FCBF is a fast correlation-based filter algorithm designed for
high-dimensional data and has been shown effective in removing
both irrelevant features and redundant features.
Method Signature:
[out] = fsFCBF(X,Y)
Output:
out: A struct containing the field 'fList', the list of features relevant
for further processing.
Input:
X:
The features on current trunk, each column is a feature vector on all
instances, and each row is a part of the instance.
Y:
The label of instances, in single column form: 1 2 3 4 5 ...
BibTex entry for:
Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution by L. Yu and H. Liu.
Discretization: An Enabling Technique H. Liu, F. Hussain, C.L. Tan, and M. Dash.
@inproceedings{Yu-Liu2003,
author = {Liu, H. and Yu, L.},
title = {Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution},
booktitle = {Correlation-Based Filter Solution". In Proceedings of The Twentieth International Conference on Machine Leaning (ICML-03)},
year = {2003},
pages = {856--863},
address = {Washington, D.C.},
publisher = {ICM}
}
@inproceedings{ author = {Liu,
H., Hussain, F., Tan, C.L., and Dash, Manoranjan} title = {Discretization: An Enabling Technique},
booktitle = {Data Mining and Knowledge Discovery},
year = {2002},
pages = {393--423},
address = {Netherlands} publisher = {Springer Netherland}
}