Long Short-Term Memory Deep-Filter in Remote Photoplethysmography

Botina-Monsalve, Deivid; Benezeth, Yannick; Macwan, Richard; Pierrart, Paul; Parra, Federico; Nakamura, Keisuke; Gómez, Randy; Mitéran, Johel

doi:10.1109/cvprw50498.2020.00161

Cited by 20 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In References [ 47 , 48 ], a LSTM network was applied for signal filtering, improving the quality of the extracted rPPG signal. As the rPPG signal extracted by conventional methods may contain several noise, filtering the noise-contaminated rPPG signal is able to produce a noiseless rPPG signal for more accurate HR estimation.…”

Section: Hybrid Deep Learning Methodsmentioning

confidence: 99%

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

Cheng

Wong

Chin

et al. 2021

Sensors

View full text Add to dashboard Cite

Heart rate (HR) is one of the essential vital signs used to indicate the physiological health of the human body. While traditional HR monitors usually require contact with skin, remote photoplethysmography (rPPG) enables contactless HR monitoring by capturing subtle light changes of skin through a video camera. Given the vast potential of this technology in the future of digital healthcare, remote monitoring of physiological signals has gained significant traction in the research community. In recent years, the success of deep learning (DL) methods for image and video analysis has inspired researchers to apply such techniques to various parts of the remote physiological signal extraction pipeline. In this paper, we discuss several recent advances of DL-based methods specifically for remote HR measurement, categorizing them based on model architecture and application. We further detail relevant real-world applications of remote physiological monitoring and summarize various common resources used to accelerate related research progress. Lastly, we analyze the implications of research findings and discuss research gaps to guide future explorations.

show abstract

Section: Hybrid Deep Learning Methodsmentioning

confidence: 99%

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

Cheng

Wong

Chin

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…This approach shows that the use of DNN for ECG interpretation can increase the quality of the analysis and increase the population's access to diagnosis. 31 Botina-Monsalve et al, 32 used LSTM with a set of public data to filter PPG waves, to improve signal quality and increase the accuracy of heart rate measurements. Also, Liang et al, 33 used a pre-trained CNN (GoogLeNet) to improve the classification and assessment of hypertension using PPG.…”

Section: Is It Time To Use Artificial Intelligence?mentioning

confidence: 99%

Smartphone-Based Screening for Cardiovascular Diseases: A Trend?

Mazzu-Nascimento¹,

Evangelista²,

Abubakar³

et al. 2021

International Journal of Cardiovascular Sciences

View full text Add to dashboard Cite

Cardiovascular diseases are the leading cause of death in the world. People living in vulnerable and poor places such as slums, rural areas and remote locations have difficulty in accessing medical care and diagnostic tests. In addition, given the COVID-19 pandemic, we are witnessing an increase in the use of telemedicine and noninvasive tools for monitoring vital signs. These questions motivate us to write this point of view and to describe some of the main innovations used for non-invasive screening of heart diseases. Smartphones are widely used by the population and are perfect tools for screening cardiovascular diseases. They are equipped with camera, flashlight, microphone, processor, and internet connection, which allow optical, electrical, and acoustic analysis of cardiovascular phenomena. Thus, when using signal processing and artificial intelligence approaches, smartphones may have predictive power for cardiovascular diseases. Here we present different smartphone approaches to analyze signals obtained from various methods including photoplethysmography, phonocardiograph, and electrocardiography to estimate heart rate, blood pressure, oxygen saturation (SpO 2 ), heart murmurs and electrical conduction. Our objective is to present innovations in non-invasive diagnostics using the smartphone and to reflect on these trending approaches. These could help to improve health access and the screening of cardiovascular diseases for millions of people, particularly those living in needy areas.

show abstract

“…Studies applying RNNs to rPPG signals are less common. An application that we cite in this paper is rPPG signal filtering, realized by D. Botina-Monsalve et al [5]. The authors proposed a three-LSTM-layer model able to learn the shape of an rPPG signal.…”

Section: Introductionmentioning

confidence: 99%

“…Since BVP signals are subject to noise related to a person's motion when measured by some PPG devices or by rPPG, we developed a GRU-based neural network to locate noisy portions in these signals. Signal segmentation seems to be relevant as simple filtering, as in [5], may be insufficient. In fact, in [36], authors were not able to use their whole dataset because of noisy contact and remote BVP signals.…”

Section: Introductionmentioning

confidence: 99%

Gated Recurrent Unit-Based RNN for Remote Photoplethysmography Signal Segmentation

Sabour¹,

Benezeth²

2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Remote Photoplethysmography (rPPG) enables quantifying blood volume variations in the skin tissues from an input video recording, using a regular RGB camera. Obtained pulse signals often contain noisy portions due to motion, leading researchers to put aside a great number of rPPG signals in their studies. In this paper, an approach using a Gated Recurrent Unit-based neural network model in order to identify reliable portions in rPPG signals is proposed. This is done by classifying rPPG signal samples into reliable and unreliable samples. For this purpose, rPPG and electrocardiography signals (ECG) were collected from 11 participants, rPPG signal samples were labeled (ECG was used as ground truth), and data were augmented to reach a total number of 11000 1-minute-long rPPG signals. We developed a model composed of a unidimensional CNN and a Bidirectional GRU (1D-CNN+B-GRU) for this study, and obtained an accuracy rate of 85.88%.

show abstract

Long Short-Term Memory Deep-Filter in Remote Photoplethysmography

Cited by 20 publications

References 32 publications

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

Deep Learning Methods for Remote Heart Rate Measurement: A Review and Future Research Agenda

Smartphone-Based Screening for Cardiovascular Diseases: A Trend?

Gated Recurrent Unit-Based RNN for Remote Photoplethysmography Signal Segmentation

Contact Info

Product

Resources

About