<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper proposes a path strategy for VR+music combination therapy in future development and introduces an emotion recognition model based on EEG signals to address its inability to quantify the therapeutic effect of emotional intervention. EEG signal feature extraction involves extracting the differential entropy of the signal as a feature and smoothing it in a time series using a linear dynamic system. On this basis, the SVN-KNN-based emotion EEG recognition algorithm is further proposed, and the KNN algorithm is weighted and adjusted by using the inter-class sample density, which avoids the interference of the imbalanced distribution of the number of samples on the performance of the classifier and improves the generalization ability of the classification model. In the VR+music combination therapy experiment, the PSD of the theta, alpha, and beta EEG bands of the patients in the observation group was higher than that before the experiment. The difference between the observation group and the control group in the CERQ-C scores after the experiment in the factors of self-blame, contemplation, blaming others, acceptance, and rational analysis was statistically highly significant (P&lt;0.01). The observation group’s treatment adherence rate and intervention satisfaction were both 96.67% and 93.33%, respectively.</p>
</abstract>

This paper proposes a path strategy for VR+music combination therapy in future development and introduces an emotion recognition model based on EEG signals to address its inability to quantify the therapeutic effect of emotional intervention. EEG signal feature extraction involves extracting the differential entropy of the signal as a feature and smoothing it in a time series using a linear dynamic system. On this basis, the SVN-KNN-based emotion EEG recognition algorithm is further proposed, and the KNN algorithm is weighted and adjusted by using the inter-class sample density, which avoids the interference of the imbalanced distribution of the number of samples on the performance of the classifier and improves the generalization ability of the classification model. In the VR+music combination therapy experiment, the PSD of the theta, alpha, and beta EEG bands of the patients in the observation group was higher than that before the experiment. The difference between the observation group and the control group in the CERQ-C scores after the experiment in the factors of self-blame, contemplation, blaming others, acceptance, and rational analysis was statistically highly significant (P<0.01). The observation group’s treatment adherence rate and intervention satisfaction were both 96.67% and 93.33%, respectively.

Pathways of VR+Music Combination Therapy to Intervene in the Emotions of Patients with Mental Disorders

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper proposes a path strategy for VR+music combination therapy in future development and introduces an emotion recognition model based on EEG signals to...

Pathways of VR+Music Combination Therapy to Intervene in the Emotions of Patients with Mental Disorders

Online veröffentlicht: 05. Juli 2024

Seitenbereich: -

Eingereicht: 11. März 2024

Akzeptiert: 26. Mai 2024

DOI: https://doi.org/10.2478/amns-2024-1695

Schlüsselwörter
VR, SVN, KNN, EEG signal, Differential entropy, Emotional intervention

© 2024 Luwen Chen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Pathways of VR+Music Combination Therapy to Intervene in the Emotions of Patients with Mental Disorders

Online veröffentlicht: 05. Juli 2024

Seitenbereich: -

Eingereicht: 11. März 2024

Akzeptiert: 26. Mai 2024

DOI: https://doi.org/10.2478/amns-2024-1695

SchlüsselwörterVR, SVN, KNN, EEG signal, Differential entropy, Emotional intervention

© 2024 Luwen Chen et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
VR, SVN, KNN, EEG signal, Differential entropy, Emotional intervention