The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems.

Objective: In this study, electroencephalography data of imagined words were classified using four different feature extraction approaches. Eight subjects were recruited for the recording of imagination with five different words, namely; ‘go’, ‘back’, ‘left’, ‘right’, and ‘stop’.

Background: Mindfulness-based training programs have consistently shown efficacy in stress reduction. However, questions regarding the optimal duration and most effective delivery methods remain. Objective: This research explores a 4-week neurofeedback-assisted mindfulness training for employees via a mobile app. The study’s core query is whether incorporating neurofeedback can amplify the benefits on stress reduction and related metrics compared with conventional mindfulness training. Methods: A total of 92 full-time employees were randomized into 3 groups: group 1 received mobile mindfulness training with neurofeedback assistance (n=29, mean age 39.72 years); group 2 received mobile mindfulness training without neurofeedback (n=32, mean age 37.66 years); and group 3 were given self-learning paper materials on stress management during their first visit (n=31, mean age 38.65 years). The primary outcomes were perceived stress and resilience scales. The secondary outcomes were mindfulness awareness, emotional labor, occupational stress, insomnia, and depression. Heart rate variability and electroencephalography were measured for physiological outcomes. These measurements were collected at 3 different times, namely, at baseline, immediately after training, and at a 4-week follow-up. The generalized estimating equation model was used for data analysis. Results: The 4-week program showed significant stress reduction (Wald χ22=107.167, P<.001) and improvements in psychological indices including resilience, emotional labor, insomnia, and depression. A significant interaction was observed in resilience (time × group, Wald χ42=10.846, P=.02). The post hoc analysis showed a statistically significant difference between groups 1 (least squares mean [LSM] 21.62, SE 0.55) and 3 (LSM 19.90, SE 0.61) at the posttraining assessment (P=.008). Group 1 showed a significant improvement (P<.001) at the posttraining assessment, with continued improvements through the 1-month follow-up assessment period (LSM 21.55, SE 0.61). Physiological indices were analyzed only for data of 67 participants (22 in group 1, 22 in group 2, and 23 in group 3) due to the data quality. The relaxation index (ratio of alpha to high beta power) from the right electroencephalography channel showed a significant interaction (time × group, Wald χ22=6.947, P=.03), with group 1 revealing the highest improvement (LSM 0.43, SE 0.15) compared with groups 2 (LSM –0.11, SE 0.10) and 3 (LSM 0.12, SE 0.10) at the 1-month follow-up assessment. Conclusions: The study demonstrated that the neurofeedback-assisted group achieved superior outcomes in resilience and relaxation during the 4-week mobile mindfulness program. Further research with larger samples and long-term follow-up is warranted. Trial Registration: ClinicalTrials.gov NCT03787407; https://clinicaltrials.gov/ct2/show/NCT03787407

Objective The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals often remain unaware of their stress levels until they face physical health issues, highlighting the necessity for regular stress monitoring. This study aimed to investigate the effectiveness of vocal biomarkers in detecting stress levels among healthy Korean employees and to contribute to digital healthcare solutions.Methods We conducted a multi-center clinical study by collecting voice recordings from 115 healthy Korean employees under both relaxed and stress-induced conditions. Stress was induced using the socially evaluated cold pressor test. The Emphasized Channel Attention, Propagation and Aggregation in Time delay neural network (ECAPA-TDNN) deep learning architecture, renowned for its advanced capabilities in analyzing person-specific voice features, was employed to develop stress prediction scores.Results The proposed model achieved a 70% accuracy rate in detecting stress. This performance underscores the potential of vocal biomarkers as a convenient and effective tool for individuals to self-monitor and manage their stress levels within digital healthcare frameworks.Conclusion The findings emphasize the promise of voice-based mental stress assessments within the Korean population and the importance of continued research on vocal biomarkers across diverse linguistic demographics.