Abstract
propose an efficient data mining system for making quick response to users and providing a friendly interface. When data tuples have higher relationship, it could contain long frequent itemsets. If apriori algorithm mines all frequent itemsets in those tuples, its candidate itemsets will become very huge and it has to scan database huge times. Meanwhile, the number of rules mined by the apriori algorithm is huge. Our method avoids mining rules through huge candidate itemsets, just mines maximal frequent itemsets and scans the database for the frequent itemsets users are interested in. First, use GA to mine the maximal frequent itemsets and show them to users. Second, let users pick up one to deduce the association rules. Final, scan the database for the real support and confidence and show them to users. So, our method can not only save many times scanning the database and make quick response to users, but provide a friendly interface that let users select his interesting rules to mine.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the SICE Annual Conference |
| Pages | 1214-1219 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2008 |
| Event | SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology - Tokyo Duration: 2008 Aug 20 → 2008 Aug 22 |
Other
| Other | SICE Annual Conference 2008 - International Conference on Instrumentation, Control and Information Technology |
|---|---|
| City | Tokyo |
| Period | 08/8/20 → 08/8/22 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Control and Systems Engineering
- Computer Science Applications
Cite this
Quick response data mining model using genetic algorithm. / Dou, Wenxiang; Furuzuki, Takayuki; Hirasawa, Kotaro; Wu, Gengfeng.
Proceedings of the SICE Annual Conference. 2008. p. 1214-1219 4654843.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Quick response data mining model using genetic algorithm
AU - Dou, Wenxiang
AU - Furuzuki, Takayuki
AU - Hirasawa, Kotaro
AU - Wu, Gengfeng
PY - 2008
Y1 - 2008
N2 - propose an efficient data mining system for making quick response to users and providing a friendly interface. When data tuples have higher relationship, it could contain long frequent itemsets. If apriori algorithm mines all frequent itemsets in those tuples, its candidate itemsets will become very huge and it has to scan database huge times. Meanwhile, the number of rules mined by the apriori algorithm is huge. Our method avoids mining rules through huge candidate itemsets, just mines maximal frequent itemsets and scans the database for the frequent itemsets users are interested in. First, use GA to mine the maximal frequent itemsets and show them to users. Second, let users pick up one to deduce the association rules. Final, scan the database for the real support and confidence and show them to users. So, our method can not only save many times scanning the database and make quick response to users, but provide a friendly interface that let users select his interesting rules to mine.
AB - propose an efficient data mining system for making quick response to users and providing a friendly interface. When data tuples have higher relationship, it could contain long frequent itemsets. If apriori algorithm mines all frequent itemsets in those tuples, its candidate itemsets will become very huge and it has to scan database huge times. Meanwhile, the number of rules mined by the apriori algorithm is huge. Our method avoids mining rules through huge candidate itemsets, just mines maximal frequent itemsets and scans the database for the frequent itemsets users are interested in. First, use GA to mine the maximal frequent itemsets and show them to users. Second, let users pick up one to deduce the association rules. Final, scan the database for the real support and confidence and show them to users. So, our method can not only save many times scanning the database and make quick response to users, but provide a friendly interface that let users select his interesting rules to mine.
UR - http://www.scopus.com/inward/record.url?scp=56749165602&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=56749165602&partnerID=8YFLogxK
U2 - 10.1109/SICE.2008.4654843
DO - 10.1109/SICE.2008.4654843
M3 - Conference contribution
AN - SCOPUS:56749165602
SN - 9784907764296
SP - 1214
EP - 1219
BT - Proceedings of the SICE Annual Conference
ER -