Search

This paper introduces a novel deep learning model for ECG signal classification using feature fusion. The proposed methodology transforms the ECG time series into a spectrogram image using a short-time Fourier transform (STFT). This spectrogram is further processed to generate a histogram of oriented gradients (HOG) and local binary pattern (LBP) features. Three separate 2D convolutional neural networks (CNNs) then analyze these three image representations in parallel. To enhance performance, the extracted features are concatenated before feeding them into a gated recurrent unit (GRU) model. The proposed approach is extensively evaluated on two ECG datasets (MIT-BIH + BIDMC and MIT-BIH) with three and five classes, respectively. The experimental results demonstrate that the proposed approach achieves superior classification accuracy compared to existing algorithms in the literature. This suggests that the model has the potential to be a valuable tool for accurate ECG signal classification, aiding in the diagnosis and treatment of various cardiovascular disorders. [ABSTRACT FROM AUTHOR]

This paper deals with the non-contact measurement of heartbeat and respiration using a millimeter-wave multiple-input–multiple-output (MIMO) frequency-modulated continuous-wave (FM-CW) radar. Monitoring heartbeat and respiration is useful for detecting cardiac diseases and understanding stress levels. Contact sensors are not suitable for these sorts of long-term measurements due to the discomfort and skin irritation they cause. Therefore, the use of non-contact sensors, such as radars, is desirable. In this study, we obtained heartbeat and respiration information from phase data measured using a millimeter-wave MIMO FM-CW radar. We propose a two-wave model based on a Fourier series expansion and extract respiration and heartbeat information as a minimization problem. This model makes it possible to produce respiration and heartbeat waveforms. The produced heartbeat waveform can be used for estimating the interbeat interval (IBI). Experiments were conducted to confirm the usefulness of the proposed method. Moreover, the estimated results were compared with the contact sensor's results. The results for both types of sensors were in good agreement. [ABSTRACT FROM AUTHOR]

Background: Wearable sensors have revolutionized cardiac health monitoring, with Seismocardiography (SCG) at the forefront due to its non-invasive nature. However, the substantial motion artefacts have hindered the translation of SCG-based medical applications, primarily induced by walking. In contrast, our innovative technique, Adaptive Bidirectional Filtering (ABF), surpasses these challenges by refining SCG signals more effectively than any motion-induced noise. ABF leverages a noise-cancellation algorithm, operating on the benefits of the Redundant Multi-Scale Wavelet Decomposition (RMWD) and the bidirectional filtering framework, to achieve optimal signal quality. Methodology: The ABF technique is a two-stage process that diminishes the artefacts emanating from motion. The first step by RMWD is the identification of the heart-associated signals and the isolating samples with those related frequencies. Subsequently, the adaptive bidirectional filter operates in two dimensions: it uses Time-Frequency masking that eliminates temporal noise while engaging in non-negative matrix Decomposition to ensure spatial correlation and dorsoventral vibration reduction jointly. The main component that is altered from the other filters is the recursive structure that changes to the motion-adapted filter, which uses vertical axis accelerometer data to differentiate better between accurate SCG signals and motion artefacts. Outcome: Our empirical tests demonstrate exceptional signal improvement with the application of our ABF approach. The accuracy in heart rate estimation reached an impressive r-squared value of 0.95 at − 20 dB SNR, significantly outperforming the baseline value, which ranged from 0.1 to 0.85. The effectiveness of the motion-artifact-reduction methodology is also notable at an SNR of − 22 dB. Consequently, ECG inputs are not required. This method can be seamlessly integrated into noisy environments, enhancing ECG filtering, automatic beat detection, and rhythm interpretation processes, even in highly variable conditions. The ABF method effectively filters out up to 97% of motion-related noise components within the SCG signal from implantable devices. This advancement is poised to become an integral part of routine patient monitoring. [ABSTRACT FROM AUTHOR]

Fibrillation (Fib) is the most well-known sort of sporadic heartbeat. The sporadic termination of electrical impulses causes the atria (the top chambers in the heart) to tremble (or fibrillate). Cardiovascular arrhythmias happen in older people with coronary disease. Now and again, individuals with Fib have no manifestations, and their condition is just recognizable upon actual assessment. The issues include inconsistent heartbeats when the heart is reliably in a sporadic mood, as anticipated through the patient well-being observation framework (PHMS). The PHMS proposed calculation is ready to anticipate the inconsistent pulses by the location of the R top in electrocardiogram signals (ECG) and the unpredictable beat anticipated by utilizing the P wave along with the QRS complex with the T wave for one heart cycle. Hence, this paper proposes a hybrid Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN), termed hybrid C-RNN, to proceed with the characterization and determination of the arrhythmic beats. This work also analyzes the QRS peak variations, followed by classification. The practicability of the heartbeat characterization utilizing hybrid C-RNN is completed by metrics like accuracy, sensitivity, and specificity. The proposed model achieved an accuracy of 98.57%, sensitivity of 1%, and specificity of 9.565217e-01%. This is compared best with some existing approaches in the result section. [ABSTRACT FROM AUTHOR]

The dataset presents the raw data of respiration and heartbeat of two human subjects monitored by 60GHz Frequency-Modulated Continuous Wave (FMCW) radar and the validation data obtained by the electrocardiogram (ECG) front-end. During the radar-based vital signs monitoring, the subjects were simultaneously equipped with the ECG front-end, integrated with an Arduino board, to collect muscle electric signal waveforms, which enabled the estimation of the actual number of respirations and heartbeats of the subjects during the radar monitoring. To assess the impact of radar parameters, as well as the angle and distance between the subjects and the radar, on monitoring accuracy, the dataset classifies the positions of the human subjects within the scene into symmetric and asymmetric cases. Monitoring was conducted using various radar modulation bandwidths across different angles and distances in an open environment where only the human subjects were present. The objective of this dataset is to facilitate the development of a reliable system for monitoring multiple subjects' respiration and heartbeat using a single-view FMCW radar, emphasizing enhancing the radar's ability to distinguish between different targets and improving the accuracy of respiratory and heartbeat rate monitoring.

Abstract Certain organoid subtypes are particularly sensitive. We explore whether moral intuitions about the heartbeat warrant unique moral consideration for newly advanced contracting cardiac organoids. Despite the heartbeat’s moral significance in organ procurement and abortion discussions, we argue that this significance should not translate into moral implications for cardiac organoids.

Certain organoid subtypes are particularly sensitive. We explore whether moral intuitions about the heartbeat warrant unique moral consideration for newly advanced contracting cardiac organoids. Despite the heartbeat's moral significance in organ procurement and abortion discussions, we argue that this significance should not translate into moral implications for cardiac organoids. [ABSTRACT FROM AUTHOR]

Learning outcome is modified by the degree to which the subject responds and pays attention to specific stimuli. Our recent research suggests that presenting stimuli in contingency with a specific phase of the cardiorespiratory rhythm might expedite learning. Specifically, expiration-diastole (EXP-DIA) is beneficial for learning trace eyeblink conditioning (TEBC) compared with inspiration-systole (INS-SYS) in healthy young adults. The aim of this study was to investigate whether the same holds true in healthy elderly adults (n = 50, aged >70 yr). Participants were instructed to watch a silent nature film while TEBC trials were presented at either INS-SYS or EXP-DIA (separate groups). Learned responses were determined as eyeblinks occurring after the tone conditioned stimulus (CS), immediately preceding the air puff unconditioned stimulus (US). Participants were classified as learners if they made at least five conditioned responses (CRs). Brain responses to the stimuli were measured by electroencephalogram (EEG). Memory for the film and awareness of the CS-US contingency were evaluated with a questionnaire. As a result, participants showed robust brain responses to the CS, acquired CRs, and reported awareness of the CS-US relationship to a variable degree. There was no difference between the INS-SYS and EXP-DIA groups in any of the above. However, when only participants who learned were considered, those trained at EXP-DIA (n = 11) made more CRs than those trained at INS-SYS (n = 13). Thus, learned performance could be facilitated in those elderly who learned. However, training at a specific phase of cardiorespiratory rhythm did not increase the proportion of participants who learned. NEW & NOTEWORTHY: We trained healthy elderly individuals in trace eyeblink conditioning, either at inspiration-systole or at expiration-diastole. Those who learned exhibited more conditioned responses when trained at expiration-diastole rather than inspiration-systole. However, there was no difference between the experimental groups in the proportion of individuals who learned or did not learn. [ABSTRACT FROM AUTHOR]

An increasing number of studies on non-contact vital sign detection using radar are now beginning to turn to data-driven neural network approaches rather than traditional signal-processing methods. However, there are few radar datasets available for deep learning due to the difficulty of acquiring and labeling the data, which require specialized equipment and physician collaboration. This paper presents a new model of heartbeat-induced chest wall motion (CWM) with the goal of generating a large amount of simulation data to support deep learning methods. An in-depth analysis of published CWM data collected by the VICON Infrared (IR) motion capture system and continuous wave (CW) radar system during respiratory hold was used to summarize the motion characteristics of each stage within a cardiac cycle. In combination with the physiological properties of the heartbeat, appropriate mathematical functions were selected to describe these movement properties. The model produced simulation data that closely matched the measured data as evaluated by dynamic time warping (DTW) and the root-mean-squared error (RMSE). By adjusting the model parameters, the heartbeat signals of different individuals were simulated. This will accelerate the application of data-driven deep learning methods in radar-based non-contact vital sign detection research and further advance the field. [ABSTRACT FROM AUTHOR]

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accumulated evidence has supported the probiotic activity of Leuconostoc mesenteroides (L. mesenteroides) which can yield beneficial metabolites via fermentation. Here, bovine milk rich in phenylalanine（PHE) was used as a source for fermentation of L. mesenteroides. The complexes of PHE with bacterial phenylalanine hydroxylase (PheH) at two temperatures were revealed via molecular dynamics simulation. Two carbon hydrogen bonds and a Pi-Alkyl T-shaped interaction were newly formed at an active site of the PheH-PHE complex. The PheH interacted with two different hydrogen atoms in an amine of PHE via conventional hydrogen bonds at 37 °C, a temperature that accelerated the milk fermentation of L. mesenteroides. Twenty-eight metabolites including various neurotransmitters in fermented milk were identified and quantified by liquid chromatography coupled to quadrupole ion trap (Q-Trap) tandem mass spectrometry. Ex ovo injection of milk ferments into the yolk sac of chicken embryos enhanced a rising temperature-induced increase in heartbeats towards the normal resting level. The neurotransmitter-rich milk ferments hold potential for using to adjust energy metabolism, referred from heart rates, during fluctuating temperature conditions.

In recent years, non-contact biometric identification has garnered significant attention owing to its flexibility and its capacity to ensure privacy and confidentiality. Previous research has predominantly centered on harnessing cardiac radar signals detected by radar systems. This paper aims to compare two methods for person identification utilizing heartbeat signals extracted from radar data. In the first approach, we directly employ the heartbeat time series data as input for a deep learning model called InceptionTime dedicated to person identification. The second method explores the viability of using spectrograms, which are images generated from cardiac radar heartbeat signals, combined with other deep learning models, ResNet and a small convolutional neural network (CNN) model built by us, to achieve the same goal. Additionally, we assessed the robustness of both methods by introducing white Gaussian noise into the signals and evaluating their performance under different noise levels. For the second method, we implemented three image denoising methods: autoencoder, deep image prior (DIP), and Dilated-Residual U-Net (DRU-Net) to denoise the spectrograms after adding noise in the time domain. Experimental results reveal that the accuracy of person identification using spectrograms is 100% without adding noise based on the public dataset. The identification accuracy is the same as that using time series data. Following the introduction of noise, the accuracy of both methods decreases; however, the method based on spectrograms exhibits a more pronounced decline in accuracy compared to the approach using time series data directly especially for the small CNN model we built. The image-based method with DIP image denoiser shows outstanding performance when the value of noise is high compared with InceptionTime.

The spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to an increased focus on the routine analysis of vital signs such as breathing and pulse rates. Radar technology has proven effective for non-contact, long-term monitoring of these vital signs, with frequency analysis being the default method for processing signals from Doppler radar owing to their inherent noise. However, conventional analysis approaches often struggle to detect weak signals buried within the sidelobes of other signals. Some data analysis techniques for Doppler radar rely on machine learning, but they struggle to generate clear time-frequency diagrams, complicating heartbeat detection. In this study, we employed non-harmonic analysis (NHA) as a frequency analysis method to mitigate sidelobe interference and implemented semantic segmentation for precise heartbeat detection. To validate the proposed approach, we conducted heartbeat detection tests both in stationary, low-noise conditions and in a noisy driving simulation environment. The results indicated that the NHA method successfully analyzed heartbeat harmonics, suggesting its potential for detecting heartbeat components through machine learning. To validate these findings, we determined the detection accuracy by comparing true and false positive rates, allowing us to quantify the detectability of heartbeats under both resting and driving simulation conditions.

This paper introduces a novel deep learning model for ECG signal classification using feature fusion. The proposed methodology transforms the ECG time series into a spectrogram image using a short-time Fourier transform (STFT). This spectrogram is further processed to generate a histogram of oriented gradients (HOG) and local binary pattern (LBP) features. Three separate 2D convolutional neural networks (CNNs) then analyze these three image representations in parallel. To enhance performance, the extracted features are concatenated before feeding them into a gated recurrent unit (GRU) model. The proposed approach is extensively evaluated on two ECG datasets (MIT-BIH + BIDMC and MIT-BIH) with three and five classes, respectively. The experimental results demonstrate that the proposed approach achieves superior classification accuracy compared to existing algorithms in the literature. This suggests that the model has the potential to be a valuable tool for accurate ECG signal classification, aiding in the diagnosis and treatment of various cardiovascular disorders.

Glyphosate‐based herbicides (GBH) have been commonly used in agriculture to inhibit weed growth and increase yields. However, due to the high solubility of these herbicides in water, they can reach aquatic environments, by infiltration, erosion, and/or lixiviation, affecting non target organisms. Thus, this study aimed to characterize the toxicity of GBH Roundup WG® (RWG®) during the embryonic and larval development of Danio rerio. Embryos (3 hours post fertilization, hpf–until hatching) and larvae (3 days post fertilization, dpf to 6 dpf) were exposed to concentrations of 0.065 and 6.5 mg L−1. They were evaluated for survival, hatching, spontaneous movements, heartbeat, morphology, and morphometry by in vivo photographs in microscope, cell proliferation and apoptosis by immunohistochemistry, and exploratory behavior and phototropism by video recording. Our results showed an increase in embryo and larvae mortality in those exposed to 0.065 mg L−1, as well as a reduction in spontaneous embryo movements. The larval heartbeats showed a decrease at 4 dpf in the group exposed to 0.065 mg L−1 and an increase at 5 and 6 dpf in both exposed groups. Cell proliferation was reduced in both groups exposed in embryos and only in the 0.065 mg L−1 group in larvae, while cell death increased in embryos exposed to 6.5 mg L−1. These results demonstrated the toxic effect of low concentrations of the herbicide RWG® during embryonic and larval development of non target organisms, as well as the importance of constantly reviewing acceptable limits for exposure in natural environments. [ABSTRACT FROM AUTHOR]

The sensation of internal bodily signals, such as when your stomach is contracting or your heart is beating, plays a critical role in broad biological and psychological functions ranging from homeostasis to emotional experience and self-awareness. The evolutionary origins of this capacity and, thus, the extent to which it is present in nonhuman animals remain unclear. Here, we show that rhesus monkeys (Macaca mulatta) spend significantly more time viewing stimuli presented asynchronously, as compared to synchronously, with their heartbeats. This is consistent with evidence previously shown in human infants using a nearly identical experimental paradigm, suggesting that rhesus monkeys have a human-like capacity to integrate interoceptive signals from the heart with exteroceptive audiovisual information. As no prior work has demonstrated behavioral evidence of innate cardiac interoceptive ability in nonhuman animals, these results have important implications for our understanding of the evolution of this ability and for establishing rhesus monkeys as an animal model for human interoceptive function and dysfunction. We anticipate that this work may also provide an important model for future psychiatric research, as disordered interoceptive processing is implicated in a wide variety of psychiatric conditions.

The heart is a very crucial organ of the body. Concerted efforts are constantly put forward to provide adequate monitoring of the heart. A heart disorder is reported to cause a lot of hidden ailments resulting in numerous deaths. Early heart monitoring using an electrocardiogram (ECG) through the advancement of computer-aided diagnostic (CAD) systems is widely used. Meanwhile, the use of human reading of ECG results are faced with many challenges of inaccurate and unreliable interpretations. Over two decades, studies provided artificial intelligence (AI) technique using machine learning (ML) algorithms as a fast and reliable technique for ECG heartbeat classification. Moreover, in recent times, deep learning (DL) techniques have been focused on providing automatic feature extraction and better classification performance. On the other hand, the challenge with the ECG data is its imbalance nature. Therefore, this paper proposes a cost-based dual convolutional attention transfer DL model for ECG classification. The proposed model uses PhysionNet-MIT-BIH and Physikalisch-Technische Bundesanstalt (PTB) Diagnostics datasets. The first part uses the MIT-BIH for ECG categorization, while representations learned from the first classifier are used for PTB analysis through transfer learning (TL). The proposed model is evaluated and compared with well-performing conventional ML models based on their F1-score and accuracy scores. Our experimental finding show that the proposed model outperformed the well-performing ML models as well as competitive with past studies for both the classification and TL part, having obtained 98.45% for both F1-score and accuracy. The proposed model is applicable to real-life trials and experiments for ECG heartbeat and other similar domains.

Copyright of Matronas Hoy is the property of Asociacion Espanola de Matronas (AEM) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Breathing and heartbeat synchronize to each other and to brain function and affect cognition in humans. However, it is not clear how cardiorespiratory rhythms modulate such basic processes as synaptic plasticity thought to underlie learning. Thus, we studied if respiration and cardiac cycle phases at burst stimulation onset affect hippocampal long‐term potentiation (LTP) in the CA3–CA1 synapse in urethane‐anesthetized adult male Sprague–Dawley rats. In a between‐subjects design, we timed burst stimulation of the ventral hippocampal commissure (vHC) to systole or diastole either during expiration or inspiration and recorded responses throughout the hippocampus with a linear probe. As classical conditioning in humans seems to be most efficient at expiration‐diastole, we also expected LTP to be most efficient if burst stimulation was targeted to expiration‐diastole. However, LTP was induced equally in all four groups and respiration and cardiac cycle phase did not modulate CA1 responses to vHC stimulation overall. This could be perhaps because we bypassed all natural routes of external influences on the CA1 by directly stimulating the vHC. In the future, the effect of cardiorespiratory rhythms on synaptic plasticity could also be studied in awake state and in other parts of the hippocampal tri‐synaptic loop. [ABSTRACT FROM AUTHOR]

Objective: Although interoceptive abnormality in patients with functional seizure (FSs) has been demonstrated using explicit tasks, implicit measurements of interoception such as the effect of interoception on perceptual brain processes have not been investigated. It has been shown that perception is normally modulated by interoceptive signals related to the different phases (systole vs diastole) of the cardiac cycle (cardiac modulation effect). Given our previous findings using explicit measures of interoception, we hypothesized that cardiac modulation would be impaired in FSs. Methods: Thirty‐two patients with FSs and 30 age‐ and sex‐matched non‐clinical individuals conducted a face intensity judgment task, in which their intensity rating when fearful or neutral faces was presented was compared between systolic and diastolic phases. They also conducted the heartbeat discrimination task as a measure of their capacity to integrate both interoceptive and exteroceptive information. Results: Patients with FSs had impaired cardiac modulation of the perception of neutral faces (corrected p =.044). Individual differences in the heartbeat discrimination task predicted the degree to which cardiac modulation occurred across the whole group (p =.028). This cardiac modulation effect was significantly associated with seizure severity (p =.021). Regardless of cardiac phase, patients rated fearful facial expressions as less intense compared to control participants (p =.006). Significance: These findings highlight impaired implicit cardiac modulation effects in patients with FSs. This reflects interoceptive dysfunction in patients with FSs, and an inability of the brain to integrate interoceptive signaling with perceptual processing. This may have implications for our understanding of the pathophysiology in FSs and inform novel diagnostic approaches. [ABSTRACT FROM AUTHOR]

The present view on heartbeat initiation is that a primary pacemaker cell or a group of cells in the sinoatrial node (SAN) center paces the rest of the SAN and the atria. However, recent high-resolution imaging studies show a more complex paradigm of SAN function that emerges from heterogeneous signaling, mimicking brain cytoarchitecture and function. Here, we developed and tested a new conceptual numerical model of SAN organized similarly to brain networks featuring a modular structure with small-world topology. In our model, a lower rate module leads action potential (AP) firing in the basal state and during parasympathetic stimulation, whereas a higher rate module leads during β-adrenergic stimulation. Such a system reproduces the respective shift of the leading pacemaker site observed experimentally and a wide range of rate modulation and robust function while conserving energy. Since experimental studies found functional modules at different scales, from a few cells up to the highest scale of the superior and inferior SAN, the SAN appears to feature hierarchical modularity, i.e., within each module, there is a set of sub-modules, like in the brain, exhibiting greater robustness, adaptivity, and evolvability of network function. In this perspective, our model offers a new mainframe for interpreting new data on heterogeneous signaling in the SAN at different scales, providing new insights into cardiac pacemaker function and SAN-related cardiac arrhythmias in aging and disease.

Aim. Interoception reflects the perception, integration and modulation of visceral signals. Currently, there is no established universal approach to cardiac interoception assessment allowing its inclusion in the diagnostic protocol for various diseases. The aim was to compare three tests of interoception self-assessment based on heart palpitations within one day in healthy subjects.Material and methods. Eighty healthy volunteers took part in the study. To assess cardiac interoception, a test with button pushes at the moment of palpitations, a feedback test in the form of synchronous and asynchronous sound signals, a heartbeat counting task at specified time intervals were conducted with simultaneous electrocardiographic recording. The obtained data were compared with each other (Wilcoxon test). Its pairwise dependence (Spearman coefficient) and dependence on body parameters (sex, age, body mass index, fat mass, anxiety) were assessed (univariate linear regression).Results. The accuracy of the heartbeat counting task turned out to be significantly higher than in the button- pressing test (p=0,005). However, both estimates correlate with each other (r=0,66, p=0,003). A positive dependence of test accuracy on sex was found for the heartbeat counting task (p=0,021) and a negative dependence on fat mass for button- pressing task (p=0,032).Conclusion. The study found that volunteers' estimates of heartbeat accuracy varied across tests and were also associated with sex and body composition. The heart rate counting task and the button- pressing task are the most suitable for interoception assessment.

Hypnotizability is a psychophysiological trait measured by scales and associated with several differences, including interoceptive accuracy and the morpho‐functional characteristics of interoception‐related brain regions. The aim of the study was to assess whether the amplitude of the heartbeat evoked cortical potential (HEP), a correlate of interoceptive accuracy, differs in participants with low (lows) and high (highs) hypnotizability scores (assessed by the Stanford Hypnotic Susceptibility Scale, Form A) before and after the induction of hypnosis. ECG and EEG were monitored in 16 highs and 15 lows during an experimental session, including open eyes baseline (B), closed eyes relaxation (R), hypnotic induction (IND), neutral hypnosis (NH), and post session baseline (Post). No significant difference was observed between groups and conditions in autonomic variables. The HEP amplitude was lower in highs than in lows at the right parietal site, likely due to hypnotizability related differences in the functional connection between the right insula and parietal cortex. It increased in highs and decreased in lows across the session, possibly due to the highs' preeminently internally directed attention and to the lows' possible disengagement from the task. Since interoception is involved in several cognitive‐emotional functions, its hypnotizability related differences may contribute to the variability of experience and behavior in daily life. Heartbeat‐evoked cortical potentials, a measure of interoceptive accuracy, are smaller in the parietal cortex of high than low hypnotizable individuals, likely due to hypnotizability related differences in insula‐parietal cortex connectivity. The absence of autonomic and other cortical differences during hypnotic induction per se suggests that induction is not greatly relevant to trance experience. This finding is novel and may extend the influence of physiological correlates of hypnotizability to daily experience due to the interoceptive accuracy involved in self‐consciousness. [ABSTRACT FROM AUTHOR]

Technological advances in biomedical research have led to a massive influx of data, including health records, -omics, imaging, and sensor data. This rapid increase in the high-dimensional, heterogeneous, and unstructured biomedical data has been challenging. The traditional methods of assessing and extracting valuable knowledge from such data prove a crucial obstacle in healthcare transformation. In this study, we have proposed a deep convolutional neural network (DCNN) for heartbeat classification. Our proposed DCNN model trained on the various heartbeat pulses audio files to identify an abnormal heartbeat. For our objective, heartbeat audio files are converted to time series data and then passed through an 8-layered 1-D convolution layer to capture the temporal characteristics. The final layer is densely connected, classifying the samples as normal or abnormal. The proposed DCNN model is tested on the test dataset and achieved accuracy, precision, recall, and F1-score 92%, 93%, 74%, and 82%, respectively. To describe the importance of the proposed DCNN model, we have compared it with essential machine learning (ML) techiniques. Based on our result analysis, we can say that the proposed model outperforms basic ML techniques in classifying an abnormal heartbeat from a normal heartbeat with an accuracy of 92.5%. Future research may use the presented concept in various domains, such as skin disease classification, covid analysis, and tumor classification. The proposed approach can also be implemented on heartbeat classification data in different forms. [ABSTRACT FROM AUTHOR]

Noncontact vital sign monitoring based on radar has attracted great interest in many fields. Heart Rate Variability (HRV), which measures the fluctuation of heartbeat intervals, has been considered as an important indicator for general health evaluation. This paper proposes a new algorithm for HRV monitoring in which frequency-modulated continuous-wave (FMCW) radar is used to separate echo signals from different distances, and the beamforming technique is adopted to improve signal quality. After the phase reflecting the chest wall motion is demodulated, the acceleration is calculated to enhance the heartbeat and suppress the impact of respiration. The time interval of each heartbeat is estimated based on the smoothed acceleration waveform. Finally, a joint optimization algorithm was developed and is used to precisely segment the acceleration signal for analyzing HRV. Experimental results from 10 participants show the potential of the proposed algorithm for obtaining a noncontact HRV estimation with high accuracy. The proposed algorithm can measure the interbeat interval (IBI) with a root mean square error (RMSE) of 14.9 ms and accurately estimate HRV parameters with an RMSE of 3.24 ms for MEAN (the average value of the IBI), 4.91 ms for the standard deviation of normal to normal (SDNN), and 9.10 ms for the root mean square of successive differences (RMSSD). These results demonstrate the effectiveness and feasibility of the proposed method in emotion recognition, sleep monitoring, and heart disease diagnosis. [ABSTRACT FROM AUTHOR]

Extreme-scale computing involves hundreds of millions of threads with multi-level parallelism running on large-scale hierarchical and heterogeneous hardware. Some OpenMP multi-threaded applications increasingly suffer from runtime hidden behaviors owning to shared resource contention as well as software- and hardware-related problems. Such hidden behaviors can result in failure and inefficiencies and are among the main challenges in system resiliency. To minimize the impact of hidden behaviors, one must quickly and accurately detect and diagnose the hidden behaviors that cause the failures. However, it is difficult to identify hidden behaviors in the dynamic and noisy data collected by OpenMP multi-threaded monitoring infrastructures. This paper presents an anthropomorphic diagnosis framework for hidden behaviors of OpenMP multi-threaded applications. In the framework, we first design injected heartbeat functions for OpenMP multi-threaded applications. Then, we leverage the heartbeat sequences to extract features of hidden behaviors. Finally, we develop a feature learning-based algorithm using heartbeat analysis, namely HSA, to diagnose hidden behaviors. To evaluate our framework, the NAS Parallel NPB benchmark, EPCC OpenMP micro-benchmark suite, and Jacobi benchmark are used to test the performance of our proposed framework. The experimental results demonstrate that our framework successfully identifies 90.3% of the injected hidden behaviors of OpenMP multi-threaded applications while acquiring low overhead. • The anthropomorphic framework is proposed for diagnosing hidden behaviors. • The framework based on heartbeats supports multi-threaded OpenMP applications. • Small-size samples also demonstrate the high efficiency of this framework. • The framework is lower overhead and is more accurate than the state-of-the-art. • The framework supports extension and specificity in most of our experiments. [ABSTRACT FROM AUTHOR]

Several studies have been published on noncontact heartbeat detection recently. Particularly, a few studies have found that radar for noncontact detection is effective for long-term monitoring. As the novel coronavirus continues to spread worldwide, the use of radar is expected to prevent the contamination of equipment by the virus and enable heartbeat detection from a safe distance. To monitor heartbeat fluctuation, heartbeat signals must be detected over a short period; however, conventional methods require approximately 5 s for detection in the stationary state of the human body. This study developed a method for detecting heartbeat in approximately 2.5 s based on nonharmonic analysis (NHA) to suppress sidelobes. The method has nearly no data length limitations in terms of frequency resolution. To validate the method, heartbeat detection is performed in a stationary state with reduced noise and a driving simulation environment with high noise. Frequency analysis of the received signals enabled the detection of heartbeat harmonics, suggesting the possibility of detecting the fundamental heartbeat frequency from its harmonics. To test this aspect, the detectability of heartbeat harmonics is determined under the stationary and driving simulation conditions from a comparison of the conventional short-time Fourier transform, continuous wavelet transforms, and the proposed NHA method.

Remote robotic interventions and maintenance tasks are frequently required in hazardous environments. Particularly, missions with a redundant mobile manipulator in the world’s most complex machine, the CERN Large Hadron Collider (LHC), are performed in a sensitive underground environment with radioactive or electromagnetic hazards, bringing further challenges in safety and reliability. The mission’s success depends on the robot’s hardware and software, and when the tasks become too unpredictable to execute autonomously, the operators need to make critical decisions. Still, in most current human-machine systems, the state of the human is neglected. In this context, a novel 3D Mixed Reality (MR) human-robot interface with the Operator Monitoring System (OMS) was developed to advance safety and task efficiency with improved spatial awareness, advanced manipulator control, and collision avoidance. However, new techniques could increase the system’s sophistication and add to the operator’s workload and stress. Therefore, for operational validation, the 3D MR interface had to be compared with an operational 2D interface, which has been used in hundreds of interventions. With the 3D MR interface, the execution of precise approach tasks was faster, with no increased workload or physiological response. The new 3D MR techniques improved the teleoperation quality and safety while maintaining similar effects on the operator. The OMS worked jointly with the interface and performed well with operators with varied teleoperation backgrounds facing a stressful real telerobotic scenario in the LHC. The paper contributes to the methodology for human-centred interface evaluation incorporating the user’s physiological state: heart rate, respiration rate and skin electrodermal activity, and combines it with the NASA TLX assessment method, questionnaires, and task execution time. It provides novel approaches to operator state identification, the GUI-OMS software architecture, and the evaluation of the 3D MR techniques. The solutions can be practically applied in mission-critical applications, such as telesurgery, space robotics, uncrewed transport vehicles and semi-autonomous machinery.

Heart rate variability (HRV), systolic blood pressure variability (BPV), and spontaneous baroreflex sensitivity (BRS) are indirect and approximate measures of autonomic regulation of the cardiovascular system. Studies have shown differences in HRV and BRS between males and females; however, no study has observed differences in BPV, HRV, or BRS between male and female athletes. One hundred males (age 21.2 ± 2.1 y; BMI 27.4 ± 4.5 kg/m2) and sixty-five females (age: 19.7 ± 1.6 y; BMI 22.7 ± 2.2 kg/m2) were assessed during the pre-season baseline. We collected resting beat-to-beat blood pressure and R-R intervals using finger photoplethysmography and a 3-lead electrocardiogram, respectively. Participants underwent a controlled slow breathing protocol (six breaths/minute: 5 s inhale, 5 s exhale) for 5 min. Spectral and linear analysis was conducted on blood pressure and ECG data. Regression curves were fitted to the blood pressure and R-R signals, with the slopes providing the BRS parameters. Male athletes had significantly (p < 0.05) lower mean heart rate, RR interval SD2/SD1, HRV % low-frequency, and higher BP high-frequency power during controlled respiration. No differences were found in any BRS parameters. HRV and BPV responses to a slow breathing protocol differed between male and female athletes; however, BRS responses did not. [ABSTRACT FROM AUTHOR]

Recently, the development of self-driving technology has progressed rapidly. However, self-driving cars have not yet become widespread. Thus, with an aging population, accidents such as road rage and acceleration and brake accidents are likely to continue. Stress is one key reason for such dangerous driving. Thus, technologies must be developed to provide mental support to drivers as required. In this study, we considered estimating driver emotions as a first step along these lines. To this end, we developed a technology to estimate emotions by collecting data on biological signals such as brain waves, heart rate, body movement, and data on a driver's operating status while they are driving. In addition, we introduce a Positive and Negative Affect Schedule (PANAS) to express the psychological states experienced by drivers. We further present the results of an analysis of data on a driver's emotions from PANAS and data obtained from electroencephalogram (EEG) readings and other biological signals from a car. In addition, the relationship between this experimental environment and the Internet of Digital Reality (IoD) is described. [ABSTRACT FROM AUTHOR]

An increasing number of studies on non-contact vital sign detection using radar are now beginning to turn to data-driven neural network approaches rather than traditional signal-processing methods. However, there are few radar datasets available for deep learning due to the difficulty of acquiring and labeling the data, which require specialized equipment and physician collaboration. This paper presents a new model of heartbeat-induced chest wall motion (CWM) with the goal of generating a large amount of simulation data to support deep learning methods. An in-depth analysis of published CWM data collected by the VICON Infrared (IR) motion capture system and continuous wave (CW) radar system during respiratory hold was used to summarize the motion characteristics of each stage within a cardiac cycle. In combination with the physiological properties of the heartbeat, appropriate mathematical functions were selected to describe these movement properties. The model produced simulation data that closely matched the measured data as evaluated by dynamic time warping (DTW) and the root-mean-squared error (RMSE). By adjusting the model parameters, the heartbeat signals of different individuals were simulated. This will accelerate the application of data-driven deep learning methods in radar-based non-contact vital sign detection research and further advance the field.

Behavior is guided by the compatibility of expectations based on past experience and the outcome. In a recent study, Fouragnan and colleagues report that absolute prediction error (PE)-related heart-evoked potentials (HEPs) differ according to the cardiac cycle phase at outcome, and that the magnitude of this effect positively correlates with reward learning in healthy adults. [ABSTRACT FROM AUTHOR]

Objectives: Examine and visualise the temporal concentration of different crime types and detect if their intensity varies through distinct moments of the week. Methods: The "heartbeat of the crime signal" is constructed by overlapping the weekly time they were suffered. This study is based on more than 220,000 crimes reported to the Mexico City Police Department between January 2016 and March 2020 to capture the day and time of crimes and detect moments of the week in which the intensity exceeds the average frequency. A new metric for the temporal concentration of crime is constructed for different types of crime and regions of the city based on the corresponding heartbeats. Results: The temporal concentration of crime is a stable signature of different types of crime. The intensity of robberies and theft is more homogeneous from Monday to Sunday, but robberies of a bank user are highly concentrated in a week, meaning that few hours of the week capture most of the burning moments. The concentration is not homogeneously distributed in the city, with some regions experiencing a much higher temporal concentration of crime. Conclusions: Crime is highly concentrated when observed in its weekly patterns, but different types of crime and regions exhibit substantially distinct concentration levels. The temporal trace indicates specific moments for the burning times of different types of crime, which is a critical element of a policing strategy. [ABSTRACT FROM AUTHOR]

ECG provides critical information in a waveform about the heart's condition. This information is crucial to physicians as it is the first thing to be performed by cardiologists. When COVID-19 spread globally and became a pandemic, the government of Saudi Arabia placed various restrictions and guidelines to protect and save citizens and residents. One of these restrictions was preventing individuals from touching any surface in public and private places. In addition, the authorities placed a mandatory rule in all public facilities and the private sector to evaluate the temperature of individuals before entering. Thus, the idea of this study stems from the need to have a touchless technique to determine heartbeat rate. This article proposes a viable and dependable method to estimate an average heartbeat rate based on the reflected light on the skin. This model uses various deep learning tools, including AlexNet, Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), and ResNet50V2. Three scenarios have been conducted to evaluate and validate the presented model. In addition, the proposed approach takes its inputs from video streams and converts these streams into frames and images. Numerous trials have been conducted on volunteers to validate the method and assess its outputs in terms of accuracy, mean absolute error (MAE), and mean squared error (MSE). The proposed model achieves an average 99.78% accuracy, MAE is 0.142 when combing LSTMs and ResNet50V2, while MSE is 1.82. Moreover, a comparative measurement between the presented algorithm and some studies from the literature based on utilized methods, MAE, and MSE are performed. The achieved outcomes reveal that the developed technique surpasses other methods. Moreover, the findings show that this algorithm can be applied in healthcare facilities and aid physicians. [ABSTRACT FROM AUTHOR]