Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies
Human dependence on computers is increasing day by day; thus, human interaction with computers must be more dynamic and contextual rather than static or generalized. The development of such devices requires knowledge of the emotional state of the user interacting with it; for this purpose, an emotio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/24/10/1322 |
| _version_ | 1797473539683516416 |
|---|---|
| author | Aditya Nalwaya Kritiprasanna Das Ram Bilas Pachori |
| author_facet | Aditya Nalwaya Kritiprasanna Das Ram Bilas Pachori |
| author_sort | Aditya Nalwaya |
| collection | DOAJ |
| description | Human dependence on computers is increasing day by day; thus, human interaction with computers must be more dynamic and contextual rather than static or generalized. The development of such devices requires knowledge of the emotional state of the user interacting with it; for this purpose, an emotion recognition system is required. Physiological signals, specifically, electrocardiogram (ECG) and electroencephalogram (EEG), were studied here for the purpose of emotion recognition. This paper proposes novel entropy-based features in the Fourier–Bessel domain instead of the Fourier domain, where frequency resolution is twice that of the latter. Further, to represent such non-stationary signals, the Fourier–Bessel series expansion (FBSE) is used, which has non-stationary basis functions, making it more suitable than the Fourier representation. EEG and ECG signals are decomposed into narrow-band modes using FBSE-based empirical wavelet transform (FBSE-EWT). The proposed entropies of each mode are computed to form the feature vector, which are further used to develop machine learning models. The proposed emotion detection algorithm is evaluated using publicly available DREAMER dataset. K-nearest neighbors (KNN) classifier provides accuracies of 97.84%, 97.91%, and 97.86% for arousal, valence, and dominance classes, respectively. Finally, this paper concludes that the obtained entropy features are suitable for emotion recognition from given physiological signals. |
| first_indexed | 2024-03-09T20:15:56Z |
| format | Article |
| id | doaj.art-d12a565a23c94583b629fb8264e45ea5 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T20:15:56Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d12a565a23c94583b629fb8264e45ea52023-11-24T00:01:41ZengMDPI AGEntropy1099-43002022-09-012410132210.3390/e24101322Automated Emotion Identification Using Fourier–Bessel Domain-Based EntropiesAditya Nalwaya0Kritiprasanna Das1Ram Bilas Pachori2Department of Electrical Engineering, Indian Institute of Technology Indore, Indore 453552, IndiaDepartment of Electrical Engineering, Indian Institute of Technology Indore, Indore 453552, IndiaDepartment of Electrical Engineering, Indian Institute of Technology Indore, Indore 453552, IndiaHuman dependence on computers is increasing day by day; thus, human interaction with computers must be more dynamic and contextual rather than static or generalized. The development of such devices requires knowledge of the emotional state of the user interacting with it; for this purpose, an emotion recognition system is required. Physiological signals, specifically, electrocardiogram (ECG) and electroencephalogram (EEG), were studied here for the purpose of emotion recognition. This paper proposes novel entropy-based features in the Fourier–Bessel domain instead of the Fourier domain, where frequency resolution is twice that of the latter. Further, to represent such non-stationary signals, the Fourier–Bessel series expansion (FBSE) is used, which has non-stationary basis functions, making it more suitable than the Fourier representation. EEG and ECG signals are decomposed into narrow-band modes using FBSE-based empirical wavelet transform (FBSE-EWT). The proposed entropies of each mode are computed to form the feature vector, which are further used to develop machine learning models. The proposed emotion detection algorithm is evaluated using publicly available DREAMER dataset. K-nearest neighbors (KNN) classifier provides accuracies of 97.84%, 97.91%, and 97.86% for arousal, valence, and dominance classes, respectively. Finally, this paper concludes that the obtained entropy features are suitable for emotion recognition from given physiological signals.https://www.mdpi.com/1099-4300/24/10/1322Fourier–Bessel series expansionspectral entropyECGEEGFBSE-EWT |
| spellingShingle | Aditya Nalwaya Kritiprasanna Das Ram Bilas Pachori Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies Entropy Fourier–Bessel series expansion spectral entropy ECG EEG FBSE-EWT |
| title | Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies |
| title_full | Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies |
| title_fullStr | Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies |
| title_full_unstemmed | Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies |
| title_short | Automated Emotion Identification Using Fourier–Bessel Domain-Based Entropies |
| title_sort | automated emotion identification using fourier bessel domain based entropies |
| topic | Fourier–Bessel series expansion spectral entropy ECG EEG FBSE-EWT |
| url | https://www.mdpi.com/1099-4300/24/10/1322 |
| work_keys_str_mv | AT adityanalwaya automatedemotionidentificationusingfourierbesseldomainbasedentropies AT kritiprasannadas automatedemotionidentificationusingfourierbesseldomainbasedentropies AT rambilaspachori automatedemotionidentificationusingfourierbesseldomainbasedentropies |