• 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¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) »ýÈ° ÆÐÅÏ ÀÎÁö¸¦ À§ÇÑ À̺¥Æ® ¿¬»ê ±â¹Ý ¿¹Ãø ¸ðµ¨ ÇнÀ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) An Approach to a Learning Prediction Model for Recognition of Daily Life Pattern based on Event Calculus
ÀúÀÚ(Author) ¹è¼®Çö   ¹æ¼ºÇõ   ¹ÚÇö±Ô   Àü¸íÁß   ±èÁ¦¹Î   ¹Ú¿µÅà  Seok-Hyun Bae   Sung-hyuk Bang   Hyun-Kyu Park   Myung-Joong Jeon   Je-Min Kim   Young-Tack Park  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 05 PP. 0466 ~ 0477 (2018. 05)
Çѱ۳»¿ë
(Korean Abstract)
±â°è ÇнÀ ¾Ë°í¸®ÁòÀÇ ¹ßÀü¿¡ µû¶ó ´Ù¾çÇÑ ¿µ¿ªÀÇ µ¥ÀÌÅÍ¿¡ ´ëÇÑ ºÐ¼® ¹× °á°ú¸¦ ¿¹ÃøÇÏ´Â ¿¬±¸µéÀÌ ÁøÇàµÇ°í ÀÖ´Ù. ±×·¯³ª ±âÁ¸ÀÇ µ¥ÀÌÅÍ ÀÇÁ¸ÀûÀÎ ±â°è ÇнÀ ±â¹ÝÀÇ Àǵµ ÀÎÁö ¹æ¹ý·ÐÀº ³ëÀÌÁî 󸮿¡ ´ëÇÑ ¾î·Á¿òÀÌ Á¸ÀçÇÏ°í, º¹ÇÕÀûÀ¸·Î ¹ß»ýÇÒ ¼ö ÀÖ´Â ÇàÀ§ Àǵµ¿¡ ´ëÇÑ ÀÎÁö¿¡¼­ ÇÑ°èÁ¡À» °¡Áø´Ù. º» ÇÑ°èÁ¡À» ±Øº¹Çϱâ À§ÇØ º» ³í¹®¿¡¼­´Â À̺¥Æ® ¿¬»ê(Event Calculus)À» ±â¹ÝÀ¸·Î 3´Ü°èÀÇ ÇàÀ§ ÀǵµÀÎÁö ¹æ¹ý·ÐÀ» Á¦¾ÈÇÑ´Ù. ù ¹ø° ´Ü°è´Â ½ÃÄö½º µ¥ÀÌÅÍ°¡ ¾î¶² ÀǵµÀÎÁö¸¦ ÆǺ°ÇÏ´Â Àǵµ Ãß·Ð ´Ü°èÀÌ´Ù. µÎ ¹ø° ´Ü°è´Â »õ·Ó°Ô Ãß·ÐµÈ ÇàÀ§ Àǵµ¸¦ ±â¹ÝÀ¸·Î ÀÌÀüºÎÅÍ À¯ÁöµÆ´ø ÇàÀ§ Àǵµ¿ÍÀÇ º´Çà °¡´É ¿©ºÎ¸¦ ÆÇ´ÜÇÏ´Â Ãæµ¹ ÇØ°á(Conflict Resolution) ´Ü°èÀÌ´Ù. ¸¶Áö¸·À¸·Î ¸¹Àº ³ëÀÌÁî·Î ÀÎÇØ ¹ß»ýµÇ´Â ¿À·ù¸¦ Ãß·ÐµÈ ÇàÀ§ Àǵµµé¿¡ ¹Ý¿µÇÏ´Â ³ëÀÌÁî °¨¼Ò(Noise Reduction) ´Ü°è·Î ÁøÇàµÈ´Ù. À̺¥Æ® ¿¬»ê ±â¹ý¿¡ ´ëÇÑ ¼º´É Æò°¡¸¦ À§ÇØ ½ÇÁ¦ ¼öÁýÇÑ µ¥ÀÌÅ͸¦ À籸ÃàÇÑ È¥ÇÕ °¡¿ì½Ã¾È ¸ðµ¨°ú ÈÞ¸®½ºÆ½ ±ÔÄ¢ ±â¹ÝÀÇ ¹ü¿ë µ¥ÀÌÅÍ»ý¼º ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. 5°³ÀÇ Àǵµ·Î ÀÌ·ç¾îÁø ¾à 13½Ã°£ÀÇ ½ÃÄö½º µ¥ÀÌÅÍ 300°³¸¦ »ç¿ëÇÏ¿© À̺¥Æ® ¿¬»êÀÇ ¼º´ÉÀ» ÃøÁ¤ÇÏ¿´°í, °¢ Àǵµ¿¡ ´ëÇØ À̺¥Æ® ¿¬»êÀÇ ¿¹Ãø °á°ú¿Í ½ÇÁ¦ È®·ü ¸ðµ¨ÀÌ Æò±Õ 89.3%ÀÇ ÀÏÄ¡µµ¸¦ º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Several studies have been conducted on data analysis and predicting results with the advance of machine learning algorithms. Still, there are many problems of cleaning the noise of the real-life dataset, which is disturbing a clear recognition on complex patterns of human intention. To overcome this limitation, this paper proposes an event calculus methodology with 3 additional steps for the recognition of human intention: intention reasoning, conflict resolution, and noise reduction. Intention reasoning identifies the intention of the living pattern time-series data. In conflict resolution, existing ongoing intentions and inferred intention are checked by a conflict graph, so that the intentions that can occur in parallel are inferred. Finally, for noise reduction, the inferred intention from the noise of living pattern data is filtered by the history of fluent. For the evaluation of the event calculus module, this paper also proposes data generation methodology based on a gaussian mixture model and heuristic rules. The performance estimation was conducted with 300 sequential instances with 5 intentions that were observed for 13 hours. An accuracy of 89.3% was achieved between the probabilistic model and event calculus module.
Å°¿öµå(Keyword) À̺¥Æ® ¿¬»ê   Ã߷Р  »ýÈ° ÆÐÅÏ ÀÎÁö   »ç¿ëÀÚ Àǵµ ¿¹Ãø   event calculus   reasoning   daily life pattern recognition   user intention prediction  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå