DocumentCode :
620176
Title :
The move ensemble method
Author :
Xiaojun Wang ; Yuan Ping ; Zhizhong Mao
Author_Institution :
Inst. of Automatization, Northeastern Univ., Shenyang, China
fYear :
2013
fDate :
25-27 May 2013
Firstpage :
2726
Lastpage :
2730
Abstract :
According to the analysis of the position relationship between expectation value (EV) and prediction values (PV) of component models in an ensemble model, a Move Ensemble method (MEM) based on a new sampling strategy is proposed in this paper. The MEM is to create up-move training data set by increasing EVs and to create down-move training data set by decreasing EVs. Then the up-move component model and the down-move component model are built on the up-move training data set and the down-move training data set, respectively. In terms of the peculiarity of this pair component model, a nonlinear combining method, which with neural network classification principle to choose the fittest weight vector for the two component models, is used. Two simulated experiments proved that the proposed move ensemble model outperforms the single model.
Keywords :
learning (artificial intelligence); neural nets; pattern classification; sampling methods; MEM; down move component model; down move training data set; expectation value; move ensemble model; neural network classification principle; nonlinear combining method; pair component model; prediction value; sampling strategy; up move component model; up move training data set; weight vector; Computational modeling; Data models; Mathematical model; Neural networks; Predictive models; Training data; Down-move component model; Down-move training data set; Move Ensemble method; Up-move component model; Up-move training data set;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2013 25th Chinese
Conference_Location :
Guiyang
Print_ISBN :
978-1-4673-5533-9
Type :
conf
DOI :
10.1109/CCDC.2013.6561405
Filename :
6561405
Link To Document :
بازگشت