Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset
Emotion recognition using EEG signals is an emerging area of research due to its broad applicability in Brain-Computer Interfaces. Emotional feelings are hard to stimulate in the lab. Emotions don’t last long, yet they need enough context to be perceived and felt. However, most EEG-relate...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10101783/ |
| _version_ | 1797835841679130624 |
|---|---|
| author | Mohammad Asif Sudhakar Mishra Majithia Tejas Vinodbhai Uma Shanker Tiwary |
| author_facet | Mohammad Asif Sudhakar Mishra Majithia Tejas Vinodbhai Uma Shanker Tiwary |
| author_sort | Mohammad Asif |
| collection | DOAJ |
| description | Emotion recognition using EEG signals is an emerging area of research due to its broad applicability in Brain-Computer Interfaces. Emotional feelings are hard to stimulate in the lab. Emotions don’t last long, yet they need enough context to be perceived and felt. However, most EEG-related emotion databases either suffer from emotionally irrelevant details (due to prolonged duration stimulus) or have minimal context, which may not elicit enough emotion. We tried to overcome this problem by designing an experiment in which participants were free to report their emotional feelings while watching the emotional stimulus. We called these reported emotional feelings “Emotional Events” in our Dataset on Emotion with Naturalistic Stimuli (DENS), which has the recorded EEG signals during the emotional events. To compare our dataset, we classify emotional events on different combinations of Valence(V) and Arousal(A) dimensions and compared the results with benchmark datasets of DEAP and SEED. Short-Time Fourier Transform (STFT) is used for feature extraction and in the classification model consisting of CNN-LSTM hybrid layers. We achieved significantly higher accuracy with our data compared to DEAP and SEED data. We conclude that having precise information about emotional feelings improves the classification accuracy compared to long-duration recorded EEG signals which might be contaminated by mind-wandering. This dataset can be used for detailed analysis of specific experienced emotions and related brain dynamics. |
| first_indexed | 2024-04-09T14:58:57Z |
| format | Article |
| id | doaj.art-b9f74bcfd8da406580b072e0e294ecb4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T14:58:57Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b9f74bcfd8da406580b072e0e294ecb42023-05-01T23:01:17ZengIEEEIEEE Access2169-35362023-01-0111399133992510.1109/ACCESS.2023.326680410101783Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# DatasetMohammad Asif0https://orcid.org/0000-0002-9517-6716Sudhakar Mishra1https://orcid.org/0000-0002-3748-7153Majithia Tejas Vinodbhai2Uma Shanker Tiwary3https://orcid.org/0000-0001-7206-9013Indian Institute of Information Technology Allahabad, Allahabad, Uttar Pradesh, IndiaIndian Institute of Information Technology Allahabad, Allahabad, Uttar Pradesh, IndiaIndian Institute of Information Technology Allahabad, Allahabad, Uttar Pradesh, IndiaIndian Institute of Information Technology Allahabad, Allahabad, Uttar Pradesh, IndiaEmotion recognition using EEG signals is an emerging area of research due to its broad applicability in Brain-Computer Interfaces. Emotional feelings are hard to stimulate in the lab. Emotions don’t last long, yet they need enough context to be perceived and felt. However, most EEG-related emotion databases either suffer from emotionally irrelevant details (due to prolonged duration stimulus) or have minimal context, which may not elicit enough emotion. We tried to overcome this problem by designing an experiment in which participants were free to report their emotional feelings while watching the emotional stimulus. We called these reported emotional feelings “Emotional Events” in our Dataset on Emotion with Naturalistic Stimuli (DENS), which has the recorded EEG signals during the emotional events. To compare our dataset, we classify emotional events on different combinations of Valence(V) and Arousal(A) dimensions and compared the results with benchmark datasets of DEAP and SEED. Short-Time Fourier Transform (STFT) is used for feature extraction and in the classification model consisting of CNN-LSTM hybrid layers. We achieved significantly higher accuracy with our data compared to DEAP and SEED data. We conclude that having precise information about emotional feelings improves the classification accuracy compared to long-duration recorded EEG signals which might be contaminated by mind-wandering. This dataset can be used for detailed analysis of specific experienced emotions and related brain dynamics.https://ieeexplore.ieee.org/document/10101783/Affective computingCNNDEAPDENSEEGemotion dataset |
| spellingShingle | Mohammad Asif Sudhakar Mishra Majithia Tejas Vinodbhai Uma Shanker Tiwary Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset IEEE Access Affective computing CNN DEAP DENS EEG emotion dataset |
| title | Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset |
| title_full | Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset |
| title_fullStr | Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset |
| title_full_unstemmed | Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset |
| title_short | Emotion Recognition Using Temporally Localized Emotional Events in EEG With Naturalistic Context: DENS# Dataset |
| title_sort | emotion recognition using temporally localized emotional events in eeg with naturalistic context dens x0023 dataset |
| topic | Affective computing CNN DEAP DENS EEG emotion dataset |
| url | https://ieeexplore.ieee.org/document/10101783/ |
| work_keys_str_mv | AT mohammadasif emotionrecognitionusingtemporallylocalizedemotionaleventsineegwithnaturalisticcontextdensx0023dataset AT sudhakarmishra emotionrecognitionusingtemporallylocalizedemotionaleventsineegwithnaturalisticcontextdensx0023dataset AT majithiatejasvinodbhai emotionrecognitionusingtemporallylocalizedemotionaleventsineegwithnaturalisticcontextdensx0023dataset AT umashankertiwary emotionrecognitionusingtemporallylocalizedemotionaleventsineegwithnaturalisticcontextdensx0023dataset |