Mental Health Monitoring for Undergraduate Students using Neural Network

Introduction; In today's academic realm, the well-being of undergraduates is a growing concern. Objective; Our project aims to tackle this by using Artificial Intelligence (AI) and Machine Learning (ML) to track and evaluate students' mental health. Method; We've analysed a dataset from a survey for undergraduates, using a mix of algorithms like SVM, Random Forest, Logistic Regression, and Neural Networks. Result; Our findings show Neural Networks as the standout performer, excelling in accuracy and other metrics. We've detailed our process from data preparation to model training, highlighting Neural Networks' superiority. By optimizing techniques like cross-validation, we've enhanced SVM, Logistic Regression, and Random Forest. Conclusion; This study not only uncovers issues but also proposes a forward-thinking solution, endorsing Neural Networks as a ground-breaking tool for mental health assessment in academia.