Feature Selection Algorithm for Palm Bio-impedance Spectroscopy based on Immune Clone

DOI

10.2991/isccca.2013.176How to use a DOI?

Keywords

palm BIS, immune clone, feature extraction, feature selection, pattern classification,

Abstract

According to the features of Palm bio-impedance spectroscopy (BIS) data, this paper suggests a kind of effective feature model of palm BIS data— elliptical model. The model combines immune clone algorithm and least squares method, establishes a palm BIS feature selection algorithm, and uses the algorithm to obtain the optimal feature subset that can completely represent the palm BIS data, and then use several classification algorithms for classification and comparison. The experimental results show that accuracy of the feature subset obtained through the algorithm in SVM classification algorithm test can reach 93.2, thereby verifying the algorithm is a valid and reliable palm BIS feature selection algorithm.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lin-tao Lü
AU  - Peng Li
AU  - Yu-xiang Yang
AU  - Fang Tan
PY  - 2013/02
DA  - 2013/02
TI  - Feature Selection Algorithm for Palm Bio-impedance Spectroscopy based on Immune Clone
BT  - Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation (ISCCCA 2013)
PB  - Atlantis Press
SP  - 702
EP  - 705
SN  - 1951-6851
UR  - https://doi.org/10.2991/isccca.2013.176
DO  - 10.2991/isccca.2013.176
ID  - Lü2013/02
ER  -