Parkinson’s disease is a progressive neurological disorder characterized by motor symptoms such as tremors, rigidity, and bradykinesia, which require continuous monitoring for effective disease management. This project presents a Cloud Integrated IoT Framework for Remote Parkinson’s Disease Tracking, implemented in the form of a battery-operated smart watch for real-time and continuous health monitoring. The proposed system employs a 9-axis gyroscope sensor (accelerometer, gyroscope, and magnetometer) to accurately capture hand motion data and quantify Parkinson’s tremors in terms of tremors per second. A TinyML-based machine learning model is deployed on the embedded device to analyze motion patterns locally, enabling efficient, low-power, and real-time tremor detection without constant cloud dependency. In addition to motion analysis, the system integrates a MAX30102 sensor to monitor vital physiological parameters such as heart rate and blood oxygen saturation (SpO₂), while body temperature is also measured for comprehensive health assessment. All real-time sensor readings, including tremor frequency, heart rate, SpO₂, and temperature, are displayed locally on an OLED display for immediate user feedback. Simultaneously, the collected data is transmitted to the ThingSpeak cloud platform, allowing remote access, visualization, and long-term data analysis by healthcare professionals and caregivers. The cloud integration enables trend monitoring, early detection of symptom progression, and data-driven clinical decision support. The compact, wearable, and low-power design of the smart watch ensures user comfort and continuous operation, making it suitable for daily use by Parkinson’s patients. Overall, the proposed system offers a cost-effective, scalable, and intelligent solution for remote Parkinson’s disease monitoring, enhancing patient care through real-time analytics, cloud connectivity, and embedded intelligence using TinyML.         Objectives:

• To design and develop a battery-operated smart watch for continuous and non-invasive monitoring of Parkinson’s disease symptoms.
• To accurately detect and quantify hand tremors (tremors per second) using a 9-axis gyroscope sensor for effective assessment of motor abnormalities.
• To implement a TinyML-based on-device intelligence model for real-time tremor analysis with low latency and reduced power consumption.
• To monitor key physiological parameters including heart rate and SpO₂ using the MAX30102 sensor and body temperature for comprehensive patient health tracking.
• To display real-time sensor readings and system status on an OLED display for immediate user awareness.
• To enable cloud integration using the ThingSpeak platform for remote data storage, visualization, and long-term trend analysis.
• To support remote monitoring by doctors and caregivers, facilitating early detection of disease progression and timely medical intervention.
• To ensure a compact, wearable, and user-friendly design suitable for daily use by Parkinson’s patients.
• To provide a cost-effective and scalable IoT-based healthcare solution for remote neurological disorder monitoring.
• To enhance patient quality of life through continuous monitoring, data-driven insights, and improved clinical decision support.

      The major building blocks of this project are:

• Battery Power supply.
• ESP32.
• 9 Axis Gyroscope.
• MAX30102.
• Temperature sensor.
• OLED.

      Software’s used:

• ARDUINO IDE.
• Embedded C language.
• Machine learning.
• Express SCH for Circuit design.

      Block Diagram:    

video: