Abstract
In a multiple sensor system, sensor S i, i = 1,2 ..., N, outputs Y (i) ∈ [0, 1], according to an unknown probability distribution P Y(i)|X, in response to input X ∈ [0, 1]. We choose a fuser - that combines the outputs of sensors - from a function class F = {f: [0, 1] N→[0, 1]} by minimizing empirical error based on an iid sample. If F satisfies the isolation property, we show that the fuser performs at least as well as the best sensor in a probably approximately correct sense. Several well-known fusers, such as linear combinations, special potential functions, and certain feedforward networks, satisfy the isolation property.
| Original language | English |
|---|---|
| Pages (from-to) | 904-909 |
| Number of pages | 6 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 23 |
| Issue number | 8 |
| DOIs | |
| State | Published - Aug 2001 |
Funding
The insightful comments of anonymous reviewers are gratefully acknowledged by the author. In particular, the connections between this work and a number of existing works would not have been possible without the generous input provided by the reviewers. A preliminary version of this paper has been presented in the Proceedings on the First International Conference on Multisource-Multisensor Information Fusion, pp. 19-26, 1998. This research is sponsored by the Engineering Research Program of the Office of Basic Energy Sciences, US Department of Energy, under contract no. DE-AC05-00OR22725 with UT-Battelle, LLC, and the US Office of Naval Research under order N00014-96-F-0415.
| Funders | Funder number |
|---|---|
| Office of Basic Energy Sciences | |
| US Department of Energy |
Keywords
- Fusion rule estimation
- Information fusion
- Multiple sensor system
- Sensor fusion