This result advocates for an effective and scalable method for recognizing changes in physiological state using non-invasive heart rate monitoring. The CNN model adaptively quantifies IHR fluctuation as well as its location in time and is suitable for differentiating between the wake and sleep stages.

We propose a novel algorithm for sleep dynamics visualization and automatic annotation by applying diffusion geometry based sensor fusion algorithm to fuse spectral information from two electroencephalograms (EEG). The diffusion geometry approach helps organize the nonlinear dynamical structure hidden in the EEG signal. The visualization is achieved by the nonlinear dimension reduction capability of the chosen diffusion geometry algorithms. For the automatic annotation purpose, the support vector machine is trained to predict the sleep stage. The prediction performance is validated on a publicly available benchmark database, Physionet Sleep-EDF [extended] SC * (SC = Sleep Cassette) and ST * (ST = Sleep Telemetry), with the leave-one-subjectout cross validation. When we have a single EEG channel (Fpz-Cz), the overall accuracy, macro F1 and Cohen's kappa achieve 82.72%,75.91% and 76.1% respectively in Sleep-EDF SC * and 78.63%, 73.58% and 69.48% in Sleep-EDF ST * . This performance is compatible with the state-of-the-art results. When we have two EEG channels (Fpz-Cz and Pz-Oz), the overall accuracy, macro F1 and Cohen's kappa achieve 84.44%,78.25% and 78.36% respectively in Sleep-EDF SC * and 79.05%, 74.73% and 70.31% in Sleep-EDF ST * . The results suggest the potential of the proposed algorithm in practical applications.

The clinical potential is shown in the real Holter signal, and we introduce a new score to evaluate the performance of the algorithm.

Local covariance structure under the manifold setup has been widely applied in the machine learning society. Based on the established theoretical results, we provide an extensive study of two relevant manifold learning algorithms, empirical intrinsic geometry (EIG) and the locally linear embedding (LLE) under the manifold setup. Particularly, we show that without an accurate dimension estimation, the geodesic distance estimation by EIG might be corrupted. Furthermore, we show that by taking the local covariance matrix into account, we can more accurately estimate the local geodesic distance. When understanding LLE based on the local covariance structure, its intimate relationship with the curvature suggests a variation of LLE depending on the "truncation scheme". We provide a theoretical analysis of the variation.

No abstract

Purpose: Biomedical sensors often exhibit cardiogenic artifacts which, while distorting the signal of interest, carry useful hemodynamic information. We propose an algorithm to remove and extract hemodynamic information from these cardiogenic artifacts. Methods:We apply a nonlinear time-frequency analysis technique, the de-shape synchrosqueezing transform (dsSST), to adaptively isolate the high-and low-frequency components of a single-channel signal. We demonstrate this technique's effectiveness by removing and deriving hemodynamic information from the cardiogenic artifact in an impedance pneumography (IP). Results: The instantaneous heart rate is extracted, and the cardiac and respiratory signals are reconstructed. Conclusions: The dsSST is suitable for generating useful hemodynamic information from the cardiogenic artifact in a single-channel IP. We propose that the usefulness of the dsSST as a recycling tool extends to other biomedical sensors exhibiting cardiogenic artifacts.

The oscillations observed in physiological time series exhibit morphological variations over time. These morphological variations are caused by intrinsic or extrinsic changes to the state of the generating system, henceforth referred to as dynamics. To model such a time series, we provide a novel hierarchical model: the wave-shape oscillatory model. In this model, timedependent variations in cycle morphology occur along a manifold called the wave-shape manifold. To estimate the wave-shape manifold associated with an oscillatory time series, study the dynamics, and visualize the time-dependent changes along it, we apply the well-established diffusion maps (DM) algorithm to the set of all observed oscillations. We provide a theoretical guarantee on the dynamical information recovered by the DM algorithm under the proposed model. Applying the proposed model to arterial blood pressure signals recorded during general anesthesia leads to the extraction of nociception information. Applying the wave-shape oscillatory model to cardiac cycles in the electrocardiogram (ECG) leads to a new ECG-derived respiratory signal.

Background: Accurate detection of QRS complexes during mobile, ultra-long-term ECG monitoring is challenged by instances of high heart rate, dramatic and persistent changes in signal amplitude, and intermittent deformations in signal quality that arise due to subject motion, background noise, and misplacement of the ECG electrodes. Purpose: We propose a revised QRS detection algorithm which addresses the above-mentioned challenges. Methods and Results: Our proposed algorithm is based on a state-of-the-art algorithm after applying two key modifications. The first modification is implementing local estimates for the amplitude of the signal. The second modification is a mechanism by which the algorithm becomes adaptive to changes in heart rate. We validated our proposed algorithm against the state-of-the-art algorithm using short-term ECG recordings from eleven annotated databases available at Physionet, as well as four ultra-long-term (14-day) ECG recordings which were visually annotated at a central ECG core laboratory. On the database of ultra-long-term ECG recordings, our proposed algorithm ADAPTIVE QRS DETECTION 2 showed a sensitivity of 99.90% and a positive predictive value of 99.73%. Meanwhile, the stateof-the-art QRS detection algorithm achieved a sensitivity of 99.30% and a positive predictive value of 99.68% on the same database. The numerical efficiency of our new algorithm was evident, as a 14-day recording sampled at 200 Hz was analyzed in approximately 157 seconds. Conclusions:We developed a new QRS detection algorithm. The efficiency and accuracy of our algorithm makes it a good fit for mobile health applications, ultra-long-term and pathological ECG recordings, and the batch processing of large ECG databases.