Application of Empirical mode Decomposition with Wavelets Support Vector Machine in time Series Data
A. Rafidah1, Ani Shabri2, Ernie Mazuin3
1A.Rafidah, Technical Foundation Department, University Kuala Lumpur, Pasir Gudang, Malaysia.
2Ani Shabri, Mathematics Department, University Technology Malaysia, Johor Bahru, Malaysia.
3Ernie Mazuin, Instrumentation & Control Engineering Department, University Kuala Lumpur, Pasir Gudang, Malaysia
Manuscript received on December 15, 2019. | Revised Manuscript received on December 20, 2019. | Manuscript published on January 10, 2020. | PP: 2451-2454 | Volume-9 Issue-3, January 2020. | Retrieval Number: C9225019320/2020©BEIESP | DOI: 10.35940/ijitee.C9225.019320
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper mainly discussed on the forecast of Thailand tourist visiting Malaysia. This paper proposed a three-stage technique in which the empirical mode decomposition (EMD) is combined with wavelet methods and support vector machine model. We used the proposed technique, EMD_WSVM to forecast two ASEAN country tourism timeseries. Detail experiments are conducted for the proposed method, in which there is a comparison between the EMD_WSVM, WSVM and SVM methods. The proposed EMD_WSVM model is determined to be dominant to the other methods in predicting the number of tourist arrivals.
Keywords: Forecasting, Tourist Arrivals, SVM Model, WSVM Model and EMD_WSVM Model.
Scope of the Article: Application of WSN in IoT