Title :
Accuracy of Classifier Combining Based on Majority Voting
Author :
Hong, Peng ; Chengde, Lin ; Linkai, Luo ; Qifeng, Zhou
Author_Institution :
Xiamen Univ., Xiamen
fDate :
May 30 2007-June 1 2007
Abstract :
In this paper, we formulate the accuracy of classifier combining which is based on majority voting, there are only two parameter involved, one is the average accuracy of individual classifiers, the other we call it lapsed accuracy (LA) is related with the efficiency of classifier combining, and we discuss the theoretical bounds of majority voting via the formula.
Keywords :
combinatorial mathematics; pattern classification; classifier combining accuracy; lapsed accuracy; majority voting; Authentication; Automatic control; Automation; Data processing; Diversity reception; Error analysis; Estimation error; Handwriting recognition; Probability; Voting; Lapsed Accuracy; classifier combination; classifier design and evaluation; combination accuracy; majority voting; theoretical bounds;
Conference_Titel :
Control and Automation, 2007. ICCA 2007. IEEE International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4244-0818-4
Electronic_ISBN :
978-1-4244-0818-4
DOI :
10.1109/ICCA.2007.4376843
