Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
ÇѱÛÁ¦¸ñ(Korean Title) |
Transient EMG ½ÅÈ£¸¦ ÀÌ¿ëÇÑ ¼Õ°¡¶ôÀÇ ¿òÁ÷ÀÓ ÃßÁ¤ |
¿µ¹®Á¦¸ñ(English Title) |
Estimation of Finger Motion using Transient EMG Signals |
ÀúÀÚ(Author) |
¹ÚÁø¿ø
ÃÖ°è¿ø
Jin Won Park
Kae Won Choi
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 49 NO. 02 PP. 0157 ~ 0165 (2022. 02) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ±ÙÀüµµ ½ÅÈ£¸¦ ±â¹ÝÀ¸·Î ¼Õ°¡¶ôÀÇ ¿òÁ÷ÀÓÀ» ÃßÃøÇϱâ À§ÇÑ µö ·¯´× ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ¿ì¸®´Â ¶ÇÇÑ ¸ðµ¨ÀÇ Á¤È®µµ¸¦ Æò°¡ÇÏ°í ºÐ¼®ÇÏ¿´´Ù. ¿ì¸®´Â ÀÇ·á ¿µ»óÀÇ ºÐ¼®¿¡ ³Î¸® ÀÌ¿ëµÇ´Â U-NetÀÇ ±¸Á¶¸¦ ¸ðµ¨¿¡ Àû¿ëÇÏ¿´´Ù. ÀϹÝÀûÀ¸·Î U-NetÀº 2Â÷¿ø ¿µ»ó 󸮿¡ ÁÖ·Î »ç¿ëµÈ´Ù. ±×·¯³ª º» ³í¹®¿¡¼´Â 8ä³Î 1Â÷¿ø ½Ã°è¿ ±ÙÀüµµ µ¥ÀÌÅ͸¦ ÀÔ·ÂÀ¸·Î »ç¿ëÇÏ°í ±× °á°ú·Î ¼Õ°¡¶ô ¿òÁ÷ÀÓ¿¡ ´ëÇÑ Á¤º¸¸¦ ¾ò´Â´Ù. 8,000°³ÀÇ µ¿ÀÛÀ¸·Î ±¸¼ºµÈ µ¥ÀÌÅÍ ¼¼Æ®¸¦ ȹµæÇßÀ¸¸ç, ÀÌ´Â ÈÆ·Ã µ¥ÀÌÅÍ ¼¼Æ®¿Í Æò°¡ µ¥ÀÌÅÍ ¼¼Æ®·Î ³ª´©¾îÁø´Ù. ¸ðµ¨ÀÇ ¿¹Ãø Á¤È®µµ´Â ¾à 89.32%ÀÌ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
In this paper, we propose a deep learning model for estimating finger movements based on EMG signals. We have also evaluated and analyzed the accuracy of the model. We have applied the U-Net structure, which is widely used in medical image analysis, to our model. In general, U-Net is mainly used for processing of two-dimensional images. However, in this paper, 8-channel one-dimensional time series EMG data is used as inputs, and information about finger movement is obtained as results. We have acquired the data set consisting of 8,000 motions, which is divided into the training and evaluation data sets. The accuracy of the prediction of our model is about 89.32%. |
Å°¿öµå(Keyword) |
±ÙÀüµµ
»ýü½ÅÈ£
µö·¯´×
ÇÕ¼º°ö ½Å°æ¸Á
electromyography
bio signals
deep learning
HCI(human computer interaction)
convolutional neural network
humancomputer interaction
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|