Separation of data via concurrently determined discriminant functions

Authors:
Hong Seo Ryoo;Kwangsoo Kim
Affiliations:
Division of Information Management Engineering, Korea University, Seoul, Korea;Division of Information Management Engineering, Korea University, Seoul, Korea
Venue:
TAMC'07 Proceedings of the 4th international conference on Theory and applications of models of computation
Year:
2007

Citing 11
Cited 0

Symbolic and Neural Learning Algorithms: An Experimental Comparison

Machine Learning
Very Simple Classification Rules Perform Well on Most Commonly Used Datasets

Machine Learning
Bilinear separation of two sets in n-space

Computational Optimization and Applications
The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
Advanced Scout: Data Mining and Knowledge Discovery in NBA Data

Data Mining and Knowledge Discovery
The Surgical Separation of Sets

Journal of Global Optimization
Analysis of Bounds for Multilinear Functions

Journal of Global Optimization
An Implementation of Logical Analysis of Data

IEEE Transactions on Knowledge and Data Engineering
Training Support Vector Machines: an Application to Face Detection

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A system for induction of oblique decision trees

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a mixed 0 - 1 integer and linear programming (MILP) model for separation of data via a finite number of nonlinear and nonconvex discriminant functions. The MILP model concurrently optimizes the parameters of the user-provided individual discriminant functions and implements a decision boundary for an optimal separation of data under analysis. The MILP model is extensively tested on six well-studied datasets in data mining research. The comparison of numerical results by the MILP-based classification of data with those produced by the multisurface method and the support vector machine in these experiments and the best from the literature illustrates the efficacy and the usefulness of the new MILP-based classification of data for supervised learning.