Abstract: C. Wang, Y. Li, S. Liu, S. Yang (2024)

Electroencephalography (EEG) has garnered significant attention in emotion recognition research due to its non-invasiveness and relatively high accuracy. However, many studies have primarily focused on the time and frequency domain characteristics of EEG for emotion identification, with nonlinear attributes often being overlooked. Additionally, the high resolution of EEG time has also been underutilized. To address this problem, we proposed a novel approach termed the time-varying recursive graph (TVRP) to visualize the temporal recursion patterns inherent in EEG signals. The proposition involved constructing a multivariate weighted recurrent network (MWRN) based on TVRP-selected reliable channels to quantify the nonlinear features of EEG networks across different emotional states. Finally, these nonlinear features were validated for sentiment recognition. The EEG signals of 28 participants listening to positive and negative music were collected for this study. TVRP analysis revealed significant temporal recurrence differences between positive and negative emotions in the frontal, parietal, and temporal regions. Positive emotional states exhibited greater continuous temporal recursion in the frontal and parietal lobes, whereas negative emotions showed more in the temporal lobe. MWRN indicated that the non-linearity of positive emotional states was notably higher than that of negative. The classification rate of optimal channel features selected based on TVRP was more accurate than all channels, with an average classification rate of 81.3%. This study highlights the utility of TVRP in visualizing temporal recursion patterns of EEG signals in various emotional states. It underscores that a channel-selection-based TVRP improves the recognition performance of emotional EEG.

Please note: The abstracts of the bibliography database may underly other copyrights.

Ihr Browser versucht gerade eine Seite aus dem sogenannten Internet auszudrucken. Das Internet ist ein weltweites Netzwerk von Computern, das den Menschen ganz neue Möglichkeiten der Kommunikation bietet.

Da Politiker im Regelfall von neuen Dingen nichts verstehen, halten wir es für notwendig, sie davor zu schützen. Dies ist im beidseitigen Interesse, da unnötige Angstzustände bei Ihnen verhindert werden, ebenso wie es uns vor profilierungs- und machtsüchtigen Politikern schützt.

Sollten Sie der Meinung sein, dass Sie diese Internetseite dennoch sehen sollten, so können Sie jederzeit durch normalen Gebrauch eines Internetbrowsers darauf zugreifen. Dazu sind aber minimale Computerkenntnisse erforderlich. Sollten Sie diese nicht haben, vergessen Sie einfach dieses Internet und lassen uns in Ruhe.

Die Umgehung dieser Ausdrucksperre ist nach §95a UrhG verboten.

Mehr Informationen unter www.politiker-stopp.de.

TVRP-based constructing complex network for EEG emotional feature analysis and recognition