Feature Selection Based on Function Model of Game Fusion

DOI

10.2991/eeic-13.2013.29How to use a DOI?

Keywords

game theory; information fusion; feature selection

Abstract

The paper introduces a new method of feature selection through the function model of game fusion. We use the traditional three steps of accomplishing feature selection by the fusion model: Firstly, fusion model can preprocess the input information, classify the information into conflict data, redundant data and complementary data, and filter the conflict data. Then, it transmits the preprocessed data to the modules of the information center. Finally, fusion model achieves the optimal situation through the fusion algorithm. We discover the complexity of these three steps will be high when the size of features is huge. Therefore, we draw on the experience of feature division and reduce the size of strategy set from power set of features to the features set.

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 Gu
AU  - Yang Zeng
AU  - Shardrom Johnson
AU  - Daniel Hsu
PY  - 2013/12
DA  - 2013/12
TI  - Feature Selection Based on Function Model of Game Fusion
BT  - Proceedings of the 3rd International Conference on Electric and Electronics
PB  - Atlantis Press
SP  - 123
EP  - 126
SN  - 1951-6851
UR  - https://doi.org/10.2991/eeic-13.2013.29
DO  - 10.2991/eeic-13.2013.29
ID  - Gu2013/12
ER  -