Tiny-PPG: A lightweight deep neural network for real-time detection of motion artifacts in photoplethysmogram signals on edge devices

Zheng, Yali; Wu, Chen; Cai, Peizheng; Zhong, Zhiqiang; Huang, Hongda; Jiang, Yuqi

doi:10.1016/j.iot.2023.101007

Cited by 9 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the below table, we compare the performance of the novel PPG-signal-quality assessment method, SQA-PhysMD, with the existing state-of-the-art methods that include Segade [23] and TinyPPG [22].…”

Section: Appendix C Evaluation Of Ppg-signal-quality Assessment Methodsmentioning

confidence: 99%

“…Machine learning-and deep learning-based methods for PPG-signal-quality assessment have recently attracted wider attention among researchers [22,23,[57][58][59]. These developments have been captured in a recent survey [60] that reviews signal-quality assessment methods for contact-based as well as imaging-based PPG.…”

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

“…These developments have been captured in a recent survey [60] that reviews signal-quality assessment methods for contact-based as well as imaging-based PPG. While the majority of works focus on developing a classifier model [58,[61][62][63] with binary inference for quality of the length of a PPG signal, a few recent works have proposed models that offer hightemporal-resolution-signal-quality assessment [20,22,23,64]. In this work, we first extend SQA-Phys, the signal-quality assessment method deployed in [20], such that the inference for signal quality is made per sample, resulting in a 1D dense segmentation task, and secondly we replace the CNN-based decoder of the encoder-decoder architecture with a decoder based on matrix decomposition [21].…”

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

“…The signal-quality labels for this training dataset are provided by the authors of [23] and are available as a part of their repository [67]. Training parameters and the model validation were conducted in line with the recent state-of-the-art works [22,23]. As most of the rPPG methods deploy face detection as an initial step of the processing pipeline, we pre-process the dataset by first cropped facial regions.…”

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

“…For the latter, we deploy SQA-PhysMD, adapted from a recent work [20], in which the CNN-based decoder module is replaced with a more efficient matrix-decomposition-based module [21] and the inference is made per sample, making it a dense 1D segmentation task. SQA-PhysMD shows significantly improved performance against the existing SOTA methods for an automated PPG-signal-quality assessment [22,23] on the iBVP dataset (preliminary results presented in Table A4 in Appendix C). The noisy segments can be flexibly removed from the ground-truth PPG signals as well as the corresponding video frames for training as well as evaluating rPPG methods.…”

Section: Introductionmentioning

confidence: 97%

See 4 more Smart Citations

iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

Joshi,

Cho

2024

Electronics

View full text Add to dashboard Cite

Remote photo-plethysmography (rPPG) has emerged as a non-intrusive and promising physiological sensing capability in human–computer interface (HCI) research, gradually extending its applications in health-monitoring and clinical care contexts. With advanced machine learning models, recent datasets collected in real-world conditions have gradually enhanced the performance of rPPG methods in recovering heart-rate and heart-rate-variability metrics. However, the signal quality of reference ground-truth PPG data in existing datasets is by and large neglected, while poor-quality references negatively influence models. Here, this work introduces a new imaging blood volume pulse (iBVP) dataset of synchronized RGB and thermal infrared videos with ground-truth PPG signals from ear with their high-resolution-signal-quality labels, for the first time. Participants perform rhythmic breathing, head-movement, and stress-inducing tasks, which help reflect real-world variations in psycho-physiological states. This work conducts dense (per sample) signal-quality assessment to discard noisy segments of ground-truth and corresponding video frames. We further present a novel end-to-end machine learning framework, iBVPNet, that features an efficient and effective spatio-temporal feature aggregation for the reliable estimation of BVP signals. Finally, this work examines the feasibility of extracting BVP signals from thermal video frames, which is under-explored. The iBVP dataset and source codes are publicly available for research use.

show abstract

Section: Appendix C Evaluation Of Ppg-signal-quality Assessment Methodsmentioning

confidence: 99%

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

Section: Pre-processing and Signal Quality Assessmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

See 3 more Smart Citations

iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

Joshi,

Cho

2024

Electronics

View full text Add to dashboard Cite

show abstract

Flexible and Multifunctional Skin Patch for Clinical Decision Support in Psychiatric Assessment

Kim,

Lee,

Lee

2024

Adv Materials Technologies

View full text Add to dashboard Cite

The recent advances in flexible and wearable electronics, along with ubiquitous biosensing technologies have enabled the continuous monitoring of health conditions outside of medical facilities. Health‐monitoring tools based on wearable sensors must be more user‐friendly, informative, and cost‐effective for daily applications owing to the increased prevalence of chronic diseases and mental illnesses. In this study, a flexible and multifunctional skin patch and a custom‐designed application for wirelessly monitoring the wearer's physical and mental health conditions are proposed. The optimized design and soft‐covering materials of the skin patch enable long‐term attachment to the body without causing discomfort or irritation to the wearer. Onboard processing of the signals enables real‐time monitoring and signal acquisition of multiple biomarkers, including the blood oxygen saturation level (SpO2), pulse rate (PR), pulse rate variability (PRV), perfusion index (PI), body movement, and temperature during daily activities. The photoplethysmography (PPG)‐based biomarkers acquired from various body sites are compared and calibrated to verify its performance. Demonstrated pilot trial shows the potential application of the skin patch for clinical decision support in psychiatric assessments that can be implemented as an assistive mental illness monitoring system for psychiatrists and researchers.

show abstract

Schrödinger spectrum and slim CNN architecture-based signal quality estimation for Photoplethysmogram signals

Sarkar,

Ghosh

2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Tiny-PPG: A lightweight deep neural network for real-time detection of motion artifacts in photoplethysmogram signals on edge devices

Cited by 9 publications

References 26 publications

iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

Flexible and Multifunctional Skin Patch for Clinical Decision Support in Psychiatric Assessment

Schrödinger spectrum and slim CNN architecture-based signal quality estimation for Photoplethysmogram signals

Contact Info

Product

Resources

About