• Something wrong with this record ?

EMG signals for finger movement classification based on short-term fourier transform and deep learning

Ivana Kralikova, Branko Babusiak, Lubomir Kralik

. 2021 ; 51 (1-4) : 15-20.

Language English Country Czech Republic

Document type Review, Research Support, Non-U.S. Gov't

Persistent link   https://www.medvik.cz/link/bmc23006620

An interface based on electromyographic (EMG) signals is considered one of the central fields in human-machine interface (HCI) research with broad practical use. This paper presents the recognition of 13 individual finger movements based on the time-frequency representation of EMG signals via spectrograms. A deep learning algorithm, namely a convolutional neural network (CNN), is used to extract features and classify them. Two approaches to EMG data representations are investigated: different window segmentation lengths and reduction of the measured channels. The overall highest accuracy of the classification reaches 95.5% for a segment length of 300 ms. The average accuracy attains more than 90% by reducing channels from four to three.

References provided by Crossref.org

Bibliography, etc.

Literatura

000      
00000naa a2200000 a 4500
001      
bmc23006620
003      
CZ-PrNML
005      
20230926115023.0
007      
ta
008      
230518s2021 xr ad f 000 0|eng||
009      
AR
024    7_
$a 10.14311/CTJ.2021.1.02 $2 doi
040    __
$a ABA008 $d ABA008 $e AACR2 $b cze
041    0_
$a eng
044    __
$a xr
100    1_
$a Králiková, Ivana $7 xx0301872 $u Department of Electromagnetic and Biomedical Engineering, Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovakia
245    10
$a EMG signals for finger movement classification based on short-term fourier transform and deep learning / $c Ivana Kralikova, Branko Babusiak, Lubomir Kralik
504    __
$a Literatura
520    9_
$a An interface based on electromyographic (EMG) signals is considered one of the central fields in human-machine interface (HCI) research with broad practical use. This paper presents the recognition of 13 individual finger movements based on the time-frequency representation of EMG signals via spectrograms. A deep learning algorithm, namely a convolutional neural network (CNN), is used to extract features and classify them. Two approaches to EMG data representations are investigated: different window segmentation lengths and reduction of the measured channels. The overall highest accuracy of the classification reaches 95.5% for a segment length of 300 ms. The average accuracy attains more than 90% by reducing channels from four to three.
650    17
$a elektromyografie $x metody $x přístrojové vybavení $7 D004576 $2 czmesh
650    _7
$a prsty ruky $x diagnostické zobrazování $x inervace $7 D005385 $2 czmesh
650    _7
$a počítačové zpracování signálu $x přístrojové vybavení $7 D012815 $2 czmesh
650    _7
$a biomedicínské technologie $x metody $x přístrojové vybavení $7 D020811 $2 czmesh
650    _7
$a biomedicínský výzkum $7 D035843 $2 czmesh
650    _7
$a lidé $7 D006801 $2 czmesh
655    _7
$a přehledy $7 D016454 $2 czmesh
655    _7
$a práce podpořená grantem $7 D013485 $2 czmesh
700    1_
$a Babušiak, Branko, $d 1983- $7 mzk2007390332 $u Department of Electromagnetic and Biomedical Engineering, Faculty of Electrical Engineering and Information Technology, University of Zilina, Zilina, Slovakia
700    1_
$a Králik, Ľubomír $7 _AN117018 $u Faculty of Management Science and Informatics, University of Zilina, Zilina, Slovakia
773    0_
$t Lékař a technika $x 0301-5491 $g Roč. 51, č. 1-4 (2021), s. 15-20 $w MED00011033
910    __
$a ABA008 $b B 1367 $c 1071 b $y p $z 0
990    __
$a 20230517141648 $b ABA008
991    __
$a 20230926115020 $b ABA008
999    __
$a ok $b bmc $g 1934177 $s 1192842
BAS    __
$a 3
BMC    __
$a 2021 $b 51 $c 1-4 $d 15-20 $i 0301-5491 $m Lékař a technika $n Lék. tech. $x MED00011033
LZP    __
$c NLK193 $d 20230926 $a NLK 2023-16/kv

Find record

Citation metrics

Archiving options