Scholarlink

<p>Cholera is a significant public health problem, especially in areas with poor water and sanitation facilities. Preceding stochastic cholera models demonstrate a circumscribed ability to reproduce unforeseen structural changes and elaborate transmission behavior because of their limited accuracy, which impacts their effectiveness for controlling strategies. In this paper, the neural networks with Bayesian regularization scheme (NNBRS) are utilized for transformative behavior prediction of the cholera epidemics with the impacts of seasonal variations. The NNBRS is proficient in predicting and generating realistic cholera dynamics with improved control strategies. The nonlinear cholera framework is governed by three stochastic differential equations incorporating Brownian motions to represent the susceptible, infectious, and number of bacteria (vibrios) in the water. The Euler–Maruyama technique is employed to generate data for the operation of NNBRS based on eight distinct scenarios of the stochastic cholera epidemic model adapting variations in infectious disease recovery rate, natural death ratio, white noise, indirect transmission rate, the bacteria half-saturation density, the total number of human hosts, shedding ratio of bacteria, and the death ratio of bacteria. The minimal spectrum of mean squared error, error histogram analysis, correlation, and regression measures effectively endorse the precision, reliability, and worth of the designed NNBRS.</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

Machine intelligent expedition with supervised Bayesian adaptive neural networks for stochastic cholera epidemic model in a periodic environment

  • 期刊论文

  • 发表日期：

    2026年1月21日

查看全文
  • Nabeela Anwar,
  • Kiran Shahzadi,
  • Muhammad Asif Zahoor Raja,
  • Iftikhar Ahmad,
  • Muhammad Shoaib,
  • Adiqa Kausar Kiani

摘要

Cholera is a significant public health problem, especially in areas with poor water and sanitation facilities. Preceding stochastic cholera models demonstrate a circumscribed ability to reproduce unforeseen structural changes and elaborate transmission behavior because of their limited accuracy, which impacts their effectiveness for controlling strategies. In this paper, the neural networks with Bayesian regularization scheme (NNBRS) are utilized for transformative behavior prediction of the cholera epidemics with the impacts of seasonal variations. The NNBRS is proficient in predicting and generating realistic cholera dynamics with improved control strategies. The nonlinear cholera framework is governed by three stochastic differential equations incorporating Brownian motions to represent the susceptible, infectious, and number of bacteria (vibrios) in the water. The Euler–Maruyama technique is employed to generate data for the operation of NNBRS based on eight distinct scenarios of the stochastic cholera epidemic model adapting variations in infectious disease recovery rate, natural death ratio, white noise, indirect transmission rate, the bacteria half-saturation density, the total number of human hosts, shedding ratio of bacteria, and the death ratio of bacteria. The minimal spectrum of mean squared error, error histogram analysis, correlation, and regression measures effectively endorse the precision, reliability, and worth of the designed NNBRS.