Design Classification Based on Matching Graph Kernels

被引：0

作者：

Strug, Barbara ^{[1
]}

Slusarczyk, Grazyna ^{[1
]}

Grabska, Ewa ^{[1
]}

机构：

[1] Jagiellonian Univ, Dept Phys Astron & Appl Comp Sci, Lojasiewicza 11, PL-30059 Krakow, Poland

来源：

MAN-MACHINE INTERACTIONS 5, ICMMI 2017 | 2018年 / 659卷

关键词：

Design patterns; Machine learning; Graph classification; Graph kernels;

D O I：

10.1007/978-3-319-67792-7_44

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The paper deals with the problem of classification of designs according to their styles. The designs are represented by means of labelled, attributed graphs. The similarity between designs is calculated with the use of a new graph kernel and then used to predict if a given design belongs to a certain style of designs. The prediction process is performed by a classification algorithm. Examples of garden designs are used to present experimental results obtained by means of the presented method.

引用

页码：449 / 458

页数：10

共 13 条

[1] Agrawal R., 1993, SIGMOD Record, V22, P207, DOI 10.1145/170036.170072
[2] [Anonymous], 2003, SIGKDD Explorations, DOI DOI 10.1145/959242.959248
[3] [Anonymous], 2003, ICML
[4] [Anonymous], 2002, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
[5] [Anonymous], 1999, TECHNICAL REPORT
[6] Borgwardt K. M., 2005, 5 IEEE INT C DATA MI, DOI DOI 10.1109/ICDM.2005.132
[7] Recent advances in graph-based pattern recognition with applications in document analysis
Bunke, Horst
Riesen, Kaspar
[J]. PATTERN RECOGNITION, 2011, 44 (05) : 1057 - 1067
[8] Gärtner T, 2008, SER MACH PERCEPT ART, V72, P1
[9] Mining frequent patterns without candidate generation: A frequent-pattern tree approach
Han, JW
Pei, J
Yin, YW
Mao, RY
[J]. DATA MINING AND KNOWLEDGE DISCOVERY, 2004, 8 (01) : 53 - 87
[10] Inokuchi A, 2000, LECT NOTES COMPUT<D>, V1910, P13

← 1 2 →