Heartsense: Estimating heart rate from smartphone photoplethysmogram using adaptive filter and interpolation

Abstract

In recent days, physiological sensing using smartphones is gaining attention everywhere for preventive health-care. In this paper, we propose a 2-stage approach for robust heart rate (HR) calculation from photoplethysmogram (PPG) signal, captured using smartphones. Firstly, Normalized Least Mean Square (NLMS) based adaptive filter is used to clean up the noisy PPG signal. Then, heart rate is calculated from the frequency spectrum, which is further fine-tuned using different interpolation techniques. Experimental results, show that the overall HR calculation improves significantly due to the proposed 2-stage approach.