Research Article
K-NN with Frequency Domain Features for Identify Fingers Movement
@INPROCEEDINGS{10.4108/eai.5-10-2022.2329544, author={Daniel Sutopo Pamungkas and Ilham Rhomadony and Wahyu Caesarendra}, title={K-NN with Frequency Domain Features for Identify Fingers Movement}, proceedings={Proceedings of the 5th International Conference on Applied Engineering, ICAE 2022, 5 October 2022, Batam, Indonesia}, publisher={EAI}, proceedings_a={ICAE}, year={2023}, month={6}, keywords={emg myo armband k-nearest neighbour}, doi={10.4108/eai.5-10-2022.2329544} }- Daniel Sutopo Pamungkas
Ilham Rhomadony
Wahyu Caesarendra
Year: 2023
K-NN with Frequency Domain Features for Identify Fingers Movement
ICAE
EAI
DOI: 10.4108/eai.5-10-2022.2329544
Abstract
Prosthetic hands, which make daily chores more accessible, are one of the improvements brought about by quick technology advancements. The study and use of technological, therapeutic, and diagnostic principles concerning human activity are known as biomechanics, and it has led to the development of new technology, such as electromyography (EMG). Human muscles contract or relax to produce EMG signals, which are signals. This study tries to pinpoint the human finger's opening and closing motion as detected by the Myo Armband sensor. The Myo Armband sensor is attached to the subject's right hand's forearm to receive signals from the EMG. FFT will be used to transfer the collected data to the frequency domain, and 70% of the EMG signal data will then be used as training data to determine the outcomes of each movement. 30% of the EMG signal data will be used to test the training results, which will then be K-Nearest Neighbor-classified. K-Nearest Neighbor classification techniques used in the study yielded a percentage of correct readings of 73.3%.
