This is the most popular network architecture in use today. The input layer of this network is a set of input units, which accept the elements of input feature vectors. The input units (neurons) are fully connected to the hidden layer with the hidden units. The hidden units (neurons) are also fully connected to the output layer. The output layer supplies the response of neural network to the activation pattern applied to the input layer. The information given to a neural net is propagated layer-by-layer from input layer to output layer through (none) one or more hidden …show more content…
(2). “High”, “Medium” and “Low” are the referential values of consequent “Diabetes” in this researechresearch. The belief distribution states present that the degree of belief associated of with “High” is 84%, 16% degree of belief associated withfor “Medium”, while 0% degree of belief is associated consider with “Low”. In this belief rule, the total degree of belief is (0.860+0.140+0.000) = 1.000; hence, the assessment the rule is complete
The BRB inference procedure system of this research methodology consists of various components such as input transformation, rule activation weight calculation, rule belief degree update mechanism, and followed by the aggregation by using ER of the rules of a BRB. Evidential Reasoning (ER) algorithm [2722] used to develop the aggregation process of inference engine of this Neuro-BRB Inference system architecture. The inference engine of this system architecture works in the following ways [2217] –