Combining Determinism and Intuition through Univariate Decision Strategies for Target Detection from Multi-sensors

Abstract : In many surveillance systems, an operator will have to make a decision on whether a target is present or not from the outputs of a sensor. Here, we assume that such an operator has at his or her disposal two sensors to give him or her more confidence in his decision-making process. In addition, we propose several univariate decision strategies which combine sensor characteristics, target probabilities and reward schemes together with deterministic and intuitive operator decision-making parameters. Further, using Chebyshev's inequality we develop a method for selecting the most robust strategy that mitigates poor performance. We illustrate through examples how different strategies will be more advantageous over others depending on the reward scheme and sensor parameters.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.inria.fr/hal-01058353
Contributor : Hal Ifip <>
Submitted on : Tuesday, August 26, 2014 - 4:16:35 PM
Last modification on : Friday, August 11, 2017 - 11:17:23 AM
Document(s) archivé(s) le : Thursday, November 27, 2014 - 4:20:29 PM

File

wcc02.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Edwin El-Mahassni. Combining Determinism and Intuition through Univariate Decision Strategies for Target Detection from Multi-sensors. Third IFIP TC12 International Conference on Artificial Intelligence (AI) / Held as Part of World Computer Congress (WCC), Sep 2010, Brisbane, Australia. pp.123-132, ⟨10.1007/978-3-642-15286-3_12⟩. ⟨hal-01058353⟩

Share

Metrics

Record views

85

Files downloads

56