Computational intelligence of Bayesian regularization backpropagation #j...

Computational intelligence of Bayesian regularization backpropagation neural networks to study the thermo-bioconvection flow of hybrid-nanofluid with thermal Radiation: Biotechnological perspectives

This study aims to develop a deep neural network that utilizes Bayesian regularization to investigate the performance of gyrotactic and oxytactic microbes in hybrid nanofluid flow over a sheet, taking into account local thermal non-equilibrium effects and thermal radiation. Two different activation functions, namely radial basis and log-sigmoid utilized in the designed network. The model improves the efficiency of pollutant removal by optimizing the dynamics of gyrotactic and oxytactic microbes under local thermal non-equilibrium conditions. The enhanced microbial activity for the degradation of organic waste and the breakdown of pollutants are made easier by the hybrid nanofluid's improved thermal and physicochemical characteristics. 80 % of the data fixed for the training of the deep neural network and 20 % data employed for the testing purpose. The base fluid water is coupled with titanium dioxide  and iron oxide  nanoparticles to produce a hybrid nanofluid. The input dataset of the network generated using the bvp4c command. To examine how the various parameters on the suggested model varied, three distinct examples were created. Various statistical metrics are taken into consideration to assess the network's accuracy and precision.

This article goal is to design a deep neural network approach optimized with Bayesian regularization algorithm to scrutinize the performance of gyrotactic and Oxytactic microbes in hybrid nanofluid flow along a sheet with thermophoresis and heat radiation characteristics. The present study scrutinizes the properties of heat transport in the absenteeism of LTECs using a simple mathematical model. The consequences of the important factors are investigated and numerical solutions are produced by employing the shooting method. This is the analysis's goal.

• ❖
  The designed deep neural network contains of dual hidden layers with 20 and 30 hidden neurons in radial-basis and log-sigmoid hidden layers respectively.
• ❖
  To analyze the precision and accuracy of the deep network the statistical measures like regression, mean square error and error histogram.
• ❖
  To regulate how Oxytactic and gyrotactic microbes influence the HNF using LTNE condition.
• ❖
  To assess how the thermal radiation affects the thermal transport of the hybrid nanofluid using HCM.
• ❖
  To examine the influences of the thermophoretic parameter on SBLflow HNF.
• ❖
  To investigate the impact of MHD on the bioconvection flow deep neural network approach trained with Bayesian regularization algorithm.
• ❖
  To inspect the properties of inter face heat transmission parameter on solid and liquid phase TBL flow HNF using.