Preprocessing of biomedical signals: Removing of the baseline artifacts

In this paper, we propose a new preprocessing algorithm for biomedical signals to remove the baseline artifacts. The proposed algorithm is based on the least squares method. It can automatically estimate the form of the baseline artifacts and eliminate it. First, our algorithm consists in using the method of ordinary least squares (OLS) to estimate the slope of linear regression line. Then, we have developed a technique that allowed us to calculate the inclination angle. Finally, we eliminated these artifacts. To evaluate the reliability and robustness of our algorithm, we tested our method on biomedical signals from PHYSIOBANK database. The results obtained by our algorithm to remove the baseline artifacts set from 96.8% to 89.43%, whereas the results of the most common method consisting in applying a nonlinear median filter with a rectangular window are 64.2 to 52.38%.