Academic Journal of Computing & Information Science, 2024, 7(6); doi: 10.25236/AJCIS.2024.070613.
Guanchen Du1, Xinghe Chen2
1College of Mathematics and Computer Science, Shantou University, Shantou, 515000, China
2School of Computer Science and Engineering, North Minzu University, Yinchuan, 750021, China
Time series prediction involves forecasting future values or events based on past data patterns and trends, providing a reliable basis for decision-making and planning, with a wide range of application prospects. Currently, many time series prediction techniques face issues such as low accuracy and high time costs, which do not meet societal needs. This paper aims to explore a new method for time series prediction, namely Convolutional Neural Networks (CNN) with an attention mechanism, to capture the key features of time series. Experiments and validations on multiple datasets have been conducted, and the results show that the proposed method significantly improves both accuracy and efficiency.
Time Series Prediction, Convolutional Neural Network, attention mechanisms
Guanchen Du, Xinghe Chen. Time Series Prediction Model Based on Convolutional Neural Networks with Attention. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 6: 81-87. https://doi.org/10.25236/AJCIS.2024.070613.
[1] Wang X, Kang Y, Hyndman R J, et al. Distributed ARIMA models for ultra long time series [J]. International Journal of Forecasting, 2023, 39 (3): 1163-1184
[2] Masini R P, Medeiros M C, Mendes E F. Machine learning advantages for time series forecasting [J]. Journal of Economic Surveys, 2023, 37 (1): 76-111
[3] Ning Y , Wang X , Yu Q ,et al.Rapid Damage Prediction and Risk Assessment for Tropical Cyclones at a Fine Grid in Guangdong Province, South China[J].International Journal of Disaster Risk Science, 2023, 14(2):237-252.DOI:10.1007/s13753-023-00485-y.
[4] Meiting C , Yaoqiu K , Ningsheng H .Early-warning of Spatiotemporal Evolvement of Land Ecological Security in Guangdong Province Based on RBF[J].Research of Soil and Water Conservation, 2015.
[5] Jiang W, Ling L, Zhang D, et al. A time series forecasting model selection framework using CNN and data augmentation for small sample data [J]. Neural Processing Letters, 2023: 1-28
[6] Hajirahimi Z, Khashii M. Hybridization of hybrid structures for time series forecasting: A review [J]. Artistic Intelligence Review, 2023, 56 (2): 1201-1261