Heart rate (HR) estimation using photoplethysmography (PPG) has drawn increasing attention in the field of wearable technology due to its advantages with higher degree of usability and lower cost than Electrocardiograph. It has been widely used in wearable devices, such as smart-watches for fitness tracking and vital sign monitoring. However, motion artifact is a strong interference, preventing accurate estimation of HR. Signal decomposition and adaptive filtering are two popular approaches for motion artifact removal, but each of them has inherent drawbacks. In this paper, a hybrid motion artifact removal method is proposed, which combines nonlinear adaptive filtering and signal decomposition, getting the best of both approaches. The method was evaluated on the PPG database used in the 2015 IEEE Signal Processing Cup. The experimental results showed that the method achieved the average absolute error of 1.16 beat per minutes (BPM) on the 12 training data sets, and 2.98 BPM on the ten testing data sets.

The estimation of heart rate (HR) based on wearable devices is of interest in fitness. Photoplethysmography (PPG) is a promising approach to estimate HR due to low cost; however, it is easily corrupted by motion artifacts (MA). In this work, a robust approach based on random forest is proposed for accurately estimating HR from the photoplethysmography signal contaminated by intense motion artifacts, consisting of two stages. Stage 1 proposes a hybrid method to effectively remove MA with a low computation complexity, where two MA removal algorithms are combined by an accurate binary decision algorithm whose aim is to decide whether or not to adopt the second MA removal algorithm. Stage 2 proposes a random forest-based spectral peak-tracking algorithm, whose aim is to locate the spectral peak corresponding to HR, formulating the problem of spectral peak tracking into a pattern classification problem. Experiments on the PPG datasets including 22 subjects used in the 2015 IEEE Signal Processing Cup showed that the proposed approach achieved the average absolute error of 1.65 beats per minute (BPM) on the 22 PPG datasets. Compared to state-of-the-art approaches, the proposed approach has better accuracy and robustness to intense motion artifacts, indicating its potential use in wearable sensors for health monitoring and fitness tracking.

Heart rate (HR) monitoring using photoplethysmography (PPG) is a promising feature in modern wearable devices. PPG is easily contaminated by motion artifacts (MA), hindering estimation of HR. For quasi-periodic motions, previous works generally focused on a few specific motions, such as walking and fast running. However, they may not work well for many different quasi-periodic motions where MA are very complex. In this paper, a robust HR monitoring scheme for different quasi-periodic motions using wrist-type PPG is proposed, which consists of dictionary learning for signal characteristics learning, human motion recognition for the current motion recognition and dictionary selection, sparse representation-based MA elimination for denoising, and spectral peak tracking for HR-related spectral peak tracking. The proposed scheme is robust to MA caused by different motions and has high accuracy. Experiments on six common quasi-periodic motions showed that the average absolute error of heart rate estimation was 2.40 beat per minute, and also showed that the proposed method is more robust than some state-of-the-art approaches for different motions.

Wearable telemonitoring of electrocardiogram (ECG) based on wireless body Area networks (WBAN) is a promising approach in next-generation patient-centric telecardiology solutions. In order to guarantee long-term effective operation of monitoring systems, the power consumption of the sensors must be strictly limited. Compressed sensing (CS) is an effective method to alleviate this problem. However, ECG signals in WBAN are usually non-sparse, and most traditional compressed sensing recovery algorithms have difficulty recovering non-sparse signals. In this paper, we proposed a fast and robust non-sparse signal recovery algorithm for wearable ECG telemonitoring. In the proposed algorithm, the alternating direction method of multipliers (ADMM) is used to accelerate the speed of block sparse Bayesian learning (BSBL) framework. We used the famous MIT-BIH Arrhythmia Database, MIT-BIH Long-Term ECG Database and ECG datasets collected in our practical wearable ECG telemonitoring system to verify the performance of the proposed algorithm. The experimental results show that the proposed algorithm can directly recover ECG signals with a satisfactory accuracy in a time domain without a dictionary matrix. Due to acceleration by ADMM, the proposed algorithm has a fast speed, and also it is robust for different ECG datasets. These results suggest that the proposed algorithm is very promising for wearable ECG telemonitoring.

Recently, classification from compressed physiological signals in compressed sensing has been successfully applied to cardiovascular disease monitoring. However, in real-time wearable electrocardiogram (ECG) monitoring, it is very difficult to directly obtain the heartbeats information from compressed ECG signals. Thus arrhythmia classification from compressed ECG signals has to be handled in fixed-length segments instead of individual heartbeats. An inevitable issue is that a fixed-length ECG segment may contain multiple different types of arrhythmia. As a result, it is not appropriate to represent the multi-type real arrhythmia with a single label. In this paper, we first introduce multiple labels into fixed-length compressed ECG segments to challenge the arrhythmia classification issue. Then, we propose a deep learning model, which can directly classify multiple different types of arrhythmia from fixed-length compressed ECG segments with the advantages of low time cost for data processing and relatively high classification accuracy at a high compression ratio. Experimental results on the MIT-BIH arrhythmia database show that the exact match rate of our proposed method has reached 96.03% at CR(Compression Ratio)=70%, 94.99% at CR=80% and 93.19% at CR=90%.

In the wearable health monitoring based on compressed sensing, atrial fibrillation detection directly from the compressed ECG can effectively reduce the time cost of data processing rather than classification after reconstruction. However, the existing methods for atrial fibrillation detection from compressed ECG did not fully benefit from the existing prior information, resulting in unsatisfactory classification performance, especially in some applications that require high compression ratio (CR). In this paper, we propose a deep learning method to detect atrial fibrillation directly from compressed ECG without reconstruction. Specifically, we design a deep network model for one-dimensional ECG signals, and the measurement matrix is used to initialize the first layer of the model so that the proposed model can obtain more prior information which benefits improving the classification performance of atrial fibrillation detection from compressed ECG. The experimental results on the MIT-BIH Atrial Fibrillation Database show that when the CR is 10%, the accuracy and F1 score of the proposed method reach 97.52% and 98.02%, respectively. Compared with the atrial fibrillation detection from original ECG, the corresponding accuracy and F1 score are only reduced by 0.88% and 0.69%. Even at a high CR of 90%, the accuracy and F1 score are still only reduced by 6.77% and 5.31%, respectively. All of the experimental results demonstrate that the proposed method is superior to other existing methods for atrial fibrillation detection from compressed ECG. Therefore, the proposed method is promising for atrial fibrillation detection in wearable health monitoring based on compressed sensing.