Security and Privacy of Cloud- and IoT-Based Medical Image Diagnosis Using Fuzzy Convolutional Neural Network

Algorithm 3

Fuzzy convolutional neural network algorithm.

	Input: assume input image Xi = 0, 1, 2, …, n, training epoch number E, batch number N, number of convolutional layer Cl, ith fuzzy rule R^k.
	Output: assign outputs Yi = 0, 1, 2, …. m, f (.) = activation function, trained parameters.
	Initialisation: randomly initialise weight Wt and membership function Mx, My, Mz.
	//Compute bias and kernel maps by minimising the loss function.
	for e = 1 to E do
	for b = 1 to B do
	//input membership function
	R^k: if Xi is , where F is the fuzzy set with ith input and kth fuzzy rule.
	fuzzification (Xi) is //fuzzy inputs
	then Yi is
	fuzzification (Wt) is //rule evaluation
	for Cl = 1 to CL do
	end
	//output membership function
	defuzzification is Y;
	fully connected (Y) is //calculate sensitivities
	cross entropy is CE;
	update ; //membership function chosen fuzzy rule.
	end
	end