• 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 : 6 / 7 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¿Ö°î Á¦°Å ½Ã°è¿­ ¼­ºê½ÃÄö½º ¸ÅĪ¿¡¼­ ºü¸¥ À妽º ±¸¼º¹ý
¿µ¹®Á¦¸ñ(English Title) Fast Index Construction in Distortion-Free Time-Series Subsequence Matching
ÀúÀÚ(Author) ±æ¸í¼±   ±è¹ü¼ö   ¹®¾ç¼¼   ±èÁøÈ£   Myeong-Seon Gil   Bum-Soo Kim   Yang-Sae Moon   Jinho Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 38 NO. 06 PP. 0367 ~ 0380 (2011. 12)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ¿Ö°î Á¦°Å ½Ã°è¿­ ¼­ºê½ÃÄö½º ¸ÅĪ¿¡¼­ À妽º¸¦ È¿À²ÀûÀ¸·Î ±¸¼ºÇÏ´Â ¹æ¹ýÀ» ´Ù·é´Ù. ±âÁ¸ÀÇ ¿Ö°î Á¦°Å ½Ã°è¿­ ¼­ºê½ÃÄö½º ¸ÅĪ¿¡¼­´Â À妽º ±¸Ãà¿¡ ¸Å¿ì ¸¹Àº ½Ã°£ÀÌ °É¸®´Âµ¥, ÀÌ´Â ¿Ö°î Á¦°ÅÀÇ ¸ðµç °¡´ÉÇÑ °æ¿ì¸¦ °í·ÁÇϱâ À§ÇØ ³Ê¹« ¸¹Àº À©µµ¿ì°¡ »ý¼ºµÇ±â ¶§¹®ÀÌ´Ù. ½ÇÁ¦·Î ±æÀÌ 30¸¸ÀÇ ½Ã°è¿­ÀÎ °æ¿ì¿¡µµ À妽º ±¸ÃàÀ» À§ÇØ ¾à 100ºÐÀÇ ¸¹Àº ½Ã°£ÀÌ °É·Á, ´ë¿ë·® ½Ã°è¿­ µ¥ÀÌÅÍ¿¡ ´ëÇؼ­´Â À妽º ±¸ÃàÀÌ ¸Å¿ì ¾î·Á¿î ´ÜÁ¡ÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ±âÁ¸ À妽º ±¸Ãà °úÁ¤À» ´Ü°èº°·Î Á¤ÇüÀûÀ¸·Î ºÐ¼®ÇÑ ÈÄ, °¢ ´Ü°èº° ¼º´É ±Ø´ëÈ­ ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ƯÈ÷, µ¿Àû ÇÁ·Î±×·¡¹Ö ±â¹ýÀ» ÀÌ¿ëÇÏ¿© PAA-¹öŶ ¹× DF-¹öŶ(distortion-free bucket)ÀÇ °³³äÀ» Á¦¾ÈÇϴµ¥, ÀÌ´Â ¹Ýº¹µÇ´Â °è»ê °á°ú¸¦ ÀúÀå-ÈÄ-Àç»ç¿ë(store-and-reuse)ÇÏ´Â ±â¹ýÀ¸·Î, À̸¦ »ç¿ëÇÏ¿© ±âÁ¸ ¹æ¹ý¿¡ ºñÇØ È¿À²ÀûÀÎ À妽º ±¸ÃàÀÌ °¡´ÉÇÏ´Ù. º» ³í¹®¿¡¼­´Â º¹Àâµµ ºÐ¼® ¹× ½ÇÇè Æò°¡¸¦ ÅëÇØ Á¦¾ÈÇÑ ¹æ¹ýÀÇ ¿ì¼ö¼ºÀ» ÀÔÁõÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper we present an efficient approach of constructing a multidimensional index in distortion-free time-series subsequence matching. Index construction of previous distortion-free subsequence matching algorithms is a very time-consuming process since it generates a huge number of windows to consider all possible positions and all possible query lengths. According to the real experiment, the index construction time reaches approximately 100 minutes for a time-series of length 300K, and this means that the index construction itself is very difficult for very large time-series databases. To solve this problem, in this paper we first thoroughly analyze the index construction steps, then discuss how to improve the performance of each step, and finally propose two advanced algorithms of efficiently constructing an index. In particular, by exploiting dynamic programming techniques, we present the concepts of PAA-bucket and DF(distortion-free)-bucket, which store-and-reuse the intermediate results repeatedly computed. Through the store-and-reuse technique, the proposed algorithms construct a multidimensional index very faster than the previous algorithm. Through analytical and empirical evaluations, we showcased the superiority of the proposed algorithms.
Å°¿öµå(Keyword) ½Ã°è¿­ µ¥ÀÌÅͺ£À̽º   µ¥ÀÌÅÍ ¸¶ÀÌ´×   ¿Ö°î Á¦°Å ½Ã°è¿­   À妽º ±¸¼º¹ý   À¯»ç ½ÃÄö½º ¸ÅĪ   Time-series databases   data mining   distortion-free time-series   index construction   similar sequence matching  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå