Measuring Heart Rate During Physical Exercise by Subspace Decomposition and Kalman Smoothing

Galli, Alessandra; Narduzzi, C.; Giorgi, Giada

doi:10.1109/tim.2017.2770818

Cited by 49 publications

(38 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AAE of these subjects are slightly higher but within the acceptable limit. However, the mean AAE and AEP over all 12 subjects of our proposed method are 1.08 ± 1.45 BPM (Mean ± SD) and 1.82% in Tables 2 and 3, which is found the lowest AAE and AEP among [13] 1.19% 1.66% 1.27% 1.41% 0.51% 1.09% 0.54% 0.47% 0.41% 2.43% 0.51% 0.81% 1.01% SPECTRAP (offline) [16] 1.04% 2.33% 0.66% 1.31% 0.74% 1.14% 1.36% 0.55% 0.52% 2.27% 0.65% 1.02% 1.12% NOANc [19] 1.59% 1.99% 1.02% 1.51% 0.75% 1.05% 0.72% 1.04% 0.76% 1.93% 0.79% 0.79% 1.16% SSA+KS [17] 2.11% 3.02% 1.11% 1.04% 0.70% 1.82% 1.04% 0.97% 0.95% 2.79% 0.91% 0.92% 1.45% Ours 0.92% 1.20% 0.52% 1.18% 0.55% 0.87% 0.63% 0.68% 0.46% 1.85% 0.65% 0.62% 0.84% all algorithm. In contrast, the AAE of TROIKA is 2.34 ± 2.47 BPM, the AEP is 1.82%.…”

Section: Results Analysismentioning

confidence: 99%

“…From Table 4 we can see that our method costs less time compared with the algorithms respectively proposed in Refs. [12], [13], and [17]. It also costs approximate time to the spectral subtraction [16] and [27], which have been recognized as the fastest method.…”

Section: Results Analysismentioning

confidence: 99%

“…1). At present, many techniques were proposed to reduce MA from PPG signal during movement, including Wavelet Denoising [8], [9], Independ Component Analysis (ICA) [10], [11], Singular Spectrum Analysis (SSA) [12], [13], Empirical Mode Decomposition (EMD) [14], [15], and [16], Kalman Filtering [17], Adaptive Filtering [18], [19], Particle Filtering [20], [21] and other mixture of methods [22], [23], etc.…”

Section: Introductionmentioning

confidence: 99%

“…This is unrealistic in realtime monitoring of actual HR, and the practicality of the algorithm is greatly reduced. Galli et al [17] presented an approach using subspace decomposition denoising algorithm, which decomposed effective component and pseudocomponent based on maximum uncorrelated criteria, and finally, the Fourier-based HR estimation would be smoothed and tracked by a Kalman filter. This algorithm can be independent of the initial evaluation of PR and has a certain robustness.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Combining Parallel Adaptive Filtering and Wavelet Threshold Denoising for Photoplethysmography-Based Pulse Rate Monitoring during Intensive Physical Exercise

Wan

Chen

Yang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Real-time pulse rate (PR) monitoring based on photoplethysmography (PPG) has been drawn much attention in recent years. However, PPG signal detected under movement is easily affected by random noises, especially motion artifacts (MA), affecting the accuracy of PR estimation. In this paper, a parallel method structure is proposed, which effectively combines wavelet threshold denoising with recursive least squares (RLS) adaptive filtering to remove interference signals, and uses spectral peak tracking algorithm to estimate real-time PR. Furthermore, we propose a parallel structure RLS adaptive filtering to increase the amplitude of spectral peak associated with PR for PR estimation. This method is evaluated by using the PPG datasets of the 2015 IEEE Signal Processing Cup. Experimental results on the 12 training datasets during subjects' walking or running show that the average absolute error (AAE) is 1.08 beats per minute (BPM) and standard deviation (SD) is 1.45 BPM. In addition, the AAE of PR on the 10 testing datasets during subjects' fast running accompanied with wrist movements can reach 2.90 BPM. Furthermore, the results indicate that the proposed approach keeps high estimation accuracy of PPG signal even with strong MA.

show abstract

Section: Results Analysismentioning

confidence: 99%

Section: Results Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining Parallel Adaptive Filtering and Wavelet Threshold Denoising for Photoplethysmography-Based Pulse Rate Monitoring during Intensive Physical Exercise

Wan

Chen

Yang

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…years ago, Zhang et al shared the datasets containing simultaneously measured acceleration and PPG signals during exercise [1], which has prompted research on MA cancelation in PPG sensors using acceleration signals. Current stateof-the-art methods have reached the accuracy of 2-3 beats per minute (bpm) on average absolute errors (AAEs) during intensive exercise [1]- [13]. Most state-of-the-art methods estimated the HR using the two main stages of MA cancelation and HR tracking.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Heart Rate Estimation From Reflectance Photoplethysmography With Acceleration Power Spectrum and Acceleration Intensity

Chung

Lee

et al. 2020

IEEE Access

View full text Add to dashboard Cite

A wearable reflectance-type photoplethysmography (PPG) sensor can be incorporated in a watch or band to provide instantaneous heart rates (HRs) with minimum inconvenience to users. However, the sensor is sensitive to motion artifacts (MAs), which results in inaccurate HR estimation. To address this problem, we propose a new neural network for deep learning to ensure accurate HR estimation even during intensive exercise. Methods: We propose a new deep neural network based on multiclass and non-uniform multilabel classification for HR estimation. It comprises of two convolutional layers, two long short-term memory (LSTM) layers, one concatenation layer, and three fully connected layers including a softmax. The proposed model feeds the power spectra from the PPG and acceleration signals along with the acceleration intensity to the input layer. We also present a new scheme to evaluate the loss value by modifying the true HR value into a Gaussian distribution. Results: We used 48 training datasets and evaluated 23 isolated testing datasets. The proposed model exhibited average absolute error of less than 1.5 bpm for all the training and test datasets-1.09 bpm for the training dataset and 1.46 bpm for the test dataset. Conclusion: The proposed model outperforms the state-of-the-art methods for accurate estimation of HR. Significance: It precisely estimates the HRs with robustness even during intensive physical exercise, as evidenced by the accuracy when PPG signals are severely corrupted by MAs. INDEX TERMS Reflectance-type photoplethysmography, instantaneous heart rate, deep learning, convolutional layer, long short-term memory (LSTM) layer.

show abstract

Heart-rate tuned comb filters for processing photoplethysmogram (PPG) signals in pulse oximetry

Alkhoury

Choi

Wang

et al. 2020

J Clin Monit Comput

View full text Add to dashboard Cite

Calculation of peripheral capillary oxygen saturation (SpO 2) levels in humans is often made with a pulse oximeter, using photoplethysmography (PPG) waveforms. However, measurements of PPG waveforms are susceptible to motion noise due to subject and sensor movements. In this study, we compare two SpO 2-level calculation techniques, and measure the effect of pre-filtering by a heart-rate tuned comb peak filter on their performance. These techniques are: (1) "Red over Infrared," calculating the ratios of AC and DC components of the red and infrared PPG signals, (AC∕DC) red (AC∕DC) infrared , followed by the use of a calibration curve to determine the SpO 2 level Webster (in: Design of pulse oximeters, CRC Press, Boca Raton, 1997); and (2) a motion-resistant algorithm which uses the Discrete Saturation Transform (DST) (Goldman in J Clin Monit Comput 16:475-83, 2000). The DST algorithm isolates individual "saturation components" in the optical pathway, which allows separation of components corresponding to the SpO 2 level from components corresponding to noise and interference, including motion artifacts. The comparison we provide here (employing the two techniques with and without pre-filtering) addresses two aspects: (1) accuracy of the SpO 2 calculations; and (2) computational complexity. We used both synthetic data and experimental data collected from human subjects. The human subjects were tested at rest and while exercising; while exercising, their measurements were subject to the impacts of motion. Our main conclusion is that if an uninterrupted high-quality heart rate measurement is available, then the "Red over Infrared" approach preceded by a heart-rate tuned comb filter provides the preferred trade-off between SpO 2-level accuracy and computational complexity. A modest improvement in SpO 2 estimate accuracy at very low SNR environments may be achieved by switching to the pre-filtered DST-based algorithm (up to 6% improvement in SpO 2 level accuracy at −10 dB over unfiltered DST algorithm and the filtered "Red over Infrared" approach). However, this improvement comes at a significant computational cost.

show abstract

Measuring Heart Rate During Physical Exercise by Subspace Decomposition and Kalman Smoothing

Cited by 49 publications

References 15 publications

Combining Parallel Adaptive Filtering and Wavelet Threshold Denoising for Photoplethysmography-Based Pulse Rate Monitoring during Intensive Physical Exercise

Combining Parallel Adaptive Filtering and Wavelet Threshold Denoising for Photoplethysmography-Based Pulse Rate Monitoring during Intensive Physical Exercise

Deep Learning for Heart Rate Estimation From Reflectance Photoplethysmography With Acceleration Power Spectrum and Acceleration Intensity

Heart-rate tuned comb filters for processing photoplethysmogram (PPG) signals in pulse oximetry

Contact Info

Product

Resources

About