Real Time Pulmonary Disease Detection Using Machine Learning on Mobile Platforms

This project focuses on the prototype development of a pulmonary disease detection system using Raspberry Pi as the central processor. The system integrates multiple sensors, including a respiratory sensor to measure breathing rate, a heartbeat sensor to monitor pulse, a pulse oximeter to detect SpO₂ levels, and a temperature sensor to record body temperature. An ADC converter is used to convert analog sensor signals into digital data for processing. The collected data is displayed on an LCD, while a buzzer provides alerts during abnormal conditions. Power is supplied to the system through a 12V adapter connected to a power supply unit. Using machine learning algorithms, particularly the Random Forest algorithm, the system processes the sensor data to predict potential pulmonary issues. The prototype also demonstrates the capability to upload collected data to an IoT platform for remote monitoring. This work establishes a foundational framework for real-time pulmonary health monitoring, enabling future enhancements in predictive diagnostics and mobile health applications.