Non-invasive Physiological Signals Research Articles

Heart rate detection of ballistocardiogram based on improved DAE and template matching method

Ballistocardiogram (BCG) is a non-invasive physiological signal detection method that can be used for non-contact detection of resting heart rate (RHR) and has been widely used in human health monitoring. However, the BCG signal is vulnerable to noise, making it challenging to accurately measure heart rate. In this paper, we propose a noise reduction model for the BCG signal based on Gramian Angular Field (GAF) and an improved Denoising Autoencoder (DAE), referred to as the GDAE model, to accurately detect heart rate in noise-contaminated signals. First, the Gramian Angular Field transform is used to convert the one-dimensional BCG signal into two-dimensional image information, highlighting the difference between the signal centroid information and noise information; after that, the transformed image is denoised by the Denoising Autoencoder to obtain a denoised BCG signal. After noise reduction, the heart rate of the subject is calculated using the adaptive template matching method. The test proves that under the strong noise interference, the proposed method improves the recall by 6.87% and the accuracy by 6.02% compared with the traditional method, indicating a better detection effect. Furthermore, the comparison test shows that the GDAE model has a significant noise reduction effect on the BCG signal, which improves the practicality of the BCG method for heart rate detection.

Non-invasive waveform analysis for emergency triage via simulated hemorrhage: An experimental study using novel dynamic lower body negative pressure model

The extent to which advanced waveform analysis of non-invasive physiological signals can diagnose levels of hypovolemia remains insufficiently explored. The present study explores the discriminative ability of a deep learning (DL) framework to classify levels of ongoing hypovolemia, simulated via novel dynamic lower body negative pressure (LBNP) model among healthy volunteers. We used a dynamic LBNP protocol as opposed to the traditional model, where LBNP is applied in a predictable step-wise, progressively descending manner. This dynamic LBNP version assists in circumventing the problem posed in terms of time dependency, as in real-life pre-hospital settings intravascular blood volume may fluctuate due to volume resuscitation. A supervised DL-based framework for ternary classification was realized by segmenting the underlying noninvasive signal and labeling segments with corresponding LBNP target levels. The proposed DL model with two inputs was trained with respective time–frequency representations extracted on waveform segments to classify each of them into blood volume loss: Class 1 (mild); Class 2 (moderate); or Class 3 (severe). At the outset, the latent space derived at the end of the DL model via late fusion among both inputs assists in enhanced classification performance. When evaluated in a 3-fold cross-validation setup with stratified subjects, the experimental findings demonstrated PPG to be a potential surrogate for variations in blood volume with average classification performance, AUROC: 0.8861, AUPRC: 0.8141, F1-score:72.16%, Sensitivity:79.06%, and Specificity:89.21%. Our proposed DL algorithm on PPG signal demonstrates the possibility to capture the complex interplay in physiological responses related to both bleeding and fluid resuscitation using this challenging LBNP setup.

Multifunctional Biosensing Platform Based on Nickel-Modified Laser-Induced Graphene.

Nickel plating electrolytes prepared by using a simple salt solution can achieve nickel plating on laser-induced graphene (LIG) electrodes, which greatly enhances the electrical conductivity, electrochemical properties, wear resistance, and corrosion resistance of LIG. This makes the LIG-Ni electrodes well suited for electrophysiological, strain, and electrochemical sensing applications. The investigation of the mechanical properties of the LIG-Ni sensor and the monitoring of pulse, respiration, and swallowing confirmed that the sensor can sense insignificant deformations to relatively large conformal strains of skin. Modulation of the nickel-plating process of LIG-Ni, followed by chemical modification, may allow for the introduction of glucose redox catalyst Ni2Fe(CN)6 with interestingly strong catalytic effects, which gives LIG-Ni impressive glucose-sensing properties. Additionally, the chemical modification of LIG-Ni for pH and Na+ monitoring also confirmed its strong electrochemical monitoring potential, which demonstrates application prospects in the development of multiple electrochemical sensors for sweat parameters. A more uniform LIG-Ni multi-physiological sensor preparation process provides a prerequisite for the construction of an integrated multi-physiological sensor system. The sensor was validated to have continuous monitoring performance, and its preparation process is expected to form a system for non-invasive physiological parameter signal monitoring, thus contributing to motion monitoring, disease prevention, and disease diagnosis.

Automatic stress detection in car drivers based on non-invasive physiological signals using machine learning techniques

Stress is now thought to be a major cause to a wide range of human health issues. However, many people may ignore their stress feelings and disregard to take action before serious physiological and mental disorders take place. The heart rate (HR) and blood pressure (BP) are the most physiological markers used in various studies to detect mental stress for a human, and because they are captured non-invasively using wearable sensors, these markers are recommended to provide information on a person’s mental state. Most stress assessment studies have been undertaken in a laboratory-based controlled environment. This paper proposes an approach to identify the mental stress of automotive drivers based on selected biosignals, namely, ECG, EMG, GSR, and respiration rate. In this study, six different machine learning models (KNN, SVM, DT, LR, RF, and MLP) have been used to classify between the stressed and relaxation states. Such system can be integrated with a Driver Assistance System (DAS). The proposed stress detection technique (SDT) consists of three main phases: (1) Biosignal Pre-processing, in which the signal is segmented and filtered. (2) Feature Extraction, in which some discriminate features are extracted from each biosignal to describe the mental state of the driver. (3) Classification. The results show that the RF classifier outperforms other techniques with a classification accuracy of 98.2%, sensitivity 97%, and specificity 100% using the drivedb dataset.

Meltdown/Tantrum Detection System for Individuals with Autism Spectrum Disorder

ABSTRACT The intensive and explosive behavioral problems associated with Autism Spectrum Disorder (ASD) are treated as ‘meltdown or tantrum,’ and it may lead to hyperactivity, impulsivity, aggression, self-injury, and irritability. The present work aims to propose and implement a noninvasive real-time deep learning based Meltdown/Tantrum Detection System (MTDS) for ASD individuals. The noninvasive physiological signals (such that heart rate, skin temperature, and galvanic skin response) were synthetically recorded with a specially designed hardware prototype. The recorded physiological signals were transmitted to an internet connected server where deep learning algorithms such as CNN, LSTM, and CNN-LSTM based Meltdown/Tantrum Detection System (MTDS) were implemented. The trained deep learning model was capable of detecting abnormal states of meltdown or tantrum through real-time received physiological signals. The proposed MTDS system was trained and tested with deep learning algorithms such as CNN, LSTM and hybrid CNN-LSTM, and it was found that hybrid CNN-LSTM was outperformed with an average training and testing accuracy of 96% with low MAE (0.10 for training and 0.04 for testing). Furthermore, 86% of the ASD caregivers favored the proposed MTDS system.

A Novel Deep Learning based Gated Recurrent Unit with Extreme Learning Machine for Electrocardiogram (ECG) Signal Recognition

Cardiovascular disease (CVD) becomes a significant risk to human lives. Electrocardiogram (ECG) is a commonly employed non-invasive physiological signal used to screen and diagnose CVD. During recent years, remarkable advances in automated ECG interpretation techniques have been witnessed. In particular, deep learning (DL) models find useful to increase the disease diagnostic performance of CVD using the ECG signals. To explore and achieve effective ECG recognition, this paper presents a Class Imbalance handing with DL based Gated Recurrent Unit (GRU) and Extreme Learning Machine (ELM) for ECG Signal Recognition, named as CIGRU-ELM model. The presented CIGRU-ELM model involves preprocessing, data sampling, feature extraction, and classification. Primarily, data preprocessing takes place to convert the ECG report to valuable data and transform it into a compatible format for further processing. In addition, Adaptive Synthetic (ADASYN) based data sampling process takes place to handle the class imbalance problem. Besides, GRU based feature extractor is applied to extract a useful set of feature vectors. Finally, ELM model based classification model is employed to determine the appropriate class label of the test ECG signal. An extensive experimental analysis is performed on the benchmark PTB-XL dataset. A detailed comparative results analysis of the proposed CIGRU-ELM model takes place to highlight the superiority of the proposed model interms of accuracy, sensitivity, specificity, kappa, Mathew correlation coefficient, and Hamming loss.

Sleep Deprivation Deteriorates Heart Rate Variability and Photoplethysmography.

IntroductionSleep deprivation has deleterious effects on cardiovascular health. Using wearable health trackers, non-invasive physiological signals, such as heart rate variability (HRV), photoplethysmography (PPG), and baroreflex sensitivity (BRS) can be analyzed for detection of the effects of partial sleep deprivation on cardiovascular responses.MethodsFifteen participants underwent 1 week of baseline recording (BSL, usual day activity and sleep) followed by 3 days with 3 h of sleep per night (SDP), followed by 1 week of recovery with sleep ad lib (RCV). HRV was recorded using an orthostatic test every morning [root mean square of the successive differences (RMSSD), power in the low-frequency (LF) and high-frequency (HF) bands, and normalized power nLF and nHF were computed]; PPG and polysomnography (PSG) were recorded overnight. Continuous blood pressure and psychomotor vigilance task were also recorded. A questionnaire of subjective fatigue, sleepiness, and mood states was filled regularly.ResultsRMSSD and HF decreased while nLF increased during SDP, indicating a decrease in parasympathetic activity and a potential increase in sympathetic activity. PPG parameters indicated a decrease in amplitude and duration of the waveforms of the systolic and diastolic periods, which is compatible with increases in sympathetic activity and vascular tone. PSG showed a rebound of sleep duration, efficiency, and deep sleep in RCV compared to BSL. BRS remained unchanged while vigilance decreased during SDP. Questionnaires showed an increased subjective fatigue and sleepiness during SDP.ConclusionHRV and PPG are two markers easily measured with wearable devices and modified by partial sleep deprivation, contradictory to BRS. Both markers showed a decrease in parasympathetic activity, known as detrimental to cardiovascular health.

PBGAN: Learning PPG Representations From GAN for Time-Stable and Unique Verification System

Photoplethysmography (PPG) is a non-invasive physiological signal that captures the changes in blood volume resulted from heart activity. It carries unique person-specific characteristics that can be utilized for biometric systems. Currently, the use of a biometric system is paramount to ensure the security of the user’s identity. Due to the high sensitivity of the PPG signal, it suffers from extreme variations within the same subject when obtained at different time instances. These variations impose a challenge to employ the PPG signal and hinder the algorithm generalization for many applications including verification and identification systems. In this work, we propose a PPG Biometric Generative Adversarial Network (PBGAN) to create synthetic person-specific and time-stable PPG signals for genuine samples. Two types of classification models are employed with the PBGAN where the focus is on verification scenarios. In addition, we expand our previously recorded PPG dataset from 100 to 170 participants where the new size guarantees the generalization capability of the proposed system. This database and another three public ones are employed to evaluate the performances in terms of uniqueness and time stability. Furthermore, we consider three different training strategies to simulate practical scenarios. The best results acquired from our collected database in terms of Equal Error Rate (EER) is 1.3% for the single-session and 11.5% for the two-sessions scenarios which demonstrate the effectiveness of the proposed method in improving the verification system’s performance. Compared to our previous work, we achieve 1.3% and 1.4% EER improvements in two-sessions’ databases with small computational times which reveals the superiority of our proposed approach for real applications. Later, the code and dataset can be accessed in https://github.com/eoduself .

Predicting hypotension in the ICU using noninvasive physiological signals

Hypotension frequently occurs in Intensive Care Units (ICU), and its early prediction can improve the outcome of patient care. Trends observed in signals related to blood pressure (BP) are critical in predicting future events. Unfortunately, the invasive measurement of BP signals is neither comfortable nor feasible in all bed settings. In this study, we investigate the performance of machine-learning techniques in predicting hypotensive events in ICU settings using physiological signals that can be obtained noninvasively. We show that noninvasive mean arterial pressure (NIMAP) can be simulated by down-sampling the invasively measured MAP. This enables us to investigate the effect of BP measurement frequency on the algorithm's performance by training and testing the algorithm on a large dataset provided by the MIMIC III database. This study shows that having NIMAP information is essential for adequate predictive performance. The proposed predictive algorithm can flag hypotension with a sensitivity of 84%, positive predictive value (PPV) of 73%, and F1-score of 78%. Furthermore, the predictive performance of the algorithm improves by increasing the frequency of BP sampling.

Deep Learning Algorithm Classifies Heartbeat Events Based on Electrocardiogram Signals.

Cardiovascular diseases (CVDs) have become the number 1 threat to human health. Their numerous complications mean that many countries remain unable to prevent the rapid growth of such diseases, although significant health resources have been invested toward their prevention and management. Electrocardiogram (ECG) is the most important non-invasive physiological signal for CVD screening and diagnosis. For exploring the heartbeat event classification model using single- or multiple-lead ECG signals, we proposed a novel deep learning algorithm and conducted a systemic comparison based on the different methods and databases. This new approach aims to improve accuracy and reduce training time by combining the convolutional neural network (CNN) with the bidirectional long short-term memory (BiLSTM). To our knowledge, this approach has not been investigated to date. In this study, Database I with single-lead ECG and Database II with 12-lead ECG were used to explore a practical and viable heartbeat event classification model. An evolutionary neural system approach (Method I) and a deep learning approach (Method II) that combines CNN with BiLSTM network were compared and evaluated in processing heartbeat event classification. Overall, Method I achieved slightly better performance than Method II. However, Method I took, on average, 28.3 h to train the model, whereas Method II needed only 1 h. Method II achieved an accuracy of 80, 82.6, and 85% compared with the China Physiological Signal Challenge 2018, PhysioNet Challenge 2017, and Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia datasets, respectively. These results are impressive compared with the performance of state-of-the-art algorithms used for the same purpose.

Classification of Perceived Human Stress using Physiological Signals.

In this paper, we present an experimental study for the classification of perceived human stress using non-invasive physiological signals. These include electroencephalography (EEG), galvanic skin response (GSR), and photoplethysmography (PPG). We conducted experiments consisting of steps including data acquisition, feature extraction, and perceived human stress classification. The physiological data of 28 participants are acquired in an open eye condition for a duration of three minutes. Four different features are extracted in time domain from EEG, GSR and PPG signals and classification is performed using multiple classifiers including support vector machine, the Naive Bayes, and multi-layer perceptron (MLP). The best classification accuracy of 75% is achieved by using MLP classifier. Our experimental results have shown that our proposed scheme outperforms existing perceived stress classification methods, where no stress inducers are used.

Evidence-based model for real-time surveillance of ARDS

Real-time health surveillance becomes important and necessary with the increase of the elderly population to preserve their quality of life. Real-time models aim to provide alerts before the severe illness occurs. Acute respiratory distress syndrome is a crucial disease of the respiratory system that threats the health of the elderly. This paper proposes a real-time model for the surveillance of ARDS based on belief functions theory. Non-invasive physiological signals are considered such as heart rate, respiratory rate, oxygen saturation and mean airway blood pressure. Different linear and nonlinear parameters are extracted from these signals; then a parameters selection procedure is performed to reduce their dimensionality. Afterwards, classifiers are constructed using parameters distributions defined in the evidence framework. Real-time prediction is then performed by combining all classifiers decisions. As results, high performances are obtained over the testing sets with performances of 77% and 71% for sensitivity and specificity, respectively.

Eliminating Individual Bias to Improve Stress Detection from Multimodal Physiological Data.

Stress monitoring is important for mental wellbeing and early detection of related disorders. The current work is focused on stress detection from multiple non-invasive physiological signals like Electroencephalogram (EEG), Photoplethysmogram (PPG) and Galvanic Skin Response (GSR). We show that, compared to using only the well known EEG band powers in different frequencies for stress detection, an early fusion with GSR and PPG features shows a significant improvement. Maximum Relevance Minimum Redundancy (mRMR) based feature selection is used to identify the most suitable physiological features correlating with stress. A major contribution of this work lies in eliminating subject-specific bias to improve the classification accuracy. We use self-reported values of Valence, Arousal and Dominance to cluster subjects and build separate classification models specific to clusters. The proposed approach is validated on a publicly available dataset comprising 146 data instances from 10 subjects. The performances of Leave-One- Subject-Out cross validation (LOSOCV) in terms of mean Fscores are 0.61 using EEG features only, 0.64 using early fusion of EEG, GSR and PPG features and 0.69 by applying our clustering technique before fusion and classification.

Sustainable Energy Generation from Piezoelectric Biomaterial for Noninvasive Physiological Signal Monitoring

Sustainable development of self-powered wearable electronics relies on bioinspired piezoelectric materials which could transduce minute deformation of human skin. In this work, fish-skin-based sustainable energy production is discussed in light of structure–property correlation. The developed energy harvester acts as a sensor that interacts with human body parts to monitor real-time physiological signals. Self-assembled collagen nanofibrils comprising fish skin show stable crystalline structure and possess nonlinear electrostriction effect without any electrical poling treatment. A fish-skin-based nanogenerator (FSKNG)/pressure sensor is ultrasensitive (sensitivity ∼27 mV N–1) and highly durable (over 75 000 cycles) and possesses very fast response time (∼4.9 ms). Importantly, in response to the external pressure (∼1.8 MPa), FSKNG generates open-circuit voltage, Voc ∼ 2 V, and short-circuit current, Isc ∼ 20 nA, due to inherent piezoelectric effect. The magnitude of the generated power (∼0.75 mW m–2) turn...

Bio-assembled, piezoelectric prawn shell made self-powered wearable sensor for non-invasive physiological signal monitoring

A human interactive self-powered wearable sensor is designed using waste by-product prawn shells. The structural origin of intrinsic piezoelectric characteristics of bio-assembled chitin nanofibers has been investigated. It allows the prawn shell to make a tactile sensor that performs also as a highly durable mechanical energy harvester/nanogenerator. The feasibility and fundamental physics of self-powered consumer electronics even from human perception is highlighted by prawn shells made nanogenerator (PSNG). High fidelity and non-invasive monitoring of vital signs, such as radial artery pulse wave and coughing actions, may lead to the potential use of PSNG for early intervention. It is presumed that PSNG has enormous future aspects in real-time as well as remote health care assessment.

Human skin interactive self-powered wearable piezoelectric bio-e-skin by electrospun poly-l-lactic acid nanofibers for non-invasive physiological signal monitoring.

Flexible and wearable piezoelectric bio e-skin (PBio-e-skin) based on electrospun poly(l-lactic acid) PLLA nanofiber membrane is demonstrated for non-invasive human physiological signal monitoring and detecting dynamic tactile stimuli. The molecular orientations of the C[double bond, length as m-dash]O dipoles by electrospinning technique result in a longitudinal piezoelectric charge co-efficient (d33) value of ∼(3 ± 1) pm V-1 realized by piezoresponse force microscopy, allowing the PBio-e-skin for pressure sensing applications. The robust mechanical strength (Young's modulus ∼50 MPa) of nanofiber membrane ensures PBio-e-skin's superior operational stability over 375 000 cycles. Owing to the superior mechanosensitivity of ∼22 V N-1, PBio-e-skin has the ability to measure subtle movement of muscle in the internal organs such as esophagus, trachea, motion of joints and arterial pressure by recognition of strains on human skin. This flexible and light weight PBio-e-skin precisely detects vital signs and provides important clinical insights without using any external power source. Eventually, the low cost, environmental friendly PBio-e-skin will have a huge impact in a broad range of applications including self-powered wearable health care systems, human-machine interfacing devices, artificial intelligence and prosthetic skin.

Noninvasive Physiological Signal Analysis and Implementation of Monitoring and Control System for Premature Infants

Noninvasive Physiological Signal Analysis and Implementation of Monitoring and Control System for Premature Infants

Noninvasive investigation of the body functional state during night sleep in microgravity

The Sonocard experiment purpose was a noninvasive physiological signal recording from sleeping humans. In 2007-2012 the experiment was made by 22 Russian members of 17 missions to the International space station. Of the overall 302 experimental sessions 47 were performed pre, 215 in and 40 after flight. The seismographic technique was used to pick up cosmonaut’s body microoscillations induced by cardiac beats, respiration and motor activity. The flight Sonocard model is a midget device fitting into the T-shirt pocket. Heart rate variability analysis (HRV) was the major method of securing conclusive evidence on stress level and blood circulation autonomic regulation. We were first to trace reorganization of the autonomic regulation at the night time on different phases of long-duration space mission and pioneered a systematic investigation of the human body functional state during sleep. It was shown that in the absence of work loads and emotional stresses the central mechanisms of circulation regulation tend to increase their activities. The characteristic subsidence of breathing waves (HF) and growth of the vascular center (LF) portion within the HRV total spectrum by the end of flight were observed. Sleep quality in the course of long-duration missions was assessed. We succeeded in the first ever sleep assessment following operations in open space. The noninvasive physiological signal recording was recommended for use in spacecrew medical monitoring and ground-based experiments.

A method of ECG template extraction for biometrics applications.

ECG has attracted widespread attention as one of the most important non-invasive physiological signals in healthcare-system related biometrics for its characteristics like ease-of-monitoring, individual uniqueness as well as important clinical value. This study proposes a method of dynamic threshold setting to extract the most stable ECG waveform as the template for the consequent ECG identification process. With the proposed method, the accuracy of ECG biometrics using the dynamic time wraping for difference measures has been significantly improved. Analysis results with the self-built electrocardiogram database show that the deployment of the proposed method was able to reduce the half total error rate of the ECG biometric system from 3.35% to 1.45%. Its average running time on the platform of android mobile terminal was around 0.06 seconds, and thus demonstrates acceptable real-time performance.

Intracranial pressure model in intensive care unit using a simple recurrent neural network through time

This paper aims to establish a patient's intracranial pressure (ICP) model in neurosurgical intensive care unit (NICU) using neural network. Non-invasive physiological signals from patients including mean arterial pressure (MAP), heart rate (HR), end-tidal of carbon dioxide (EtCO 2) and regional cerebral oxygenation (rSO 2) were measured. However, ICP remains ill-defined, complicated and non-linear because it is affected by many predictable and unpredictable factors. Our study employs the structure of recurrent network to develop a modified neural network algorithm called a simple recurrent neural network through time (SRNNTT). The proposed recurrent neural network combines Elman architecture of the simple recurrent network structure and backpropagation through time. In order to demonstrate the performance of the proposed model, four kinds of neural-network classifiers have been tested on Mackey–Glass differential-delay equation which is a chaotic time series signal. Finally, we used this SRNNTT model to build the ICP model using data from six head-injured patients. Although the accuracy of the ICP model is still far from ideal, the methodology used non-invasive vital signs (i.e., MAP, HR, EtCO 2, and rSO 2) to predict an invasive, dangerous and expensive signal (i.e., ICP) has achieved this monitoring system more safely and flexibly in NICU.