Multilayer networks with higher-order interaction reveal the impact of collective behavior on epidemic dynamics.

The ongoing COVID-19 pandemic has inflicted tremendous economic and societal losses. In the absence of pharmaceutical interventions, the population behavioral response, including situational awareness and adherence to non-pharmaceutical intervention policies, has a significant impact on contagion dynamics. Game-theoretic models have been used to reproduce the concurrent evolution of behavioral responses and disease contagion, and social networks are critical platforms on which behavior imitation between social contacts, even dispersed in distant communities, takes place. Such joint contagion dynamics has not been sufficiently explored, which poses a challenge for policies aimed at containing the infection. In this study, we present a multi-layer network model to study contagion dynamics and behavioral adaptation. It comprises two physical layers that mimic the two solitary communities, and one social layer that encapsulates the social influence of agents from these two communities. Moreover, we adopt high-order interactions in the form of simplicial complexes on the social influence layer to delineate the behavior imitation of individual agents. This model offers a novel platform to articulate the interaction between physically isolated communities and the ensuing coevolution of behavioral change and spreading dynamics. The analytical insights harnessed therefrom provide compelling guidelines on coordinated policy design to enhance the preparedness for future pandemics.

Active learning and relevance vector machine in efficient estimate of basin stability for large-scale dynamic networks.

The interconnectivity between constituent nodes gives rise to cascading failure in most dynamic networks, such as a traffic jam in transportation networks and a sweeping blackout in power grid systems. Basin stability (BS) has recently garnered tremendous traction to quantify the reliability of such dynamical systems. In power grid networks, it quantifies the capability of the grid to regain the synchronous state after being perturbated. It is noted that detection of the most vulnerable node or generator with the lowest BS or N-1 reliability is critical toward the optimal decision making on maintenance. However, the conventional estimation of BS relies on the Monte Carlo (MC) method to separate the stable and unstable dynamics originated from the perturbation, which incurs immense computational cost particularly for large-scale networks. As the BS estimate is in essence a classification problem, we investigate the relevance vector machine and active learning to locate the boundary of stable dynamics or the basin of attraction in an efficient manner. This novel approach eschews the large number of sampling points in the MC method and reduces over 95% of the simulation cost in the assessment of N-1 reliability of power grid networks.

Intrinsic recurrence quantification analysis of nonlinear and nonstationary short-term time series.

Recurrence analysis is a powerful tool to appraise the nonlinear dynamics of complex systems and delineate the inherent laminar, divergent, or transient behaviors. Oftentimes, the effectiveness of recurrence quantification hinges upon the accurate reconstruction of the state space from a univariate time series with a uniform sampling rate. Few, if any, existing approaches quantify the recurrence properties from a short-term time series, particularly those sampled at a non-uniform rate, which are fairly ubiquitous in studies of rare or extreme events. This paper presents a novel intrinsic recurrence quantification analysis to portray the recurrence behaviors in complex dynamical systems with only short-term observations. As opposed to the traditional recurrence analysis, the proposed approach represents recurrence dynamics of a short-term time series in an intrinsic state space formed by proper rotations, attained from intrinsic time-scale decomposition (ITD) of the short time series. It is shown that intrinsic recurrence quantification analysis (iRQA), patterns harnessed from the corresponding recurrence plot, captures the underlying nonlinear and nonstationary dynamics of those short time series. In addition, as ITD does not require uniform sampling of the time series, iRQA is also applicable to unevenly spaced temporal data. Our findings are corroborated in two case studies: change detection in the Lorenz time series and early-stage identification of atrial fibrillation using short-term electrocardiogram signals.

Multi-fidelity modeling in sequential design for stability identification in dynamic time-delay systems.

Time delay arises in a variety of real-world complex systems. A high-fidelity simulation generally renders high accuracy to simulate the dynamic evolution of such complex systems and appraise quantity of interest for process design and response optimization. Identification of limit states exemplifies such applications, which outlines the boundary that separates distinct regions (e.g., stability region) in parameter space. While design of experiments is the common procedure to evaluate decision functions to sketch the boundary, it crucially relies on the quantity and quality of sampling points. This has made it infeasible to explore a large parameter design space with expensive-to-evaluate high-fidelity simulations. Furthermore, the complex contour of stability region in time-delay systems nullifies most existing sequential design paradigms, including adaptive classification approaches. On the other hand, low-fidelity surrogate modeling efficiently emulates a high-fidelity simulation, albeit at the expense of accuracy, not ideal to inspect the system behavior near the critical boundary. In this study, we investigate a multifidelity approach to delineate the stability region in a sequential fashion: sampling points are first evaluated by the low-fidelity surrogate modeling, and only those selected according to the exploration-exploitation trade-off principle are then assessed by a high-fidelity simulation to approximate the stability boundary. The application in a numerical case study of the delayed Mathieu equation as well as a real-world machining process corroborates the proposed approach.

Image-Decomposition-Enhanced Deep Learning for Detection of Rotor Cores in Cardiac Fibrillation.

OBJECTIVE: Rotors, regions of spiral wave reentry in cardiac tissues, are considered as the drivers of atrial fibrillation (AF), the most common arrhythmia. Whereas physics-based approaches have been widely deployed to detect the rotors, in-depth knowledge in cardiac physiology and electrogram interpretation skills are typically needed. The recent leap forward in smart sensing, data acquisition, and Artificial Intelligence (AI) has offered an unprecedented opportunity to transform diagnosis and treatment in cardiac ailment, including AF. This study aims to develop an image-decomposition-enhanced deep learning framework for automatic identification of rotor cores on both simulation and optical mapping data. METHODS: We adopt the Ensemble Empirical Mode Decomposition algorithm (EEMD) to decompose the original image, and the most representative component is then fed into a You-Only-Look-Once (YOLO) object-detection architecture for rotor detection. Simulation data from a bi-domain simulation model and optical mapping acquired from isolated rabbit hearts are used for training and validation. RESULTS: This integrated EEMD-YOLO model achieves high accuracy on both simulation and optical mapping data (precision: 97.2%, 96.8%, recall: 93.8%, 92.2%, and F1 score: 95.5%, 94.4%, respectively). CONCLUSION: The proposed EEMD-YOLO yields comparable accuracy in rotor detection with the gold standard in literature.

A value-based deep reinforcement learning model with human expertise in optimal treatment of sepsis.

Deep Reinforcement Learning (DRL) has been increasingly attempted in assisting clinicians for real-time treatment of sepsis. While a value function quantifies the performance of policies in such decision-making processes, most value-based DRL algorithms cannot evaluate the target value function precisely and are not as safe as clinical experts. In this study, we propose a Weighted Dueling Double Deep Q-Network with embedded human Expertise (WD3QNE). A target Q value function with adaptive dynamic weight is designed to improve the estimate accuracy and human expertise in decision-making is leveraged. In addition, the random forest algorithm is employed for feature selection to improve model interpretability. We test our algorithm against state-of-the-art value function methods in terms of expected return, survival rate, action distribution and external validation. The results demonstrate that WD3QNE obtains the highest survival rate of 97.81% in MIMIC-III dataset. Our proposed method is capable of providing reliable treatment decisions with embedded clinician expertise.

Heterogeneous recurrence analysis of heartbeat dynamics for the identification of sleep apnea events.

Obstructive sleep apnea (OSA) is a common sleep disorder that affects 24% of adult men and 9% of adult women. It occurs due to the occlusion of the upper airway during sleep, thereby leading to a decrease of blood oxygen level that triggers arousals and sleep fragmentation. OSA significantly impacts the quality of sleep and it is known to be responsible for a number of health complications, such as high blood pressure and type 2 diabetes. Traditional diagnosis of OSA relies on polysomnography, which is expensive, time-consuming and inaccessible to the general population. Recent advancement of sensing provides an unprecedented opportunity for the screening of OSA events using single-channel electrocardiogram (ECG). However, existing approaches are limited in their ability to characterize nonlinear dynamics underlying ECG signals. As such, hidden patterns of OSA-altered cardiac electrical activity cannot be fully revealed and understood. This paper presents a new heterogeneous recurrence model to characterize the heart rate variability for the identification of OSA. A nonlinear state space is firstly reconstructed from a time series of RR intervals that are extracted from single-channel ECGs. Further, the state space is recursively partitioned into a hierarchical structure of local recurrence regions. A new fractal representation is designed to efficiently characterize state transitions among segmented sub-regions. Statistical measures are then developed to quantify heterogeneous recurrence patterns. In addition, we integrate classification models with heterogeneous recurrence features to differentiate healthy subjects from OSA patients. Experimental results show that the proposed approach captures heterogeneous recurrence patterns in the transformed space and provides an effective tool to detect OSA using one-lead ECG signals.

Wireless Wearable Multisensory Suite and Real-Time Prediction of Obstructive Sleep Apnea Episodes.

Obstructive sleep apnea (OSA) is a common sleep disorder found in 24% of adult men and 9% of adult women. Although continuous positive airway pressure (CPAP) has emerged as a standard therapy for OSA, a majority of patients are not tolerant to this treatment, largely because of the uncomfortable nasal air delivery during their sleep. Recent advances in wireless communication and advanced ("bigdata") preditive analytics technologies offer radically new point-of-care treatment approaches for OSA episodes with unprecedented comfort and afforadability. We introduce a Dirichlet process-based mixture Gaussian process (DPMG) model to predict the onset of sleep apnea episodes based on analyzing complex cardiorespiratory signals gathered from a custom-designed wireless wearable multisensory suite. Extensive testing with signals from the multisensory suite as well as PhysioNet's OSA database suggests that the accuracy of offline OSA classification is 88%, and accuracy for predicting an OSA episode 1-min ahead is 83% and 3-min ahead is 77%. Such accurate prediction of an impending OSA episode can be used to adaptively adjust CPAP airflow (toward improving the patient's adherence) or the torso posture (e.g., minor chin adjustments to maintain steady levels of the airflow).

Forecasting the evolution of nonlinear and nonstationary systems using recurrence-based local Gaussian process models.

An approach based on combining nonparametric Gaussian process (GP) modeling with certain local topological considerations is presented for prediction (one-step look ahead) of complex physical systems that exhibit nonlinear and nonstationary dynamics. The key idea here is to partition system trajectories into multiple near-stationary segments by aligning the boundaries of the partitions with those of the piecewise affine projections of the underlying dynamic system, and deriving nonparametric prediction models within each segment. Such an alignment is achieved through the consideration of recurrence and other local topological properties of the underlying system. This approach was applied for state and performance forecasting in Lorenz system under different levels of induced noise and nonstationarity, synthetic heart-rate signals, and a real-world time-series from an industrial operation known to exhibit highly nonlinear and nonstationary dynamics. The results show that local Gaussian process can significantly outperform not just classical system identification, neural network and nonparametric models, but also the sequential Bayesian Monte Carlo methods in terms of prediction accuracy and computational speed.