Performance Analysis of Various Machine Learning Techniques for Mental Health Tracking

Artificial intelligence technologies called “machine learning” automatically build models from data in order to improve decision-making. An examination of ML that can be utilized for mental illness treatment has been prompted by the upsurge in mental health diseases and the directive for efficient medical sustenance. The quality of life for patients is improved and treatment outcomes are increased when mental health issues are identified early. Therefore, it is critical to address basic mental health issues that, if left unattended, could develop into more serious issues. The analysis and diagnosis of medical data can today be accomplished with the help of machine learning algorithms. The conventional (CCTV) system for tracking patient activity is ineffective and expensive, and employing a sensor-based system is particularly challenging because of depleted battery life. The real goal is to provide a critical review, and literature review, about all the machine learning techniques which are supervised-based. These techniques include Random Forest Classification, KNN Classifier, Logistic Regression, Decision Tree Classifier, Bagging, Boosting, & Stacking. And to determine the most effective machine-learning technique for monitoring someone’s mental health. It has been found that Accuracy and ROC Curve plays an important role for comparing the ML models. The outcomes clearly show that stacking generated more precise outcomes by showing the accuracy of 82%.