Research on Quality Evaluation of Online Reservation Hotel APP Based on a RBF Neural Network and Support Vector Machine

Research on Quality Evaluation of Online Reservation Hotel APP Based on a RBF Neural Network and Support Vector Machine

Ma Xiang (Changchun Vocational Institute of Technology, China)
Copyright: © 2020 |Pages: 15
DOI: 10.4018/IJISSS.2020040104

Abstract

In order to evaluate the quality of online reservation hotel APP, RBF neural and support vector machine are used to evaluate the quality of online reservation hotel APP. First, the basic theory of the RBF neural network is studied, and the training algorithm of the RBF neural network is designed. Second, the basic model of support vector machine is analyzed, and the training algorithm is designed. Third, the evaluation index system of online reservation hotel APP is designed, and the weight of every index is established based on questionnaires and expert interview, and the evaluation simulation is carried out for 25 online reservation hotel APP, results show that the RBF neural network and support vector machine can obtain consistent evaluation results, and the support vector machine has better evaluation performance.
Article Preview
Top

Introduction

The online reservation hotel APP is a direct selling platform that designed for hotel products and services based on intelligent mobile platform of IOS or Android system. The online reservation hotel APP is an novel promotion mode of hotel products and services, which can provide the hotel reservation and search service, the consumer can get the following information, such as hotel type, hotel brand, hotel star, hotel price, hotel address, hotel location, hotel facilities and hotel surrounding environment. The current economy has already entered the service economical time (Yun, 2017; Carolina, 2018). The service quality has played important role in enhancing the core competence of hotel, the service quality management has become an important problem of develop hotel. In order to improve the quality evaluation correctness of online reservation hotel APP, an effective evaluation method should be used. The BP neural network and support vector machine are two representative machine learning methods (Maryam, et al., 2019; Stumpf, 2018). The BP neural network can find out statistical rules from a large number of learning samples and can evaluate the new samples. Radial Basis Function (RBF) neural network has been widely used in system modeling, control, fault diagnosis and other fields because of its simple structure and strong approximation ability. Therefore, RBF neural network has attracted many scholars' attention and research, and the parameter optimization of RBF neural network has been deeply studied. Different optimization algorithms have been applied to parameter optimization of RBF neural network, such as gradient descent algorithm, recursive least squares algorithm, etc. However, these algorithms have poor robustness and are easy to fall into local optimum. Excellent solution and other defects. Dynamic optimization design of RBF neural network is an effective method to ensure that RBF neural network always works under structural and parameter combination optimization. In order to obtain compact RBF neural network structure, scholars at home and abroad have proposed compact trial method, growth method, deletion method, growth deletion method and evolutionary algorithm. The network itself is usually the approximation of functions or algorithms, or it can be said to be the expression of logical strategies. In recent ten years, the research of artificial neural network has been more and more in-depth, and many achievements have been achieved. Artificial neural networks have successfully solved many problems in the fields of intelligent robots, pattern recognition, prediction and estimation, automatic control, medicine, biology and economy. It shows good intelligence in practical problems that are difficult to solve by modern computers. Artificial neural network (ANN) inspiration comes from the results of modern neuroscience research, trying to process information by simulating the neural network processing and memory of human brain. Since the 21st century, breakthroughs have been made not only in the theoretical research of neural networks, but also in the application research of some fields of neural networks. Wang Shoujue, Institute of Semiconductor Research, Chinese Academy of Sciences, and others applied in pattern recognition, GAFNE, a neural network model for medical diagnosis proposed by Zhou Zhihua, Nanjing University, and Liao Xiaofeng, Southwest University, to study the stability and robustness of neural networks and their extensive application in pattern recognition and automatic control, etc. 。 Because the neural network has good performance in studying the approximation of non-linear functions and can solve the regression problem well, it is widely used as a tool for evaluation and prediction in practical applications. This paper chooses BP neural network model to apply to online hotel APP quality evaluation, mainly considering the advantages of the model in the following aspects:

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing