Presenting a new method to separate fetal heart signals from the mother by using sequential quadratic programming

One of the most common causes of death during the birth of babies is heart failure. Diagnosis of this disease requires observation of heart activity. Since the electrical signals recorded in the mother’s abdomen contain a lot of information such as: mother’s heart signal, mother’s and fetus’s muscle activity, fetus’s brain activity and environmental noises, researchers are looking for ways to separate the fetus’s heart signals from the mother’s are. The proposed method has super-linear convergence, which provides global convergence results and an exact solution to solve the sub-problem. The performance of the proposed method is compared with the best existing methods and the results show that the proposed method has the lowest error rate and the highest speed in separating fetal heart signals from the mother compared to other methods.