TY - GEN
T1 - The study of unstable cut-point decision tree generation based-on the partition impurity
AU - WANG, Xi-Zhao
AU - ZHAO, Hui-Qin
AU - WANG, Shuai
N1 - This research is supported by the Natural Science Foundation of Hebei Province (F2008000635), by the key project foundation of applied fundamental research of Hebei Province (08963522D), by the plan of 100 excellent innovative scientists of the first group in Education Department of Hebei Province, by the Scientific Research Foundation of Hebei Province (06213548), and by the youth natural science foundation of Hebei University (2008Q01).
PY - 2009
Y1 - 2009
N2 - This paper is to discuss the reduction of computation complexity in decision tree generation for the numerical-valued attributes. The proposed method is based on the partition impurity. The partition impurity minimization is used to select the expanded attribute for generation the sub-node during the tree growth. After inducing the unstable cut-points of numerical-attributes, it is analytically proved that the partition impurity minimization can always be obtained at the unstable cut-points. It implies that the computation on stable cut-points may not be considered during the tree growth. Since the stable cut-points are far more than unstable cut-points, the experimental results show that the proposed method can reduce the computational complexity greatly.
AB - This paper is to discuss the reduction of computation complexity in decision tree generation for the numerical-valued attributes. The proposed method is based on the partition impurity. The partition impurity minimization is used to select the expanded attribute for generation the sub-node during the tree growth. After inducing the unstable cut-points of numerical-attributes, it is analytically proved that the partition impurity minimization can always be obtained at the unstable cut-points. It implies that the computation on stable cut-points may not be considered during the tree growth. Since the stable cut-points are far more than unstable cut-points, the experimental results show that the proposed method can reduce the computational complexity greatly.
KW - Gini Index
KW - Information entropy
KW - Numerical-valued attributes decision trees
KW - Partition impurity
KW - Unstable cut-point
UR - http://www.scopus.com/inward/record.url?scp=70350738634&partnerID=8YFLogxK
U2 - 10.1109/ICMLC.2009.5212144
DO - 10.1109/ICMLC.2009.5212144
M3 - Conference paper (refereed)
AN - SCOPUS:70350738634
SN - 9781424437023
T3 - International Conference on Machine Learning and Cybernetics (ICMLC)
SP - 1891
EP - 1897
BT - Proceedings of the 2009 International Conference on Machine Learning and Cybernetics
PB - IEEE
T2 - 2009 International Conference on Machine Learning and Cybernetics
Y2 - 12 July 2009 through 15 July 2009
ER -