Abstract
A generic fusion problem is studied for multiple sensors whose outputs are probabilistically related to their inputs according to unknown distributions. Sensor measurements are provided as iid input-output samples, and an empirical risk minimization method is described for designing fusers with distribution-free performance bounds. The special cases of isolation and projective fusers for classifiers and function estimators, respectively, are described in terms of performance bounds. The isolation fusers for classifiers are probabilistically guaranteed to perform at least as good as the best classifier. The projective fusers for function estimators are probabilistically guaranteed to perform at least as good as the best subset of estimators.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chow, C.K.: Statistical independence and threshold functions. IEEE Trans. Electronic Computers EC-16, 66–68 (1965)
Devroye, L., Gyorfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, New York (1996)
Giacinto, G., Roli, F.: Dynamic classifier selection based on multiple classifier behavior. Pattern Recognition 34, 1879–1881 (2001)
Grofman, B., Owen, G. (eds.): Information Pooling and Group Decision Making. Jai Press Inc., Greenwich (1986)
Kittler, J., Roli, F. (eds.): Multiple Classifier Systems, vol. 1857. Springer, Berlin (2000)
Kurkova, V.: Kolmogorov’s theorem and multilayer neural networks. Neural Networks 5, 501–506 (1992)
Madan, R.N., Rao, N.S.V.: Guest editorial on information/decision fusion with engineering applications. Journal of Franklin Institute 336B(2), 199–204 (1999)
Nobel, A.: Histogram regression estimation using data-dependent partitions. Annals of Statistics 24(3), 1084–1105 (1996)
Rao, N.S.V.: Distributed decision fusion using empirical estimation. IEEE Transactions on Aerospace and Electronic Systems 33(4), 1106–1114 (1996)
Rao, N.S.V.: Fusion methods in multiple sensor systems using feedforward neural networks. Intelligent Automation and Soft Computing 5(1), 21–30 (1998)
Rao, N.S.V.: To fuse or not to fuse: Fuser versus best classifier. In: SPIE Conference on Sensor Fusion: Architectures, Algorithms, and Applications II, pp. 25–34 (1998)
Rao, N.S.V.: Vector space methods for sensor fusion problems. Optical Engineering 37(2), 499–504 (1998)
Rao, N.S.V.: Multiple sensor fusion under unknown distributions. Journal of Franklin Institute 336(2), 285–299 (1999)
Rao, N.S.V.: On optimal projective fusers for function estimators. In: Second International Conference on Information Fusion, pp. 296–301 (1999)
Rao, N.S.V.: Projective method for generic sensor fusion problem. In: IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems, pp. 1–6 (1999)
Rao, N.S.V.: Finite sample performance guarantees of fusers for function estimators. Information Fusion 1(1), 35–44 (2000)
Rao, N.S.V.: On fusers that perform better than best sensor. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(8), 904–909 (2001)
Rao, N.S.V.: Multisensor fusion under unknown distributions: Finite sample performance guarantees. In: Hyder, A.K. (ed.) Multisensor Fusion, Kluwer Academic Pub., Dordrecht (2002)
Rao, N.S.V.: Nearest neighbor projective fuser for fucntion estimation. In: Proceedings of International Conference on Information Fusion (2002)
Rao, N.S.V., Iyengar, S.S.: Distributed decision fusion under unknown distributions. Optical Engineering 35(3), 617–624 (1996)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Varshney, P.K.: Distributed Detection and Data Fusion. Springer, Heidelberg (1997)
Windeatt, T., Roli, F. (eds.): Multiple Classifier Systems. Springer, Berlin (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rao, N.S.V. (2004). A Generic Sensor Fusion Problem: Classification and Function Estimation. In: Roli, F., Kittler, J., Windeatt, T. (eds) Multiple Classifier Systems. MCS 2004. Lecture Notes in Computer Science, vol 3077. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-25966-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-540-25966-4_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22144-9
Online ISBN: 978-3-540-25966-4
eBook Packages: Springer Book Archive