Photoplethysmographic Signals Research Articles

A real-time cardiac output monitoring system based on photoplethysmography

Abstract Cardiac output is a critical parameter for assessing the cardiovascular system, and thermodilution is commonly used as CO monitoring in clinical settings. Thermodilution cannot be applied in continuous monitoring due to invasion. Photoplethysmography signal originates from the cardiovascular system. We proposed a CO continuous monitoring system based on photoplethysmography and deep learning method. PPG waveform parameters are extracted during the pre-processing stage, and fed into the deep learning model to calculate cardiac output. The system employs an analog front-end chip and an HPS_FPGA architecture to capture PPG signals. The pre-processing and the deep learning model-driven algorithm are designed in Python on the custom Linux for HPS. It realizes the real-time processing of the PPG signals and the continuous monitoring of cardiac output. Validated by an FPGA, the system reported average cardiac output monitoring results of approximately 5.09 L/min at rest and about 7.39 L/min after exercise.

Research on dynamic blood oxygen saturation measurement based on motion noise reconstruction combined with convex combination least mean square adaptive filter

The performance of a pulse oximeter based on photoelectric detection is greatly affected by motion noise (MA) in the photoplethysmographic (PPG) signal. This paper presents an algorithm for detecting motion oxygen saturation, which reconstructs a motion noise reference signal using ensemble of complete adaptive noise and empirical mode decomposition combined with multi-scale permutation entropy, and eliminates MA in the PPG signal using a convex combination least mean square adaptive filters to calculate dynamic oxygen saturation. The test results show that, under simulated walking and jogging conditions, the mean absolute error (MAE) of oxygen saturation estimated by the proposed algorithm and the reference oxygen saturation are 0.05 and 0.07, respectively, with means absolute percentage error (MAPE) of 0.05% and 0.07%, respectively. The overall Pearson correlation coefficient reaches 0.971 2. The proposed scheme effectively reduces motion artifacts in the corrupted PPG signal and is expected to be applied in portable photoelectric pulse oximeters to improve the accuracy of dynamic oxygen saturation measurement.

Exploring the dynamic relationship: Changes in photoplethysmography features corresponding to intracranial pressure variations

This study investigates the relationship between photoplethysmography (PPG) signals and intracranial pressure (ICP) through two primary hypotheses. Firstly, it examines whether alterations in PPG-derived features correspond to changes in ICP levels. Secondly, it explores whether these changes are more pronounced in features derived from “cerebral” long-distance near-infrared (NIR) PPG data compared to “extracerebral” short-distance NIR-PPG data. A clinical dataset comprising synchronised measurements from a non-invasive NIR-PPG sensor and an intra-parenchymal, invasive ICP pressure probe across 27 patients was compiled. From this dataset, two distinct datasets were derived, comprising short and long-distance NIR-PPG data. Within each dataset, 141 features were extracted for every one-minute window of non-invasive NIR-PPG data, including original, first derivative, and second derivative features. Correlation analysis using Spearman’s correlation and a non-parametric Kruskal–Wallis test across the range of ICP values were conducted to evaluate the relationship between features and ICP levels. The results support both hypotheses, showing significant correlations between the features and ICP levels. Specifically, 77.30% and 79.43% of features significantly correlated (p<0.05) with the label in distal and proximal datasets, respectively. Kruskal–Wallis analysis revealed that 81.56% and 75.89% of features significantly changed (p<0.05) across ICP groups 0–10, 10–20, and 20–39 mmHg. The distal dataset yielded a meaningfully higher absolute average correlation coefficient of all features and significantly correlated features in-comparison to the proximal dataset of 25.76% and 24.24% respectively. These findings indicate NIR-PPG features are reflective of variations in ICP.

Determining the Optimal Window Duration to Enhance Emotion Recognition Based on Galvanic Skin Response and Photoplethysmography Signals

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 indices. We found an optimum window duration of 3 s with 50% overlap and achieved accuracies of 0.75 and 0.74 for both arousal and valence, respectively. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.94 for arousal. 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.

Heart Pulse Transmission Parameters of Multi-Channel PPG Signals for Cuffless Estimation of Arterial Blood Pressure: Preliminary Study

The paper describes a method developed for the indirect cuffless estimation of arterial blood pressure (ABP) from two/three-channel photoplethysmography (PPG) signals. It is important when the actual ABPs cannot be measured, e.g., during scanning inside a magnetic resonance imager. The proposed procedure uses heart pulse transmission parameters (HPTPs) extracted from the second derivative PPG signals. The linear regression method was used to calculate the relation between the determined HPTPs and the ABPs measured in parallel by a blood pressure monitor. The ABP values were estimated by the inverse conversion characteristic calculated from these linear relations. Three auxiliary investigations were performed first to find appropriate settings for PPG signal processing. We tested the accuracy of ABP estimation using two small corpora of multi-channel PPG records sensed during our previous experiments. We also analyzed the distribution of the determined HPTP values depending on the hand and gender for the mapping of a mutual relationship of HPTPs and measured ABPs. The final estimation errors were evaluated graphically (by correlation scatter plots and Bland–Altman plots) and numerically (by a correlation coefficient between the measured and estimated ABPs and by enumeration of the relative estimation error). The obtained results achieve acceptable mean values of −2.6/−3.5 mm Hg for systolic/diastolic ABPs.

Beat-by-Beat Estimation of Hemodynamic Parameters in Left Ventricle Based on Phonocardiogram and Photoplethysmography Signals Using a Deep Learning Model: Preliminary Study.

Beat-by-beat monitoring of hemodynamic parameters in the left ventricle contributes to the early diagnosis and treatment of heart failure, valvular heart disease, and other cardiovascular diseases. Current accurate measurement methods for ventricular hemodynamic parameters are inconvenient for monitoring hemodynamic indexes in daily life. The objective of this study is to propose a method for estimating intraventricular hemodynamic parameters in a beat-to-beat style based on non-invasive PCG (phonocardiogram) and PPG (photoplethysmography) signals. Three beagle dogs were used as subjects. PCG, PPG, electrocardiogram (ECG), and invasive blood pressure signals in the left ventricle were synchronously collected while epinephrine medicine was injected into the veins to produce hemodynamic variations. Various doses of epinephrine were used to produce hemodynamic variations. A total of 40 records (over 12,000 cardiac cycles) were obtained. A deep neural network was built to simultaneously estimate four hemodynamic parameters of one cardiac cycle by inputting the PCGs and PPGs of the cardiac cycle. The outputs of the network were four hemodynamic parameters: left ventricular systolic blood pressure (SBP), left ventricular diastolic blood pressure (DBP), maximum rate of left ventricular pressure rise (MRR), and maximum rate of left ventricular pressure decline (MRD). The model built in this study consisted of a residual convolutional module and a bidirectional recurrent neural network module which learnt the local features and context relations, respectively. The training mode of the network followed a regression model, and the loss function was set as mean square error. When the network was trained and tested on one subject using a five-fold validation scheme, the performances were very good. The average correlation coefficients (CCs) between the estimated values and measured values were generally greater than 0.90 for SBP, DBP, MRR, and MRD. However, when the network was trained with one subject's data and tested with another subject's data, the performance degraded somewhat. The average CCs reduced from over 0.9 to 0.7 for SBP, DBP, and MRD; however, MRR had higher consistency, with the average CC reducing from over 0.9 to about 0.85 only. The generalizability across subjects could be improved if individual differences were considered. The performance indicates the possibility that hemodynamic parameters could be estimated by PCG and PPG signals collected on the body surface. With the rapid development of wearable devices, it has up-and-coming applications for self-monitoring in home healthcare environments.

Open-source synthetic photoplethysmographic signal generator with analog output.

The photoplethysmographic (PPG) signal of the finger is being used to create embedded devices that estimate physiological variables. This project outlines an innovative method for developing a synthetic PPG generator that produces both actual reference digital signals and their equivalent analog signals using open-source technology. A series of PPG profiles is synthesized using three variant Gaussian functions. A low-frequency trend induced by respiratory frequency and background noise are then added. To generate a diverse range of continuously variable PPG profiles within specified boundaries and customizable levels of interference, all parameters undergo random fluctuations on a cycle-by-cycle basis, as per user-defined constraints. The generated signal is then converted into its equivalent analog form through the use of an RC filter that low-frequency filters a Pulse-Width Modulation square wave that is modulated directly by the generated signal. The software returns different PPG profiles and allows the signal comparison before vs after the addition of different-intensity modulated respiratory trends and background noise. The digital signal is faithfully converted into an equivalent analog voltage signal capable of reproducing not only the waveform profile but also the respiratory trend and various levels of noise.

An explainable echo state network trained from photoplethysmography signals for equine life stage prediction

An explainable echo state network trained from photoplethysmography signals for equine life stage prediction

Stable Operation and Enhanced Sensitivity via Composite Structure Design for Efficient Photoplethysmography and Motion Sensors

Healthcare sensors have attracted lots of interests owing to saving a patient's life by continuously monitoring the patient's health via early diagnosis of the symptoms by using healthcare sensors. Many health-care sensors are available in wearable application that can monitor continuously patient health. There are some common parameters such as a heart rate and human motion that are used to monitor human activity.In order to realize stable operation of health-care sensors, material designs are required considering human-body compatibility. In this research, light-sensors fabricated from low-toxicity organic materials by introducing neutral poly(3,4-ethylenedioxythiophene)-(polystyrene sulfonate) (PEDOT-(PSS)) to improve human-body compatibility as well as to strengthen photoplethysmography (PPG) signal. [1] Neutral PEDOT-(PSS) with heterocyclic 1,3-diazole (HDZ) enhances the polymerization degree, carrier mobility, and other physicochemical properties. Consequently, the presented OPD-based PPG sensor has the ability to diagnose blood circulation status and cardiovascular diseases.Second, we fabricate motion sensors by utilizing metallic glass, i.e., amorphous metallic alloy, which is an alloy composition without grain boundaries and long-range ordering. The unique structure of metallic glass results in excellent tensile strength and strain-resistivity as well as chemical stability to those of conventional metals. The Al-Sm MG-based sensors results in enhanced sensitivity and considerable device stability, because of its amorphous phase. [2][1] Adv. Funct. Mater. 2023, 10.1002/adfm.202309271[2] Electrochimica Acta, 2023, 446, 142053

A Deep Transfer Learning Approach for Sleep Stage Classification and Sleep Apnea Detection Using Wrist-Worn Consumer Sleep Technologies.

Obstructive sleep apnea (OSA) is a common, underdiagnosed sleep-related breathing disorder with serious health implications Objective - We propose a deep transfer learning approach for sleep stage classification and sleep apnea (SA) detection using wrist-worn consumer sleep technologies (CST). Methods - Our model is based on a deep convolutional neural network (DNN) utilizing accelerometers and photo-plethysmography signals from nocturnal recordings. The DNN was trained and tested on internal datasets that include raw data from clinical and wrist-worn devices; external validation was performed on a hold-out test dataset containing raw data from a wrist-worn CST. Results - Training on clinical data improves performance significantly, and feature enrichment through a sleep stage stream gives only minor improvements. Raw data input outperforms feature-based input in CST datasets. The system generalizes well but performs slightly worse on wearable device data compared to clinical data. However, it excels in detecting events during REM sleep and is associated with arousal and oxygen desaturation. We found; cases that were significantly underestimated were characterized by fewer of such event associations. Conclusion - This study showcases the potential of using CSTs as alternate screening solution for undiagnosed cases of OSA. Significance - This work is significant for its development of a deep transfer learning approach using wrist-worn consumer sleep technologies, offering comprehensive validation for data utilization, and learning techniques, ultimately improving sleep apnea detection across diverse devices.

SiamQuality: a ConvNet-based foundation model for photoplethysmography signals

Objective. Physiological data are often low quality and thereby compromises the effectiveness of related health monitoring. The primary goal of this study is to develop a robust foundation model that can effectively handle low-quality issue in physiological data. Approach. We introduce SiamQuality, a self-supervised learning approach using convolutional neural networks (CNNs) as the backbone. SiamQuality learns to generate similar representations for both high and low quality photoplethysmography (PPG) signals that originate from similar physiological states. We leveraged a substantial dataset of PPG signals from hospitalized intensive care patients, comprised of over 36 million 30 s PPG pairs. Main results. After pre-training the SiamQuality model, it was fine-tuned and tested on six PPG downstream tasks focusing on cardiovascular monitoring. Notably, in tasks such as respiratory rate estimation and atrial fibrillation detection, the model’s performance exceeded the state-of-the-art by 75% and 5%, respectively. The results highlight the effectiveness of our model across all evaluated tasks, demonstrating significant improvements, especially in applications for heart monitoring on wearable devices. Significance. This study underscores the potential of CNNs as a robust backbone for foundation models tailored to physiological data, emphasizing their capability to maintain performance despite variations in data quality. The success of the SiamQuality model in handling real-world, variable-quality data opens new avenues for the development of more reliable and efficient healthcare monitoring technologies.

Compensatory reserve index during central hypovolemia and volume loading in healthy young and older hyperthermic adults: A pilot study.

The compensatory reserve index (CRI), derived from machine learning algorithms from peripherally obtained photoplethysmography signals, provides a non-invasive assessment of cardiovascular stability, that may be useful clinically. Briefly, the CRI device provides a value between 0 and 1, with 1 reflecting full compensable capabilities and 0 reflecting little to no compensable capabilities. However, the CRI algorithm was developed in younger to middle aged adults, such that it is unknown if older age modulates CRI responses to cardiovascular challenges. In young and older subjects, we compared CRI responses to normothermic and hyperthermic progressive lower body negative pressure (LBNP), and volume loading with saline infusion. Eleven younger (20-36 years) and 10 older (61-75 years) healthy participants underwent (1) graded normothermic LBNP up to 30 mmHg, (2) graded hyperthermic (1.5°C increase in blood temperature) LBNP up to 30 mmHg, and (3) infusion of 15 mL/kg saline (volume loading) with hyperthermia maintained. CRI was obtained throughout each procedure. CRI at 30 mmHg LBNP was 0.18 and 0.24 units greater in the older group during normothermic and hyperthermic LBNP, respectively. However, CRI was not different between age groups at any other LBNP stage, nor did CRI change with volume loading regardless of age. In response to passive hyperthermia alone, regression analyses showed that heart rate was the strongest predictor of CRI. Blood temperature, rate pressure product, and stroke volume were also predictive of CRI but to a lesser extent. In conclusion, age attenuates the reduction in CRI during progressive normothermic and hyperthermic LBNP, but only at 30 mmHg. Second, the CRI was unchanged during volume loading in all subjects. Future studies should determine whether the age differences in CRI reflect age differences in LBNP tolerance.

Understanding the physiological transmission mechanisms of photoplethysmography signals: a comprehensive review.

Objective. The widespread adoption of Photoplethysmography (PPG) as a non-invasive method for detecting blood volume variations and deriving vital physiological parameters reflecting health status has surged, primarily due to its accessibility, cost-effectiveness, and non-intrusive nature. This has led to extensive research around this technique in both daily life and clinical applications. Interestingly, despite the existence of contradictory explanations of the underlying mechanism of PPG signals across various applications, a systematic investigation into this crucial matter has not been conducted thus far. This gap in understanding hinders the full exploitation of PPG technology and undermines its accuracy and reliability in numerous applications.Approach. Building upon a comprehensive review of the fundamental principles and technological advancements in PPG, this paper initially attributes the origin of PPG signals to a combination of physical and physiological transmission processes. Furthermore, three distinct models outlining the concerned physiological transmission processes are synthesized, with each model undergoing critical examination based on theoretical underpinnings, empirical evidence, and constraints.Significance. The ultimate objective is to form a fundamental framework for a better understanding of physiological transmission processes in PPG signal generation and to facilitate the development of more reliable technologies for detecting physiological signals.

An efficient model for extracting respiratory and blood oxygen saturation data from photoplethysmogram signals by removing motion artifacts using heuristic-aided ensemble learning model

Patients with surgical, pulmonary, and cardiac problems, continual monitoring of Oxygen Saturation of a Person (SpO2) and Respiratory Rate (RR) is essential. Similarly, the persons with cardiopulmonary health issues, RR estimation is crucial. The performance of the ventilator assistance and lung medicines are evaluated using SpO2 and RR. For the persons, those who are living alone with respiratory illnesses need a compulsory estimation of RR. In case of serious illness, the RR might face abrupt changes. The immobility of the disturbance and RR makes the RR evaluation from the PhotoPlethysmoGraphic (PPG) signals is a difficult challenge. So, an efficient RR and SpO2 estimation framework from the PPG signal using the deep learning method is developed in this paper. At first, the PPG signal is collected from standard data sources. The collected PPG signals undergo signal pre-processing. The pre-processing procedures include Motion Artifacts (MA) removal and filtering techniques. The pre-processed signals are split into distinct windows. From the split windows of the signals, the spectral features, RR, and Respiratory Peak Variance (RPV) features are extracted. The retrieved features are selected optimally with the help of Advanced Golden Tortoise Beetle Optimizer (AGTBO). The weights are chosen optimally with the same AGTBO. The optimally selected features are fused with the optimal features to get the weighted optimal features. These weighted optimal features are fed into the Ensemble Learning-based RR and SpO2 Estimation Network (ELRR-SpO2EN). The ensemble learning model is developed by combining Multilayer Perceptron (MLP), AdaBoost, and Attention-based Long Short Term Memory (A-LSTM). The performance of the developed RR and SpO2 estimation model is compared with other existing techniques. The experimental analysis results revealed that the proposed AGTBO-ELRR-SpO2EN model attained 96 % accuracy for the second dataset, which is higher than the conventional models such as MLP (90 %), Adaboost (92 %), A-LSTM (92 %), and MLP-ADA-ALSTM (94 %). Thus, it has been confirmed that the designed RR and SpO2 estimation framework from PPG signals is more efficient than the other conventional models.

A Self-Supervised Algorithm for Denoising Photoplethysmography Signals for Heart Rate Estimation From Wearables

A Self-Supervised Algorithm for Denoising Photoplethysmography Signals for Heart Rate Estimation From Wearables

Improved sleep stage predictions by deep learning of photoplethysmogram and respiration patterns

Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.

End-to-end multimodal emotion recognition based on facial expressions and remote photoplethysmography signals.

Emotion is a complex physiological phenomenon, and a single modality may be insufficient for accurately determining human emotional states. This paper proposes an end-to-end multimodal emotion recognition method based on facial expressions and non-contact physiological signals. Facial expression features and remote photoplethysmography (rPPG) signals are extracted from facial video data, and a transformer-based cross-modal attention mechanism (TCMA) is used to learn the correlation between the two modalities. The results show that the accuracy of emotion recognition can be slightly improved by combining facial expressions with accurate rPPG signals. The performance is further improved with the use of TCMA, for which the binary classification accuracy of valence and arousal is 91.11% and 90.00%, respectively. Additionally, when experiments are conducted using the whole dataset, an increased accuracy of 7.31% and 4.23% for the binary classification of valence and arousal, and an improved accuracy of 5.36% for the four classifications of valence-arousal are achieved when TCMA is used in modal fusion, compared to using only facial expression modality, which fully demonstrates the effectiveness and robustness of TCMA. This method makes it possible to realize multimodal emotion recognition of facial expressions and contactless physiological signals in reality.

Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities

The educational environment plays a vital role in the development of students who participate in athletic pursuits both in terms of their physical health and their ability to detect fatigue. As a result of recent advancements in deep learning and biosensors benefitting from edge computing resources, we are now able to monitor the physiological fatigue of students participating in sports in real time. These devices can then be used to analyze the data using contemporary technology. In this paper, we present an innovative deep learning framework for forecasting fatigue in athletic students following physical exercise. It addresses the issue of lack of precision computational models and extensive data analysis in current approaches to monitoring students’ physical activity. In our study, we classified fatigue and non-fatigue based on photoplethysmography (PPG) signals. Several deep learning models are compared in the study. Using limited training data, determining the optimal parameters for PPG presents a significant challenge. For datasets containing many data points, several models were trained using PPG signals: a deep residual network convolutional neural network (ResNetCNN) ResNetCNN, an Xception architecture, a bidirectional long short-term memory (BILSTM), and a combination of these models. Training and testing datasets were assigned using a fivefold cross validation approach. Based on the testing dataset, the model demonstrated a proper classification accuracy of 91.8%.

Dynamic spectral extraction method with approximately the same optical path length of non-invasive quantitative analysis of human blood components

The non-invasive quantitative analysis of blood components using spectroscopic methods based on Beer-Lambert law, and dynamic spectroscopic theory needs to meet the four applicable conditions of this law. However, in practical applications, due to the scattering characteristics of human tissue, it is difficult to meet the two conditions (parallel monochromatic light and non-scattering homogeneous system of absorbing substances), which will reduce the accuracy of quantitative analysis. To reduce the principle error caused by scattering, this paper proposes an extraction method for dynamic spectra with approximately the same optical path length. This method extracts approximately the same absorbance values from photoplethysmographic (PPG) spectral signals. A smaller absorbance value corresponds to a thinner blood layer, in which light can be approximated as parallel light, thus maximizing the satisfaction of the conditions of Beer-Lambert law. In the experimental, compared with the traditional single-edge extraction method, the proposed method has higher prediction accuracy. The correlation coefficients of the total cholesterol and triglycerides increased by 31.22% and 38.05%, and the root mean square errors decreased by 29.63% and 37.14%. The results show that the methods can significantly enhance the robustness of non-invasive quantitative analysis of blood components based on dynamic spectral theory.

DNN-BP: a novel framework for cuffless blood pressure measurement from optimal PPG features using deep learning model.

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.