Heart rate estimation in PPG signals using Convolutional-Recurrent Regressor. (June 2022)

• Record Type: Journal Article
• Authors: Ismail, Shahid; Siddiqi, Imran; Akram, Usman
• Is Part Of: Computers in biology and medicine. Volume 145(2022)
• Publication Date: 2022-06
• Subjects: PPG Signal -- Deep learning -- Convolutional-recursive networks -- Empirical mode decomposition; IEEE Signal Processing Cup (SPC) -- Singular Spectrum Analysis (SSA) -- Sparse signal reconstruction (SSR) -- Focal under-determined system solver (FOCUSS) -- Artificial neural networks (ANN) -- Convolutional neural networks (CNN) -- Long short term memory (LSTM) -- Binary Cornet (b-Cornet) -- Convolutional and recurrent neural networks (C-RNN) -- and fractional Brownian motion (fBm); Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105470
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Heart rate monitoring using PPG signal has emerged as an attractive as well as an applied research problem which enjoys a renewed interest in the recent years. Spectral analysis of PPG for heart rate monitoring, though effective when the subject is at rest, suffers from performance degradation in case of motion artifacts which mask the peak related with the actual heart rate. Leveraging the recent advancements in deep (machine) learning and exploiting the signal, spectral and time-frequency perspectives, we introduce an effective method for heart rate estimation from PPG signals acquired from subjects performing different exercises. We extract a set of features characterizing the signal and feed these feature sequences to a hybrid convolutional-recurrent neural network (C-RNN) in a regression framework. Experimental study on the benchmark IEEE signal processing cup dataset reports low error rates reading 2.41 ± 2.90 bpm for subject-dependent and 3.8 ± 2.3 bpm for subject-independent protocol thus, validating the ideas put forward in this study. Graphical abstract: Image 1 Highlights: Heart rate estimation from PPG signals using a hybrid of signal processing and machine learning techniques. Signal characterization using statistical, time and frequency features. Learning to estimate heartrate through a Convolutional-Recurrent Regressor. A shallow network architecture allowing real time applications. Comprehensive experimental study in subject-dependent and subject-independent protocols.