No abstract

Ballistocardiographs (BCGs), which record the mechanical activity of the heart, have been a subject of interest for several years because of their advantages in providing unobtrusive physiological measurements. BCGs could also be useful for monitoring the biological signals of infants without the need for physical confinement. In this study, we describe a physiological signal monitoring bed based on load cells and assess an algorithm to extract the heart rate and breathing rate from the measured load-cell signals. Four infants participated in a total of 13 experiments. As a reference signal, electrocardiogram and respiration signals were simultaneously measured using a commercial device. The proposed automatic algorithm then selected the optimal sensor from which to estimate the heartbeat and respiration information. The results from the load-cell sensor signals were compared with those of the reference signals, and the heartbeat and respiration information were found to have average performance errors of 2.55% and 2.66%, respectively. The experimental results verify the positive feasibility of BCG-based measurements in infants.

We developed an automatic slow-wave sleep (SWS) detection algorithm that can be applied to groups of healthy subjects and patients with obstructive sleep apnea (OSA). This algorithm detected SWS based on autonomic activations derived from the heart rate variations of a single sensor. An autonomic stability, which is an SWS characteristic, was evaluated and quantified using R-R intervals from an electrocardiogram (ECG). The thresholds and the heuristic rule to determine SWS were designed based on the physiological backgrounds for sleep process and distribution across the night. The automatic algorithm was evaluated based on a fivefold cross validation using data from 21 healthy subjects and 24 patients with OSA. An epoch-by-epoch (30 s) analysis showed that the overall Cohen's kappa, accuracy, sensitivity, and specificity of our method were 0.56, 89.97%, 68.71%, and 93.75%, respectively. SWS-related information, including SWS duration (min) and percentage (%), were also calculated. A significant correlation in these parameters was found between automatic and polysomnography scorings. Compared with similar methods, the proposed algorithm convincingly discriminated SWS from non-SWS. The simple method using only R-R intervals has the potential to be utilized in mobile and wearable devices that can easily measure this information. Moreover, when combined with other sleep staging methods, the proposed method is expected to be applicable to long-term sleep monitoring at home and ambulatory environments.

No abstract

The current algorithm only using R-R intervals can be applied to mobile and wearable devices that acquire heart-rate-related signals; therefore, it is appropriate for sleep monitoring in the home and ambulatory environments. Further, long-term sleep monitoring could provide useful information to clinicians and patients for the diagnosis and treatments of sleep-related disorders and individual health care.

Polysomnography (PSG) is the gold-standard for sleep apnea and hypopnea syndrome (SAHS) diagnosis. Because the PSG system is not suitable for long-term continuous use owing to the high cost and discomfort caused by attached multi-channel sensors, alternative methods using a non-contact sensor have been investigated. However, the existing methods have limitations in that the radar-person distance is fixed, and the detected apnea hypopnea (AH) event cannot be provided in real-time. In this paper, therefore, we propose a novel approach for real-time AH event detection with impulse-radio ultra-wideband (IR-UWB) radar using a deep learning model. 36 PSG recordings and simultaneously measured IR-UWB radar data were used in the experiments. After the clutter was removed, IR-UWB radar images were segmented by sliding a 20-s window at 1-s shift, and categorized into two classes: AH and N. A hybrid model combining the convolutional neural networks and long short-term memory networks was trained with the data, which consisted of class-balanced segments. Time sequenced classified outputs were then fed to an event detector to identify valid AH events. Therefore, the proposed method showed a Cohen's kappa coefficient of 0.728, sensitivity of 0.781, specificity of 0.956, and an accuracy of 0.930. According to the apnea-hypopnea index (AHI) estimation analysis, the Pearson's correlation coefficient between the estimated AHI and reference AHI was 0.97. In addition, the average accuracy and kappa of SAHS diagnosis was 0.98 and 0.96, respectively, for AHI cutoffs of ≥ 5, 15, and 30 events/h. The proposed method achieved the state-of-the-art performance for classifying SAHS severity without any handengineered feature regardless of the user's location. Our approach can be utilized for a cost-effective and reliable SAHS monitoring system in a home environment.INDEX TERMS convolutional neural network, impulse-radio ultra-wideband, long short-term memory network, non-contact monitoring, sleep apnea and hypopnea syndrome

Human physiological systems have a major role in maintenance of internal stability. Previous studies have found that these systems are regulated by various types of interactions associated with physiological homeostasis. However, whether there is any interaction between these systems in different individuals is not well-understood. The aim of this research was to determine whether or not there is any interaction between the physiological systems of independent individuals in an environment where they are connected with one another. We investigated the heart rhythms of co-sleeping individuals and found evidence that in co-sleepers, not only do independent heart rhythms appear in the same relative phase for prolonged periods, but also that their occurrence has a bidirectional causal relationship. Under controlled experimental conditions, this finding may be attributed to weak cardiac vibration delivered from one individual to the other via a mechanical bed connection. Our experimental approach could help in understanding how sharing behaviors or social relationships between individuals are associated with interactions of physiological systems.

No abstract