• 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 B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ´ëÁß±³Åë ÀÌ¿ë ±ËÀû ºÐ¼®¿¡ ÀÇÇÑ »ó½À °æ·Î ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) Personalized Habitual Path Classification based on Public Transportation Trajectory
ÀúÀÚ(Author) ÃÖÁ¤È­   ÀÌÇâÁø   ±èÀºÁÖ   ¹éÇýÁ¤   ¹Ú¿µÅà  Jung-Hwa Choi   Hyang-Jin Lee   Eunju Kim   Hea-Jung Back   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 39 NO. 03 PP. 0225 ~ 0235 (2012. 03)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº Hi-path Navi(habitual path navigator)¶ó ºÒ¸®´Â °³ÀÎÀÇ ´ëÁß±³Åë À̵¿ ±ËÀû¿¡ µû¸¥ »ó½À °æ·Î ºÐ·ù ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Hi-path Navi´Â ½º¸¶Æ®ÆùÀÇ GPS ¼¾¼­·ÎºÎÅÍ ¼öÁýÇÑ ´ë·®ÀÇ À§Ä¡¿Í ¼Óµµ Á¤º¸¸¦ ÅëÇØ °³ÀÎÀÇ À̵¿ ±ËÀûÀ» ÇнÀÇÏ¿© »ó½À °æ·Î(Áï »ó½ÀÀû Á¤Ã¼ ±¸°£ ¶Ç´Â Ãâ/Åð±Ù ¹ö½º °æ·Î)¸¦ ºÐ·ùÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ³× °¡Áö ±â¼úÀ» Æ÷ÇÔÇÑ´Ù. ù°, À̹ÌÁö ó¸® ¾Ë°í¸®ÁòÀ» »ç¿ëÇÏ¿© ´ë·®ÀÇ GPS Á¤º¸ Áß¿¡ ±³ÅëÀ» ÀÌ¿ëÇÑ ±¸°£À» ÃßÃâÇÑ´Ù. ´ÙÀ½À¸·Î, ±³Åë ±¸°£ ³» ÀÌ¿ëÇÑ ¹ö½º ³ë¼±À» ÀÎÁöÇϱâ À§ÇØ ¼Óµµ Á¤º¸¸¦ ºÐ¼®ÇÏ¿© Á¤Áö ±¸°£À» ÃßÃâÇÑ´Ù. ±×¸®°í ±³Åë ±¸°£ ³» ½ÃÀÛ°ú ³¡ À§Ä¡¸¦ Áö³ª´Â ¹ö½º ³ë¼±ÀÇ Èĺ¸ ÁýÇÕÀ» ±¸ÇÑ´Ù. ¸¶Áö¸·À¸·Î °³ÀÎÀÌ ÀÌ¿ëÇÑ ±ËÀû°ú °¡Àå À¯»çÇÑ ¹ö½º ³ë¼±À» ã´Â´Ù. À̸¦ À§ÇØ Á÷±³ °Å¸®¸¦ ÀÌ¿ëÇÑ´Ù. º» ¿¬±¸´Â »ó½ÀÀûÀÎ Á¤Ã¼±¸°£ÀÌ ¸¹Àº Çѱ¹ÀÇ ¼­¿ï Áö¿ª¿¡¼­ 3¸íÀÇ »ç¿ëÀÚ°¡ 8ÁÖ µ¿¾È ¼öÁýÇÑ ½ÇÁ¦ À̵¿±ËÀû µ¥ÀÌÅÍ·Î ½ÇÇèÇÏ¿´´Ù. ½ÇÇèÇÑ °á°ú, »ç¿ëÀÚ°¡ ½ÇÁ¦ ÀÌ¿ëÇÏ´Â ¹ö½º ¹øÈ£¸¦ Á¤È®È÷ ¸ÂÃèÀ¸¸ç, °³ÀÎ À̵¿±ËÀû°ú ÀÏÄ¡ÇÏ´Â ½ÇÁ¦ ¹ö½º ³ë¼±ÀÇ ¹ö½º Á¤·ùÀåÀ» 93.3% Á¤È®ÇÏ°Ô Ã£¾Ò´Ù. ÀÌ °á°ú´Â À¯Å¬¸®µð¾È(euclidean) °Å¸®¿Í ¸ÇÇÏź(manhattan) °Å¸® ÃøÁ¤¹ý¿¡ ºñÇØ Æò±ÕÀûÀ¸·Î 17% ´õ Á¤È®ÇÏ°í 13¹è ºü¸¥ ¼º´ÉÀ» º¸¿´´Ù. Á¦¾ÈÇÑ ¹æ¹ýÀº ½º¸¶Æ®Æù »ç¿ëÀÚÀÇ °³ÀÎ ¿©Á¤¿¡ µû¸¥ ½Ç½Ã°£ ±³Åë Á¤º¸ ¼­ºñ½º¿¡ È°¿ëµÇ¾î »ç¿ëÀÚÀÇ ÀÎÁö·Îµå(load)¸¦ ÁÙÀÏ ¼ö ÀÖ´Ù.
¿µ¹®³»¿ë
(English Abstract)
We present a new method for assisting the automated public transportation routing services offered to smart phone users called Habitual path navigator (Hi-path Navi). Hi-path Navi uses a novel algorithm to classify the habitual paths (e.g., sections with a heavy traffic jam or one of the usual paths that lead to the user's workplace). The proposed method has four key applications: (1) extraction of transportation segments from the user's trajectories using image processing algorithm; (2) extraction of habitual stationary points to identify bus routes from transportation segments by analyzing the trajectory's velocity data; (3) detection of candidate bus routes which pass through the starting and ending point of the transportation segment; (4) finding of the most likely bus route considering habitual stationary points of transportation segments. Especially, application (4) is based on a distance measure so called rectilinear distance. We experimentally validated the proposed method using the data of the actual trajectories of three users who collected over a period of eight weeks respectively. The experimental results indicated a success rate of 100% for a comparison of an actual bus route and showed the actual bus stops matching to the user's trajectory with precision of 93.3%. This result was found to be averagely 17% more precise and 13 times faster than that of the Euclidean distance and Manhattan distance algorithms. In summary, we present a novel solution to assist an automated public transportation service offered to users during journeys and to minimize the cognitive load of the user.
Å°¿öµå(Keyword) ½º¸¶Æ®Æù   °³ÀÎ ´ëÁß ±³Åë ¼­ºñ½º   À̵¿ ±ËÀû   »ó½À °æ·Î ºÐ·ù   Á÷±³ °Å¸®   Smart Phone   GPS   Personalized Public Transportation Service   User Trajectory   Habitual Path Classification   Rectilinear Distance  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå