Study on Finger Gesture Interface Using One-Channel EMG
Electromyography (EMG) is used to recognize user finger gestures for applications in real-time interfaces. Finger movements are classified by preprocessing to extract the features from the collected EMG data, which are then used for machine learning. The data were extracted using the overlapped segm...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10835803/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592939890507776 |
|---|---|
| author | Hee-Yeong Yang Young-Shin Han Choon-Sung Nam |
| author_facet | Hee-Yeong Yang Young-Shin Han Choon-Sung Nam |
| author_sort | Hee-Yeong Yang |
| collection | DOAJ |
| description | Electromyography (EMG) is used to recognize user finger gestures for applications in real-time interfaces. Finger movements are classified by preprocessing to extract the features from the collected EMG data, which are then used for machine learning. The data were extracted using the overlapped segmentation method to ensure sufficient training data. The preprocessing of EMG data uses standard formulae, such as integrated EMG (IEMG) and mean absolute value (MAV). Furthermore, preprocessing involves using original data, simple moving average (SMA), and Fast Fourier transform (FFT) for feature extraction. Subsequently, these preprocessed data sets are used to train machine learning models, facilitating a comparative analysis. Four machine learning models were used: eXtreme Gradient Boost, Random Forest, k-Nearest Neighbors, and Logistic Regression. The experimental results revealed the best accuracy from preprocessing using a simple moving average followed by a Fourier transform, but classification was not possible using all nine finger movements. On the other hand, it showed more than 90% accuracy because the model learned by reducing it to a specific finger gesture. Rest movements, index finger taps, and force-taps movements achieved the highest accuracy, approximately 95%. |
| format | Article |
| id | doaj-art-8f2cd948bdc9419f867a352656278a7c |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8f2cd948bdc9419f867a352656278a7c2025-01-21T00:01:49ZengIEEEIEEE Access2169-35362025-01-01139606961410.1109/ACCESS.2025.352768410835803Study on Finger Gesture Interface Using One-Channel EMGHee-Yeong Yang0Young-Shin Han1Choon-Sung Nam2https://orcid.org/0000-0001-9238-5275Department of Software Convergence Engineering, Inha University, Michuhol-gu, Incheon, South KoreaFrontier College, Inha University, Michuhol-gu, Incheon, South KoreaDepartment of Software Convergence Engineering, Inha University, Michuhol-gu, Incheon, South KoreaElectromyography (EMG) is used to recognize user finger gestures for applications in real-time interfaces. Finger movements are classified by preprocessing to extract the features from the collected EMG data, which are then used for machine learning. The data were extracted using the overlapped segmentation method to ensure sufficient training data. The preprocessing of EMG data uses standard formulae, such as integrated EMG (IEMG) and mean absolute value (MAV). Furthermore, preprocessing involves using original data, simple moving average (SMA), and Fast Fourier transform (FFT) for feature extraction. Subsequently, these preprocessed data sets are used to train machine learning models, facilitating a comparative analysis. Four machine learning models were used: eXtreme Gradient Boost, Random Forest, k-Nearest Neighbors, and Logistic Regression. The experimental results revealed the best accuracy from preprocessing using a simple moving average followed by a Fourier transform, but classification was not possible using all nine finger movements. On the other hand, it showed more than 90% accuracy because the model learned by reducing it to a specific finger gesture. Rest movements, index finger taps, and force-taps movements achieved the highest accuracy, approximately 95%.https://ieeexplore.ieee.org/document/10835803/Data preprocessingEMGfinger gesture recognitionmachine learningone channel data user interface |
| spellingShingle | Hee-Yeong Yang Young-Shin Han Choon-Sung Nam Study on Finger Gesture Interface Using One-Channel EMG IEEE Access Data preprocessing EMG finger gesture recognition machine learning one channel data user interface |
| title | Study on Finger Gesture Interface Using One-Channel EMG |
| title_full | Study on Finger Gesture Interface Using One-Channel EMG |
| title_fullStr | Study on Finger Gesture Interface Using One-Channel EMG |
| title_full_unstemmed | Study on Finger Gesture Interface Using One-Channel EMG |
| title_short | Study on Finger Gesture Interface Using One-Channel EMG |
| title_sort | study on finger gesture interface using one channel emg |
| topic | Data preprocessing EMG finger gesture recognition machine learning one channel data user interface |
| url | https://ieeexplore.ieee.org/document/10835803/ |
| work_keys_str_mv | AT heeyeongyang studyonfingergestureinterfaceusingonechannelemg AT youngshinhan studyonfingergestureinterfaceusingonechannelemg AT choonsungnam studyonfingergestureinterfaceusingonechannelemg |