Detection and Classification of Nonstationary Signals: Application to Uterine EMG for Prognostication of Premature Delivery

Abstract

In recent literature, several techniques have been adopted to reject noise from EMG recordings, which is important for using EMG techniques in clinics and research work. In this paper, the least mean square (LMS) and recursive least square (RLS) adaptive algorithms have been proposed to denoise uterine EMG signals taken from the open-source database TPEHG. Simulations were performed in the MATLAB Simulink environment. The obtained results were then compared with the wavelet transform and 0.34–1.0 Hz bandpass filter using signal-to-noise ratio measures. The results showed that the RLS-based algorithm performs the best among the other tested algorithms; the possible use of uterine EMG signals for prognostication of premature vs. term delivery has been taken into consideration.