For modeling by ANN, you must have the input and output data and then use the three layers input , hidden and output layer.

Thank you sir for your valuable guidance. 

For modeling of ANN,you must choose input as desired by you and the number of parameters to be evaluated must be as the output.The hidden layer can be one or two depending upon the complexity of the problem and the output layer will be the number of parameters to be evaluated and tested. The back propagation algorithm can be utilized in training of all ANN models.This algorithm uses the supervised training techniques where the network weights and biases are initialized randomly at the begining of the training phases.

Sir, you can initialize weights between 0 and 1. Then you can check the accuracy of prediction and based on the results you can keep on changing your no of hidden units and hidden layers till you get an optimum value. But increasing the hidden layers may increase your program complexity. One way to do it is split your attributes and apply neural networking and then combine the results to predict your desired output. 

Thank you sir for your help and support 

Dear Researcher

I think you can find the answer in the attached papers:

1. https://www.researchgate.net/publication/224132638_Modeling_of_forced_dermal_wound_healing_using_intelligent_techniques

2. https://www.researchgate.net/publication/232651566_Modeling_of_Dermal_Wound_Healing-Remodeling_Phase_by_Neural_Networks

also to achieve better result you optimize your ANN by GA, PSO, RPLNN and other optimization techniques :

1. https://www.researchgate.net/publication/306048088_Optimizing_radio_frequency_identification_network_planning_through_ring_probabilistic_logic_neurons

2. https://www.researchgate.net/publication/303402995_Modeling_Mechanical_Properties_of_FSW_Thick_Pure_Copper_Plates_and_Optimizing_It_Utilizing_Artificial_Intelligence_Techniques

3. https://www.researchgate.net/publication/269367058_Introducing_Genetic_Algorithm_as_an_Intelligent_Optimization_Technique

Conference Paper Modeling of forced dermal wound healing using intelligent techniques

Article Modeling of Dermal Wound Healing-Remodeling Phase by Neural Networks

Article Introducing Genetic Algorithm as an Intelligent Optimization Technique

Article Modeling Mechanical Properties of FSW Thick Pure Copper Plat...

Article Optimizing radio frequency identification network planning t...

Thank you very much Aydin Azizi sir for your detailed explanation and useful resource material.

Thank you very much.

From:- D.B.Jani

For the model equation using weights in ANN you can use the garson algorithm (1991) or Goh (1995) to determine the relative importance of each input with weights. With the relative importance of each input you can make a nonlinear multivariable regression and have your model.

Thank you Yassine Mahdi sir for your help and support.

From:-

D.B. Jani

Thank you Yassine Mahdi sir for your help and support.

From:-

D.B. Jani