Prognostic models based on linear separability

Authors:
Leon Bobrowski
Affiliations:
Faculty of Computer Science, Bialystok Technical University, Bialystok and Institute of Biocybernetics and Biomedical Engineering, PAS, Warsaw, Poland
Venue:
ICDM'11 Proceedings of the 11th international conference on Advances in data mining: applications and theoretical aspects
Year:
2011

Citing 5
Cited 0

Applied multivariate statistical analysis

Applied multivariate statistical analysis
Design of piecewise linear classifiers from formal neurons by a basis exchange technique

Pattern Recognition
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Ranked linear models and sequential patterns recognition

Pattern Analysis & Applications
Selection of high risk patients with ranked models based on the CPL criterion functions

ICDM'10 Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects

Quantified Score

Hi-index	0.00

Visualization

Abstract

Prognostic models are often designed on the basis of learning sets in accordance with multivariate regression methods. Recently, the interval regression and the ranked regression methods have been developed. Both these methods are useful in modeling censored data used in survival analysis. Designing the interval regression models as well as the ranked regression models can be treated similarly as the problem of linear classifier designing and linked to the concept of linear separability used in pattern recognition. The term linear separability refers to the examination of separation of two sets by a hyperplane in a given feature space.