vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff72572b00000076fd020001000300
Data mining techniques used in many applications as there is an incredible growth in records and it is not feasible to find a solution manually. Amongst them, the medical records in data mining gains more popularity and have many missed values due to emergency cases or complicated situation etc. These missing values have a great influence in the desired output. The traditional mining procedure has to be enhanced to handle that between them and adjust the parameters to minimize the errors. The activation function in the neuron performs the non-linear transformation function making it capable to learn and perform more complex tasks. This function plays a vital role in the output process. This work focus on this function and made some enhancement by applying multi logit regression with Maximum A posteriori method in activation function to handle multi-class classification The proposed Enhanced Activation function in Multi-Layer Perceptron is implemented in Weka 3.9.6 and it is compared with traditional MLP with suitable evaluation metrics.