Article citationsMore >>

Rhif, M., Abbes, A. Ben, Farah, I. R., Martínez, B., & Sang, Y. (2019). Wavelet transform application for/in non-stationary time-series analysis: A review. In Applied Sciences (Switzerland) (Vol. 9, Issue 7, p. 1345). Multidisciplinary Digital Publishing Institute.

has been cited by the following article:

Article

Horizontal Divide and Conquer Methods for Non-Linear Time Series Forecasting Using LSTM-ANN; a Comparative Study Based on Simulated Data

1Department of Statistics, University of Colombo, Colombo, Sri Lanka


American Journal of Applied Mathematics and Statistics. 2023, Vol. 11 No. 2, 63-69
DOI: 10.12691/ajams-11-2-4
Copyright © 2023 Science and Education Publishing

Cite this paper:
Navoda Hettige, WMND Basnayake. Horizontal Divide and Conquer Methods for Non-Linear Time Series Forecasting Using LSTM-ANN; a Comparative Study Based on Simulated Data. American Journal of Applied Mathematics and Statistics. 2023; 11(2):63-69. doi: 10.12691/ajams-11-2-4.

Correspondence to: Navoda  Hettige, Department of Statistics, University of Colombo, Colombo, Sri Lanka. Email: dininavo@gmail.com

Abstract

Time series forecasting holds a vital significance across diverse domains; however, accurately predicting the future is challenging due to the inherent complexity and non-linear nature of the data. One promising strategy for tackling non-linear time series data is the utilization of hybrid models, which have the potential to enhance forecasting accuracy. In this research paper, a comparative study is conducted, focusing on different approaches to horizontally partition data and fit Long short-term memory artificial neural network models (LSTM ANN). By using simulated data, this study effectively evaluates the efficacy of these approaches. The results demonstrate that DWT-LSTM, EEMD-LSTM, and CEEMDAN-LSTM techniques outperformed the EMD-LSTM and Threshold-LSTM models.

Keywords