Development of tourism resources based on fpga microprocessor and convolutional neural network

Accuracy of inbound tourism demand, it is important for the development and implementation of inbound tourism strategy. Use the FPGA, as in the common traditional mechanical, convolution neural network, learn how they are wide, it is being used to traffic demand forecasting model. This over fitting, the difficulty of the parameters, as such convolution neural network, drawbacks that receive, and due to the minimum number of problem set. The proposed system has a combination of neural networks and FPGA convolution to establish tourism demand forecasting neural network. The most advanced methods for the country's tourism research for traditional statistical methods, predictive models and artificial intelligence soft computing techniques. Please improve tourism research and modelling method introduces significant prediction accuracy of artificial intelligence methods. The results showed that, compared with, including FPGA traditional neural network neural network convolution essence of traditional statistical methods and methods can improve the prediction accuracy. This approach provides a more accurate forecast travel demand model is a better choice. Develop and compare various classifiers based on convolutional neural networks (CNN) and long short-term memory networks (LSTM). These classifiers were trained and validated with data from hotels located on the island of Tenerife. An analysis of our findings shows that the most accurate and robust estimators are those based on LSTM recurrent neural networks.