The 2023 wearable photoplethysmography roadmap

Physiological Measurement, Journal Year: 2023, Volume and Issue: 44(11), P. 111001 - 111001

Published: July 26, 2023

Abstract Photoplethysmography is a key sensing technology which used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are to monitor physiological parameters including heart rate rhythm, track activities like sleep exercise. Yet, has potential provide much more information on health wellbeing, could inform clinical decision making. This Roadmap outlines directions for research development realise the full of photoplethysmography. Experts discuss topics within areas sensor design, signal processing, applications, directions. Their perspectives valuable guidance researchers developing technology.

Language: Английский

---

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

Published: Feb. 9, 2024

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

Language: Английский

---

A Novel Frequency-Tracking Algorithm for Noncontact Vital Sign Monitoring

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(19), P. 23044 - 23057

Published: Aug. 23, 2023

Noncontact vital sign monitoring, based on mm-wave frequency-modulated continuous wave (FMCW) radar, can be widely applied in elderly care, clinical diagnoses, and in-vehicle occupant detection. The radar monitor the Doppler signal reflected by chest displacement then analyze phase change of echo to get respiration heartbeat signals. This article proposes a frequency-tracking method an improved birth–death strategy calculate rate real-time. There are two main steps estimate from frames within second. First, M-Rife algorithm is employed interpolate frequency each frame. Second, find matching points between adjacent second using ratio for point link. Then, choose longest link whose initial closer at last value tail will current proposed simulated public noncontact dataset verify its feasibility accuracy. To further demonstrate method, this carried out series experiments. experimental results show that has accuracy 98% real-time reduces effect clutter respiratory harmonics rate.

Language: Английский

---

IDTL-rPPG: Remote heart rate estimation using instance-based deep transfer learning

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 95, P. 106416 - 106416

Published: May 14, 2024

Language: Английский

---

Domain Knowledge Integrated CNN-xLSTM-xAtt Network with Multi Stream Feature Fusion for Cuffless Blood Pressure Estimation from Photoplethysmography Signals

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127994 - 127994

Published: May 1, 2025

Language: Английский

---

Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Applied Intelligence, Journal Year: 2024, Volume and Issue: 54(6), P. 4564 - 4584

Published: March 1, 2024

Abstract Currently, learning physiological vital signs such as blood pressure (BP), hemoglobin levels, and oxygen saturation, from Photoplethysmography (PPG) signal, is receiving more attention. Despite successive progress that has been made so far, continuously revealing new aspects characterizes field a rich research topic. It includes diverse number of critical points represented in signal denoising, data cleaning, employed features, feature format, selection, domain, model structure, problem formulation (regression or classification), combinations. worth noting extensive efforts are devoted to utilizing different variants machine deep models while transfer not fully explored yet. So, this paper, we introducing per-beat rPPG-to-BP mapping scheme based on learning. An interesting representation 1-D PPG 2-D image proposed for enabling powerful off-the-shelf image-based through resolves limitations about training size due strict cleaning. Also, it enhances generalization by exploiting underlying excellent extraction. Moreover, non-uniform distribution (data skewness) partially resolved logarithmic transformation. Furthermore, double cleaning applied contact testing rPPG beats well. The quality the segmented tested checking some related metrics. Hence, prediction reliability enhanced excluding deformed beats. Varying relaxed selecting during intervals highest strength. Based experimental results, system outperforms state-of-the-art systems sense mean absolute error (MAE) standard deviation (STD). STD test decreased 5.4782 3.8539 SBP DBP, respectively. MAE 2.3453 1.6854 results BP estimation real video reveal reaches 8.027882 6.013052 estimated videos 7.052803 5.616028 Graphical abstract Proposed camera-based monitoring

Language: Английский

---

A Lightweight Hybrid Model Using Multiscale Markov Transition Field for Real-Time Quality Assessment of Photoplethysmography Signals

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2023, Volume and Issue: 28(2), P. 1078 - 1088

Published: Nov. 10, 2023

The proliferation of wearable devices has escalated the standards for photoplethysmography (PPG) signal quality. This study introduces a lightweight model to address imperative need precise, real-time evaluation PPG quality, followed by its deployment and validation utilizing our integrated upper computer hardware system.

Language: Английский

---

Heart Rate Estimation in Driver Monitoring System Using Quality-guided Spectrum Peak Screening

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2024, Volume and Issue: 73, P. 1 - 14

Published: Jan. 1, 2024

Remote photoplethysmography (rPPG) enables heart rate (HR) measurement under stable illumination and low noise conditions. However, challenges arise due to rapid lighting changes, significant head movements, vehicle vibrations during driving, impacting the recovery of clear rPPG signals rendering denoising techniques alone inadequate in entirely eliminating interference. To address these challenges, we introduce an innovative approach, “Quality-guided Spectral Peak Screening” (QSPS), for monitoring driver’s HR driving. First, developed a signal evaluation framework assessing quality across multiple facial regions following wavelet filtering. Subsequently, by leveraging information, spectral peak screening algorithm is applied from regions, mitigating impact residual on rPPG. The precise determined integrating scores short-term stability various regions. Our method employed commercially available driver system equipped with monochrome camera. Test results show QSPS’s robustness compared established NIR-based detection methods. In driving scenarios, QSPS achieves Mean Absolute Error 4.32 bpm, root mean square error 6.15 percentage time estimation errors smaller than 6 bpm 68.8%. Furthermore, exhibits excellent performance extended 10-min monitoring, Pearson correlation coefficient 0.943 night test 0.906 day test.

Language: Английский

---

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

Electronics, Journal Year: 2024, Volume and Issue: 13(7), P. 1334 - 1334

Published: April 2, 2024

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

Language: Английский

---

PhysioKit: An Open-Source, Low-Cost Physiological Computing Toolkit for Single- and Multi-User Studies

Sensors, Journal Year: 2023, Volume and Issue: 23(19), P. 8244 - 8244

Published: Oct. 4, 2023

The proliferation of physiological sensors opens new opportunities to explore interactions, conduct experiments and evaluate the user experience with continuous monitoring bodily functions. Commercial devices, however, can be costly or limit access raw waveform data, while low-cost are efforts-intensive setup. To address these challenges, we introduce PhysioKit, an open-source, computing toolkit. PhysioKit provides a one-stop pipeline consisting (i) sensing data acquisition layer that configured in modular manner per research needs, (ii) software application enables acquisition, real-time visualization machine learning (ML)-enabled signal quality assessment. This also supports basic visual biofeedback configurations synchronized for co-located remote multi-user settings. In validation study 16 participants, shows strong agreement research-grade on measuring heart rate variability metrics data. Furthermore, report usability survey results from 10 small-project teams (44 individual members total) who used 4-6 weeks, providing insights into its use cases benefits. Lastly, discuss extensibility potential impact toolkit community.

Language: Английский

---