Notice of RetractionHybridization of adaptive Neuro-Fuzzy Inference System and data preprocessing techniques for tourist arrivals forecasting

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

Intelligent solutions, based on artificial intelligence (AI) technologies, to solve complicated practical problems in various sectors are becoming more and more widespread nowadays, because of their flexibility, symbolic reasoning, and explanation capabilities. Meanwhile, accurate forecasts on tourism demand and study on the pattern of the tourism demand from various origins is essential for the tourism-related industries to formulate efficient and effective strategies on maintaining and boosting tourism industry in a country. In this paper we develop a hybrid AI model to deal with tourist arrival forecasting problems. The hybrid model adopts Adaptive Neuro-Fuzzy Inference System (ANFIS) and data preprocessing techniques such as feature selection and data clustering. At the first stage which is feature selection stage, it uses stepwise regression analysis (SRA) to choose the key variables be considered in the model and eliminate low impact factors. At the second stage it employs Self Organization Map (SOM) neural network to divide the data into sub-populations and reduce the complexity of the data space to something more homogeneous. Finally, all clusters will be fed into Adaptive Neuro-Fuzzy Inference System (ANFIS) to construct an expert system with the ability of tourist arrival forecasting. Evaluation of the proposed model will be carried out by applying it on a case study of Taiwanese tourist arrivals in Hong Kong and results will be compared with other studies which have used the same data set. Results show- that the proposed model has high accuracy in comparison with rest of the models, so it can be considered as a suitable tool for tourist arrival forecasting problems.