An Accurate Non-accelerometer-based PPG Motion Artifact Removal Technique using CycleGAN

Zargari, Amir Hosein Afandizadeh; Aqajari, Seyed Amir Hossein; Khodabandeh, Hadi; Rahmani, Amir M.; Kurdahi, Fadi

doi:10.48550/arxiv.2106.11512

Cited by 6 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine and deep learning based works on PPG denoising have emerged. For instance, [15] utilizes the principal component analysis along with an artificial neural network, while [16] considers a cycle generative adversarial network for noise removal from PPG signals.…”

Section: Related Workmentioning

confidence: 99%

A Deep Learning & Fast Wavelet Transform-based Hybrid Approach for Denoising of PPG Signals

Ahmad¹,

Mehmood²,

Rahman³

et al. 2023

Preprint

View full text Add to dashboard Cite

This letter presents a novel hybrid method that leverages deep learning to exploit the multi-resolution analysis capability of the wavelets, in order to denoise a photoplethysmography (PPG) signal. Under the proposed method, a noisy PPG sequence of length N is first decomposed into L detailed coefficients using the fast wavelet transform (FWT). Then, the clean PPG sequence is reconstructed as follows. A custom feedforward neural network (FFNN) provides the binary weights for each of the wavelet sub-signals outputted by the inverse-FWT block. This way, all those sub-signals which correspond to noise or artefacts are discarded during reconstruction. The FFNN is trained on the Beth Israel Deaconess Medical Center (BIDMC) dataset under the supervised learning framework, whereby we compute the mean squared-error (MSE) between the denoised sequence and the reference clean PPG signal, and compute the gradient of the MSE for the back-propagation. Numerical results show that the proposed method effectively denoises the corrupted PPG and video-PPG signal.

show abstract

Section: Related Workmentioning

confidence: 99%

A Deep Learning & Fast Wavelet Transform-based Hybrid Approach for Denoising of PPG Signals

Ahmad¹,

Mehmood²,

Rahman³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A generative adversarial network (GAN), first proposed by Goodfellow in 2014 [10], is comprised of two networks, a generator (G) and a discriminator (D) which are trained in an adversarial (minimax) way; G generates fake signals that can confuse D, while D judges whether the generated signals p(t) = G(x(t)) is a fake or a true one. Recent works with GANs in this, and related areas, are quite promising: in [11], a GAN was used to remove low intensity motion noise from PPG signals by representing the PPG as a two dimensional (correlation) image array allowing a standard image-based GAN architecture to be used; and the removal of ocular artifacts from electroencephalography (EEG) data, necessary in a variety of brain-computer interface applications, was attempted in [16].…”

Section: A Generative Adversarial Networkmentioning

confidence: 99%

“…A general issue, with a method such as this, is that noisefree data is generally needed for training purposes. In [11], where the motion effects are only due to sensor motion (and not complicated by the change in the pulsatile cardiac signal necessary to create that motion, such as occurs in medium-high intensity exercise), the periods where the sensor is at rest may be used as noise-free (ground truth) data. Conversely, in [16], state-of-the art electro-oculography based algorithms are assumed to provide the best approximation to cleaned data, but it will still only be an approximation.…”

Section: A Generative Adversarial Networkmentioning

confidence: 99%

PPG-GAN: An Adversarial Network to De-noise PPG Signals during Physical Activity

Zheng

Derakhshani

Barrett

et al. 2022

2022 IEEE International Conference on E-Health Networking, Application &Amp; Services (HealthCom)

View full text Add to dashboard Cite

Quality photoplethysmographic (PPG) signals are essential for accurate physiological assessment. However, the PPG acquisition process is often accompanied by spurious motion artefacts (MAs), especially during medium-high intensity physical activity. This study proposes a generative adversarial network (PPG-GAN) to create de-noised versions of measure PPG signals.The Adaptive Notch Filtration (ANF) algorithm, which enables the extraction of accurate heart rates (HR) and respiration rates (RR) from PPG signals, is used as the approximate reference signal to train the PPG-GAN. The generated PPG signals from test inputs provide a heart rate (HR) with a mean absolute error of 1.68 bpm for the IEEE-SPC dataset. A comparison with goldstandard HR and RR measurements, for our in-house dataset, show the errors in absolute value of less than 5%. The generated PPG signals, for the test clips, show a very strong correlation with their reference values, R ≈ 0.98. The results suggest that PPG-GAN could be a paradigm for MA-free PPG signal processing specifically for personal healthcare, even during high intensity activity.

show abstract

“…PPG sensors are widely employed in wearable devices [ 5 , 6 ]. PPG sensors emit infrared rays to the skin and measure the amount of blood flow by determining the amount of rays absorbed in red blood cells.…”

Section: Introductionmentioning

confidence: 99%

“…The PPG data are also influenced by the subject’s skin characteristic and motion artifact; these factors make raw data produce noise [ 6 , 15 , 16 ]. In order to reduce the noise of signal, a motion reduction technique for respiratory rate was proposed [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Photoplethysmography-Based Distance Estimation for True Wireless Stereo

et al. 2023

View full text Add to dashboard Cite

Recently, supplying healthcare services with wearable devices has been investigated. To realize this for true wireless stereo (TWS), which has limited resources (e.g., space, power consumption, and area), implementing multiple functions with one sensor simultaneously is required. The Photoplethysmography (PPG) sensor is a representative healthcare sensor that measures repeated data according to the heart rate. However, since the PPG data are biological, they are influenced by motion artifact and subject characteristics. Hence, noise reduction is needed for PPG data. In this paper, we propose the distance estimation algorithm for PPG signals of TWS. For distance estimation, we designed a waveform adjustment (WA) filter that minimizes noise while maintaining the relationship between before and after data, a lightweight deep learning model called MobileNet, and a PPG monitoring testbed. The number of criteria for distance estimation was set to three. In order to verify the proposed algorithm, we compared several metrics with other filters and AI models. The highest accuracy, precision, recall, and f1 score of the proposed algorithm were 92.5%, 92.6%, 92.8%, and 0.927, respectively, when the signal length was 15. Experimental results of other algorithms showed higher metrics than the proposed algorithm in some cases, but the proposed model showed the fastest inference time.

show abstract

An Accurate Non-accelerometer-based PPG Motion Artifact Removal Technique using CycleGAN

Cited by 6 publications

References 0 publications

A Deep Learning & Fast Wavelet Transform-based Hybrid Approach for Denoising of PPG Signals

A Deep Learning & Fast Wavelet Transform-based Hybrid Approach for Denoising of PPG Signals

PPG-GAN: An Adversarial Network to De-noise PPG Signals during Physical Activity

Photoplethysmography-Based Distance Estimation for True Wireless Stereo

Contact Info

Product

Resources

About