High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18
Applied Sciences · 16.07.2024 · 14 (14) · 6175
DOI: 10.3390/app14146175 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 16.07.2024. Verfasst von Longxin Yao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, the Professorial and Doctoral Scientific Research Foundation of Huizhou University.
Abstract (Originalsprache)
The high-accuracy detection of multiple distinct human emotions is crucial for advancing affective computing, mental health diagnostics, and human–computer interaction. The integration of deep learning networks with entropy measures holds significant potential in neuroscience and medicine, especially for analyzing EEG-based emotion states. This study proposes a method combining ResNet18 with differential entropy to identify five types of human emotions (happiness, sadness, fear, disgust, and neutral) from EEG signals. Our approach first calculates the differential entropy of EEG signals to capture the complexity and variability of the emotional states. Then, the ResNet18 network is employed to learn feature representations from the differential entropy measures, which effectively captures the intricate spatiotemporal dynamics inherent in emotional EEG patterns using residual connections. To validate the efficacy of our method, we conducted experiments on the SEED-V dataset, achieving an average accuracy of 95.61%. Our findings demonstrate that the combination of ResNet18 with differential entropy is highly effective in classifying multiple distinct human emotions from EEG signals. This method shows robust generalization and broad applicability, indicating its potential for extension to various pattern recognition tasks across different domains.
Förderung
- National Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research Foundation
- the Professorial and Doctoral Scientific Research Foundation of Huizhou University
- the Planning Project of Enhanced Independent Innovation Ability of Huizhou University
Zitieren
APA
Yao, L., Lu, Y., Qian, Y., He, C., & Wang, M. (2024). High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18. Applied Sciences, 14(14), 6175. https://doi.org/10.3390/app14146175
Vancouver
Yao L, Lu Y, Qian Y, He C, Wang M. High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18. Applied Sciences. 2024;14(14):6175. doi:10.3390/app14146175
BibTeX
@article{Yao2024,
author = {Yao, Longxin and Lu, Yun and Qian, Yukun and He, Changjun and Wang, Mingjiang},
title = {High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18},
journal = {Applied Sciences},
year = {2024},
volume = {14},
number = {14},
pages = {6175},
doi = {10.3390/app14146175}
}
EUVIMED