A novel classification model for cotton yarn quality based on trained neural network using genetic algorithm

This paper introduces a novel classification model for cotton yarn quality. The proposed model is composed of two major techniques namely: Artificial Neural Network (ANN) and genetic algorithm (GA). First, training the ANN on encoding database to extract the weights between input and hidden layer, and hidden and output layer. Consequently, the output function for each output node of ANN can be constructed as a function of input attributes values and the specific obtained weights. This function is nonlinear exponential function depending only on the values of input attributes. Second, the genetic algorithm is used to find the optimal values of the input chromosomes (attributes) which maximize the nonlinear exponential function of the output node of ANN. Finally, the results of the optimum chromosomes are decoded and used to get a rule belonging to a specific class.