Evaluating deep learning models for heart disease prediction in IOT enabled health care systems

The proposed system focuses on evaluating deep learning and machine learning models for heart disease prediction in an IoT-enabled healthcare environment. The system integrates multiple hardware components such as Arduino for sensor control, NodeMCU for cloud communication, and an LCD for real-time display of patient parameters. Physiological data including heart rate and body temperature are collected using a heartbeat sensor and temperature sensor, respectively. Additionally, a webcam is incorporated to monitor visual cues that may indicate abnormal health conditions. The collected data is transmitted to an IoT platform via NodeMCU for remote monitoring and storage. A Random Forest algorithm is employed to analyze the sensor data and predict the likelihood of heart disease. In case of abnormal readings or high-risk predictions, a buzzer alert system is activated to provide immediate warning. This integrated system enables continuous health monitoring, early detection, and timely intervention, making it suitable for smart healthcare applications.