New Association Rule Mining on Multiband Satellitic Image Data

被引:0
作者
Wang, Hai-hui [1 ]
Ren, Min [1 ]
机构
[1] Wuhan Inst Technol, Sch Engn & Comp Sci, Wuhan 430073, Peoples R China
来源
2008 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-11 | 2008年
关键词
Association Rule Mining; Data Mining; Multiband Satellitic Image Data; Transaction Patterns;
D O I
10.1109/CCDC.2008.4597944
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Association rule mining is one of the most important problems of data mining. Since multi-band image data contains huge amounts of information, it's a very potent area to discover useful rules. Compared to traditional market "basket data", multiband satellitic image has specific characteristics and also presents specific difficulties. Two problems need to be solved to apply Association rule mining on multiband satellitic images. The first is to deal with quantitative attributes. The second is to efficiently handle huge quantities of information. For the first problem, partitioning quantitative data into intervals is a simple but effective way. For the second problem, we propose a new approach based on transaction patterns and occurrence counting, which simplifies the calculation of support and is much more efficient. A modified apriori algorithm is given for which performance analysis shows obvious improvements.
引用
收藏
页码:3322 / 3325
页数:4
相关论文
共 6 条
  • [1] Parallel mining of association rules
    Agrawal, R
    Shafer, JC
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1996, 8 (06) : 962 - 969
  • [2] Agrawal R., 1994, Proceedings of the 20th International Conference on Very Large Data Bases. VLDB'94, P487
  • [3] Das K, 2000, INFORMATION REUSE AND INTEGRATION, P111
  • [4] Gibson P., 2000, INTRO REMOTE SENSING
  • [5] Miller H., 2001, GEOGRAPHIC DATA MINI
  • [6] PERRIZO W, 2001, LNCS, V2118, P274