Forecasting Trend of Coronavirus Disease 2019 using Multi-Task Weighted TSK Fuzzy System

Artificial intelligence– (AI) based fog/edge computing has become a promising paradigm for infectious disease. Various AI algorithms are embedded in cooperative fog/edge devices to construct medical Internet of Things environments, infectious disease forecast systems, smart health, and so on. However, these systems are usually done in isolation, which is called single-task learning. They do not consider the correlation and relationship between multiple/different tasks, so some common information in the model parameters or data characteristics is lost. In this study, each data center in fog/edge computing is considered as a task in the multi-task learning framework. In such a learning framework, a multi-task weighted Takagi-Sugeno-Kang (TSK) fuzzy system, called MW-TSKFS, is developed to forecast the trend of Coronavirus disease 2019 (COVID-19). MW-TSKFS provides a multi-task learning strategy for both antecedent and consequent parameters of fuzzy rules. First, a multi-task weighted fuzzy c-means clustering algorithm is developed for antecedent parameter learning, which extracts the public information among all tasks and the private information of each task. By sharing the public cluster centroid and public membership matrix, the differences of commonality and individuality can be further exploited. For consequent parameter learning of MW-TSKFS, a multi-task collaborative learning mechanism is developed based on ε-insensitive criterion and L2 norm penalty term, which can enhance the generalization and forecasting ability of the proposed fuzzy system. The experimental results on the real COVID-19 time series show that the forecasting tend model based on multi-task the weighted TSK fuzzy system has a high application value.

Weakly Supervised Spatial Deep Learning for Earth Image Segmentation Based on Imperfect Polyline Labels

In recent years, deep learning has achieved tremendous success in image segmentation for computer vision applications. The performance of these models heavily relies on the availability of large-scale high-quality training labels (e.g., PASCAL VOC 2012). Unfortunately, such large-scale high-quality training data are often unavailable in many real-world spatial or spatiotemporal problems in earth science and remote sensing (e.g., mapping the nationwide river streams for water resource management). Although extensive efforts have been made to reduce the reliance on labeled data (e.g., semi-supervised or unsupervised learning, few-shot learning), the complex nature of geographic data such as spatial heterogeneity still requires sufficient training labels when transferring a pre-trained model from one region to another. On the other hand, it is often much easier to collect lower-quality training labels with imperfect alignment with earth imagery pixels (e.g., through interpreting coarse imagery by non-expert volunteers). However, directly training a deep neural network on imperfect labels with geometric annotation errors could significantly impact model performance. Existing research that overcomes imperfect training labels either focuses on errors in label class semantics or characterizes label location errors at the pixel level. These methods do not fully incorporate the geometric properties of label location errors in the vector representation. To fill the gap, this article proposes a weakly supervised learning framework to simultaneously update deep learning model parameters and infer hidden true vector label locations. Specifically, we model label location errors in the vector representation to partially reserve geometric properties (e.g., spatial contiguity within line segments). Evaluations on real-world datasets in the National Hydrography Dataset (NHD) refinement application illustrate that the proposed framework outperforms baseline methods in classification accuracy.

Spatio-Temporal Event Forecasting Using Incremental Multi-Source Feature Learning

The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model’s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features’ dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an N th-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.

Effect of optimal filtering parameters for autoregressive model AR(p) on motor unit action potential signal

Error is one element of the autoregressive (AR) model, which is supposed to be white noise. Correspondingly assumption that white noise error is a normal distribution in electromyography (EMG) estimation is one of the common causes for error maximization. This paper presents the effect of a suitable choice of filtering function based on the non-invasive analysis properties of motor unit action potential signal, extracted from a non-invasive method-the high spatial resolution (HSR) electromyography (EMG), recorded during low-level isometric muscle contractions. The final prediction error procedure is used to find the number of parameters in the model. The error signal parameter, the simulated deviation from the actual signals, is suitably filtered to obtain optimally appropriate estimates of the parameters of the automatic regression model. It is filtered to acquire optimally appropriate estimates of the parameters of the automatic regression model. Then appropriate estimates of spectral power shapes are obtained with a high degree of efficiency compared with the robust method under investigation. Extensive experiment results for the proposed technique have shown that it provides a robust and reliable calculation of model parameters. Moreover, estimates of power spectral profiles were evaluated efficiently.

State-of-Health of Li-ion Battery Estimation Based on the Efficiency of the Charge Transfer Extracted from Impedance Spectra

Several studies show that impedance spectroscopy is a suitable method for online battery diagnosis and State-of-Health (SoH) estimation. However, the most common method is to model the acquired impedance spectrum with equivalent circuits and focus on the most sensitive parameters, namely the charge-transfer resistance. This paper introduces first a detailed model of a battery cell, which is then simplified and adapted to the observable spectrum behavior. Based on the physical meaning of the model parameters, we propose a novel approach for SoH assessment combining parameters of the impedance spectrum by building the ratio of the solid electrolyte interphase (SEI) resistance to the total resistance of SEI and the charge transfer. This ratio characterizes the charge-transfer efficiency at the electrodes’ surfaces and should decrease systematically with SoH. Four different cells of the same type were cycled 400 times for the method validation, and impedance spectroscopy was performed at every 50th cycle. The results show a systematic correlation between the proposed ratio and the number of cycles on individual cell parameters, which build the basis of a novel online method of SoH assessment.

Maximum approximate likelihood estimation of general continuous-time state-space models

Continuous-time state-space models (SSMs) are flexible tools for analysing irregularly sampled sequential observations that are driven by an underlying state process. Corresponding applications typically involve restrictive assumptions concerning linearity and Gaussianity to facilitate inference on the model parameters via the Kalman filter. In this contribution, we provide a general continuous-time SSM framework, allowing both the observation and the state process to be non-linear and non-Gaussian. Statistical inference is carried out by maximum approximate likelihood estimation, where multiple numerical integration within the likelihood evaluation is performed via a fine discretization of the state process. The corresponding reframing of the SSM as a continuous-time hidden Markov model, with structured state transitions, enables us to apply the associated efficient algorithms for parameter estimation and state decoding. We illustrate the modelling approach in a case study using data from a longitudinal study on delinquent behaviour of adolescents in Germany, revealing temporal persistence in the deviation of an individual's delinquency level from the population mean.

An Accelerated Thrombosis Model for Computational Fluid Dynamics Simulations in Rotary Blood Pumps

Purpose Thrombosis ranks among the major complications in blood-carrying medical devices and a better understanding to influence the design related contribution to thrombosis is desirable. Over the past years many computational models of thrombosis have been developed. However, numerically cheap models able to predict localized thrombus risk in complex geometries are still lacking. The aim of the study was to develop and test a computationally efficient model for thrombus risk prediction in rotary blood pumps. Methods We used a two-stage approach to calculate thrombus risk. The first stage involves the computation of velocity and pressure fields by computational fluid dynamic simulations. At the second stage, platelet activation by mechanical and chemical stimuli was determined through species transport with an Eulerian approach. The model was compared with existing clinical data on thrombus deposition within the HeartMate II. Furthermore, an operating point and model parameter sensitivity analysis was performed. Results Our model shows good correlation (R2 > 0.93) with clinical data and identifies the bearing and outlet stator region of the HeartMate II as the location most prone to thrombus formation. The calculation of thrombus risk requires an additional 10–20 core hours of computation time. Conclusion The concentration of activated platelets can be used as a surrogate and computationally low-cost marker to determine potential risk regions of thrombus deposition in a blood pump. Relative comparisons of thrombus risk are possible even considering the intrinsic uncertainty in model parameters and operating conditions.

Correlations of Rock-Physics Model Parameters From Bayesian Analysis: Pressure- and Porosity-Dependent Models Applied to Unconsolidated Sands

Correlations of rock-physics model inputs are important to know to help design informative prior models within integrated reservoir-characterization workflows. A Bayesian framework is optimal to determine such correlations. Within that framework, we use velocity and porosity measurements on unconsolidated, dry, and clean sands. Three pressure- and three porosity-dependent rock-physics models are applied to the data to examine relationships among the inputs. As with any Bayesian formulation, we define a prior model and calculate the likelihood in order to evaluate the posterior. With relatively few inputs to consider for each rock-physics model, we found that sampling the posterior exhaustively to be convenient. The results of the Bayesian analyses are multivariate histograms that indicate most likely values of the input parameters given the data to which the rock-physics model was fit. When the Bayesian procedure is repeated many times for the same data, but with different prior models, correlations emerged among the input parameters in a rock-physics model. These correlations were not known previously. Implications, for the pressure- and porosity-dependent models examined here, are that these correlations should be utilized when applying these models to other relevant data sets. Furthermore, additional rock-physics models should be examined similarly to determine any potential correlations in their inputs. These correlations can then be taken advantage of in forward and inverse problems posed in reservoir characterization.

The Application of a Genetic Algorithm to the Optimization of a Mesoscale Model for Emergency Response

Besides solving the equations of momentum, heat, and moisture transport on the model grid, mesoscale weather models must account for subgrid-scale processes that affect the resolved model variables. These are simulated with model parameterizations, which often rely on values preset by the user. Such ‘free’ model parameters, along with others set to initialize the model, are often poorly constrained, requiring that a user select each from a range of plausible values. Finding the values to optimize any forecasting tool can be accomplished with a search algorithm, and one such process – the genetic algorithm (GA) – has become especially popular. As applied to modeling, GAs represent a Darwinian process – an ensemble of simulations is run with a different set of parameter values for each member, and the members subsequently judged to be most accurate are selected as ‘parents’ who pass their parameters onto a new generation. At the Department of Energy’s Savannah River Site in South Carolina, we are applying a GA to the Regional Atmospheric Modeling System (RAMS) mesoscale weather model, which supplies input to a model to simulate the dispersion of an airborne contaminant as part of the site’s emergency response preparations. An ensemble of forecasts is run each day, weather data are used to ‘score’ the individual members of the ensemble, and the parameters from the best members are used for the next day’s forecasts. As meteorological conditions change, the parameters change as well, maintaining a model configuration that is best adapted to atmospheric conditions.