A5084881904- Numerical methods in engineering
- COVID-19 epidemiological studies
- Advanced Numerical Analysis Techniques
- Image and Signal Denoising Methods
- Model Reduction and Neural Networks
- Mathematical and Theoretical Epidemiology and Ecology Models
- Advanced Numerical Methods in Computational Mathematics
- Network Security and Intrusion Detection
- Fractional Differential Equations Solutions
- Opinion Dynamics and Social Influence
- Computational Physics and Python Applications
- Numerical methods for differential equations
University of Turin
2024
COMSATS University Islamabad
2022-2024
Istituto Nazionale di Alta Matematica Francesco Severi
2024
<abstract> <p>Artificial neural networks (ANNs) have transformed machine learning and computational intelligence by providing unprecedented powers in modeling complicated data addressing a wide range of challenges. In the field ANNs, back propagation is key approach for training networks. However, obtaining optimum network efficiency while tackling over fitting controlling uncertainty difficult task. The present study employs Bayesian Regularization Method with Neural Network...
Time delays play an important part in modeling the fact that one cannot be communicable for a long time after becoming sick. Delay can triggered by variety of epidemiological situations. The most egregious causes delay are infection latency vector and infected host. dynamics susceptible, infected, recovered cross-immune (SIRC) classed-based model having time-delay transmission spread COVID-19 abbreviated as (SIRC-CTC-19) investigated this study using intelligent numerical computing paradigm...
<title>Abstract</title> In this article, we present a new numerical algorithm to detect the kernel shape parameter and subdomain radius size within partition of unity method for scattered data interpolation. Since an adaptive search such hyperparameters is quite expensive from computational point view, propose use leave-one-out cross validation technique combined with univariate global optimization tools class Lipschitz derivative-free method. Particularly, consider efficient strategies...
In this article we present an adaptive residual subsampling scheme designed for kernel based interpolation. For optimal choice of the shape parameter consider some cross validation (CV) criteria, using efficient algorithms $k$-fold CV and leave-one-out (LOOCV) as a special case. framework, selection within method is totally automatic, provides highly reliable accurate results any kind kernel, guarantees existence uniqueness interpolant. Numerical show performance new scheme, also giving...