Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë
ÇѱÛÁ¦¸ñ(Korean Title) |
È®·ü ±×·¡ÇÁ ¸ðµ¨À» ÀÌ¿ëÇÑ ½º¸¶Æ®Æù »ç¿ëÀÚÀÇ À̵¿°æ·Î ÇнÀ ¹× ½Ç½Ã°£ ¿¹Ãø ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
Real-time Route Inference and Learning for Smartphone Users using Probabilistic Graphical Models |
ÀúÀÚ(Author) |
Çã¹Î¿À
°¸í±¸
ÀÓº´±Ç
Ȳ±Ô¹é
¹Ú¿µÅÃ
À庴Ź
Min-Oh Heo
Myunggu Kang
Byoung-Kwon Lim
Kyu-Baek Hwang
Young-Tack Park
Byoung-Tak Zhang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 39 NO. 06 PP. 0425 ~ 0435 (2012. 06) |
Çѱ۳»¿ë (Korean Abstract) |
½º¸¶Æ®ÆùÀº À§Ä¡, °¡¼Óµµ, ¼Ò¸®¸¦ ÃøÁ¤ÇÒ ¼ö ÀÖ´Â ¼¾¼µéÀ» žÀçÇÏ°í ÀÖÀ¸¸ç, »ç¿ëÀÚ°¡ ´Ã ÈÞ´ë ÇÏ·Á´Â ±â±â¶ó´Â Ư¼ºÀ» Áö´Ñ´Ù. ÀÌ·¯ÇÑ ¼¾¼ Á¤º¸µéÀ» ±â·ÏÇÏ¿© ¸¸µç µ¥ÀÌÅÍ ÁýÇÕÀº ½º¸¶Æ®Æù »ç¿ëÀÚÀÇ ÀÏ»óÀûÀÎ ÇൿÆÐÅÏÀ» Æ÷ÇÔÇÏ°Ô µÇ¸ç, °³ÀÎÈµÈ ¸ðµ¨¸µ¿¡ Àû¿ëÇÒ ¼ö ÀÖ´Ù. ÀÌ¿¡, º» °í¿¡¼´Â µ¿Àû º£ÀÌÁö¾È¸Á(dynamic Bayesian network)°ú Rao-Blackwellized particle filtering(RBPF)¸¦ ÀÌ¿ëÇÏ¿© °üÃøµÈ ¼¾¼°ªÀ» ±âÁØÀ¸·Î ÇöÀç »ç¿ëÀÚ°¡ ¹æ¹®ÇÏ·Á´Â Àå¼Ò ¹× ÀÌ¿ëÇÒ °æ·Î¸¦ ½Ç½Ã°£À¸·Î ¿¹ÃøÇÏ´Â ¹æ¹ý°ú ¸ðµ¨ ÇнÀ¹æ¹ýÀ» Á¦½ÃÇÏ°íÀÚ ÇÑ´Ù. À̸¦ À§ÇÏ¿© 64ÀÏ µ¿¾È GPS, °¡¼Óµµ ¼¾¼, Çൿ ÀÎÁö±â µ¥ÀÌÅ͸¦ 1ÃÊ °£°ÝÀ¸·Î ¼öÁýÇÏ¿©, ÁÖ¿ä ¹æ¹®Àå¼Ò ¹× °æ·Î¸¦ ÃßÃâÇÏ°í, ¿¹ÃøÀ» ½ÃµµÇÏ¿´´Ù. À̷κÎÅÍ, Á¦½ÃÇÑ ¸ðµ¨ÀÌ »ç¿ëÀÚÀÇ Àǵµ¸¦ ³ªÅ¸³»°í ÀÖÀ½À» È®ÀÎÇÏ¿´´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Smartphones are equipped with a rich set of embedded sensors such as accelerometer, GPS, digital compass, microphone and camera. And most smartphone users are carrying them outdoor at all times. Sensor-logged datasets contain user-specific activity patterns, which enable modeling personalized usual lives. Here, we propose a real-time route inference and learning method using dynamic Bayesian networks (DBNs) and Rao-Blackwellized particle filtering (RBPF) given sequential observed values. For experimental verification, we gathered personal sensor data of GPS, accelerometer and action recognizer for 64 days and extracted significant places and routes from them. And we predicted traveling destinations and routes probabilistically. The experimental results showed that |
Å°¿öµå(Keyword) |
½º¸¶Æ®Æù ¼¾¼ µ¥ÀÌÅÍ
Çൿ ÀνÄ
À̵¿°æ·Î ¿¹Ãø ¹®Á¦
µ¿Àû º£ÀÌÁö¾È¸Á
¶ó¿Àºí·¢À£ ÆÄƼŬ ÇÊÅÍ
smartphone sensor data
activity recognition
route prediction problem
dynamic Bayesian network
Rao-Blackwellized particle filter
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|