• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ³í¹®Áö D : µ¥ÀÌŸº£À̽º

Á¤º¸°úÇÐȸ ³í¹®Áö D : µ¥ÀÌŸº£À̽º

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) µ¥ÀÌÅÍ ¸¶À̴׿¡¼­ ºñÆ® Ŭ·¯½ºÅ͸µÀ» ÀÌ¿ëÇÑ Çâ»óµÈ FP-Growth
¿µ¹®Á¦¸ñ(English Title) Advanced FP-Growth using Bit Clustering in Data Mining
ÀúÀÚ(Author) ±èÀÇÂù   Ȳº´¿¬   Eui-Chan Kim   Byung-Yeon Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 38 NO. 05 PP. 0280 ~ 0288 (2011. 10)
Çѱ۳»¿ë
(Korean Abstract)
¸¹Àº µ¥ÀÌÅÍ ¸¶ÀÌ´× ±â¹ýµé Áß¿¡ ¿¬°ü±ÔÄ¢À» ´Ù·ç´Â ¿¬±¸°¡ ¸¹ÀÌ ÀÌ·ïÁö°í ÀÖ´Ù. ¿¬°ü±ÔÄ¢ ±â¹ýµµ ´Ù¾çÇÏ°Ô ¿¬±¸µÇ°í Àִµ¥ ±× Áß ºó¹ß ÆÐÅÏ Æ®¸®(FP-Tree)¶ó´Â ¹æ¹ýÀ» ÀÌ¿ëÇÏ¿© ºó¹ß ÆÐÅÏÀ» ã¾Æ³»´Â ¿¬±¸°¡ È°¹ßÈ÷ ÁøÇàµÇ°í ÀÖ´Ù. ºó¹ß ÆÐÅÏ Æ®¸®´Â ±âÁ¸¿¡ Àß ¾Ë·ÁÁ® ÀÖ´Â ¿¬°ü±ÔÄ¢ »ý¼º ±â¹ýÀÎ Apriori ±â¹ýº¸´Ù ¿ì¼öÇÑ ¼º´ÉÀ» °¡Áö´Â ¹æ¹ýÀÌ´Ù. ±×·¯³ª ºó¹ß ÆÐÅÏ Æ®¸®´Â °úµµÇÑ Å©±âÀÇ FP-Tree¸¦ »ý¼ºÇÏ¿© ¼öÇà ¼º´ÉÀ» ¶³¾î¶ß¸®´Â ¹®Á¦Á¡À» °¡Áö°í ÀÖ´Ù. ÀÌÀü ¿¬±¸¿¡¼­´Â ÀÌ ¹®Á¦¸¦ ÇØ°áÇÏ¿´Áö¸¸ ¸ðµç µ¥ÀÌÅÍÁýÇÕ¿¡ Àû¿ëÇϱ⿡´Â ¹®Á¦°¡ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÀÌ·¯ÇÑ ¹®Á¦°¡ ¹«¾ùÀÎÁö »ìÆ캸°í, À̸¦ ÇØ°áÇϱâ À§ÇØ B-Trans+ Ŭ·¯½ºÅ͸µÀ» Á¦¾ÈÇÑ´Ù. À̸¦ ÀÌ¿ëÇÏ¿© Á» ´õ È¿À²ÀûÀ¸·Î °úµµÇÑ Å©±âÀÇ FP-Tree »ý¼ºÀ» ÁÙ¿© ¸Þ¸ð¸® °ø°£ »ç¿ëÀ» ÁÙÀÌ°í ±ÔÄ¢ »ý¼º ¼öÇà ¼º´ÉÀ» Çâ»ó½ÃÄ×´Ù.
¿µ¹®³»¿ë
(English Abstract)
Numerous studies have dealt with the association rules of a number of data mining techniques. From this point of view, studies identifying frequent patterns using frequent pattern trees are progressing actively. The FP-Growth technique using a frequent pattern tree shows superior performance over the existing well-known "Apriori" technique. However, the FP-Tree has a problem that is to degrade performance because of the considerable FP-Tree size. This problem is solved to previous research, but it has another problem to be inapplicable to all dataset. In this paper, we look at what is this problem, and propose the clustering of B-Trans to solve the problem. As we reduce more effectively the fairly large size created by FP-Tree by using B-Trans , memory size is decreased and the performance of creating rules is enhanced.
Å°¿öµå(Keyword) µ¥ÀÌÅÍ ¸¶ÀÌ´×   µ¥ÀÌÅͺ£À̽º   ¿¬°ü±ÔÄ¢   Ŭ·¯½ºÅ͸µ   data mining   database   association rules   clustering   FP-Growth  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå