Title :
A new classification algorithm based on SJEP
Author :
Peng, Hong ; Wang, Cong ; Yu, Zong-Xiao
Author_Institution :
China Univ. of Min., Mech. & Electr. Eng., Beijing, China
Abstract :
This paper presents a new algorithm based on SJEP classification (SJEP_Classifier).The classification algorithm makes use of the distinction between JEP powerful capabilities, at the same time using the most effective jump Emerging Patterns (SJEP) as the classification is based on, enhanced the algorithm to noise tolerance, reducing the complexity of the algorithm. Experimental results show that, SJEP_Classifier than the CAB and the C4.5 classification algorithm has higher classification accuracy than JEP_Classifier higher efficiency.
Keywords :
pattern classification; tolerance analysis; SJEP classification; complexity reduction; effective jump emerging pattern; noise tolerance; Accuracy; Classification algorithms; Data analysis; Data mining; Noise reduction; Testing; Training data; CBA; Classification Algorithm; Data Mining; JEP; SJEP;
Conference_Titel :
Computer Engineering and Technology (ICCET), 2010 2nd International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-6347-3
DOI :
10.1109/ICCET.2010.5485266