Particle filter-based noise reduction of PPG signals for robust emotion recognition

In this paper, we address the problem of noise reduction of photoplethysmography (PPG) signals acquired from a wristwatch-type PPG array sensor. The previous noise reduction approaches assumed that the noise sources are stationary. However, in real situations, PPG signals often get corrupted by nonstationary movement noise. To reduce such noise, we propose to estimate the desired signal from corrupted signals by using a particle filter. The performance of the proposed noise reduction algorithm is evaluated and compared with the conventional Kalman filter-based algorithm. In computer experiments using real PPG signals, the proposed algorithm is shown to effectively reduce the movement noise and improve emotion recognition accuracy absolutely by 8.3 % and 8.2 % in the case of arm movements and road walking, respectively, compared with the Kalman filter-based algorithm.