusion is a challenging problem owing to the uncertainty and reliability of the sources involved, as well as the incompleteness of the data obtained. In this paper we propose a framework to aggregate information from different sensors imaging the same view of the same object. After classification is performed to give hard membership values to well defined pixels, a fuzzy membership is assigned to 'mixed' pixels using a reliability criteria of the sensor to a particular object class. Once this classification process is complete, a fusion procedure is outlined utilizing concepts of compatibility, partial aggregation and reinforcement. Thus, the fused data sets will contain contributions from individual sensors based on the reliability of the individual sensors and the compatibility of the sensors compared to the most reliable sensor for the particular object class, using an appropriate distance measure. When the reliability of the sensors fall within acceptable distance measures, Ordered Weighting Average (OWA) operators and fuzzy measures are used to decided weightage of the data from different sensors to be fused. When the sensors are equally reliable, a reinforcement procedure is adopted, and finally, a partial aggregation is performed.