Ballistocardiography Research Articles

Skin feature point tracking using deep feature encodings

AbstractFacial feature tracking is a key component of imaging ballistocardiography (BCG) where accurate quantification of the displacement of facial keypoints is needed for good heart rate estimation. Skin feature tracking enables video-based quantification of motor degradation in Parkinson’s disease. While traditional computer vision algorithms like Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), and Lucas-Kanade method (LK) have been benchmarks due to their efficiency and accuracy, they often struggle with challenges like affine transformations and changes in illumination. In response, we propose a pipeline for feature tracking, that applies a convolutional stacked autoencoder to identify the most similar crop in an image to a reference crop containing the feature of interest. The autoencoder learns to represent image crops into deep feature encodings specific to the object category it is trained upon. We train the autoencoder on facial images and validate its ability to track skin features in general using manually labelled face and hand videos of small and large motion recorded in our lab. Our evaluation protocol is comprehensive, including quantification of errors in human annotation. The tracking errors of distinctive skin features (moles) are so small that we cannot exclude the fact that they stem from the manual labelling based on a $$\chi ^2$$ χ 2 -test. With a mean error of 0.6–3.3 pixels, our method outperformed the other methods in all but one scenario. More importantly, our method was the only one that did not diverge. We also compare our method with the latest state-of-the-art transformer for feature matching by Google—Omnimotion. Our results indicate that our method is superior at tracking different skin features under large motion conditions and that it creates better feature descriptors for tracking, matching, and image registration compared to both traditional algorithms and the latest Omnimotion.

Remote Monitoring of Sympathovagal Imbalance During Sleep and Its Implications in Cardiovascular Risk Assessment: A Systematic Review.

Nocturnal sympathetic overdrive is an early indicator of cardiovascular (CV) disease, emphasizing the importance of reliable remote patient monitoring (RPM) for autonomic function during sleep. To be effective, RPM systems must be accurate, non-intrusive, and cost-effective. This review evaluates non-invasive technologies, metrics, and algorithms for tracking nocturnal autonomic nervous system (ANS) activity, assessing their CV relevance and feasibility for integration into RPM systems. A systematic search identified 18 relevant studies from an initial pool of 169 publications, with data extracted on study design, population characteristics, technology types, and CV implications. Modalities reviewed include electrodes (e.g., electroencephalography (EEG), electrocardiography (ECG), polysomnography (PSG)), optical sensors (e.g., photoplethysmography (PPG), peripheral arterial tone (PAT)), ballistocardiography (BCG), cameras, radars, and accelerometers. Heart rate variability (HRV) and blood pressure (BP) emerged as the most promising metrics for RPM, offering a comprehensive view of ANS function and vascular health during sleep. While electrodes provide precise HRV data, they remain intrusive, whereas optical sensors such as PPG demonstrate potential for multimodal monitoring, including HRV, SpO2, and estimates of arterial stiffness and BP. Non-intrusive methods like BCG and cameras are promising for heart and respiratory rate estimation, but less suitable for continuous HRV monitoring. In conclusion, HRV and BP are the most viable metrics for RPM, with PPG-based systems offering significant promise for non-intrusive, continuous monitoring of multiple modalities. Further research is needed to enhance accuracy, feasibility, and validation against direct measures of autonomic function, such as microneurography.

Identifying Gravity-Related Artifacts on Ballistocardiography Signals by Comparing Weightlessness and Normal Gravity Recordings (ARTIFACTS): Protocol for an Observational Study.

Modern ballistocardiography (BCG) and seismocardiography (SCG) use acceleration sensors to measure oscillating recoil movements of the body caused by the heartbeat and blood flow, which are transmitted to the body surface. Acceleration artifacts occur through intrinsic sensor roll, pitch, and yaw movements, assessed by the angular velocities of the respective sensor, during measurements that bias the signal interpretation. This observational study aims to generate hypotheses on the detection and elimination of acceleration artifacts due to the intrinsic rotation of accelerometers and their differentiation from heart-induced sensor accelerations. Multimodal data from 4 healthy participants (3 male and 1 female) using BCG-SCG and an electrocardiogram will be collected and serve as a basis for signal characterization, model modulation, and location vector derivation under parabolic flight conditions from µg to 1.8g. The data will be obtained during a parabolic flight campaign (3 times 30 parabolas) between September 24 and July 25 (depending on the flight schedule). To detect the described acceleration artifacts, accelerometers and gyroscopes (6-degree-of-freedom sensors) will be used for measuring acceleration and angular velocities attributed to intrinsic sensor rotation. Changes in acceleration and angular velocities will be explored by conducting descriptive data analysis of resting participants sitting upright in varying gravitational states. A multimodal data set will serve as a basis for research into a noninvasive and gentle method of BCG-SCG with the aid of low-noise and synchronous 3D gyroscopes and 3D acceleration sensors. Hypotheses will be generated related to detecting and eliminating acceleration artifacts due to the intrinsic rotation of accelerometers and gyroscopes (6-degree-of-freedom sensors) and their differentiation from heart-induced sensor accelerations. Data will be collected entirely and exclusively during the parabolic flights, taking place between September 2024 and July 2025. Thus, as of June 2024, no data have been collected yet. The data will be analyzed until December 2025. The results are expected to be published by June 2026. The study will contribute to understanding artificial acceleration bias to signal readings. It will be a first approach for a detection and elimination method. Deutsches Register Klinische Studien DRKS00034402; https://drks.de/search/en/trial/DRKS00034402. PRR1-10.2196/63306.

Emerging Paradigms in Fetal Heart Rate Monitoring: Evaluating the Efficacy and Application of Innovative Textile-Based Wearables.

This comprehensive review offers a thorough examination of fetal heart rate (fHR) monitoring methods, which are an essential component of prenatal care for assessing fetal health and identifying possible problems early on. It examines the clinical uses, accuracy, and limitations of both modern and traditional monitoring techniques, such as electrocardiography (ECG), ballistocardiography (BCG), phonocardiography (PCG), and cardiotocography (CTG), in a variety of obstetric scenarios. A particular focus is on the most recent developments in textile-based wearables for fHR monitoring. These innovative devices mark a substantial advancement in the field and are noteworthy for their continuous data collection capability and ergonomic design. The review delves into the obstacles that arise when incorporating these wearables into clinical practice. These challenges include problems with signal quality, user compliance, and data interpretation. Additionally, it looks at how these technologies could improve fetal health surveillance by providing expectant mothers with more individualized and non-intrusive options, which could change the prenatal monitoring landscape.

Nanocomposite Multimodal Sensor Array Integrated with Auxetic Structure for an Intelligent Biometrics System.

A multimodal sensor array, combining pressure and proximity sensing, has attracted considerable interest due to its importance in ubiquitous monitoring of cardiopulmonary health- and sleep-related biometrics. However, the sensitivity and dynamic range of prevalent sensors are often insufficient to detect subtle body signals. This study introduces a novel capacitive nanocomposite proximity-pressure sensor (NPPS) for detecting multiple human biometrics. NPPS consists of a carbon nanotube-paper composite (CPC) electrode and a percolating multiwalled carbon nanotube (MWCNT) foam enclosed in a MWCNT-coated auxetic frame. The fractured fibers in the CPC electrode intensify an electric field, enabling highly sensitive detection of proximity and pressure. When pressure is applied to the sensor, the synergic effect of MWCNT foam and auxetic deformation amplifies the sensitivity. The simple and mass-producible fabrication protocol allows for building an array of highly sensitive sensors to monitor human presence, sleep posture, and vital signs, including ballistocardiography (BCG). With the aid of a machine learning algorithm, the sensor array accurately detects blood pressure (BP) without intervention. This advancement holds promise for unrestricted vital sign monitoring during sleep or driving.

DR.BEAT: Rule-Based Algorithm for SCG Analysis Without ECG Reference.

The DR.BEAT project aims to develop an accelerometer-based, wearable sensor system for measuring ballistocardiographic (BCG) signals, coupled with signal processing and visualization, to support cardiac health monitoring. A rule-based heartbeat detection was developed to enable the derivation of health parameters independent of an existing reference. This paper outlines the algorithm's methodology and provides an initial evaluation of its performance based on seismocardiographic (SCG) measurements obtained from an initial study involving twelve heart-healthy adults. On average, 87.6% of the heartbeats over all measurements, 97.6% of the heartbeats at rest and 71.9% of the heartbeats during physical stress could be detected.

A Wearable Sandwich Heterostructure Multimode Fiber Optic Microbend Sensor for Vital Signal Monitoring.

This work proposes a highly sensitive sandwich heterostructure multimode optical fiber microbend sensor for heart rate (HR), respiratory rate (RR), and ballistocardiography (BCG) monitoring, which is fabricated by combining a sandwich heterostructure multimode fiber Mach-Zehnder interferometer (SHMF-MZI) with a microbend deformer. The parameters of the SHMF-MZI sensor and the microbend deformer were analyzed and optimized in detail, and then the new encapsulated method of the wearable device was put forward. The proposed wearable sensor could greatly enhance the response to the HR signal. The performances for HR, RR, and BCG monitoring were as good as those of the medically approved commercial monitors. The sensor has the advantages of high sensitivity, easy fabrication, and good stability, providing the potential for application in the field of daily supervision and health monitoring.

Changepoint Detection in Heart Rate Variability Indices in Older Patients Without Cancer at End of Life Using Ballistocardiography Signals: Preliminary Retrospective Study.

In an aging society such as Japan, where the number of older people continues to increase, providing in-hospital end-of-life care for all deaths, and end-of-life care outside of hospitals, such as at home or in nursing homes, will be difficult. In end-of-life care, monitoring patients is important to understand their condition and predict survival time; this information gives family members and caregivers time to prepare for the end of life. However, with no clear indicators, health care providers must subjectively decide if an older patient is in the end-of-life stage, considering factors such as condition changes and decreased food intake. This complicates decisions for family members, especially during home-based care. The purpose of this preliminary retrospective study was to determine whether and how changes in heart rate variability (HRV) indices estimated from ballistocardiography (BCG) occur before the date of death in terminally ill older patients, and ultimately to predict the date of death from the changepoint. This retrospective pilot study assessed the medical records of 15 older patients admitted to a special nursing home between August 2019 and December 2021. Patient characteristics and time-domain HRV indices such as the average normal-to-normal (ANN) interval, SD of the normal-to-normal (SDNN) interval, and root mean square of successive differences (RMSSD) from at least 2 months before the date of death were collected. Overall trends of indices were examined by drawing a restricted cubic spline curve. A repeated measures ANOVA was performed to evaluate changes in the indices over the observation period. To explore more detailed changes in HRV, a piecewise regression analysis was conducted to estimate the changepoint of HRV indices. The 15 patients included 8 men and 7 women with a median age of 93 (IQR 91-96) years. The cubic spline curve showed a gradual decline of indices from approximately 30 days before the patients' deaths. The repeated measures ANOVA showed that when compared with 8 weeks before death, the ratio of the geometric mean of ANN (0.90, 95% CI 0.84-0.98; P=.005) and RMSSD (0.83, 95% CI 0.70-0.99; P=.03) began to decrease 3 weeks before death. The piecewise regression analysis estimated the changepoints for ANN, SDNN, and RMSSD at -34.5 (95% CI -42.5 to -26.5; P<.001), -33.0 (95% CI -40.9 to -25.1; P<.001), and -35.0 (95% CI -42.3 to -27.7; P<.001) days, respectively, before death. This preliminary study identified the changepoint of HRV indices before death in older patients at end of life. Although few data were examined, our findings indicated that HRV indices from BCG can be useful for monitoring and predicting survival time in older patients at end of life. The study and results suggest the potential for more objective and accurate prognostic tools in predicting end-of-life outcomes.

Cardiac output estimation using ballistocardiography: a feasibility study in healthy subjects

There is no reliable automated non-invasive solution for monitoring circulation and guiding treatment in prehospital emergency medicine. Cardiac output (CO) monitoring might provide a solution, but CO monitors are not feasible/practical in the prehospital setting. Non-invasive ballistocardiography (BCG) measures heart contractility and tracks CO changes. This study analyzed the feasibility of estimating CO using morphological features extracted from BCG signals. In 20 healthy subjects ECG, carotid/abdominal BCG, and invasive arterial blood pressure based CO were recorded. BCG signals were adaptively processed to isolate the circulatory component from carotid (CCc) and abdominal (CCa) BCG. Then, 66 features were computed on a beat-to-beat basis to characterize amplitude/duration/area/length of the fluctuation in CCc and CCa. Subjects’ data were split into development set (75%) to select the best feature subset with which to build a machine learning model to estimate CO and validation set (25%) to evaluate model’s performance. The model showed a mean absolute error, percentage error and 95% limits of agreement of 0.83 L/min, 30.2% and − 2.18–1.89 L/min respectively in the validation set. BCG showed potential to reliably estimate/track CO. This method is a promising first step towards an automated, non-invasive and reliable CO estimator that may be tested in prehospital emergencies.

Multichannel ballistocardiography: A comparative analysis of heartbeat detection across different body locations.

The paper presents a validation of novel multichannel ballistocardiography (BCG) measuring system, enabling heartbeat detection from information about movements during myocardial contraction and dilatation of arteries due to blood expulsion. The proposed methology includes novel sensory system and signal processing procedure based on Wavelet transform and Hilbert transform. Because there are no existing recommendations for BCG sensor placement, the study focuses on investigation of BCG signal quality measured from eight different locations within the subject's body. The analysis of BCG signals is primarily based on heart rate (HR) calculation, for which a J-wave detection based on decision-making processes was used. Evaluation of the proposed system was made by comparing with electrocardiography (ECG) as a gold standard, when the averaged signal from all sensors reached HR detection sensitivity higher than 95% and two sensors showed a significant difference from ECG measurement.

Nonlinear Heart Rate Variability Analysis for Sleep Stage Classification Using Integration of Ballistocardiogram and Apple Watch.

Wearable or non-contact, non-intrusive devices present a practical alternative to traditional polysomnography (PSG) for daily assessment of sleep quality. Physiological signals have been known to be nonlinear and nonstationary as the body adapts to states of rest or activity. By integrating more sophisticated nonlinear methodologies, the accuracy of sleep stage identification using such devices can be improved. This advancement enables individuals to monitor and adjust their sleep patterns more effectively without visiting sleep clinics. Six participants slept for three cycles of at least three hours each, wearing PSG as a reference, along with an Apple Watch, an actigraphy device, and a ballistocardiography (BCG) bed sensor. The physiological signals were processed with nonlinear methods and trained with a long short-term memory (LSTM) model to classify sleep stages. Nonlinear methods, such as return maps with advanced techniques to analyze the shape and asymmetry in physiological signals, were used to relate these signals to the autonomic nervous system (ANS). The changing dynamics of cardiac signals in restful or active states, regulated by the ANS, were associated with sleep stages and quality, which were measurable. Approximately 73% agreement was obtained by comparing the combination of the BCG and Apple Watch signals against a PSG reference system to classify rapid eye movement (REM) and non-REM sleep stages. Utilizing nonlinear methods to evaluate cardiac dynamics showed an improved sleep quality detection with the non-intrusive devices in this study. A system of non-intrusive devices can provide a comprehensive outlook on health by regularly measuring sleeping patterns and quality over time, offering a relatively accessible method for participants. Additionally, a non-intrusive system can be integrated into a user's or clinic's bedroom environment to measure and evaluate sleep quality without negatively impacting sleep. Devices placed around the bedroom could measure user vitals over longer periods with minimal interaction from the user, representing their natural sleeping trends for more accurate health and sleep disorder diagnosis.

P040 Comparisons of Heart Rate Variability Indices Derived from the Sheet-type Device beneath the Mattress with those from the Electrocardiogram

Abstract Introduction A sheet-type device beneath the mattress was developed for non-invasive monitoring of cardiac rhythm during sleep and in bedridden end-of-life elderly patients, enabling the acquisition of ballistocardiography (BCG) signals. BCG represents minute vibrations in the body associated with cardiac ejection of blood and has recently been utilized to estimate heart rate variability (HRV) indices. This study aimed to compare HRV indices derived from BCG with those obtained from simultaneously measured electrocardiogram (ECG) and assess their agreement. Methods Healthy subjects (14 males, 11 females; age 40.6±12.8 yrs.) were recruited between August 2022 and April 2023. Subjects laid on a bed with the device placed under their pillow, while ECG was recorded for 20 minutes. Time-domain indices (mean normal-to-normal (NN) interval) and frequency-domain indices (low frequency (LF) and high frequency (HF)) were calculated, and linear associations were examined by correlation analysis. Bland-Altman analysis was employed to evaluate the agreement between the indices. Results Significant positive associations were observed between BCG and ECG indices in mean NN interval (r=0.994, p&amp;lt;0.001) and LF (r=0.685, p&amp;lt;0.001) and HF (r=0.687, p&amp;lt;0.001). Bland-Altman analysis demonstrated good agreement in mean NN (mean of pairwise difference (MPD): 1.07; limits of agreement (LA): -12.57-14.70; ratio: 0.01), but poor agreement in LF (MPD: -4.32; LA: -30.42-21.78; ratio: 0.63) and HF (MPD: 4.29; LA: -21.70-30.28; ratio: 0.45) based on the ratios (&amp;gt; 0.2). Conclusion The high correlation and good agreement between mean NN intervals suggest that the BCG device can serve as an alternative to HRV for estimating NN interval.

Iontronic Textile‐based Capacitive Pressure Sensor for Unconstrained Respiration and Heartbeat Monitoring

AbstractLong‐term surveillance records of cardiac activity are essential for people at potential risk of cardiovascular disease. However, the existing mainstream technologies for cardiac monitoring, such as electrocardiography (ECG) and photoplethysmography (PPG), are inconvenient and prone to skin allergies due to contact measurements. Ballistocardiography (BCG) is a vibration signal related to cardiac activity, which can be monitored in an unconstrained way. Herein, an iontronic textile‐type flexible capacitive pressure sensor (i‐TFCPS) based on ionic liquid doped hollow‐porous fiber is developed to monitor physiological signals. With a high sensitivity of 7.26 kPa−1, a wide pressure range (10 Pa–600 kPa), a fast response time of 30 ms, and decent durability over 3500 cycles, the i‐TFCPS is simultaneously capable of detecting and tracking the static and dynamic changes of sitting posture, and subtle physiological information, such as respiration and BCG signals. Benefits from the iontronic textile as sensitive dielectric, the capacitive pressure sensor is able to monitor the subtle BCG signal under high static pressure in an unconstrained state, showing great potential for unobtrusive cardiac monitoring in home, office and hospital.

The kinocardiograph for assessment of fluid status in patients with acute decompensated heart failure.

To improve telemonitoring strategies in heart failure patients, there is a need for novel non-obtrusive sensors that monitor parameters closely related to intracardiac filling pressures. This proof-of-concept study aims to evaluate the responsiveness of cardiac kinetic energy (KE) measured with the Kinocardiograph (KCG), consisting of a seismocardiographic (SCG) sensor and a ballistocardiographic (BCG) sensor, during treatment of patients with acute decompensated heart failure. Eleven patients with acute decompensated heart failure who were hospitalized for treatment with intravenous diuretics received daily KCG measurements. The KCG measurements were compared with the diameter of the inferior vena cava (IVC) and body weight. Follow-up stopped at discharge, that is, in the recompensated state. Median (interquartile range) weight and IVC diameter decreased significantly after diuretic treatment [weight 74.5 (67.6-98.7) to 73.3 (66.7-95.6) kg, P=0.003; IVC diameter 2.47 (2.33-2.99) to 1.78 (1.65-2.47) cm, P=0.03]. In contrast with BCG measurements, significant changes in median KE measured with SCG were observed during the passive filling phase of the diastole [SGG: 0.48 (0.39-0.60) to 0.69 (0.56-0.84), P=0.026; BCG: 0.68 (0.46-0.73) to 0.68 (0.59-0.82), P=0.062], the active filling phase of the diastole [SCG: 0.38 (0.30-0.61) to 0.31 (0.09-0.47), P=0.016; BCG: 0.29 (0.17-0.39) to 0.26 (0.20-0.34), P=0.248], and the ratio between the passive and active filling phases [SCG: 2.76 (1.68-5.30) to 5.02 (3.13-10.17), P=0.006; BCG: 5.87 (3.57-7.55) to 5.27 (3.95-9.43), P=0.790]. The correlations between changes in KE during the passive and active filling phases, using SCG, and changes in weight or IVC were non-significant. Systolic KE did not show significant changes. KE measured with the KCG using SCG is highly responsive to changes in fluid status. Future research is needed to confirm its accuracy in a larger study population and specifically its application for detection of clinical deterioration in the home-environment.

Optimization and evaluation of a mobile IMU-based ballistocardiography system

Abstract In recent decades ballistocardiography (BCG) has regained popularity as a way to measure the mechanical activ- ity of the heart. In this paper we present and evaluate a new iteration of our mobile BCG measurement system. The pro- posed system uses an inertial measurement unit (IMU) placed on the carotid artery to derive the BCG. We conducted a mea- surement series to evaluate the system and to do an initial in- vestigation into whether more complex heart parameters can be derived from BCG data. The evaluation shows that heart rate (HR) and heart rate variability (HRV) calculated using BCG data, agrees well with the reference measurement and amplitudes calculated are mostly comparable in range to other papers. In conclusion, the system can reliably derive features from BCG data that can be used in further research.

Compressed sensing framework for BCG signals based on the optical fiber sensor.

A compressed sensing (CS) framework is built for ballistocardiography (BCG) signals, which contains two parts of an optical fiber sensor-based heart monitoring system with a CS module and an end-to-end deep learning-based reconstruction algorithm. The heart monitoring system collects BCG data, and then compresses and transmits the data through the CS module at the sensing end. The deep learning-based algorithm reconstructs compressed data at the received end. To evaluate results, three traditional CS reconstruction algorithms and a deep learning method are adopted as references to reconstruct the compressed BCG data with different compression ratios (CRs). Results show that our framework can reconstruct signals successfully when the CR grows from 50% to 95% and outperforms other methods at high CRs. The mean absolute error (MAE) of the estimated heartbeat rate (HR) is lower than 1 bpm when the CR is below 95%. The proposed CS framework for BCG signals can be integrated into the IoMT system, which has great potential in health care for both medical and home use.

Noninvasive Cuffless Blood Pressure Monitoring. How Mechanism-Driven and Data-Driven Models Can Help in Clinical Practice

Continuous noninvasive cuffless blood pressure (BP) monitoring is essential for early detection and treatment of hypertension. In this paper, we provide an overview of the recent advancements in cuffless BP sensors. These include contact wearable sensors such as electrocardiography (ECG), photoplethysmography (PPG), contact non-wearable sensors such as ballistocardiography (BCG), and contactless sensors such as video plethysmography (VPG). These sensors employ different measuring mechanisms such as pulse arrival time (PAT), pulse transit time (PTT), and pulse wave analysis (PWA) to estimate BP. However, challenges exist in the effective use and interpretation of signal features to obtain clinically reliable BP measurements. The correlations between signal features and BP are obtained by mechanism-driven models which use physiological principles to identify mathematical correlations, and data-driven models which use machine learning algorithms to analyze observational data to identify multidimensional correlations. On the one hand, applying mechanism-driven models to non-linear scenarios and incomplete or noisy data is challenging On the other hand, data-driven models require a large amount of data in order to prevent physically inconsistent predictions, resulting in poor generalization. From this perspective, this paper proposes to combine the strengths of mechanism-driven and data-driven approaches to obtain a more comprehensive approach, the physiology-informed machine-learning approach, with the goal of enhancing the accuracy, interpretability, and scalability of continuous cuffless BP monitoring. This holds promise for personalized clinical applications and the advancement of hypertension management.

Noninvasive Measurement of Vital Signs With the Optical Fiber Sensor Based on Deep Learning

As a vital sign of human, ballistocardiography (BCG) signal is widely used to indicate the health status of an individual. It can be captured by optical fiber sensor in a non-invasive way. Besides, some significant physiological information, such as heart rate (HR) and respiration rate (RR), can also be extracted from BCG signal. As a medical instrument characterized by low power consumption, no interference, no invasion and the capability of real-time health monitoring, optical fiber sensor provides an effective solution to health care monitoring. However, when long-term monitoring of HR and RR is required for patients, it is necessary to collect a large amount of BCG data, which incurs a considerable amount of time and labor costs. To solve this problem, a novel deep learning model is proposed in this paper, namely ELA. Long-short term memory (LSTM) has the capability to memorize long-distance information states. According to this method, the improved empirical mode decomposition (EMD) algorithm (VEMD) is applied to convert the complex problem of HR and RR time series prediction into multiple sub-problems with relatively simple intrinsic mode function (IMF) component sequence prediction. Then, the proposed ELA model is adopted to model the HR and RR sub-sequences decomposed by VEMD. Accordingly, the results of IMF component subsequence prediction are obtained, with all the prediction results linearly summed to obtain the final prediction result. Moreover, experimental results are obtained to demonstrate the superiority of ELA and the R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> is 0.9946, indicating the excellent performance of the proposed model in the assessment and prediction of vital signs.

Sleep condition detection and assessment with optical fiber interferometer based on machine learning

The prevalence of sleep disorders has increased because of the fast-paced and stressful modern lifestyle, negatively impacting the quality of human life and work efficiency. It is crucial to address sleep problems. However, the current practice of diagnosing sleep disorders using polysomnography (PSG) has limitations such as complexity, large equipment, and low portability, hindering its practicality for daily use. To overcome these challenges, in this article an optical fiber sensor is proposed as a viable solution for sleep monitoring. This device offers benefits like low power consumption, non-invasiveness, absence of interference, and real-time health monitoring. We introduce the sensor with an optical fiber interferometer to capture ballistocardiography (BCG) and electrocardiogram (ECG) signals from the human body. Furthermore, a new machine learning method is proposed for sleep condition detection. Experimental results demonstrate the superior performance of this architecture and the proposed model in monitoring and assessing sleep quality.

Noninvasive Human Ballistocardiography Assessment Based on Deep Learning

Ballistocardiography (BCG) is a vibration signal of human cardiac activity, which can be obtained by optical fiber sensor in a non-invasive way. The proposed optical fiber sensor as a low power consumption, non-contact, non-invasive real-time health monitoring instrument, has been developed into an effective health care monitoring method. However, when people need to monitor BCG for a long time, a large number of BCG data needs to be collected, which is time-consuming, costly and labor-intensive. To solve this problem, in this paper, we proposed a novel deep learning model, termed BCGNET. Firstly, convolutional neural network (CNN) is used to extract the short-term dependence between multivariate loads. Then, the recurrent neural network (RNN) model is used to capture the long-term dependence of load sequence, and the ultra-long-term repetitive pattern of load sequence is fully studied by using the long-short term memory network with recurrent-skip. Finally, autoregressive layer and full connection layer are used for combined prediction. Extensive experimental results demonstrate the superiority of BCGNET, the accuracy is 91.43% achieved by the proposed BCGNET compared with CNN (89.61%), RNN (89.88%) and multi-head attention network (MHA-Net) (90.22%), and also show the proposed model has good performance in BCG prediction and assessment.