Scholarlink

<p>The Ebola virus disease (EVD) poses a significant threat to public health due to its rapid transmission and high mortality rate. Accurate modelling for the comprehension of transmission of this malady is essential for planning effective containment and its outcome strategies. In this work, we analyse a four-dimensional compartmental model (susceptible, infectious, deceased, recovered) of EVD to understand its epidemiological behaviour. To enhance the predictive power and accuracy of the model, artificial intelligence (AI) technique, a specifically supervised neural network using Levenberg–Marquardt backpropagation recurrent neural network (L-MBRNN), is applied. Reference solutions are obtained using Runge–Kutta method. The AI-based approach is validated by comparing with numerical solutions, statistical analysis and absolute error assessment to confirm the reliability and precision of the applied method. This fusion of biological modelling and machine learning provides a robust framework for investigating the dynamics of Ebola.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Numerical treatment of Ebola virus model using artificial neural networks

  • 期刊论文

  • 发表日期：

    2025年11月24日

查看全文
  • Iftikhar Ahmad,
  • Muhammad Ozair,
  • Takasar Hussain,
  • Mir Muhammad Abubakar,
  • Muhammad Asif Zahoor Raja

摘要

The Ebola virus disease (EVD) poses a significant threat to public health due to its rapid transmission and high mortality rate. Accurate modelling for the comprehension of transmission of this malady is essential for planning effective containment and its outcome strategies. In this work, we analyse a four-dimensional compartmental model (susceptible, infectious, deceased, recovered) of EVD to understand its epidemiological behaviour. To enhance the predictive power and accuracy of the model, artificial intelligence (AI) technique, a specifically supervised neural network using Levenberg–Marquardt backpropagation recurrent neural network (L-MBRNN), is applied. Reference solutions are obtained using Runge–Kutta method. The AI-based approach is validated by comparing with numerical solutions, statistical analysis and absolute error assessment to confirm the reliability and precision of the applied method. This fusion of biological modelling and machine learning provides a robust framework for investigating the dynamics of Ebola.