Browse

A design framework for hierarchical ensemble of multiple feature extractors and multiple classifiers

Cited 24 time in Web of Science Cited 18 time in Scopus
Authors
Kim, Kyounghoon; Lin, Helin; Choi, Jin Young; Choi, Kiyoung
Issue Date
2016-04
Publisher
ELSEVIER SCI LTD
Citation
Pattern Recognition, Vol.52, pp. 1-16
Keywords
A design framework for hierarchical ensemble of multiple feature extractors and multiple classifiers자연과학Ensemble of detection systemsMultiple feature extractorsMultiple classifiersPedestrian detectionReinforcement learningBayesian network
Abstract
It is well-known that ensemble of classifiers can achieve higher accuracy compared to a single classifier system. This paper pays attention to ensemble systems consisting of multiple feature extractors and multiple classifiers (MFMC). However, MFMC increases the system complexity dramatically, leading to a highly complex combinatorial optimization problem. In order to overcome the complexity while exploiting the diversity of MFMC, we suggest in this paper a hierarchical ensemble of MFMC and its optimizing framework. By constructing local groups of feature extractors and classifiers and then combining them as a global group, the approach achieves a better scalability. Both reinforcement machine learning and Bayesian networks are adopted to enhance the accuracy. We apply the proposed method to vision based pedestrian detection and recognition of handwritten numerals. Experimental results show that the proposed framework outperforms the previous ensemble methods in terms of accuracy. (C) 2015 Elsevier Ltd. All rights reserved.
ISSN
0031-3203
Language
English
URI
https://hdl.handle.net/10371/116941
DOI
https://doi.org/10.1016/j.patcog.2015.11.006

https://doi.org/10.1016/j.patcog.2015.11.006
Files in This Item:
There are no files associated with this item.
Appears in Collections:
College of Engineering/Engineering Practice School (공과대학/대학원)Dept. of Electrical and Computer Engineering (전기·정보공학부)Journal Papers (저널논문_전기·정보공학부)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse