Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
½º¸¶Æ®Æù»óÀÇ Áö´ÉÇü °³ÀÎÈ ¼ºñ½º¸¦ À§ÇÑ °ÀÎÇÑ ÆÄƼŬ ÇÊÅÍ ±â¹ÝÀÇ »ç¿ëÀÚ °æ·Î ¿¹Ãø |
¿µ¹®Á¦¸ñ(English Title) |
Robust Particle Filter Based Route Inference for Intelligent Personal Assistants on Smartphones |
ÀúÀÚ(Author) |
¹éÇýÁ¤
¹Ú¿µÅÃ
Haejung Baek
Young Tack Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 02 PP. 0190 ~ 0202 (2015. 02) |
Çѱ۳»¿ë (Korean Abstract) |
½º¸¶Æ®Æù³» GPS ¹× ´Ù¾çÇÑ ¼¾¼ µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© ½º¸¶Æ®Æù »ç¿ëÀÚÀÇ À̵¿ ÆÐÅÏÀ» ÇнÀÇÏ°í, À̸¦ ±â¹ÝÀ¸·Î »ç¿ëÀÚ ¸ñÀûÁö¿Í °æ·Î¸¦ ¿¹ÃøÇÏ¿© »ç¿ëÀÚÀÇ Àǵµ¿¡ ¸Â´Â ¼ºñ½º¸¦ Á¦°øÇÏ´Â À§Ä¡±â¹Ý Áö´ÉÇü °³ÀÎÈ ¼ºñ½º(Intelligent personal assistant) ¿¬±¸°¡ È°¹ßÈ÷ ÁøÇà µÇ°í ÀÖ´Ù. À§Ä¡±â¹Ý °³ÀÎÈ ¼ºñ½ºÀÇ Áö´É¼ºÀº ºÒ¿ÏÀüÇÑ ¼¾¼ µ¥ÀÌÅͷκÎÅÍ »ç¿ëÀÚ À̵¿ Á¤º¸¸¦ ó¸®ÇÏ¿©, ½Ç½Ã°£À¸·Î »ç¿ëÀÚÀÇ °æ·Î¸¦ ¿¹ÃøÇÏ´Â Á¤È®¼º°ú È¿À²¼º¿¡ Á¿ìµÈ´Ù. º» ³í¹®Àº ºÒ¿ÏÀüÇÑ Á¤º¸·ÎºÎÅÍ »ç¿ëÀÚÀÇ °æ·Î¿Í ¸ñÀûÁö¸¦ Ãß·ÐÇÏ´Â µ¿Àû º£ÀÌÁö¾È ³×Æ®¿öÅ© ±â¹ÝÀÇ °ÀÎÇÑ ÆÄƼŬ ÇÊÅÍ(Robust particle filter)¸¦ Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÑ °ÀÎÇÑ ÆÄƼŬ ÇÊÅÍ ¹æ¹ýÀº ºÎÁ¤È®ÇÏ°í, ºÒ¿ÏÀüÇÑ ¼¾¼ Á¤º¸¸¦ º¸¿ÏÇÒ ¼ö ÀÖ´Â ÆÄƼŬ »ý¼º, ½Ç½Ã°£¿¡ °è»ê º¹Àâµµ¸¦ °¨¼Ò½ÃÅ°´Â È¿À²ÀûÀÎ ½ºÀ§Äª ÇÔ¼ö¿Í °¡ÁßÄ¡ ÇÔ¼ö, ÆÄƼŬÀÇ Á¤È®µµ¸¦ Çâ»ó½ÃÅ°´Â ÀçÇ¥º»È·Î ±¸¼ºµÇ¸ç, »ç¿ëÀÚÀÇ ¸ñÀûÁö¿Í °æ·ÎÀÇ ¿¹Ãø Á¤È®¼º°ú È¿À²¼ºÀÇ ¼º´ÉÀ» Çâ»ó½ÃÄ×´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Much research has been conducted on location-based intelligent personal assistants that can understand a user's intention by learning the user's route model and then inferring the user's destinations and routes using data of GPS and other sensors in a smartphone. The intelligence of the location-based personal assistant is contingent on the accuracy and efficiency of the real-time predictions of the user's intended destinations and routes by processing movement information based on uncertain sensor data. We propose a robust particle filter based on Dynamic Bayesian Network model to infer the user's routes. The proposed robust particle filter includes a particle generator to supplement the incorrect and incomplete sensor information, an efficient switching function and an weight function to reduce the computation complexity as well as a resampler to enhance the accuracy of the particles. The proposed method improves the accuracy and efficiency of determining a user's routes and destinations.
|
Å°¿öµå(Keyword) |
°ÀÎÇÑ ÆÄƼŬ ÇÊÅÍ
°æ·Î ¿¹Ãø
À§Ä¡ ±â¹Ý Áö´ÉÇü °³ÀÎÈ ¼ºñ½º
½º¸¶Æ®Æù ¼¾¼
robust particle filtering
route inference
location-based intelligent personal assistant
smartphone sensors
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|