Approximation of Loss and Risk in Selected Granular Systems

Authors:
Marcin Szczuka
Affiliations:
Institute of Mathematics, The University of Warsaw, Warsaw, Poland 02-097
Venue:
RSFDGrC '09 Proceedings of the 12th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing
Year:
2009

Citing 5
Cited 1

Essentials of fuzzy modeling and control

Essentials of fuzzy modeling and control
Rough Sets: Theoretical Aspects of Reasoning about Data

Rough Sets: Theoretical Aspects of Reasoning about Data
Complex Patterns

Fundamenta Informaticae - Concurrency Specification and Programming (CS&P 2003)
Handbook of Granular Computing

Handbook of Granular Computing
Optimization in Discovery of Compound Granules

Fundamenta Informaticae - Concurrency Specification and Programming (CS&P)

Risk assessment in granular environments

Transactions on rough sets XIII

Quantified Score

Hi-index	0.00

Visualization

Abstract

We discuss the notion of risk in generally understood classification support systems. We consider the situation when granularity is involved in information system we work with. We propose a method for approximating the loss function and introduce a technique for assessing the empirical risk from experimental data. We discuss the general methodology and possible directions of development in the area of constructing compound classification schemes.