Real-time Monitoring and Prediction of Respiratory Diseases Using IoT and Machine Learning
S. Aghalya, N. Venkatesvara Rao, Rohit Roy, C. Srinivasan, M. S. Godwin Premi
Abstract
Early detection and intervention are essential for respiratory disease management and patient outcomes. The paper presents an integrated system that integrates Internet of Things (IoT) devices, such as sensors and a control unit, with cloud connectivity and RNN-based machine learning algorithms. Sensors in IoT devices capture breathing data, including the condition of the lungs, breathing patterns, and surrounding parameters. For real-time analysis and processing, this data is sent to the cloud. A cloud-connected controller manages data flow between sensors and the cloud network. It integrates data from various sensors to provide a complete respiratory parameter view. Processing acquired data requires determining resources and storage from the cloud infrastructure. Recurrent Neural Networks-based machine learning techniques are used to learn from respiratory data temporal patterns. The RNN model uses acquired data information to predict sequential connections, such as respiratory disease development. The RNN model predictions and insights are sent to the controller, healthcare practitioners, and patients in real time. Alerts notification can provide rapid illness management and individualized suggestions. Continuous respiration monitoring, real-time analysis and predictions are enabled in the cloud. These preventative measures can enhance patient care and outcomes while reducing hospitalizations, emergency department visits, and healthcare consumption. Overall, the proposed system provides a potential solution for continuously tracking and predicting respiratory conditions, providing patients and healthcare professionals with significant insights and actions for respiratory disease management.