Title | ||
---|---|---|
Training neural networks by electromagnetism-like mechanism algorithm for tourism arrivals forecasting |
Abstract | ||
---|---|---|
Because of accurate forecasting of tourist arrivals is very important for tourism industry, various tourist arrivals forecasting models have been developed. The aim of this paper is to introduce the basic theoretical principles of electromagnetism-like mechanism (EM) algorithm and design a new neural network model for tourism forecasting which uses the EM algorithm as the learning rule (EMNN). The EMNN is applied to two major tourism demand forecasting methods-econometrical model and time series analysis. In numerical experiment, this study tests the accuracy of EMNN model and compares the EMNN model with other traditional forecasting models, such as moving average (MV) and multiple regressions (MR). We also compares EMNN model with artificial intelligence approaches, for instance, the adaptive network-based fuzzy inference system (ANFIS) model and basic feed-forward neural networks model. Based on the experimental results, we can see that the EMNN model owns excellent performance in forecasting tourist arrivals. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/BICTA.2010.5645207 | BIC-TA |
Keywords | Field | DocType |
neural network,time series analysis,tourism arrivals forecasting,fuzzy reasoning,econometrical model,tourism demand forecasting,learning rule,moving average processes,travel industry,learning (artificial intelligence),regression analysis,tourism industry,neural networks training,electromagnetism-like mechanism,moving average,emnn,electromagnetism like mechanism algorithm,econometrics,feedforward neural nets,feedforward neural networks,time series,multiple regressions,adaptive network based fuzzy inference system,em algorithm,learning artificial intelligence,predictive models,multiple regression,econometric model,feed forward neural network,neural network model,artificial intelligent,forecasting | Time series,Feedforward neural network,Demand forecasting,Computer science,Algorithm,Learning rule,Artificial intelligence,Probabilistic forecasting,Adaptive neuro fuzzy inference system,Artificial neural network,Moving average,Machine learning | Conference |
Volume | Issue | ISBN |
null | null | 978-1-4244-6437-1 |
Citations | PageRank | References |
1 | 0.35 | 6 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qing Wu | 1 | 21 | 2.00 |
Chunjiang Zhang | 2 | 82 | 8.90 |
Liang Gao | 3 | 176 | 21.99 |
Xinyu Li | 4 | 381 | 65.75 |