Search

AbstractThe most common and contagious bacterial skin disease i.e. skin sores (impetigo) mostly affects newborns and young children. On the face, particularly around the mouth and nose area, as well as on the hands and feet, it typically manifests as reddish sores. In this study, a neuro-evolutionary global algorithm is introduced to solve the dynamics of nonlinear skin sores disease model (SSDM) with the help of an artificial neural network. The global genetic algorithm is integrated with local sequential quadratic programming (GA-LSQP) to obtain the optimal solution for the proposed model. The designed differential model of skin sores disease is comprised of susceptible (S), infected (I), and recovered (R) categories. An activation function based neural network modeling is exploited for skin sores system through mean square error to achieve best trained weights. The integrated approach is validated and verified through the comparison of results of reference Adam strategy with absolute error analysis. The absolute error results give accuracy of around 10−11 to 10−5, demonstrating the worthiness and efficacy of proposed algorithm. Additionally, statistical investigations in form of mean absolute deviation, root mean square error, and Theil’s inequality coefficient are exhibited to prove the consistency, stability, and convergence criteria of the integrated technique. The accuracy of the proposed solver has been examined from the smaller values of minimum, median, maximum, mean, semi-interquartile range, and standard deviation, which lie around 10−12 to 10−2. [ABSTRACT FROM AUTHOR]

This investigation aims to investigate the pine wilt disease model (PWDM) employing hybrid bio-inspired algorithm. The artificial neural networks-based genetic algorithm (ANNs-GA) as global search and sequential quadratic programming (SQP) serve as local search framework. The model consists of two populations, i.e. host (h) and vector (v). There are four classes in host population representing susceptible host (S h) , exposed host (E h) , asymptomatic host (A h) and infectious host (I h) whereas in vector susceptible (S v) and infectious (I v) class are present. Activation function is introduced for the formulation of the fitness-based function as mean squared error by using nonlinear PWD equations for the accomplishment of ANNs-GASQP paradigm. The stability, robustness and effectiveness of proposed paradigm is comparatively evaluated through Adam numerical scheme with absolute error analysis. Computational complexity of GASQP is determined by convergence criteria of best global weight, fitness evaluation, time, generations, iterations, function counts and mean square error. Moreover, the statistical analysis is performed via Theil's inequality coefficients (TICs), mean of absolute deviation (MAD) and root mean squared error (RMSE) for multiple trials of ANNs-GASQP. Results reveal that accuracy is obtained up to 3–11 decimal places which proves the reliability of proposed ANNs-GASQP solver. [ABSTRACT FROM AUTHOR]

The major purpose of this article is to exploit the strength of the Intelligent Back-propagated Neural Networks of Levenberg Marquardt Technique (IBNN-LMT) to study three-dimensional (3D) squeezed flow model of carbon nanotubes (SFM-CNTs) relying on water in a revolving network with a rigid ground wall. The impact of magnetohydrodynamic (MHD) and thermal radiation has been investigated. Similarity transformation is utilized to convert partial differential equations (PDEs) into ordinary differential equations (ODEs). For numerous nanofluids constructed of SWCNT and MWCNT, the influence of each parameter on velocity, temperature, Bejan number, and entropy production is estimated. The overall entropy optimization was also computed. The major outcome of this research is to examine the impacts of flowing parameters on CNTs when squeezing parameters are changed. Moreover, the estimated solution is evaluated for designed SFM-CNTs by using a testing method and comparing it to a standard solution that has been backed up by performance studies based on MSE convergence, error histogram, and regression studies. The velocity profile f (χ) along y-axis intensifies with the intensification in S , φ ,and A. Where Ω gives a dual performance with the increment in the function, as with the increase in M , f (χ) provides decreasing performance. The temperature function θ (χ) increase as the increment in S , Ec ,and Ec m and decrease with the increase in φ and R. The solution is accurate up to 4 to 10 decimal places which proves the worth and effectiveness of the proposed IBNN-LMT solver. [ABSTRACT FROM AUTHOR]