Online Learning for Wearable EEG-Based Emotion Classification
Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2387 |
| _version_ | 1797614359509204992 |
|---|---|
| author | Sidratul Moontaha Franziska Elisabeth Friederike Schumann Bert Arnrich |
| author_facet | Sidratul Moontaha Franziska Elisabeth Friederike Schumann Bert Arnrich |
| author_sort | Sidratul Moontaha |
| collection | DOAJ |
| description | Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9% (Arousal) and 25.8% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87% (Arousal) and 82% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification. |
| first_indexed | 2024-03-11T07:11:19Z |
| format | Article |
| id | doaj.art-51351ed6f86547b5a2df31db739503e9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:11:19Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-51351ed6f86547b5a2df31db739503e92023-11-17T08:34:01ZengMDPI AGSensors1424-82202023-02-01235238710.3390/s23052387Online Learning for Wearable EEG-Based Emotion ClassificationSidratul Moontaha0Franziska Elisabeth Friederike Schumann1Bert Arnrich2Digital Health—Connected Healthcare, Hasso Plattner Institute, University of Potsdam, 14482 Potsdam, GermanyDigital Health—Connected Healthcare, Hasso Plattner Institute, University of Potsdam, 14482 Potsdam, GermanyDigital Health—Connected Healthcare, Hasso Plattner Institute, University of Potsdam, 14482 Potsdam, GermanyGiving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9% (Arousal) and 25.8% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87% (Arousal) and 82% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.https://www.mdpi.com/1424-8220/23/5/2387online learningreal-timeemotion classificationAMIGOS datasetwearable EEG (muse and neurosity crown)psychopy experiments |
| spellingShingle | Sidratul Moontaha Franziska Elisabeth Friederike Schumann Bert Arnrich Online Learning for Wearable EEG-Based Emotion Classification Sensors online learning real-time emotion classification AMIGOS dataset wearable EEG (muse and neurosity crown) psychopy experiments |
| title | Online Learning for Wearable EEG-Based Emotion Classification |
| title_full | Online Learning for Wearable EEG-Based Emotion Classification |
| title_fullStr | Online Learning for Wearable EEG-Based Emotion Classification |
| title_full_unstemmed | Online Learning for Wearable EEG-Based Emotion Classification |
| title_short | Online Learning for Wearable EEG-Based Emotion Classification |
| title_sort | online learning for wearable eeg based emotion classification |
| topic | online learning real-time emotion classification AMIGOS dataset wearable EEG (muse and neurosity crown) psychopy experiments |
| url | https://www.mdpi.com/1424-8220/23/5/2387 |
| work_keys_str_mv | AT sidratulmoontaha onlinelearningforwearableeegbasedemotionclassification AT franziskaelisabethfriederikeschumann onlinelearningforwearableeegbasedemotionclassification AT bertarnrich onlinelearningforwearableeegbasedemotionclassification |