Our research ventured into the emerging domain of fog computing, focusing on its application in the healthcare sector, specifically for mental health evaluation. We developed a three-tiered architecture— user, fog, and cloud—to provide patients with a seamless and secure environment to assess their mental well-being. Patients interact with the system through a web application, where they can input their data, view encrypted details, and receive predictive analytics about their mental health.

The user tier anticipates the patient's mental state based on their responses to a questionnaire. The fog computing layer shoulders the primary responsibilities of data collection, security, storage, and preprocessing. Its placement reduces the data load on the cloud, subsequently reducing latency and providing a quicker response to users. Using the renowned "Mental Health in Tech Survey," we've equipped our system with the Random Forest Classifier algorithm on the cloud tier to ensure our predictions about the patient's mental well-being are both accurate and actionable. The AES encryption method is employed to ensure medical data remains confidential. A rigorous series of data transformations converts input data into unreadable cipher text, thereby fortifying it against unauthorized access.

​

Keywords: Fog Computing, Predictive Analysis, AES Algorithm, Fog Nodes, Healthcare, Cloud, End Users