Modified Squirrel Algorithm for Fault Tolerance Using Photoplethysmography in IoT Applications

The previous 10 years witnessed a lot of research into healthcare services and their technological advancements. The Internet of Things is producing an unparalleled amount and diversity of information. However, by the period the information reaches the cloud for processing, the chance to act on it may have passed. Instead of transmitting large amounts of IoT information to the cloud, fog computing investigates the most time-sensitive data at the network border, near where it was produced. The Internet of Things improves incident awareness and response time. A unique real-time approach for precise motion-tolerant heart rate (HR) and pulse oximeter oxygen saturation (SpO2) retrieval from wearable photoplethysmographic (PPG) biosensors is investigated in this study. A technique based on PPG signals is offered, and the Modified S quirrel Algorithm for accurately calculating HR from PPG signals tainted by severe motion distortions is suggested. This proposed technique enhances network reliability while also speeding up operations. The calculated pulse rate from PPGs agreed well with reference points from a contact pulse-oximeter. In 87 % of the epochs, the mistake of pulse rate prediction was less than 3% of the individual average pulse rate, and in 98 % of the epochs, the error was less than 7%. The suggested method's major purpose is to minimize service latency and overheads while increasing cloud dependability and capacities.