Choquet integral ridge regression

Authors

Siva K. Kakula, College of Computing
Anthony Pinar, Michigan Technological UniversityFollow
Timothy C. Havens, Michigan Technological UniversityFollow
Derek T. Anderson, University of Missouri

Document Type

Conference Proceeding

Publication Date

8-26-2020

Department

Department of Electrical and Computer Engineering; College of Computing

Abstract

The Choquet integral (ChI) is an aggregation function that is defined with respect to a fuzzy measure (FM). Many ChI-based decision aggregation methods have been proposed to learn the underlying FM. However, FM's boundary and monotonicity constraints have limited the applicability of such methods to decision-level fusion. In a recent work, we removed the constraints on FM to develop a regression model based on the ChI. Our model has a generalized bias that enables capability beyond previously proposed ChI regression approaches. We also developed an approach for learning the parameters of the ChI regression from training data. In this paper, we develop a method to apply ℓ2-regularization on our training algorithm. In our experiments on real-world benchmark data sets, ridge regularized-ChI regression has outperformed the unregularized version in 22 out of 30 (73%) experiments. Also, when compared with several competing regression methods, results show that our approach has superior performance.

Publisher's Statement

© 2020 IEEE. Publisher’s version of record: https://doi.org/10.1109/FUZZ48607.2020.9177657

Publication Title

IEEE International Conference on Fuzzy Systems

ISBN

9781728169323

Recommended Citation

Kakula, S., Pinar, A., Havens, T. C., & Anderson, D. (2020). Choquet integral ridge regression. IEEE International Conference on Fuzzy Systems, 2020-July. http://doi.org/10.1109/FUZZ48607.2020.9177657
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/14431