Title :
Acquisition of Characteristic TTSP Graph Patterns by Genetic Programming
Author :
Nagai, Satoshi ; Miyahara, Tetsuhiro ; Suzuki, Yusuke ; Uchida, Tomoyuki
Author_Institution :
Grad. Sch. of Inf. Sci., Hiroshima City Univ., Hiroshima, Japan
Abstract :
Machine learning and data mining from graph structured data are studied intensively. TTSP (Two-Terminal Series Parallel) graphs are used as data models for electric networks and scheduling. A TTSP graph is a directed a cyclic graph obtained by recursively applying "series" and "parallel" operations. We propose an evolutionary method for acquiring characteristic TTSP graph patterns from positive and negative data by using Genetic Programming.
Keywords :
data mining; directed graphs; genetic algorithms; learning (artificial intelligence); characteristic TTSP graph patterns; data mining; directed acyclic graph; electric networks; electric scheduling; evolutionary method; genetic programming; graph structured data; machine learning; negative data; positive data; two-terminal series parallel graphs; Data mining; Educational institutions; Evolutionary computation; Genetic programming; Sociology; Statistics; genetic programming; graph mining; machine learning;
Conference_Titel :
Advanced Applied Informatics (IIAIAAI), 2012 IIAI International Conference on
Conference_Location :
Fukuoka
Print_ISBN :
978-1-4673-2719-0
DOI :
10.1109/IIAI-AAI.2012.73
