Combining neural network model with seasonal time series ARIMA model

By Fang-Mei Tseng, Hsiao-Cheng Yu, Gwo-Hshiung Tzeng. 2002

359 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/29d09a073df25741c2d98f93fc08903bddf2facd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Yao Dong
2. Mehdi Khashei
3. Mehdi Bijari
4. Jianzhou Wang
5. Mu-Chen Chen
6. Ge Zhao
7. Yuanyuan Wang
8. Yu Wei

In Management Science and Operations Research

1. K. Prabheesh
2. F. Las-Heras
3. L. Diaz-Robles
4. Yao Dong
5. John G. Watson
6. Mehdi Khashei
7. Mehdi Bijari
8. Jianzhou Wang

Citations in the corpus

• Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: A case study of China (2012, methodology): “The roots of wq(y)¼0 and yp(y)¼0 should all lie outside the unit circle (Box and Jenkins, 1976; Tseng et al., 2002; Koutroumanidis et al., 2006).”
• Improvement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs) (2009, methodology): “Tseng et al. [57] proposed using a hybrid model called SARIMABP that combines the seasonal ARIMA (SARIMA) model and the back-propagation (BP) neural network model to predict seasonal time series data.”
• A case study on a hybrid wind speed forecasting method using BP neural network (2011, background): “Although there are many similar forecasting approaches in which neural networks have been built on deseasonalised time series data, they have mainly been used to predict aggregate retail sales [8], temperature [7], streamflow [27], total production value and soft drink [25] and total new privately o”
• Implications of COVID-19 Pandemic on the Global Trade Networks (2020, background): “First, it deals with problems of seasonality, non-stationarity, and varying patterns of nonlinearity present in economic and financial time series (Tseng, Yu, and Tzeng 2002).”
• A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile (2008, methodology): “…2007), fish catch (Gutie´rrez-Estrada et al., 2007) production values of the machinery industry (Chen and Wang, 2007), fish community diversity (Gutie´rrez-Estrada et al., 2008), and in other areas (Tseng et al., 2002; Zhang, 2003; Zhang and Qi, 2005), but all of them are not related to air quality.”
• An artificial neural network (p, d, q) model for timeseries forecasting (2010, positive): “Tseng, Yu, and Tzeng (2002) proposed using a hybrid model called SARIMABP that combines the seasonal auto-regressive integrated moving average (SARIMA) model and the back-propagation neural network model to predict seasonal time series data.”
• Forecasting SO 2 Pollution Incidents by means of Elman Artificial Neural Networks and ARIMA Models (2013, methodology): “[11] showed that the hybrid performed better than ARIMA or ANN alone.”
• Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks (2012, methodology): “…several previous studies have proposed hybrid MLP models by incorporating the ARIMA model (Zhang, 2003; Zeng et al., 2008), seasonal ARIMA model (Tseng et al., 2002; Zhang and Qi, 2005), genetic algorithms (Vlahogianni et al., 2005), fuzzy logic rules (Rojas et al., 2008; Zhang and Ye, 2008),…”