Design of a Multi-Sensors Wearable System for Continuous Monitoring of People with Parkinson’s Disease

This project presents the design and implementation of a multi-sensor wearable system for continuous home monitoring of individuals with Parkinson’s disease. The system is developed using an Arduino Mega microcontroller integrated with various sensors, including a MAX pulse oximeter for measuring SpO₂ and heart rate, a blood pressure sensor for BP monitoring, an ADXL345 accelerometer for fall detection, an ADXL335 sensor for tremor analysis, and an IR sensor for sleep monitoring. Additionally, GPS and GSM modules are incorporated to enable real-time location tracking and emergency communication. Sensor data is continuously transmitted to a Python-based platform, where machine learning algorithms analyze vital parameters such as BPM and SpO₂ to detect abnormalities. When critical conditions are identified, the system automatically sends alerts through email, SMS, and phone calls to caregivers. Immediate alerts are also generated by the Arduino for events such as falls, abnormal BP, and excessive tremors, ensuring rapid response. All collected data is stored locally in Excel and uploaded to an IoT platform for remote monitoring and analysis, thereby improving patient safety, enabling continuous health tracking, and reducing caregiver workload.