<p>Hepatitis B virus (HBVD) is a serious liver infection that can lead to chronic disease, cancer or liver cirrhosis. Its early detection and control are crucial due to its global prevalence and life-threatening complications. HBVD progression can be modeled as a dynamical system to analyze the interaction between viral load, immune response, and treatment over time. In this paper, a novel hybrid method using morlet wavelet neural networks (MWNN) is explored to analyze the dynamics of the HBVD transmission model. The combination of Archimedes optimization algorithm (AOA) and neural network algorithm (NNA), namely MWNN-AOA-NNA is applied, the optimization of network training through minimization problems is efficiently handled by the integrated heuristic features of AOA-NNA. The activation function derived from mean square errors (MSE) is designed to enhance the performance of MWNN-AOA-NNA within the proposed model. The results obtained from the approximations provided by MWNN-AOA-NNA matched with the reference solution obtained from Adam numerical approach. The stability, robustness and convergence of the proposed HBVD model are evaluated utilizing mean square error and Theil's inequality coefficient. The most of these values are in the range of <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="40435_2025_1814_Article_IEq1.gif" Format="GIF" Height="19" Rendition="HTML" Resolution="72" Type="Linedraw" Width="91" /> </InlineMediaObject> <EquationSource Format="TEX">${10}^{-9}-{10}^{-4},$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <msup> <mrow> <mn>10</mn> </mrow> <mrow> <mo>-</mo> <mn>9</mn> </mrow> </msup> <mo>-</mo> <msup> <mrow> <mn>10</mn> </mrow> <mrow> <mo>-</mo> <mn>4</mn> </mrow> </msup> <mo>,</mo> </mrow> </math></EquationSource> </InlineEquation> for all classes of the model. In addition, the exceptional reliability and precision, the established MWNN-AOA-NNA technique is distinguished by its simplicity, broader applicability and flexibility.</p>

Meta-heuristic tuned morlet wavelet-based neural network to analyze the dynamics of hepatitis B-virus

期刊论文
发表日期：

2025年8月28日

查看全文

Muhammad Naeem Aslam,
Muhammad Amir,
Javed Hussain,
Muhammad Sarmad Arshad,
Mohamed Kallel

摘要

Hepatitis B virus (HBVD) is a serious liver infection that can lead to chronic disease, cancer or liver cirrhosis. Its early detection and control are crucial due to its global prevalence and life-threatening complications. HBVD progression can be modeled as a dynamical system to analyze the interaction between viral load, immune response, and treatment over time. In this paper, a novel hybrid method using morlet wavelet neural networks (MWNN) is explored to analyze the dynamics of the HBVD transmission model. The combination of Archimedes optimization algorithm (AOA) and neural network algorithm (NNA), namely MWNN-AOA-NNA is applied, the optimization of network training through minimization problems is efficiently handled by the integrated heuristic features of AOA-NNA. The activation function derived from mean square errors (MSE) is designed to enhance the performance of MWNN-AOA-NNA within the proposed model. The results obtained from the approximations provided by MWNN-AOA-NNA matched with the reference solution obtained from Adam numerical approach. The stability, robustness and convergence of the proposed HBVD model are evaluated utilizing mean square error and Theil's inequality coefficient. The most of these values are in the range of ${10}^{-9}-{10}^{-4},$ $10^{- 9} - 10^{- 4},$ for all classes of the model. In addition, the exceptional reliability and precision, the established MWNN-AOA-NNA technique is distinguished by its simplicity, broader applicability and flexibility.