Multi-Headed Conv-LSTM Network for Heart Rate Estimation during Daily Living Activities

Are Activity Wrist-Worn Devices Accurate for Determining Heart Rate during Intense Exercise?

The market for wrist-worn devices is growing at previously unheard-of speeds. A consequence of their fast commercialization is a lack of adequate studies testing their accuracy on varied populations and pursuits. To provide an understanding of wearable sensors for sports medicine, the present study examined heart rate (HR) measurements of four popular wrist-worn devices, the (Fitbit Charge (FB), Apple Watch (AW), Tomtom runner Cardio (TT), and Samsung G2 (G2)), and compared them with gold standard measurements derived by continuous electrocardiogram examination (ECG). Eight athletes participated in a comparative study undergoing maximal stress testing on a cycle ergometer or a treadmill. We analyzed 1,286 simultaneous HR data pairs between the tested devices and the ECG. The four devices were reasonably accurate at the lowest activity level. However, at higher levels of exercise intensity the FB and G2 tended to underestimate HR values during intense physical effort, while the TT and AW devices were fairly reliable. Our results suggest that HR estimations should be considered cautiously at specific intensities. Indeed, an effective intervention is required to register accurate HR readings at high-intensity levels (above 150 bpm). It is important to consider that even though none of these devices are certified or sold as medical or safety devices, researchers must nonetheless evaluate wrist-worn wearable technology in order to fully understand how HR affects psychological and physical health, especially under conditions of more intense exercise.

Datasets for learning of unknown characteristics of dynamical systems

The ability to uncover characteristics based on empirical measurement is an important step in understanding the underlying system that gives rise to an observed time series. This is especially important for biological signals whose characteristic contributes to the underlying dynamics of the physiological processes. Therefore, by studying such signals, the physiological systems that generate them can be better understood. The datasets presented consist of 33,000 time series of 15 dynamical systems (five chaotic and ten non-chaotic) of the first, second, or third order. Here, the order of a dynamical system means its dimension. The non-chaotic systems were divided into the following classes: periodic, quasi-periodic, and non-periodic. The aim is to propose datasets for machine learning methods, in particular deep learning techniques, to analyze unknown dynamical system characteristics based on obtained time series. In technical validation, three classifications experiments were conducted using two types of neural networks with long short-term memory modules and convolutional layers.

Analysis of photoplethysmogram signal to estimate heart rate during physical activity using fractional fourier transform - A sampling frequency independent and reference signal-less method

BACKGROUND AND OBJECTIVE

Acquiring accurate and reliable health information using a PPG signal in wearable devices requires suppressing motion artifacts. This paper presents a method based on the Fractional Fourier transform (FrFT) to effectively suppress the motion artifacts in a Photoplethysmogram (PPG) signal for an accurate estimation of heart rate (HR).

METHODS

By analyzing various PPG signals recorded under various physiological conditions and sampling frequencies, the proposed work determines an optimal value of the fractional order of the proposed FrFT. The proposed FrFT-based algorithm separates the motion artifacts component from the acquired PPG signal. Finally, the HR estimation accuracy during the strong motion artifact-affected windows is improved using a post-processing technique. The efficacy of the proposed method is evaluated by computing the root mean square error (RMSE).

RESULTS

The performance of the proposed algorithm is compared with methods in recent studies using test and training datasets from the IEEE Signal Processing Cup (SPC). The proposed method provides the mean absolute error of 1.88 beats per minute (BPM) on all twenty-three recordings.

CONCLUSIONS

The proposed method uses the Fourier method in the fractional domain. A noisy signal is rotated into an intermediate plane between the time and frequency domains to separate the signal from the noise. The algorithm incorporates FrFT analysis to suppress motion artifacts from PPG signals to estimate HR accurately. Further, a post-processing step is used to track the HR for accurate and reliable HR estimation. The proposed FrFT-based algorithm doesn't require additional reference accelerometers or hardware to estimate HR in real-time. The noise and signal separation is optimum for a fractional order (a) value in the vicinity of 0.6. The optimized value of fractional order is constant irrespective of the physical activity and sampling frequency.

Forecasting COVID-19 Epidemic Trends by Combining a Neural Network with Rt Estimation

On 31 December 2019, a cluster of pneumonia cases of unknown etiology was reported in Wuhan (China). The cases were declared to be Coronavirus Disease 2019 (COVID-19) by the World Health Organization (WHO). COVID-19 has been defined as SARS Coronavirus 2 (SARS-CoV-2). Some countries, e.g., Italy, France, and the United Kingdom (UK), have been subjected to frequent restrictions for preventing the spread of infection, contrary to other ones, e.g., the United States of America (USA) and Sweden. The restrictions afflicted the evolution of trends with several perturbations that destabilized its normal evolution. Globally, Rt has been used to estimate time-varying reproduction numbers during epidemics. Methods: This paper presents a solution based on Deep Learning (DL) for the analysis and forecasting of epidemic trends in new positive cases of SARS-CoV-2 (COVID-19). It combined a neural network (NN) and an Rt estimation by adjusting the data produced by the output layer of the NN on the related Rt estimation. Results: Tests were performed on datasets related to the following countries: Italy, the USA, France, the UK, and Sweden. Positive case registration was retrieved between 24 February 2020 and 11 January 2022. Tests performed on the Italian dataset showed that our solution reduced the Mean Absolute Percentage Error (MAPE) by 28.44%, 39.36%, 22.96%, 17.93%, 28.10%, and 24.50% compared to other ones with the same configuration but that were based on the LSTM, GRU, RNN, ARIMA (1,0,3), and ARIMA (7,2,4) models, or an NN without applying the Rt as a corrective index. It also reduced MAPE by 17.93%, the Mean Absolute Error (MAE) by 34.37%, and the Root Mean Square Error (RMSE) by 43.76% compared to the same model without the adjustment performed by the Rt. Furthermore, it allowed an average MAPE reduction of 5.37%, 63.10%, 17.84%, and 14.91% on the datasets related to the USA, France, the UK, and Sweden, respectively.

DeepPulse: An Uncertainty-aware Deep Neural Network for Heart Rate Estimations from Wrist-worn Photoplethysmography

Wearable Photoplethysmography (PPG) has gained prominence as a low cost, unobtrusive and continuous method for physiological monitoring. The quality of the collected PPG signals is affected by several sources of interference, predominantly due to physical motion. Many methods for estimating heart rate (HR) from PPG signals have been proposed with Deep Neural Networks (DNNs) gaining popularity in recent years. However, the "black-box" and complex nature of DNNs has caused a lack of trust in the predicted values. This paper contributes DeepPulse, an uncertainty-aware DNN method for estimating HR from PPG and accelerometer signals, with aims of increasing trust of the predicted HR values. To the best of the authors' knowledge no PPG HR estimation method has considered aleatoric and epistemic uncertainty metrics. The results show DeepPulse is the most accurate method for DNNs with smaller network sizes. Finally, recommendations are given to reduce epistemic uncertainty, validate uncertainty estimates, improve the accuracy of DeepPulse as well as reduce the model size for resource-constrained edge devices.