An IoT-based wearable system using accelerometers and machine learning for fetal movement monitoring

Fetal movement is an essential index of fetal well-being. However, existing technologies in clinical applications cannot provide an effective, long-term and easily accessible way for fetal movement monitoring. This paper presents a wearable system using accelerometers and machine learning for automatic monitoring of fetal movement. To realize the concept of the e-health home care, Internet of Things (IoT) is applied on the system to connect all the terminal monitoring units to a control center. The whole system mainly consists of two parts: the local monitoring unit and the remote health evaluation unit, respectively. The local monitoring unit includes: (1) a garment integrating accelerometers for data acquisition and an embedded system for signal processing and machine learning, (2) an Android-based local monitoring platform used for visualization of statistics on fetal health status based on information received from the garment via Bluetooth. The local monitoring unit is also designed to alarm the mother if fetal movements reduce significantly or if the intensity is weakened. The remote health evaluation unit consists of a cloud computing platform and an expert system. Connecting each terminal local monitoring unit via the Internet, the remote health evaluation unit allows an expert to access the information at distance for further medical supervision, make advanced diagnosis as well as take actions in case of emergency. The cloud computing platform is also designed for convergence of medical data from each individual patient to build a general medical database for scientific research. The proposed local fetal movement monitoring unit along with the remote health evaluation platform could be regarded as a good example of IoT application in the field of smart textile and home healthcare.