arXiv subjects

John Malik

Publications and source records attributed to John Malik.

10 recordsLinked to original sources

arXiv2024

Unsupervised Ensembling of Multiple Software Sensors with Phase Synchronization: A Robust Approach For Electrocardiogram-derived Respiration

Objective: We aimed to fuse the outputs of different electrocardiogram-derived respiration (EDR) algorithms to create one EDR signal that is of higher quality. Methods: We viewed each EDR algorithm as a software sensor that recorded breathing activity from a different vantage point, identified high-quality software sensors based on the respiratory signal quality index, aligned the highest-quality EDRs with a phase synchronization technique based on the graph connection Laplacian, and finally fused those aligned, high-quality EDRs. We refer to the output as the sync-ensembled EDR signal. The proposed algorithm was evaluated on two large-scale databases of whole-night polysomnograms. We evaluated the performance of the proposed algorithm using three respiratory signals recorded from different hardware sensors, and compared it with other existing EDR algorithms. A sensitivity analysis was carried out for a total of five cases: fusion by taking the mean of EDR signals, and the four cases of EDR signal alignment without and with synchronization and without and with signal quality selection. Results: The sync-ensembled EDR algorithm outperforms existing EDR algorithms when evaluated by the synchronized correlation (γ-score), optimal transport (OT) distance, and estimated average respiratory rate (EARR) score, all with statistical significance. The sensitivity analysis shows that the signal quality selection and EDR signal alignment are both critical for the performance, both with statistical significance. Conclusion: The sync-ensembled EDR provides robust respiratory information from electrocardiogram. Significance: Phase synchronization is not only theoretically rigorous but also practical to design a robust EDR.

eess.SP↗

arXiv2021

Wave-shape oscillatory model for nonstationary periodic time series analysis

The oscillations observed in many time series, particularly in biomedicine, 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 these time series (including and specifically pathophysiological ones) and estimate the underlying dynamics, we provide a novel wave-shape oscillatory model. In this model, time-dependent variations in cycle shape 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 the wave-shape manifold, we propose a novel algorithm coined Dynamic Diffusion map (DDmap) by applying 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 DDmap algorithm under the proposed model. Applying the proposed model and algorithm to arterial blood pressure (ABP) signals recorded during general anesthesia leads to the extraction of nociception information. Applying the wave-shape oscillatory model and the DDmap algorithm to cardiac cycles in the electrocardiogram (ECG) leads to ectopy detection and a new ECG-derived respiratory signal, even when the subject has atrial fibrillation.

stat.AP↗

arXiv2021

Correcting Automated and Manual Speech Transcription Errors using Warped Language Models

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of errors that appear in automatic or manual transcriptions of spoken language by exposing the language model to the same types of errors during training. In this work we propose a novel approach that takes advantage of the robustness of warped language models to transcription noise for correcting transcriptions of spoken language. We show that our proposed approach is able to achieve up to 10% reduction in word error rates of both automatic and manual transcriptions of spoken language.

cs.CL↗

arXiv2020

An Adaptive QRS Detection Algorithm for Ultra-Long-Term ECG Recordings

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 showed a sensitivity of 99.90% and a positive predictive value of 99.73%. Meanwhile, the state-of-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.

eess.SP↗

arXiv2019

Diffuse to fuse EEG spectra -- intrinsic geometry of sleep dynamics for classification

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-subject-out 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.

eess.SP↗

arXiv2019

Recycling cardiogenic artifacts in impedance pneumography

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.

physics.data-an↗

arXiv2019

Connecting Dots -- from Local Covariance to Empirical Intrinsic Geometry and Locally Linear Embedding

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.

math.ST↗

arXiv2018

Sleep-wake classification via quantifying heart rate variability by convolutional neural network

Fluctuations in heart rate are intimately tied to changes in the physiological state of the organism. We examine and exploit this relationship by classifying a human subject's wake/sleep status using his instantaneous heart rate (IHR) series. We use a convolutional neural network (CNN) to build features from the IHR series extracted from a whole-night electrocardiogram (ECG) and predict every 30 seconds whether the subject is awake or asleep. Our training database consists of 56 normal subjects, and we consider three different databases for validation; one is private, and two are public with different races and apnea severities. On our private database of 27 subjects, our accuracy, sensitivity, specificity, and AUC values for predicting the wake stage are 83.1%, 52.4%, 89.4%, and 0.83, respectively. Validation performance is similar on our two public databases. When we use the photoplethysmography instead of the ECG to obtain the IHR series, the performance is also comparable. A robustness check is carried out to confirm the obtained performance statistics. 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.

stat.AP↗

arXiv2017

Single-lead f-wave extraction using diffusion geometry

A novel single-lead f-wave extraction algorithm based on the modern diffusion geometry data analysis framework is proposed. The algorithm is essentially an averaged beat subtraction algorithm, where the ventricular activity template is estimated by combining a newly designed metric, the "diffusion distance," and the non-local Euclidean median based on the non-linear manifold setup. We coined the algorithm DD-NLEM. Two simulation schemes are considered, and the new algorithm DD-NLEM outperforms traditional algorithms, including the average beat subtraction, principal component analysis, and adaptive singular value cancellation, in different evaluation metrics with statistical significance. The clinical potential is shown in the real Holter signal, and we introduce a new score to evaluate the performance of the algorithm.

physics.data-an↗

arXiv2015

Mutants of compactified representations revisited

We show that the mutants of compactified representations constructed by Franz and Puppe can be written as intersections of real quadrics involving division algebras and as generalizations of polygon spaces. We also show that these manifolds are connected sums of products of spheres.

math.AT↗