[Multi-source adversarial adaptation with calibration for electroencephalogram-based classification of meditation and resting states].

A new machine-learning model, the model-calibrated multi-source adversarial adaptation network (CMAAN), improves the accuracy of monitoring meditation states from electroencephalogram (EEG) signals. The model trains multiple domain-adversarial neural networks between different individuals and then calibrates them with a small amount of labeled data from the target person. Tested on EEG data from 18 people undergoing methamphetamine rehabilitation, the model achieved 73.09% classification accuracy. The approach addresses the challenge of large individual differences in EEG signals, and the learned model also reveals key EEG frequency bands and brain regions involved in meditation.

Study at a glance

Abstract

Meditation aims to guide individuals into a state of deep calm and focused attention, and in recent years, it has shown promising potential in the field of medical treatment. Numerous studies have demonstrated that electroencephalogram (EEG) patterns change during meditation, suggesting the feasibility of using deep learning techniques to monitor meditation states. However, significant inter-subject differences in EEG signals poses challenges to the performance of such monitoring systems. To address this issue, this study proposed a novel model-calibrated multi-source adversarial adaptation network (CMAAN). The model first trained multiple domain-adversarial neural networks in a pairwise manner between various source-domain individuals and the target-domain individual. These networks were then integrated through a calibration process using a small amount of labeled data from the target domain to enhance performance. We evaluated the proposed model on an EEG dataset collected from 18 subjects undergoing methamphetamine rehabilitation. The model achieved a classification accuracy of 73.09%. Additionally, based on the learned model, we analyzed the key EEG frequency bands and brain regions involved in the meditation process. The proposed multi-source domain adaptation framework improves both the performance and robustness of EEG-based meditation monitoring and holds great promise for applications in biomedical informatics and clinical practice.