Classical Error Research Articles

A multi-layer neural network approach for the stability analysis of the Hepatitis B model

In the present study, we explore the dynamics of Hepatitis B virus infection, a significant global health issue, through a newly developed dynamics system. This model is distinguished by its inclusion of asymptomatic carriers and the impact of vaccination and treatment strategies. Compared to Hepatitis A, Hepatitis B poses a more serious health risk, with some cases progressing from acute to chronic. To diagnose and predict disease recurrence, the basic reproduction number (R0) is calculated. We investigate the stability of the disease’s dynamics under different conditions, using the Lyapunov function to confirm our model’s global stability. Our findings highlight the relevance of vaccination and early treatment in reducing Hepatitis B virus spread, making them a useful tool for public health efforts aiming at eradicating Hepatitis B virus. In our research, we investigate the dynamics of a specific model that is characterized by a system of differential equations. This work uses deep neural networks (DNNs) technique to improve model accuracy, proving the use of DNNs in epidemiological modeling. Additionally, we want to find the curves that suit the target solutions with the minimum residual errors. The simulations we conducted demonstrate our methodology’s capability to accurately predict the behavior of systems across various conditions. We rigorously test the solutions obtained via the DNNs by comparing them to benchmark solutions and undergoing stages of testing, validation, and training. To determine the accuracy and reliability of our approach, we perform a series of analyses, including convergence studies, error distribution evaluations, regression analyses, and detailed curve fitting for each equation.

Helmholtz FEM solutions are locally quasi-optimal modulo low frequencies

Abstract For h-FEM discretisations of the Helmholtz equation with wavenumber k, we obtain k-explicit analogues of the classic local FEM error bounds of Nitsche and Schatz (Math. Comput. 28(128), 937–958 1974), Wahlbin (1991, §9), Demlow et al.(Math. Comput. 80(273), 1–9 2011), showing that these bounds hold with constants independent of k, provided one works in Sobolev norms weighted with k in the natural way. We prove two main results: (i) a bound on the local $$H^1$$ H 1 error by the best approximation error plus the $$L^2$$ L 2 error, both on a slightly larger set, and (ii) the bound in (i) but now with the $$L^2$$ L 2 error replaced by the error in a negative Sobolev norm. The result (i) is valid for shape-regular triangulations, and is the k-explicit analogue of the main result of Demlow et al. (Math. Comput. 80(273), 1–9 2011). The result (ii) is valid when the mesh is locally quasi-uniform on the scale of the wavelength (i.e., on the scale of $$k^{-1}$$ k - 1 ) and is the k-explicit analogue of the results of Nitsche and Schatz (Math. Comput. 28(128), 937–958 1974), Wahlbin (1991, §9). Since our Sobolev spaces are weighted with k in the natural way, the result (ii) indicates that the Helmholtz FEM solution is locally quasi-optimal modulo low frequencies (i.e., frequencies $$\lesssim k$$ ≲ k ). Numerical experiments confirm this property, and also highlight interesting propagation phenomena in the Helmholtz FEM error.

Impact of tooth loss and patient characteristics on coronary artery calcium score classification and prediction.

This study, for the first time, explores the integration of data science and machine learning for the classification and prediction of coronary artery calcium (CAC) scores. It focuses on tooth loss and patient characteristics as key input features to enhance the accuracy of classifying CAC scores into tertiles and predicting their values. Advanced analytical techniques were employed to assess the effectiveness of tooth loss and patient characteristics in the classification and prediction of CAC scores. The study utilized data science and machine learning methodologies to analyze the relationships between these input features and CAC scores. The research evaluated the individual and combined contributions of patient characteristics and tooth loss on the accuracy of identifying individuals at higher risk of cardiovascular issues related to CAC. The findings indicated that patient characteristics were particularly effective for tertile classification of CAC scores, achieving a classification accuracy of 75%. Tooth loss alone provided more accurate predicted CAC scores with the smallest average mean squared error of regression and with a classification accuracy of 71%. The combination of patient characteristics and tooth loss demonstrated improved accuracy in identifying individuals at higher risk with the best sensitivity rate of 92% over patient characteristics (85%) and tooth loss (88%). The results highlight the significance of both oral health indicators and patient characteristics in predictive modeling and classification tasks for CAC scores. By integrating data science and machine learning techniques, the research provides a foundation for further exploration of the connections between oral health, patient characteristics, and cardiovascular outcomes, emphasizing their importance in advancing the accuracy of CAC score classification and prediction.

Electricity consumption forecasting in Brazil: A structural Bayesian dynamic approach

ABSTRACT The main aim of this paper is to project electricity consumption for the five Brazilian regions using the Bayesian Structural Time-series (BSTS) which presents the best prediction evaluated within the sample. This methodology estimates fourteen models, each with a different specification in terms of its functional form, which ensures flexibility and can vary in terms of levels, trends, and treatment of seasonal fluctuations, as well as dealing with different hypotheses on regression errors or disturbances. The forecast validation criteria calculated for a 24-month horizon showed very satisfactory results. The findings corroborated expectations regarding the suitability of this methodology for drawing up projections. In every case, the forecasting error was 5% or less, which is the reference figure for distribution utilities. In the Center-West, Southeast and South regions, this indicator fell below 3%. The model thus appears to be a robust tool for utilities to project electricity demands.

Nonlinear Dynamic Analysis of Riemann–Liouville Fractional-Order Damping Giant Magnetostrictive Actuator

Abstract In view of the large errors in the integer-order prediction model of the current giant magnetostrictive actuator (GMA), existing studies have shown that the fractional-order theory can improve the classical integer-order error situation. To this end, the Riemann–Liouville (R–L) fractional-order calculus theory is applied to the damping part of the GMA system; based on the averaging method and the power series method, the analytical and numerical solutions of the system are obtained, respectively, the motion of the GMA system is obtained through simulation, the parameters affecting the main resonance response of the system are analyzed as well as the motion characteristics of the system under the parameters, and the bifurcation and chaotic characteristics of the system are analyzed qualitatively and quantitatively. It is shown that the fractional-order model can improve the prediction accuracy of the system, the fractional order has a significant effect on the motion of the system, and the interval of the periodical motion parameter is less than an integer when the order of the damping term is (0,1), and the system can be induced to shift to periodic motion by changing the parameters.

Thermal Runaway Warning of Lithium Battery Based on Electronic Nose and Machine Learning Algorithms

Characteristic gas detection can be an efficient way to predict the degree of thermal runaway of a lithium battery. In this work, a sensor array consisting of three commercial MOS sensors was employed to discriminate between three target gases, CO, H2 and a mixture of the two, which are characteristic gases released during the thermal runaway of lithium batteries. In this work, an integrated model that makes the classification stage results one of the feature inputs for the concentration regression stage was employed, successfully reducing the RMSE of the concentration regression results. In addition, we also explored the influence of the selection of the response time length on the classification and regression tasks, achieving the best results in a short time through the optimum algorithm. To assess the impact of time duration sensor data on the results, we selected four time windows of different length and extracted the corresponding sensor response data for subsequent processing. Initially, principal component analysis (PCA) was used to visualise the clustering of the three target gas samples at room temperature, providing a preliminary data analysis. For the classification phase, we chose three classification algorithms—MLP (Multilayer Perceptron), ELM (Extreme Learning Machine), and SVM (Support Vector Machine)—and performed a comprehensive comparison of their classification and generalisation abilities using grid search for hyperparameter optimisation and five-fold cross-validation. The results demonstrated that MLP achieved 99.23% classification accuracy during the 20 s response period. In the concentration regression phase, we combined the classification results with the raw features to create a new feature set, which was then input into a multi-output MLP regression model. The root mean square error (RMSE) employing the new feature set was used to measure the prediction error. Ultimately, the findings showed that the input of combined features significantly reduced the regression error for the mixed gas.

Advancing urban health in Portugal: exploring liveability and its association with mental morbidity

Abstract Background As cities face challenges posed by urbanisation, it becomes essential to understand how city planning can contribute to protecting public health. In this study, we aimed to assess the liveability of different areas in Lisbon, Portugal, by developing a liveability index at the parish level. Secondly, we aimed to explore its association with hospitalisation due to mental disorders. Methods The liveability index was built based on the World Health Organisation’s Urban Health Index methodology. We obtained data on liveability related to housing, socio-economic conditions and access to services (e.g. healthcare) from the 2011 census and other open data sources for Lisbon’s parishes (n = 22). Data on hospital admissions due to mental disorders was sourced at the parish level from the national database for hospital morbidity for the period 2013-2016 and sex-age-standardised. Binomial negative regression was employed to estimate the association between the liveability index tertiles and observed hospital admissions. We used the expected number of hospitalisations as the offset variable and tested for spatial autocorrelation among the regression residuals. Results Our analysis showed that living in the most liveable parishes is associated with a significant decrease in the standardised admission ratio due to mental disorders, compared to living in the least liveable areas (Incidence Relative Ratio=0.643; 95% CI: 0.427, 0.967). We did not observe any geographical pattern in the regression residuals (Moran’s I= -0.035, p = 0.427). Conclusions Our findings show disparities in liveability among Lisbon’s parishes and identify a protective association between living in higher liveability areas and hospital admissions due to mental disorders. This work should prompt further studies concerning this subject to inform urban planning policies to improve liveability and equally reduce the risk of mental health-related harm within cities. Key messages • A spatial index to assess liveability in urban areas was developed. The association between the liveability of Lisbon’s parishes and hospital admissions due to mental disorders was explored. • We found a significant protective association between higher liveability and hospital admissions due to mental disorders. This work is relevant to inform the implementation of urban planning policies.

Bayesian Empirical Likelihood Regression for Semiparametric Estimation of Optimal Dynamic Treatment Regimes.

We propose a semiparametric approach to Bayesian modeling of dynamic treatment regimes that is built on a Bayesian likelihood-based regression estimation framework. Methods based on this framework exhibit a probabilistic coherence property that leads to accurate estimation of the optimal dynamic treatment regime. Unlike most Bayesian estimation methods, our proposed method avoids strong distributional assumptions for the intermediate and final outcomes by utilizing empirical likelihoods. Our proposed method allows for either linear, or more flexible forms of mean functions for the stagewise outcomes. A variational Bayes approximation is used for computation to avoid common pitfalls associated with Markov Chain Monte Carlo approaches coupled with empirical likelihood. Through simulations and analysis of the STAR*D sequential randomized trial data, our proposed method demonstrates superior accuracy over Q-learning and parametric Bayesian likelihood-based regression estimation, particularly when the parametric assumptions of regression error distributions may be potentially violated.

Deterministic equivalent and error universality of deep random features learning*

Abstract This manuscript considers the problem of learning a random Gaussian network function using a fully connected network with frozen intermediate layers and trainable readout layer. This problem can be seen as a natural generalization of the widely studied random features model to deeper architectures. First, we prove Gaussian universality of the test error in a ridge regression setting where the learner and target networks share the same intermediate layers, and provide a sharp asymptotic formula for it. Establishing this result requires proving a deterministic equivalent for traces of the deep random features sample covariance matrices which can be of independent interest. Second, we conjecture the asymptotic Gaussian universality of the test error in the more general setting of arbitrary convex losses and generic learner/target architectures. We provide extensive numerical evidence for this conjecture. In light of our results, we investigate the interplay between architecture design and implicit regularization.

Machine Learning for the Genomic Prediction of Growth Traits in a Composite Beef Cattle Population.

The adoption of genomic selection is prevalent across various plant and livestock species, yet existing models for predicting genomic breeding values often remain suboptimal. Machine learning models present a promising avenue to enhance prediction accuracy due to their ability to accommodate both linear and non-linear relationships. In this study, we evaluated four machine learning models-Random Forest, Support Vector Machine, Convolutional Neural Networks, and Multi-Layer Perceptrons-for predicting genomic values related to birth weight (BW), weaning weight (WW), and yearling weight (YW), and compared them with other conventional models-GBLUP (Genomic Best Linear Unbiased Prediction), Bayes A, and Bayes B. The results demonstrated that the GBLUP model achieved the highest prediction accuracy for both BW and YW, whereas the Random Forest model exhibited a superior prediction accuracy for WW. Furthermore, GBLUP outperformed the other models in terms of model fit, as evidenced by the lower mean square error values and regression coefficients of the corrected phenotypes on predicted values. Overall, the GBLUP model delivered a superior prediction accuracy and model fit compared to the machine learning models tested.

Optimal Subsampling for Functional Quasi-Mode Regression with Big Data

We propose investigating optimal subsampling for functional regression with massive datasets based on the mode value, which is referred to as functional quasi-mode regression, to reduce data volume and alleviate computational burden. Using data-adaptive weights derived from regression residuals, the suggested regression offers enhanced robustness against nonnormal errors compared to traditional least squares or maximum likelihood estimation methods. To estimate the model, we employ B-spline basis functions to approximate the functional coefficient and include a penalty term in the objective function for enforcing smoothness in the resulting estimator. We adopt a computationally efficient mode-expectation-maximization algorithm, augmented by a Gaussian kernel, for numerical estimation. Under mild regularity conditions, we derive the asymptotic distributions of both full data and subsample quasi-mode estimators. The optimal subsampling probabilities by minimizing the asymptotic variance-covariance matrix under A- and L-optimality criteria are identified. These optimal probabilities rely on the full data estimate, prompting the development of a two-step algorithm to approximate the optimal subsampling procedure. The resultant algorithm is processing-efficient and can significantly reduce computational time compared to the full data approach. We also establish the asymptotic normality of the quasi-mode estimator obtained through this two-step algorithm. To assess finite sample performance, we conduct Monte Carlo simulations and analyze air quality data, showcasing the effectiveness of the developed estimator. Supplemental materials for this article are available online.

Heat transfer enhancement using ternary hybrid nanofluid for cross-viscosity model with intelligent Levenberg-Marquardt neural networks approach incorporating entropy generation

Thermal heat transfer analysis of trihybrid nanofluids using an intelligent Levenberg-Marquardt neural network (ANN-LMA) approach, with a focus on entropy generation, has been conducted. The flow equations were modeled in Cartesian coordinates and simplified using dimensionless variables. Partial differential equations were converted into ordinary differential equations through appropriate similarity transformations. These ordinary differential equations were then solved using the finite element method applied to a data set evaluated from (ANN-LMA) approach. This dataset can be input into MATLAB to generate predicted solutions for flow patterns. The ANN-LMA technique was employed to evaluate the efficiency of heat transfer characteristics for nanofluids in various scenarios. Incorporating carbon nanotubes (both single-wall (SWCNT) and multi-wall (MWCNT)) along with iron oxide in water, the study demonstrates their effectiveness in enhancing heat transfer. These nanofluids have broad industrial applications, such as in coolant enhancement, cancer therapy, and solar radiation management, and show promising results. This study specifically examines the flow properties of water-based CNT cross-trihybrid nanofluids over a convectively heated surface, leveraging their unique characteristics. Improvements in heat transfer are achieved through the introduction of dissipative heat, thermal radiation, and external heat sources or sinks. The performance of the computational solver was assessed using error histograms, regression analyses, and Mean Squared Error (MSE) results. The physical significance of the designed factors is graphically depicted and discussed in detail. It was found that radiative heat increases surface heat energy through substantial accumulation, thereby enhancing heat transfer properties, while dissipative heat, due to Joule dissipation and other external sources, significantly raises the fluid temperature.

Simulation case study of precise orbit determination for IGSO satellites using onboard Ka/GNSS observations

Abstract Inter-satellite links can provide a more accurate space reference for IGSO satellites than onboard GNSS side-lobe signals. In this study, POD quality is analyzed based on onboard Ka/GNSS observations by utilizing a simulated IGSO satellite orbit. Considering the similar orbit altitude, we first select three IGSO satellites from BDS-3 as target satellites. These satellites have actual Ka-band measurements available, along with other BDS-3 satellites and ground anchor stations, allowing us to assess the POD performance. The Ka-band availability of these IGSO satellites can serve as a means to evaluate the maximum utilization of BDS Ka-band resources. In terms of the POD results, the root mean square (RMS) of the Ka-band residuals can reach 10.9 cm, and the orbit consistency in the 3D direction is better than 0.35 m. In addition, simulations are conducted for onboard GNSS, inter-satellite link (ISL), and ground anchor-satellite link (GSL), considering the different constraints on the Ka-band resources. With only GNSS measurements, the 3D orbit accuracy is approximately 1.5 m, but when additional ISL and GSL measurements are considered, the POD accuracy can surpass 0.28 m. These results illustrate that incorporating Ka-band measurements can effectively enhance the POD accuracy for high-orbit satellites.

Risk management committee and earnings management: evidence from an emerging market

PurposeThis study examines whether the risk management committee (RMC) mitigates earnings management (EM) in Nigeria.Design/methodology/approachThe study used a sample of 365 firm-year observations of Nigerian-listed nonfinancial companies from 2018 to 2022. Driscoll and Kraay’s fixed-effect standard error regression model is used to test the hypotheses.FindingsThe study finds that RMC size, expertise, meeting frequency and membership overlapping with the audit committee have a negative effect on both accrual earnings management (AEM) and real earnings management (REM). While RMC independence is found to have a negative effect on REM. Moreover, additional tests reveal that RMC effectiveness is significantly associated with lower EM practices. Further analysis using the industry level finds that RMC attributes mitigate EM practices in some industries. The results remain after rigorous, robust analysis for endogeneity and alternative regressions.Research limitations/implicationsThis study is limited to a sample of Nigerian-listed nonfinancial service companies for a period of five years, resulting in the non-generalizability of the findings to different contexts as the countries’ internal policies and regulations varied.Practical implicationsThe findings have important implications for regulators, policymakers and investors that a stand-alone RMC can effectively help to evaluate potential risk activities and implement a proper risk management system, thereby mitigating EM practices. The result can help investors, analysts and other stakeholders across the international community in considering RMC information to evaluate potential risk and earnings management practices.Originality/valueFollowing the NCCG 2018 reform in Nigeria that requires listed firms to create a standalone RMC, this study is among the earliest that examines the effect of RMC attributes on EM practices and emerging markets. As such, the findings may draw the attention of regulators and policymakers across the African market and the international community to the monitoring role of RMC attributes in mitigating EM practices.

Feature selection with annealing for forecasting financial time series

Stock market and cryptocurrency forecasting is very important to investors as they aspire to achieve even the slightest improvement to their buy-or-hold strategies so that they may increase profitability. However, obtaining accurate and reliable predictions is challenging, noting that accuracy does not equate to reliability, especially when financial time-series forecasting is applied owing to its complex and chaotic tendencies. To mitigate this complexity, this study provides a comprehensive method for forecasting financial time series based on tactical input–output feature mapping techniques using machine learning (ML) models. During the prediction process, selecting the relevant indicators is vital to obtaining the desired results. In the financial field, limited attention has been paid to this problem with ML solutions. We investigate the use of feature selection with annealing (FSA) for the first time in this field, and we apply the least absolute shrinkage and selection operator (Lasso) method to select the features from more than 1000 candidates obtained from 26 technical classifiers with different periods and lags. Boruta (BOR) feature selection, a wrapper method, is used as a baseline for comparison. Logistic regression (LR), extreme gradient boosting (XGBoost), and long short-term memory are then applied to the selected features for forecasting purposes using 10 different financial datasets containing cryptocurrencies and stocks. The dependent variables consisted of daily logarithmic returns and trends. The mean-squared error for regression, area under the receiver operating characteristic curve, and classification accuracy were used to evaluate model performance, and the statistical significance of the forecasting results was tested using paired t-tests. Experiments indicate that the FSA algorithm increased the performance of ML models, regardless of problem type. The FSA hybrid models showed better performance and outperformed the other BOR models on seven of the 10 datasets for regression and classification. FSA-based models also outperformed Lasso-based models on six of the 10 datasets for regression and four of the 10 datasets for classification. None of the hybrid BOR models outperformed the hybrid FSA models. Lasso-based models, excluding the LR type, were comparable to the best models for six of the 10 datasets for classification. Detailed experimental analysis indicates that the proposed methodology can forecast returns and their movements efficiently and accurately, providing the field with a useful tool for investors.

Heterogeneity-aware integrative regression for ancestry-specific association studies.

Ancestry-specific proteome-wide association studies (PWAS) based on genetically predicted protein expression can reveal complex disease etiology specific to certain ancestral groups. These studies require ancestry-specific models for protein expression as a function of SNP genotypes. In order to improve protein expression prediction in ancestral populations historically underrepresented in genomic studies, we propose a new penalized maximum likelihood estimator for fitting ancestry-specific joint protein quantitative trait loci models. Our estimator borrows information across ancestral groups, while simultaneously allowing for heterogeneous error variances and regression coefficients. We propose an alternative parameterization of our model that makes the objective function convex and the penalty scale invariant. To improve computational efficiency, we propose an approximate version of our method and study its theoretical properties. Our method provides a substantial improvement in protein expression prediction accuracy in individuals of African ancestry, and in a downstream PWAS analysis, leads to the discovery of multiple associations between protein expression and blood lipid traits in the African ancestry population.

Does financial expertise influence Islamic bank risk-taking?

PurposeThis study investigated how the financial expertise of the board of directors, risk management committee (RMC), audit committee (AC) and Shariá Supervisory Board (SSB) influences the risk-taking of Islamic banks.Design/methodology/approachThe study utilized unbalanced panel data for a sample of 43 full-fledged Islamic banks from 15 countries over 12 years (2010–2021). We employed feasible generalized least squares (FGLS) and heteroskedastic panels corrected standard errors (HPCSE) regression regressions as the primary estimation methods and used a two-step system generalized method of moments (GMM) estimator for robustness checks.FindingsThe results indicate that board financial expertise decreases insolvency and credit risks. Similarly, AC financial expertise and SSB financial expertise reduce insolvency and portfolio risks but increase credit risk. In contrast, RMC financial expertise raises insolvency risk. The remaining relationships are statistically insignificant.Research limitations/implicationsDue to the lack of disclosure regarding the educational and professional background of the board and committee members in the annual reports of some Islamic banks, this research used a sample of only 43 full-fledged Islamic banks operating in fifteen countries from 2010 to 2021.Practical implicationsThe findings can assist both local and international regulators in revising corporate governance codes and risk management guidelines in such a way as to ensure that the financial experts appointed to the board, AC, RMC and SSB, are capable of controlling excessive risk-taking behavior in Islamic banks.Originality/valueThis study contributes to the literature by providing comprehensive empirical evidence that corporate governance financial expertise influences the risk-taking behavior of Islamic banks.

Multilayer deep-learning intelligent computing for the numerical analysis of unsteady heat and mass transfer in MHD Carreau Nanofluid model

The objective of this article is to investigate the mechanism of unsteady heat and mass transfer (HMT) in a magnetohydrodynamics Carreau nanofluid flow (MHD-CNFF). To accomplish this, we utilized a novel artificial intelligence-based (AI) method, deep learning predictive technique combined with Levenberg-Marquardt scheme (DLPT-LMS). The similarity transformation is applied to convert the partial differential equations (PDEs) into a set of non-linear ordinary differential equations (ODEs). We numerically solved these resulting ODEs using the Adam numerical approach in sophisticated “Mathematica” software. The influence of Brownian motion parameter, thermophoresis parameters, Prandtl number, Lewis number, and mass transfer parameters on the temperature, velocity, and concentration profile is analyzed using a synthetic dataset. This evaluation is conducted across different variation of MHD-CNFF by leveraging DLPT-LMS. The absolute error (AE) across various iteration of MHD-CNFF demonstrated a progressive drop, indicating the accuracy of DLPT-LMS. The outcomes of this investigation revealed that the AE ranged from 10-3 to 10-8 which shows a minimum error between actual and predicted value. Additionally, the MSE confirmed the accuracy of proposed DLPT-LMS in predicting the behavior of velocity, temperature, and concentration profiles, with lower values showing better predictions. The model accuracy was reinforced by performance results, including regression analysis and error histograms. Error values gradually decreased during training, validation, and testing phases, exhibiting a robust convergence and indicating the highly reliability of AI-based algorithm for investigating intricate fluid dynamics in MHD-CNFF systems.

Navigating stroke care: Geospatial assessment of regional stroke center accessibility: Geospatial Assessment of Stroke Centers

IntroductionReducing time between stroke onset and hospital intervention is crucial for positive outcomes in stroke patients. While EMS utilization decreases time to intervention, many US regions are not within timely proximity to an advanced-care-capable stroke center (ASC), defined as a comprehensive or thrombectomy-capable center. This study aims to utilize geographic methodology to identify regions in Wisconsin with both high stroke mortality and low physical accessibility to certified stroke centers (SCs), particularly ASCs. MethodsGeocoded mortality records for stroke death between 2015 and 2020 were accessed from the Wisconsin Department of Health Services. Indirectly age-standardized mortality ratios (SMRs) were estimated continuously across Wisconsin using adaptive spatial filtering and mortality records at the census block group level; the surface was then averaged by census tract for tract level SMRs. Addresses for SC locations within Wisconsin and bordering states were collected, and drive times from Wisconsin census tract centroids to the nearest SC subtypes were estimated. Drive times and mortality ratios were evaluated at the tract level alongside Rural-Urban Commuting Area (RUCA) codes. Spatial error regression modeling was used to determine RUCA classifications with the highest stroke risk independent of accessibility to stroke centers. ResultsApproximately 50%, 68%, and 78% of Wisconsin residents resided within 30, 45, and 60 minutes of an ASC, respectively. Median drive time from census tract centroids to the nearest ASC were highest for rural tracts (M=90 minutes, IQR=68-115) compared to small-town (M=82 minutes, IQR=49-113), micropolitan (M=53 minutes, IQR=43-77), and metropolitan tracts (M=19 minutes, IQR=11-35; p<0.001). Clusters of high stroke SMRs were found in urban centers as well as rural areas irrespective of county declinations. Spatial regression modeling suggested small-town census tracts had the highest SMR irrespective of physical accessibility to care and spatial correlation. In small-town census tracts >45 minutes from the nearest ASC, the median stroke SMR was 1.12 (IQR=0.94-1.40) with 226,000 residents and 150 stroke deaths per year. ConclusionSmall-town areas are associated with both long drive distance to ASC locations and high stroke mortality. Geographical analyses reveal apparent stroke care deserts and may inform strategic allocation of emergency medicine resources and coverage.

Development of a machine learning based fileless malware filter system for cyber-security

Over the years, the increased rate of perturbated malware based cyber-attack has presented many challenges and triggered the need for immediate solution all over the world. This was addressed in this paper development of a machine learning based fileless malware filter system for cyber security. Fileless malware which can come inform of Memory Resident Fileless malware or Windows Registry fileless malware are known to have no executable files, resides in the system memory or the windows registry. It doesn’t write any files to disk making it very challenging to detect us[1]ing traditional signature-based methods. It often leverage legitimate tools such as Windows Management Instrumentation and PowerShell to carry out its malicious activities. The methods used were data collection, data extraction, Deep Neural Network (DNN), activation function, training algorithm and classification. The methods were designed using structural and mathematical approaches which employed architectural diagrams, flow charts and self-defining equations to develop the new system. The training of the DNN was done using Gradient Descent Algorithms (GDA) to generate the malware filter algorithm. The filters were implemented with Simulink, tested and validated. The results were also evaluated using Regression (R) and Mean Square Error (MSE analyzer) and it showed R values of 0.9931 and MSE performance also recorded 0.002088Mu. This implied that the filter developed was able to detect and remove malware on the network.