2018³â Ãß°èÇмú´ëȸ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
LSTM ±â¹ýÀ» Àû¿ëÇÑ UTD µ¥ÀÌÅÍ Çൿ ºÐ·ù |
¿µ¹®Á¦¸ñ(English Title) |
Classification of Behavior of UTD Data using LSTM Technique |
ÀúÀÚ(Author) |
Á¤°Ü¿î
¾ÈÁö¹Î
½Åµ¿ÀÎ
¿ø°Ç
¹ÚÁ¾¹ü
Jeung Gyeo-wun
Ahn Ji-min
Shin Dong-in
Won Geon
Park Jong-bum
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 22 NO. 02 PP. 0477 ~ 0479 (2018. 10) |
Çѱ۳»¿ë (Korean Abstract) |
º» ¿¬±¸´Â Àΰø½Å°æ¸ÁÀÇ ÇÑ Á¾·ùÀÎ LSTM(Long Short-Term Memory) ±â¹ýÀ» È°¿ëÇϱâ À§ÇÏ¿© ÁøÇàÇÏ¿´´Ù. UTD(University of Texas at Dallas)°¡ °ø°³ÇÑ 27Á¾ µ¿ÀÛ µ¥ÀÌÅÍ Áß 3Ãà °¡¼Óµµ ¹× °¢¼Óµµ µ¥ÀÌÅ͸¦ ±âº» LSTM ¹× Deep Residual Bidir-LSTM ±â¹ý¿¡ Àû¿ëÇÏ¿© ÇൿÀ» ºÐ·ùÇØ º¸¾Ò´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
This study was carried out to utilize LSTM(Long Short-Term Memory) technique which is one kind of artificial neural network. Among the 27 types of motion data released by the UTD(University of Texas at Dallas), 3-axis acceleration and angular velocity data were applied to the basic LSTM and Deep Residual Bidir-LSTM techniques to classify the behavior.
|
Å°¿öµå(Keyword) |
LSTM Technique
Long Short-Term Memory Technique
Multimodal Human Action Dataset
acceleration
angular velocity
classification
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|