Real-time data fusion technique for validation of an autonomous system
Bojan Cukic; Mladenovski, M.; Desovski, D.; Yerramalla, S.
Object-Oriented Real-Time Dependable Systems, 2005. WORDS 2005. 10th IEEE International Workshop on
Volume , Issue , 2-4 Feb. 2005 Page(s): 121 - 128
Digital Object Identifier 10.1109/WORDS.2005.48
Summary: We describe a data fusion technique suitable for use in validation of a real-time autonomous system. The technique is based on the Dempster-Shafer theory and Murphy's rule for beliefs combination. The methodology is applied for fusing the learning stability estimates, provided by an online neural network monitoring methodology, into a single probabilistic learning stability measure. The case study shows that our data fusion technique is capable of handing real-time requirements and provides unique, meaningful results for interpreting the stability information provided by the online monitoring system.
View citation and abstract |