Diseases such as diabetes are known to reduce blood circulation in the capillaries and arterioles; however, there are no devices that can easily measure this on a daily basis. In this study, we developed a tool for measuring finger photoplethysmograms using green-light and near-infrared LEDs. We then conducted photoplethysmography on 25 diabetic inpatients/outpatients as well as 21 adult males and females who had not been diagnosed or treated for diabetes, hypertension, or cardiovascular disease (as a control group). In the diabetic patients, the inverse full width at half maximum velocity plethysmogram (1/FWHMVPG) tended to be smaller compared to the control group, and the delay in the green light a-wave peak relative to the near-infrared light a-wave peak in the acceleration plethysmogram was significantly increased. The results suggest that peripheral hemodynamics could be easily estimated at home using a photoplethysmography device mounted on a ring-wearable device.

In this paper, we present the design of a wearable photoplethysmography (PPG) system, R-band for acquiring the PPG signals. PPG signals are influenced by the respiration or breathing process and hence can be used for estimation of respiration rate. R-Band detects the PPG signal that is routed to a Bluetooth low energy device such as a nearbyplaced smartphone via microprocessor. Further, we developed an algorithm based on Extreme Learning Machine (ELM) regression for the estimation of respiration rate. We proposed spectral kurtosis features that are fused with the state-ofthe-art respiratory-induced amplitude, intensity and frequency variations-based features for the estimation of respiration rate (in units of breaths per minute). In contrast to the neural network (NN), ELM does not require tuning of hidden layer parameter and thus drastically reduces the computational cost as compared to NN trained by the standard backpropagation algorithm. We evaluated the proposed algorithm on Capnobase data available in the public domain.

Photoplethysmography (PPG) is widely utilized in wearable healthcare devices due to its convenient measurement capabilities. However, the unrestricted behavior of users often introduces artifacts into the PPG signal. As a result, signal processing and quality assessment play a crucial role in ensuring that the information contained in the signal can be effectively acquired and analyzed. Traditionally, researchers have discussed signal quality and processing algorithms separately, with individual algorithms developed to address specific artifacts. In this paper, we propose a quality-aware signal processing mechanism that evaluates incoming PPG signals using signal quality index (SQI) and selects the appropriate processing method based on the SQI. Unlike conventional processing approaches, our proposed mechanism recommends processing algorithms based on the quality of each signal, offering an alternative option for designing signal processing flows. Furthermore, our mechanism achieves a favorable trade-off between accuracy and energy consumption, which are the key considerations in long-term heart rate monitoring.

The capability of measuring specific neurophysiological and autonomic parameters plays a crucial role in the objective evaluation of the human’s mental and emotional states. These human aspects are commonly known in scientific literature to be involved in a wide range of processes, such as the stress and arousal. These aspects represent a relevant factor especially in real and operational environment. Neurophysiological autonomic parameters, such as the Electrodermal Activity (EDA) and Photoplethysmographic data (PPG), have been usually investigated through research-graded devices, therefore resulting in a high degree of invasiveness, which could negatively interfere with the monitored user’s activity. For such a reason, in the last decade the recent consumer-grade wearable devices, usually designed for fitness tracking purposes, are receiving an increasing attention from the scientific community, being characterized by higher comfort, easiness of use and, therefore, by higher compatibility with dailylife environments. The present preliminary study aimed at assessing the reliability of a consumer wearable device, i.e., the Fitbit Sense, with respect to a research-graded wearable, i.e., the Empatica E4 wristband, and a laboratory device, i.e., the Shimmer GSR3+. The EDA and PPG were collected among 12 participants while performing multiple resting conditions. The results demonstrated that the EDA and PPG-derived features computed through the wearable and research devices were positively and significantly correlated, while the reliability of the consumer device resulted to be significantly lower.

In this work, an algorithm was developed to measure the respiration rate for an embedded device that can be used by a field robot for relief operation. With this algorithm, the rate measurement was calculated based on direct influences of respiratory-induced intensity variation (RIIV) on blood flow in cardiovascular pathways. For that, a photoplethysmogram (PPG) sensor was used to determine changes in heartbeat frequencies. The PPG sensor readings were filtered using an Information Filter and a Fast Fourier transform (FFT) to determine the state of RIIV. With a relatively light initialization, the information filter can estimate unknown variables based on a series of measurements containing noise and other inaccuraties. Therefore, this filter is suitable for application on an embedded device. For faster calculation time in the implementation, the FFT analysis was calculated only for a major peak in the frequency domain. Test and measurement of respiration rate was conducted based on the device algorithm and spirometer. Heartbeat measurement was also evaluated by comparing the heartbeat data of the PPG sensor and the medical tool kit. Based on the test, the implemented algorithm can measure respiration rate with about 80% accuracy compared with the spirometer.

Background: During pregnancy, major physiological changes occur in every system. Understanding the hemodynamic changes in different stages of pregnancy can help to identify abnormal states during pregnancy. Harmonic analysis could be a useful tool in monitoring the state of the ventricular-arterial system during pregnancy. The aim of this study was to investigate the specific statistical relationships between changes in harmonic indices during different stages of pregnancy. Methods: A Total of 380 women (190 pregnant women and 190 age-matched non-pregnant women), with ages ranging from 20 to 45, were enrolled in the study. The visit measured the subject’s hemodynamic parameters including heart rate, systolic blood pressure (SBP), diastolic blood pressure (DBP) and photoplethysmography (PPG). SBP and DBP were evaluated by an automatic blood pressure monitor. PPG signal were continuously recorded for 12-seconds using a PPG sensor. Spectrum analysis of the PPG signal was performed to evaluate the first five harmonic components (C1 – C5) and harmonic phases (P1 – P5). Result: A comparison between pregnant women and non-pregnant women showed that the non-pregnant women had lower DBP, C3, C5 and P5 (p<0.05). Waist Circumference, Heart rate, C2, C4 and P2 were higher in pregnant women. Logistic regression analysis was used to determine the associations between pregnancy and harmonics indices. C2, C4 and P3 were positively and P1 and P4 were negatively associated with pregnancy after controlling age, BMI, waist circumference, heart rate, SBP and DBP. Conclusion: The results of this study provide information on the changes in the harmonic frequency components during various stages of pregnancy. The harmonic components of the PPG signal have independent predictive value for changes in a woman's physiology during pregnancy. Since non-invasive PPG measurements can be performed frequently and easily, in the future, it is possible that the hemodynamic changes from some pregnancy-related disorders could be studied by harmonic analysis.

Non-invasive heart rate (HR) monitoring is important in clinical settings as it plays a critical role in diagnosing a range of health conditions and assessing well-being. Presently, the gold standards for HR measurement are all based on sensors which require skin contact. Apart from inconvenience, contact sensors have proven problematic in certain scenarios – they cannot be used when mechanical isolation of the patient is imperative (burn victims, patients with shaky hands and feet), cause skin damage to premature babies in the ICU and increase the risk of spreading infections. Non-contact HR monitoring using a camera has been recently shown to be a viable alternative. It is now possible to record cardiac-synchronous blood volume variations from facial videos of human subjects under ambient lighting. These variations produce corresponding changes in skin reflectance which can be extracted as a raw reflectance photoplethysmography (rPPG) signal and processed to reveal HR. In this project, an algorithmic framework for webcam-based HR detection was successfully implemented in MATLAB. The investigation was based on 100 self-captured videos (dark-skinned subject) and 48 videos (from 12 subjects, all but one fair-skinned) obtained from COHFACE – an online database of facial videos and corresponding physiological signals. While the performance metrics (mean error, SNR) of the rPPG signals obtained from the self-captured videos were poor (best case mean error of 22%), they were good enough to demonstrate the success of the implementation. The poor results were primarily imputed to skin tone as rPPG SNR is known to be particularly low for dark tones. The results of the COHFACE videos were far superior, with mean error ranging from 3% to 15% (among 8 different rPPG signals) and 0% to 9% under ambient and dedicated lighting, respectively. This investigation sets the foundation for future research directed at optimizing rPPG performance metrics for dark-skinned subjects.

Heart rate and blood pressure, along with body temperature and respiratory rate, are two of the four parameters used to assess the state of bodily functions, as both measures are indicators of heart activity. Therefore, these measurements become a basic procedure in patient diagnosis, necessitating techniques that can obtain them accurately and reliably, while being as non-intrusive as possible for the patient. Using video data, these two vital signs can be determined at any time and place. To achieve this, artificial intelligence techniques such as machine learning and deep learning 6 can be applied to overcome the main limitations of conventional remote photoplethysmography (rPPG). This document explains the technical and methodological aspects involved, including the acquisition and preprocessing of video data, the extraction of the rPPG signal, and its subsequent processing, as well as the artificial intelligence model for heart rate estimation and the mathematical modeling for blood pressure estimation. We compared the results for heart rate and blood pressure extracted from videos recorded by a basic smartphone front-camera to a blood pressure monitor and achieved results with reasonable accuracy and correlation. These results are part of the AIVA project, grant agreement 2021/C005/00145071. This project has been funded by Red.es through the Spanish 2021 call for grants aimed at research and development projects in artificial intelligence and other digital technologies.

Optical tissue imaging has several advantages over the routine clinical imaging methods, including non-invasiveness (does not change the structure of tissues), remote operation (avoids infection) and ability to quantify the tissue condition by means of specific image parameters. Dermatologists and other skin experts need compact (preferably pocket-size), self-sustained and easy-to-use imaging devices. The operational principles and designs of ten portable in-vivo skin imaging prototypes developed at the Biophotonics Laboratory of Institute of Atomic Physics and Spectroscopy, University of Latvia during the recent five years are presented in this paper. Four groups of imaging devices are considered. Multi-spectral imagers offer possibilities for distant mapping of specific skin parameters, so facilitating better diagnostics of skin malformations. Autofluorescence intensity and photobleaching rate imagers show a promising potential for skin tumor identification and margin delineation. Photoplethysmography video-imagers ensure remote detection of cutaneous blood pulsations and can provide real-time information on cardiovascular parameters and anesthesia efficiency. Multimodal skin imagers perform several of the above-mentioned functions by taking a number of spectral and video images with the same image sensor. Design details of the developed prototypes and results of clinical tests illustrating their functionality are presented and discussed.

Respiratory rate is an important biomarker that indicates changes in the clinical condition of critically ill patients, so a surveillance tool that can accurately monitor the changing respiratory rate in real time is needed. Through investigating various pairs of machine learning models, we proposed new machine learning model for real-time respiratory rate estimation using photoplethysmogram. New photoplethysmogram-driven respiratory rate dataset(StMary) was collected from surgical intensive care unit of a tertiary referral hospital, using photoplethysmogram signal collector. For 50patients and 50healthy volunteers, 2-minute photoplethysmogram was collected for each subject twice. To evaluate the respiratory rate of subject, it was inputted into the deep neural network model we built, and dataset was splitted into training, validation, testing dataset, then 4-fold cross validation was exploited. Our deep neural network model trained with StMary and two public datasets(BIDMC and CapnoBase) individually, or selectively merged dataset had shown a low error rate in respiration rate measurements. Our model trained with StMary showed low mean absolute error score(1.0273±0.8965), and trained with 3 datasets(CapnoBase, BIDMC and StMary) showed a lower error rate(1.7359±1.6724) than the model trained with CapnoBase and BIDMC(1.9480±1.6751). We could verify the performance of model evaluating respiratory rate from photoplethysmogram, and our dataset could contribute as the clinical research data that supports artificial intelligence models evaluating respiratory rate and surveillance tools to test whether their monitoring function works properly.

Photoplethysmography (PPG) is a simple-to-perform vascular optics measurement technique that can detect changes in blood volume in the microvascular tissue bed. Beat-to-beat analysis of the PPG waveform enables the study of the variability of pulse features such as amplitude and pulse arrival time (PAT), and when quantified in the time and frequency domains, has considerable potential to shed light on perfusion changes associated with peripheral arterial disease (PAD). In this pilot study innovative multi-site bilateral finger and toe PPG recordings from 43 healthy control subjects and 31 PAD subjects were compared (recordings each at least 5 minutes, collected in a warm temperature-controlled room). Beat-to-beat normalized amplitude and PAT variability was then quantified in the time-domain using SD and IQR measures and in the frequency-domain bilaterally using Magnitude Squared Coherence (MSC). Significantly reduced normalized amplitude variability (healthy control 0.0384 (IQR 0.0217-0.0744) vs PAD 0.0160 (0.0080-0.0338) (p<0.001) and significantly increased PAT variability (healthy control 0.0063 (0.0052-0.0086) vs PAD 0.0093 (0.0078-0.0144) (p<0.001) was demonstrated in PAD using the time-domain analysis. Frequency-domain analysis demonstrated significantly lower MSC values across a range of frequency bands for PAD patients. These changes suggest a loss of right-to-left body side coherence and cardiovascular control in PAD. This study has also demonstrated the feasibility of using these measurement and analysis methods in studies investigating multi-site PPG variability for a wide range of cardiac and vascular patient groups.

Animal welfare remains a very important issue in the livestock sector but monitoring animal welfare in an objective and continuous way remains a serious challenge. Monitoring animal welfare based upon physiological measurements instead of audio-visual scoring of behaviour would be a step forward. One of the obvious physiological signals related to welfare and stress is heart rate. The objective of this research was to measure heart rate (beat per minutes) on pigs with technology that soon will be affordable. Affordable heart rate monitoring is done today at large scale on humans using the Photo Plethysmography (PPG) technology. We used PPG sensors on pig’s body to test whether it allows getting reliable heart rate signal. A continuous wavelet transform (CWT)-based algorithm is developed to decouple the cardiac pulse waves from the pig. Three different wavelets, namely 2^nd, 4^th and 6^th order Derivative of Gaussian (DOG, are tested. We show results of the developed PPG-based algorithm against electrocardiograms (ECG) as a reference measure for heart rate and this for an anesthetized versus a non-anesthetised animal. We tested three different anatomical body positions (ear, leg and tail) and give results for each body position of the sensor. In summary, it can be concluded that the agreement between PPG-based heart rate technique and reference sensor goes from 91 to 95 percentage. In this paper we showed the potential of using the PPG-based technology to assess pig’s hear rate.

The chicken embryo is a widely used experimental animal-model in many studies such as developmental biology and to study the physiological responses and adaptation to altered environments as well as for cancer and neurobiology research. Embryonic heart rate is an important physiological variable useful as an index reflecting the embryo's natural activity and is considered one of the most difficult parameters to measure. An acceptable measurement technique of embryonic heart rate should provide a reliable cardiac signal quality while maintaining adequate gas exchange through the eggshell along the incubation and embryonic developmental period. In this paper, we presented a detailed design and methodology for a non-invasive PPG-based prototype (Egg-PPG) for real-time and continuous monitoring of embryonic heart rate during incubation. An automatic embryonic cardiac wave detection algorithm, based on normalised spectral entropy, is described. The developed algorithm successfully estimated the embryonic heart rate with 98.7% accuracy. We believe that the developed overall system presented in this paper is showing a promising solution for non-invasion, real-time monitoring of embryonic cardiac signal, which can be used in both experimental studies (e.g., developmental embryology and cardiovascular research) and in industrial incubation applications.

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely Lyapunov Exponent, Approximate Entropy, and Poincaré’s indices. We found an optimum window duration of 11 seconds and 16 seconds for valence and arousal, respectively, with 50% overlap, and achieved an accuracy of 0.76 in both dimensions. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.92. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

Wearable cardiac sensors pave the way to advanced cardiac monitoring applications based on heart rate variability (HRV). In real-life settings, heart rate (HR) measurements are subject to mo-tion artifacts that can be timely removed from the recordings. This leads to frequent data loss in the HR signal, especially for commercial devices based on photoplethysmography (PPG). The cur-rent study had two main goals: (i) to provide a white-box quality index that estimates the amount of missing samples in any piece of HR signal; and (ii) to quantify the impact of data loss on feature extraction in a PPG-based HR signal. This was done by comparing real-life recordings from com-mercial sensors featuring both PPG (Empatica E4) and ECG (Zephyr BioHarness 3). After an out-lier rejection process, our quality index was used to isolate portions of ECG-based HR signal that could be used as benchmark, to validate the output of Empatica E4 at the signal level and at the feature level. Our results showed high accuracy for estimating the mean HR, poor accuracy for short-term HRV features and moderate accuracy for longer-term HRV features. Levels of error could be substantially reduced by using our quality index to identify time windows with few or no missing data.

Stress is an inherent sensation of being unable to handle demands and occurrences. If not properly managed, stress can develop into a chronic condition, leading to the onset of additional chronic health issues like cardiovascular illnesses and diabetes. Various stress meters have been suggested in the past, along with diverse approaches for its estimate. However, in the case of more serious health issues such as hypertension and diabetes, the results can be significantly improved. This study presents the design and implementation of a distributed wearable sensor computing platform with multiple channels. The platform aims to estimate stress levels in diabetes patients by utilizing a fuzzy logic algorithm that is based on the assessment of several physiological indicators. Additionally, a mobile application was created to monitor users' stress levels and integrate data on their blood pressure and blood glucose levels. Validation experiments were performed on patients with chronic diabetes, and the initial findings are presented in the study.

Near-infrared (NIR) photodetectors (PDs) have attracted much attention in noninvasive medical diagnosis and treatment. Especially, the self-filtered NIR PDs are highly demandable for tremendous biomedical application due to their strong ability in wavelength discrimination. In this work, we designed and then fabricated a Si micro-holes array/Graphene (Si MHA/Gr) van der Waals (vdW) Schottky NIR photodiode by using PbS quantum dots (QDs) coating. The device exhibits a unique self-filtered NIR response with a responsivity of 0.7 A/W at -1 V and a response time of 61 μs, which are higher than that without PbS QDs coating and even most of previous Si/Gr Schottky photodiodes. The light trapping of the Si MHA and the PbS QDs coating can be attributed to the high responsivity of the vdW photodiode. Furthermore, the presented NIR photodiode can also be integrated in photoplethysmography (PPG) for real-time heart-rate (HR) monitoring. The extracted HR is in great accord with the value measured with the patient monitor by analyzing the Fourier transform of the stable and reliable fingertip PPG waveform, suggesting its potential for practical applications.

Stress has emerged as a major concern in modern society, significantly impacting human health and well-being. Statistical evidence underscores the extensive social influence of stress, especially in terms of work-related stress and associated healthcare costs. This work addresses the critical need for accurate stress detection, emphasising its far-reaching effects on health and social dynamics. Focusing on remote stress monitoring, this work proposes an efficient deep learning framework to discern stress from facial videos. In contrast to research on wearable devices, this paper investigates the application of *dl for stress detection based on *rppg. The methodology involves selecting suitable *dl models (*lstm, *gru, *1dcnn), optimising hyperparameters, and investigating augmentation techniques. 1D-CNNv1 model achieved the best performance compared to other approaches, particularly with augmentation techniques such as linear interpolation and white noise, achieving a stress classification accuracy of 95.83% while maintaining excellent computational efficiency. The experimental results demonstrate the use of *dl for stress detection based on *rppg, with the potential to make significant contributions to the international standard in the field.