A Singular Value Decomposition-Entropy Based Rhythm Wave Sequence Representation Method for Emotion Analysis Using EEG Signals.

Saved in:

Bibliographic Details
Title:	A Singular Value Decomposition-Entropy Based Rhythm Wave Sequence Representation Method for Emotion Analysis Using EEG Signals.
Authors:	Li, Jiawen¹ lijiawen@gpnu.edu.cn, Ling, Chen² lingchen@gpnu.edu.cn, Ren, Ximing¹ renximing@gpnu.edu.cn, Feng, Guanyuan³ zyzc75@gmail.com
Source:	IAENG International Journal of Applied Mathematics. Jul2026, Vol. 56 Issue 7, p2767-2774. 8p.
Subjects:	Electroencephalography, Emotion recognition, Applied sciences, Brain waves, Entropy, Singular value decomposition, Brain-computer interfaces, Statistical models
Abstract:	Electroencephalography (EEG) holds great promise for analyzing human emotional states. However, conventional approaches mainly rely on static features, overlooking the rich temporal dynamics of neural oscillations. To this end, we present Rhythm Wave Sequence (RWS), a novel representation method that encodes dominant brain rhythms as sequence data. By partitioning the time-frequency plane of EEG signals into short segments and then applying Singular Value Decomposition (SVD)-entropy, each specific segment is mapped to the most dominant rhythm, thereby generating a symbolic string for one EEG channel. Subsequently, to validate RWS, we compare scalp connectivity derived from the generated sequences with that via traditional methods applied to raw signals. The convergence between the two sets demonstrates that RWS preserves essential spatial information despite its compressed form. More importantly, RWS-derived connectivity exhibits within-subject stability across different emotional states, revealing an individualized neural signature. In contrast, pronounced between-subject variability within the same emotional state underscores the inherent heterogeneity of affective brain organization and advocates for personalized modeling in affective computing. Additionally, by adopting a data-driven perspective, we further identify representative scalp channels (AF3, F7, P7, O1) that contribute to emotion-related cortical networks, providing new insights into the neural substrates of emotion. Our findings establish RWS as a parsimonious representation that bridges temporal dynamics and spatial connectivity, benefiting the development of personalized Brain-Computer Interfaces (BCIs) for EEG-based emotion analysis. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Applied Mathematics is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Electroencephalography (EEG) holds great promise for analyzing human emotional states. However, conventional approaches mainly rely on static features, overlooking the rich temporal dynamics of neural oscillations. To this end, we present Rhythm Wave Sequence (RWS), a novel representation method that encodes dominant brain rhythms as sequence data. By partitioning the time-frequency plane of EEG signals into short segments and then applying Singular Value Decomposition (SVD)-entropy, each specific segment is mapped to the most dominant rhythm, thereby generating a symbolic string for one EEG channel. Subsequently, to validate RWS, we compare scalp connectivity derived from the generated sequences with that via traditional methods applied to raw signals. The convergence between the two sets demonstrates that RWS preserves essential spatial information despite its compressed form. More importantly, RWS-derived connectivity exhibits within-subject stability across different emotional states, revealing an individualized neural signature. In contrast, pronounced between-subject variability within the same emotional state underscores the inherent heterogeneity of affective brain organization and advocates for personalized modeling in affective computing. Additionally, by adopting a data-driven perspective, we further identify representative scalp channels (AF3, F7, P7, O1) that contribute to emotion-related cortical networks, providing new insights into the neural substrates of emotion. Our findings establish RWS as a parsimonious representation that bridges temporal dynamics and spatial connectivity, benefiting the development of personalized Brain-Computer Interfaces (BCIs) for EEG-based emotion analysis. [ABSTRACT FROM AUTHOR]
ISSN:	19929978