Time Domain Analysis for Fetal Movement Detection Using Accelerometer Data

Fetal movement patterns are a measurement of fetal well-being. Therefore, it is important to ascertain fetal movements to avoid fetal morbidity and death. In this research, accelerometer data acquired from pregnant mothers were analyzed in order to recognize the fetal movement patterns. Identification of fetal movements from the accelerometer data is arduous due to the presence of mother's respiratory movements and mother's laugh signals in the data. Hence, time domain analysis was utilized to separate fetal movements from the data. The fetal movements were separated hierarchically by considering the Eigenvalues and Eigenvectors of the auto correlation matrix. The proposed method identified fetal movements with an accuracy of 95%. As the next scope of this work, it is expected to identify abnormalities in the fetal movements to predict the well-being of the fetus.