Resilience intervention is used to train and improve one's resilience level, however current studies used various psychometric instruments for resilience evaluation that are subjective, tedious, and prone to bias. In this study, electroencephalogram (EEG) has been chosen as a potential candidate for a new resilience assessment method that aims to rectify the limitations of existing psychometric instruments. The aim of the work is to create a practical resilience assessment system using EEG, which can classify low or high resilience level with high accuracy and generalization. The proposed system uses Virtual Reality headset to simulate rest and task conditions during EEG data acquisition. Connor-Davidson Resilience Scale (CD-RISC) is used to determine the actual resilience score of each participant. Results indicate that Linear Discriminant Analysis (LDA), NaÏve Bayes (NB), and Support Vector Machine (SVM) using ReliefF for feature selection yields the best model performances, however other feature extraction and selection methods need to be explored to improve predictive strength of features on resilience.

Flow of Data Collection

In this study, the EEG signals from healthy participants are collected to assess resilience during task conditions. Participants are recruited through advertisements at two data collection sites: an early childhood education centre and a research centre. The experimental protocol implemented in this study has received ethical approval from the UPSI Ethics Committee (2020-0121-01). Before the EEG recording, the participants are given an online form to fill in their personal details and complete a 25-item Conor-Davidson Resilience Scale (CD-RISC). This is to obtain the true resilience score of the participant. The participants are categorized as either low or high resilient based on the collected CD-RISC scores. With reference to the percentile method used in the questionnaire guideline [26] to distribute sample of a study into four quartiles, the 50th percentile of the scores (i.e., median) from this study sample is used as the threshold to label the participants.

Recording participant's EEG signal while wearing VR headset

Enhanced Understanding of Brain Function: Provides real-time data on brain activity, allowing for the monitoring and analysis of how the brain responds to stress and other stimuli. Offers immersive environments that can simulate stressful or challenging situations in a controlled and repeatable manner.

Improved Mental Health Interventions: By understanding how individuals respond to stress and other psychological challenges, more effective therapeutic interventions can be developed. Personalized treatment plans can be created based on individual resilience profiles.

Personalized Assessment: Offers detailed and personalized insights into an individual's resilience, allowing for customized intervention and training programs.

Real-time Feedback: Real-time monitoring of brain activity provides immediate feedback, which can be crucial for adjusting interventions on the fly.

Comparison of testing accuracies between classifiers for sequential and averaged features.

Rising Mental Health Awareness: Growing recognition of mental health issues and the importance of resilience has led to increased demand for innovative assessment and intervention tools.

Education: Schools and universities can use the system to help students manage stress and improve academic performance. Special education programs can benefit from tailored resilience training for students with specific needs.

Innovative Combination: The integration of EEG and VR provides a unique and advanced method for assessing and building resilience, setting it apart from traditional methods.

Advancements in Technology: Improvements in EEG and VR technologies make it feasible to develop sophisticated and reliable systems for resilience assessment.