Forecast model of perceived demand of museum tourists based on neural network integration

Abstract

With the development of experiential tourism and the improvement of people’s living standards, people have begun to transform tourist destinations into museum tourism. However, no effective method for predicting the demand for museum tourism has yet emerged. In order to be able to build a prediction model that can perceive the needs of museum tourists, this article uses advanced algorithms based on neural network integration and calls different algorithms: QPSO-BPNN, QPSO, PSO, PSO-BPNN, and BPNN. When the training ratio increases to 90%, the prediction accuracy of the three algorithms, BPNN, PSO, and PSO-BPNN, is less than 80%, and the prediction accuracy of the QPSO-BPNN algorithm has reached 92.5%. Under the condition of equal training set ratio, the prediction accuracy of QPSO-BPNN algorithm is always significantly higher than that of PSO-BPNN algorithm. When the training set proportions are 50%, 70%, and 90%, the changes in population size parameters have little effect on the prediction accuracy of the algorithm. Based on the above experiments, it is known that the QPSO-BPNN algorithm is less sensitive to the size of the population, and the algorithm has good robustness. With the increase in the number of initial classifiers, the prediction accuracy of the QPSO-BPNN algorithm has improved significantly. The experimental results are consistent with the previous theoretical derivation analysis, and the accuracy of the algorithm has a positive correlation with the number of classifiers.