Heart Rate Estimation from Incomplete Electrocardiography Signals

Abstract

As one of the most remarkable indicators of physiological health, heart rate (HR) has become an unfailing investigation for researchers. Unlike many existing methods, this article proposes an approach to implement short-time HR estimation from electrocardiography in time series missing patterns. Benefiting from the rapid development of deep learning, we adopted a bidirectional long short-term memory model (Bi-LSTM) and temporal convolution network (TCN) to recover complete heartbeat signals from those with durations are less than one cardiac cycle, and the estimated HR from recovered segment combining the input and the predicted output. We also compared the performance of Bi-LSTM and TCN in PhysioNet dataset. Validating the method over a resting heart rate range of 60–120 bpm in the database without significant arrhythmias and a corresponding range of 30–150 bpm in the database with arrhythmias, we found that networks provide an estimated approach for incomplete signals in a fixed format. These results are consistent with real heartbeats in the normal heartbeat dataset (γ > 0.7, RMSE < 10) and in the arrhythmia database (γ > 0.6, RMSE < 30), verifying that HR could be estimated by models in advance. We also discussed the short-time limits for the predictive model. It could be used for physiological purposes such as mobile sensing in time-constrained scenarios, and providing useful insights for better time series analyses in missing data patterns.

Machine Learning in RADAR-based Physiological Signals Sensing: A Scoping Review of the Models, Datasets and Metrics

“…Continuous vital signs monitoring can prevent life-threatening scenarios by providing early warnings before a decline of the patient's status [104]. In this sub-category of papers on value estimation we include papers dealing with the estimation of vital signs, such as HR (n = 21) [17], [22], [25], [28], [29], [52], [55]- [57], [62], [64], [74], [76], [82], [87], [91], [93], [96]- [98], BR [58], [66], [88], [89], [99], [102] (n = 6), both HR and BR [31], [34], [40], [53], [54], [92], [103] (n = 7), BP [65], [67], [75], [83], [85], [100], [101] (n = 7), oxygen saturation (SpO2) [84] (n = 1), and spyrometric indices [61] (n = 1) in a given windows of observation.…”

“…For the hybrid architecture the deep learning model used was an encoder-decoder type in combination with extracted features from K-nearest neighbour. The general [17], [22], [25], [28], [29], [31], [34], [40], [52]- [58], [61], [62], [64]- [67], [74]- [76], [82]- [89], [91]- [93], [96]- [103] Signal reconstruction (n = 18)…”

“…Radar Signal Processing and feature extraction Range Azimuth Elevation [36] Range Time [29], [30], [34], [40], [41], [52], [55], [60], [64], [66]- [70], [72], [78], [79], [83], [85], [86], [95]- [97], [99] Doppler time (Spectrogram) [31], [54], [56], [58], [63], [70], [72], [91]- [93], [98]…”

Data-Fusion-Based Quality Enhancement for HR Measurements Collected by Wearable Sensors

“…However, the performance of this type of approach is sensitive to the data quality. Bidirectional long-short-term-memory (Bi-LSTM) neural network and temporal convolutional network (TCN) [20] were adopted to model the HR temporal patterns and estimate the missing data, given a large amount of historical HR for model training. However, these models are only designed to estimate missing values in a short period, such as one cardiac cycle.…”

Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

“…Nowadays many methods commonly used to measure heart rate, including electrocardiography [3], optical [4] [5], acoustic [6], and piezoelectric [7]. At this stage, people's requirements for heart rate detection do not only stop at high accuracy, but also require non-invasiveness, strong real-time capability, and convenience.…”