a risk profile for information fusion algorithms信息融合算法的风险.pdfVIP

Entropy 2011, 13, 1518-1532; doi:10.3390/ OPEN ACCESS entropy ISSN 1099-4300 /journal/entropy Article A Risk Profile for Information Fusion Algorithms Kenric P. Nelson 1,*, Brian J. Scannell 1 and Herbert Landau 2 1 Raytheon Integrated Defense Systems, 235 Presidential Way, Woburn, MA 01801, USA; E-Mail: Brian_J_Scannell@ 2 Raytheon Integrated Defense Systems, 2461 S. Clark St., Suite 1000, Arlington, VA 22202, USA; E-Mail: Herbert_Landau@ * Author to whom correspondence should be addressed; E-Mail: Kenric_P_Nelson@. Received: 17 May 2011; in revised form: 4 August 2011 / Accepted: 11 August 2011 / Published: 17 August 2011 Abstract: E.T. Jaynes, originator of the maximum entropy interpretation of statistical mechanics, emphasized that there is an inevitable trade-off between the conflicting requirements of robustness and accuracy for any inferencing algorithm. This is because robustness requires discarding of information in order to reduce the sensitivity to outliers. The principal of nonlinear statistical coupling, which is an interpretation of the Tsallis entropy generalization, can be used to quantify this trade-off. The coupled-surprisal, p 1 ln (p ) , is a generalization of Shannon surprisal or the logarithmic scoring rule, given a forecast p of a true event by an inferencing algorithm. The coupling parameter 1 q , where q