Optimal decision methods and most notably the Bayesian decision are sensitive to uncertainty in the statistics of the patterns to be classified. Errors in the associated probabilities and distributions would degrade the performance of these methods. We present here a robust-satisficing decision-rule whose robustness to uncertainty in the priors is maximized given a performance demand. We apply the method to a two-class medical classification problem. We show that the robust-satisficing decision-rule is more robust to uncertainty in the priors than the optimal Bayesian decision-rule at sub-optimal performance levels. We present 4 propositions which characterize the robust-satisficing classifier. In addition we demonstrate the capabilities of this method when applied to uncertainty in the conditional probability density functions.
Skip Nav Destination
ASME 2008 9th Biennial Conference on Engineering Systems Design and Analysis
July 7–9, 2008
Haifa, Israel
Conference Sponsors:
- International
ISBN:
978-0-7918-4837-1
PROCEEDINGS PAPER
Info Gap Bayesian Classification Available to Purchase
Carmit Keren,
Carmit Keren
Technion-Israel Institute of Technology, Haifa, Israel
Search for other works by this author on:
Miriam Zacksenhouse,
Miriam Zacksenhouse
Technion-Israel Institute of Technology, Haifa, Israel
Search for other works by this author on:
Yakov Ben-Haim
Yakov Ben-Haim
Technion-Israel Institute of Technology, Haifa, Israel
Search for other works by this author on:
Carmit Keren
Technion-Israel Institute of Technology, Haifa, Israel
Miriam Zacksenhouse
Technion-Israel Institute of Technology, Haifa, Israel
Yakov Ben-Haim
Technion-Israel Institute of Technology, Haifa, Israel
Paper No:
ESDA2008-59188, pp. 87-91; 5 pages
Published Online:
July 6, 2009
Citation
Keren, C, Zacksenhouse, M, & Ben-Haim, Y. "Info Gap Bayesian Classification." Proceedings of the ASME 2008 9th Biennial Conference on Engineering Systems Design and Analysis. Volume 3: Design; Tribology; Education. Haifa, Israel. July 7–9, 2008. pp. 87-91. ASME. https://doi.org/10.1115/ESDA2008-59188
Download citation file:
7
Views
Related Proceedings Papers
Related Articles
Uncertainty of Integral System Safety in Engineering
ASME J. Risk Uncertainty Part B (June,2022)
An Efficient First-Principles Saddle Point Searching Method Based on Distributed Kriging Metamodels
ASME J. Risk Uncertainty Part B (March,2018)
Effects of the Fractional Laplacian Order on the Nonlocal Elastic Rod
Response
ASME J. Risk Uncertainty Part B (September,2017)
Related Chapters
Constrained Noninformative Priors with Uncertain Constraints: A Hierarchical Simulation Approach (PSAM-0437)
Proceedings of the Eighth International Conference on Probabilistic Safety Assessment & Management (PSAM)
mDFA of an Early Date
Modified Detrended Fluctuation Analysis (mDFA)
The Final Word on Exam Questions
A Quick Guide to API 510 Certified Pressure Vessel Inspector Syllabus