DocumentCode :
262909
Title :
Comparison of identity fusion algorithms using estimations of confusion matrices
Author :
Golino, G. ; Graziano, A. ; Farina, A. ; Mellano, W. ; Ciaramaglia, F.
Author_Institution :
Selex ES, Rome, Italy
fYear :
2014
fDate :
7-10 July 2014
Firstpage :
1
Lastpage :
7
Abstract :
Scope of this paper is to investigate the performances of different identity declaration fusion algorithms in terms of probability of correct classification, supposing that the information for combination of the inferences from the different classifier is affected by measurement errors. In particular, these information have been assumed to be provided in the form of confusion matrices. Six identity fusion algorithms from literature with different complexity have been included in the comparison: heuristic methods such as voting and Borda Count, Bayes´ and Dempster-Shafer´s methods and the Proportional Redistribution Rule n° 1 in the Dempster-Shafer´s framework.
Keywords :
Bayes methods; estimation theory; inference mechanisms; matrix algebra; pattern classification; sensor fusion; uncertainty handling; Bayes method; Borda count method; Dempster-Shafer method; classification probability; confusion matrix estimation; heuristic methods; identity declaration fusion algorithms; measurement errors; proportional redistribution rule; Accuracy; Classification algorithms; Complexity theory; Estimation; Inference algorithms; Monte Carlo methods; Sensors; confusion matrix; identity fusion; target classification;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Fusion (FUSION), 2014 17th International Conference on
Conference_Location :
Salamanca
Type :
conf
Filename :
6916062
Link To Document :
بازگشت