Artificial Neural Network (ANN)-Based Analysis and Optimal Control of Smoking Dynamics with Global Sensitivity Assessment
| dc.contributor.author | Omrane, Ines Ben | |
| dc.contributor.author | Ullah, Naeem | |
| dc.contributor.author | Alhamzi, Ghaliah | |
| dc.contributor.author | Jeelani, Mohammadi Begum | |
| dc.date.accessioned | 2026-08-06T10:55:37Z | |
| dc.date.available | 2026-08-06T10:55:37Z | |
| dc.date.issued | 2026-06-01 | |
| dc.description.abstract | The main objective of this study is to investigate smoking dynamics, identify the most influential factors governing smoking behavior, and develop effective intervention strategies through the integration of fractional-order modeling, sensitivity analysis, optimal control theory, and artificial neural networks (ANNs). A nonlinear fractional-order compartmental model is formulated by dividing the population into potential smokers, light smokers, heavy smokers, and quit smokers. The smoking reproduction number is derived to characterize the transmission and persistence of smoking behavior within the population. To determine the impact of model parameters on smoking dynamics, both normalized forward sensitivity analysis and global sensitivity analysis based on Latin Hypercube Sampling (LHS) with Partial Rank Correlation Coefficient (PRCC) are performed. The obtained results identify the most sensitive transmission and progression parameters and demonstrate their important role in shaping smoking prevalence within the community. Furthermore, the classical integer-order model is compared with the fractional-order formulation, where the fractional model provides a more realistic description due to its ability to incorporate memory and hereditary effects associated with smoking behavior. An optimal control framework involving awareness and treatment strategies is further introduced to investigate effective smoking reduction policies. The numerical results demonstrate that awareness campaigns reduce smoking initiation, while treatment interventions increase smoking cessation, and the combined implementation of both strategies produces the most significant reduction in smoking prevalence. The consistency between the sensitivity analysis and optimal control results further supports the reliability of the proposed framework. Numerical simulations are carried out to analyze the qualitative and quantitative behavior of the system under different epidemiological scenarios. In addition, an ANN-based computational framework is employed as an efficient numerical tool to accurately approximate the complex dynamics of the proposed fractional-order smoking model with very low prediction error. Overall, the present study provides a comprehensive mathematical and computational framework for understanding, analyzing, and controlling smoking behavior within a population. | |
| dc.identifier.citation | Fractal and Fractional, 10(6), 2026 | |
| dc.identifier.doi | 10.3390/fractalfract10060409 | |
| dc.identifier.issn | 25043110 | |
| dc.identifier.other | 2-s2.0-105042703008 | |
| dc.identifier.uri | https://dspace.kmitl.ac.th/handle/123456789/18124 | |
| dc.source | Fractal and Fractional | |
| dc.subject | artificial neural network | |
| dc.subject | fractional-order model | |
| dc.subject | memory effects | |
| dc.subject | optimal control | |
| dc.subject | sensitivity analysis | |
| dc.subject | smoking dynamics | |
| dc.subject | smoking reproduction number | |
| dc.title | Artificial Neural Network (ANN)-Based Analysis and Optimal Control of Smoking Dynamics with Global Sensitivity Assessment | |
| dc.type | Article |