Title :
HGR: a new rule induction algorithm based on extension matrices
Author :
Chen, Weijun ; Lin, Fuzong ; Li, Jianmin ; Zhang, Bo
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Abstract :
The paper proposes a heuristic, attribute-based data mining algorithm, HGR (heuristic grouping), based on the newly-developed extension matrix approach. First, the GROUP module is used to partition the positive examples of a specific class in a given example set into different groups, and then the COMP module is used to find a conjunctive complex for each group. The empirical comparison shows that the HGR predicative accuracy is competitive with its immediate predecessor, the HCV algorithm, and the famous ID3-like algorithm C4.5
Keywords :
data mining; group theory; learning (artificial intelligence); matrix algebra; optimisation; COMP module; GROUP module; data mining; extension matrix; heuristic grouping; heuristic inductive algorithm; knowledge discovery; learning algorithms; rule induction; variable-valued logic rules; Computer science; Data mining; Decision trees; Heuristic algorithms; Intelligent systems; Laboratories; Machine learning; Machine learning algorithms; Paper technology; Partitioning algorithms;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983038
