Optimasi Neural Network Dengan Menggunakan Algoritma Genetika Untuk Prediksi Jumlah Kunjungan Wisatawan

Abstract

West Nusa Tenggara is one of the tourist attractions in Indonesia which has a certain attraction for tourists. With the increase in tourism in NTB, it is necessary to make adequate efforts to maintain tourist objects and attractions. In an effort to maintain a tourist attraction, the NTB provincial tourism office needs to analyze and predict the arrival of local and international tourists. The current analysis and prediction process is still being carried out by collecting data from each tourist attraction entrance. The processed data produces predictions of tourist arrivals, both local and international, where the data processing process takes a long time and requires high human resources. To overcome these problems, it is done by applying computational predictions. Computational predictions can minimize the prediction time and human resources required. The method used is a neural network algorithm with optimized parameters using a genetic algorithm. The optimized parameters are the hidden layer, the number of neurons in the input layer, momentum and others. The data used is time series data from 1997 to 2018. From the neural network experiment, the parameters of the number of neurons in the input layer xt-7 are determined, the number of neurons in the hidden layer 10, the training cycle value is 400, the learning rate value is 0.3 and the momentum value is 0.2. From the experiment, the RMSE value of 0.050 was obtained. While the RMSE value for the neural network algorithm parameters optimized using the genetic algorithm is 0.044. Because of this, it can be stated genetic algorithm with neural network can be used to determine the hidden layer and the number of hidden nodes, the right features, momentum, initialize, and optimize the weight of the neural network. So that the application of the genetic algorithm to optimize the parameter values of the neural network algorithm is better than the application of the neural network algorithm without optimization.