Time Series Forecasting Based on Cloud Process Neural Network
Time series forecasting has been an important tool in many areas such as agriculture, finance, management, production or sales. In recent years, a large literature has evolved on the use of artificial neural networks (ANN) in time series forecasting. However conventional ANN is limited by its instan...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2015-09-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/25868644.pdf |
_version_ | 1811337770713481216 |
---|---|
author | Bing Wang Shaohua Xu Xiaohong Yu Panchi Li |
author_facet | Bing Wang Shaohua Xu Xiaohong Yu Panchi Li |
author_sort | Bing Wang |
collection | DOAJ |
description | Time series forecasting has been an important tool in many areas such as agriculture, finance, management, production or sales. In recent years, a large literature has evolved on the use of artificial neural networks (ANN) in time series forecasting. However conventional ANN is limited by its instantaneous synchronization inputs, it is difficult to express accumulative time effect and lacks certain processing ability for uncertainty factors (e.g., randomness, fuzziness ) hidden in time series. Thus a cloud process neural network (CPNN) model is put forward in the paper for time series forecasting. It combines cloud model's expression ability for uncertainty concepts and process neural network's dynamic signal processing method, converts quantitative time series inputs into multiple qualitative sub-cloud concepts, and then finds out the association rule between input and output variables through mining inherent law among multiple sub-clouds. For CPNN learning, this paper proposes a learning strategy based on cat swarm optimization algorithm, which could optimize the network structure and learning parameters simultaneously to improve the network approximation and generalization ability. Finally, the model and algorithm is used in individual household electric power consumption time series forecasting and ASP flooding oil recovery index forecasting. In order to improve the quality of training samples, phase space reconstruction theory is employed to reconstruct one-dimensional time series into high-dimensional phase space as training sample set. Simulation results show that compared to conventional process neural networks and adaptive neuro fuzzy inference system, the proposed method improves the prediction accuracy and provides a new solution for time series pattern classification and forecast analysis. |
first_indexed | 2024-04-13T18:00:39Z |
format | Article |
id | doaj.art-5fb95c5dd40948a7b68566e882031e14 |
institution | Directory Open Access Journal |
issn | 1875-6883 |
language | English |
last_indexed | 2024-04-13T18:00:39Z |
publishDate | 2015-09-01 |
publisher | Springer |
record_format | Article |
series | International Journal of Computational Intelligence Systems |
spelling | doaj.art-5fb95c5dd40948a7b68566e882031e142022-12-22T02:36:16ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832015-09-018510.1080/18756891.2015.1099905Time Series Forecasting Based on Cloud Process Neural NetworkBing WangShaohua XuXiaohong YuPanchi LiTime series forecasting has been an important tool in many areas such as agriculture, finance, management, production or sales. In recent years, a large literature has evolved on the use of artificial neural networks (ANN) in time series forecasting. However conventional ANN is limited by its instantaneous synchronization inputs, it is difficult to express accumulative time effect and lacks certain processing ability for uncertainty factors (e.g., randomness, fuzziness ) hidden in time series. Thus a cloud process neural network (CPNN) model is put forward in the paper for time series forecasting. It combines cloud model's expression ability for uncertainty concepts and process neural network's dynamic signal processing method, converts quantitative time series inputs into multiple qualitative sub-cloud concepts, and then finds out the association rule between input and output variables through mining inherent law among multiple sub-clouds. For CPNN learning, this paper proposes a learning strategy based on cat swarm optimization algorithm, which could optimize the network structure and learning parameters simultaneously to improve the network approximation and generalization ability. Finally, the model and algorithm is used in individual household electric power consumption time series forecasting and ASP flooding oil recovery index forecasting. In order to improve the quality of training samples, phase space reconstruction theory is employed to reconstruct one-dimensional time series into high-dimensional phase space as training sample set. Simulation results show that compared to conventional process neural networks and adaptive neuro fuzzy inference system, the proposed method improves the prediction accuracy and provides a new solution for time series pattern classification and forecast analysis.https://www.atlantis-press.com/article/25868644.pdfCloud process neural networkTime series forecastingCloud theoryCat swarm optimizationPhase space reconstruction |
spellingShingle | Bing Wang Shaohua Xu Xiaohong Yu Panchi Li Time Series Forecasting Based on Cloud Process Neural Network International Journal of Computational Intelligence Systems Cloud process neural network Time series forecasting Cloud theory Cat swarm optimization Phase space reconstruction |
title | Time Series Forecasting Based on Cloud Process Neural Network |
title_full | Time Series Forecasting Based on Cloud Process Neural Network |
title_fullStr | Time Series Forecasting Based on Cloud Process Neural Network |
title_full_unstemmed | Time Series Forecasting Based on Cloud Process Neural Network |
title_short | Time Series Forecasting Based on Cloud Process Neural Network |
title_sort | time series forecasting based on cloud process neural network |
topic | Cloud process neural network Time series forecasting Cloud theory Cat swarm optimization Phase space reconstruction |
url | https://www.atlantis-press.com/article/25868644.pdf |
work_keys_str_mv | AT bingwang timeseriesforecastingbasedoncloudprocessneuralnetwork AT shaohuaxu timeseriesforecastingbasedoncloudprocessneuralnetwork AT xiaohongyu timeseriesforecastingbasedoncloudprocessneuralnetwork AT panchili timeseriesforecastingbasedoncloudprocessneuralnetwork |