Using a predictive model based on fuzzy logic methods to test the mental health of students

Students’ mental health assessment is vital to reduce psychological disorders due to their environment, education, etc. Assessment and prediction of such disorders using periodically observed data and activities are important for providing early rehabilitation therapy to improve health. The central problem addressed in this study is the growing difficulty in early detection and continuous assessment of student mental health conditions, which are often influenced by complex, non-linear interactions among academic stressors, lifestyle behaviors, and psychological responses. Conventional statistical or machine learning models frequently struggle to capture these uncertainties and provide interpretable insights that educators or counselors can act upon. This article introduces a Fuzzy Predictive Model (FPM) using Statistical Observation Data (SOD) to improve students’ physiological responses to stress. The proposed model leverages time-sensitive observation data to extract distinct combinatorial features. These features are related to stress and mental illness experienced by the students under different environmental conditions. The fuzzy derivatives are provided with appropriate rehabilitation solutions based on the membership combinations. If any such combination remains unaddressed, the observation interval is changed, and rehabilitation solutions are provided. Therefore, this proposed model aims to converge the combinations that increase mental illness to ensure fewer possibilities of adverse student health impacts.