Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model
Motor imagery (MI) electroencephalography (EEG) signals are widely used in BCI systems. MI tasks are performed by imagining doing a specific task and classifying MI through EEG signal processing. However, it is a challenging task to classify EEG signals accurately. In this study, we propose a LSTM-b...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/5/1186 |
| _version_ | 1797615514822901760 |
|---|---|
| author | Jeonghee Hwang Soyoung Park Jeonghee Chi |
| author_facet | Jeonghee Hwang Soyoung Park Jeonghee Chi |
| author_sort | Jeonghee Hwang |
| collection | DOAJ |
| description | Motor imagery (MI) electroencephalography (EEG) signals are widely used in BCI systems. MI tasks are performed by imagining doing a specific task and classifying MI through EEG signal processing. However, it is a challenging task to classify EEG signals accurately. In this study, we propose a LSTM-based classification framework to enhance classification accuracy of four-class MI signals. To obtain time-varying data of EEG signals, a sliding window technique is used, and an overlapping-band-based FBCSP is applied to extract the subject-specific spatial features. Experimental results on BCI competition IV dataset 2a showed an average accuracy of 97% and kappa value of 0.95 in all subjects. It is demonstrated that the proposed method outperforms the existing algorithms for classifying the four-class MI EEG, and it also illustrates the robustness on the variability of inter-trial and inter-session of MI data. Furthermore, the extended experimental results for channel selection showed the best performance of classification accuracy when using all twenty-two channels by the proposed method, but an average kappa value of 0.93 was achieved with only seven channels. |
| first_indexed | 2024-03-11T07:26:31Z |
| format | Article |
| id | doaj.art-6612306beed948f68c950cb70bde1287 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T07:26:31Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6612306beed948f68c950cb70bde12872023-11-17T07:32:51ZengMDPI AGElectronics2079-92922023-03-01125118610.3390/electronics12051186Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning ModelJeonghee Hwang0Soyoung Park1Jeonghee Chi2Department of Computer Software, Namseoul University, Cheonan 31020, Republic of KoreaDepartment of Computer Science and Engineering, Konkuk University, Seoul 05029, Republic of KoreaDepartment of Computer Science and Engineering, Konkuk University, Seoul 05029, Republic of KoreaMotor imagery (MI) electroencephalography (EEG) signals are widely used in BCI systems. MI tasks are performed by imagining doing a specific task and classifying MI through EEG signal processing. However, it is a challenging task to classify EEG signals accurately. In this study, we propose a LSTM-based classification framework to enhance classification accuracy of four-class MI signals. To obtain time-varying data of EEG signals, a sliding window technique is used, and an overlapping-band-based FBCSP is applied to extract the subject-specific spatial features. Experimental results on BCI competition IV dataset 2a showed an average accuracy of 97% and kappa value of 0.95 in all subjects. It is demonstrated that the proposed method outperforms the existing algorithms for classifying the four-class MI EEG, and it also illustrates the robustness on the variability of inter-trial and inter-session of MI data. Furthermore, the extended experimental results for channel selection showed the best performance of classification accuracy when using all twenty-two channels by the proposed method, but an average kappa value of 0.93 was achieved with only seven channels.https://www.mdpi.com/2079-9292/12/5/1186multi-class motor imageryEEG classificationFBCSPoverlapping windowoverlapping bandpass filterLSTM |
| spellingShingle | Jeonghee Hwang Soyoung Park Jeonghee Chi Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model Electronics multi-class motor imagery EEG classification FBCSP overlapping window overlapping bandpass filter LSTM |
| title | Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model |
| title_full | Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model |
| title_fullStr | Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model |
| title_full_unstemmed | Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model |
| title_short | Improving Multi-Class Motor Imagery EEG Classification Using Overlapping Sliding Window and Deep Learning Model |
| title_sort | improving multi class motor imagery eeg classification using overlapping sliding window and deep learning model |
| topic | multi-class motor imagery EEG classification FBCSP overlapping window overlapping bandpass filter LSTM |
| url | https://www.mdpi.com/2079-9292/12/5/1186 |
| work_keys_str_mv | AT jeongheehwang improvingmulticlassmotorimageryeegclassificationusingoverlappingslidingwindowanddeeplearningmodel AT soyoungpark improvingmulticlassmotorimageryeegclassificationusingoverlappingslidingwindowanddeeplearningmodel AT jeongheechi improvingmulticlassmotorimageryeegclassificationusingoverlappingslidingwindowanddeeplearningmodel |