Smart Infant-Monitoring System with Machine Learning Model to Detect Physiological Activities and Ambient Conditions

The paper presents development of a smart infant monitoring system using multiple non-invasive sensors to detect various physiological functions. The system can evaluate different physiological activities such as respiration, movement, noise, position, as well as ambient temperature, and humidity. By processing the acquired data from different sensor modules, the system can generate alarm signals for adverse situations such as the occurrence of apnea, seizure, or noisy and uncomfortable environmental conditions. The system will also be able to detect critical respiratory conditions by analyzing breathing data and saturated blood oxygen level (SpO2) using machine learning (ML) models such as neural networks. The proposed system allows the caregiver to monitor the condition of the patient from a remote location by implementing wireless communication with a remote computer or a cell phone.