Đánh giá bằng thực nghiệm phương pháp dự báo lai ghép giữa ARIMA và RBFNN theo mô hình tuần tự cộng

Các tác giả

  • Thanh Son Nguyen Ho Chi Minh City University of Technology and Education, Vietnam https://orcid.org/0000-0003-0191-9150
  • Chi Cong Pham Ho Chi Minh City Open University, Vietnam

Email tác giả liên hệ:

sonnt@hcmute.edu.vn

DOI:

https://doi.org/10.54644/jte.2024.1520

Từ khóa:

Chuỗi thời gian, mô hình dự báo, dự báo chuỗi thời gian, ARIMA, RBFNN

Tóm tắt

Chuỗi thời gian là một chuỗi các giá trị đo được tại các thời điểm khác nhau. Chuỗi thời gian là loại dữ liệu có trong hầu hết các lĩnh vực khác nhau. Dự báo trên chuỗi thời gian là một bài toán quan trọng trong khai thác dữ liệu. Độ chính xác của dự báo đóng vai trò quan trọng trong hỗ trợ việc ra quyết định trong nhiều lĩnh vực của cuộc sống. Vì vậy, việc nghiên cứu cải tiến độ chính xác của dự báo luôn được các nhà nghiên cứu quan tâm thực hiện. rất nhiều mô hình dự báo chuỗi thời gian đã được đề xuất từ những mô hình cổ điển như ARIMA đến những mô hình ANN. Mô hình ARIMA và ANN đã được nghiên cứu sử dụng để dự báo trong các lĩnh vực cụ thể nào đó như tài chính, chứng khoán, ô nhiễm không khí, v.v... Trong nghiên cứu này, chúng tôi đánh giá bằng thực nghiệm mô hình lai ghép giữa ARIMA và RBFNN theo mô hình tuần tự công trên các tập dữ liệu thực của các lĩnh vực khác nhau. Kết quả thực nghiệm cho thấy mô hình lai ghép có độ chính xác dự báo tốt hơn trường hợp dùng riêng rẽ từng mô hình ARIMA hoặc RBFNN.

Tải xuống: 0

Dữ liệu tải xuống chưa có sẵn.

Tiểu sử của Tác giả

Thanh Son Nguyen, Ho Chi Minh City University of Technology and Education, Vietnam

Nguyen Thanh Son received his B.S. in Information Technology from Faculty of Information Technolgy, Ho Chi Minh City University of Natural Sciences, Vietnam where he also received his Master degree in the same branch. He is currently Ph.D. student in Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology, Vietnam. His main research interest is include artificial intelligence, machine learning, deep learning, time series data mining and association rule mining. He can be contacted at email: sonnt@hcmute.edu.vn

ORCID:  https://orcid.org/0000-0003-0191-9150

Chi Cong Pham, Ho Chi Minh City Open University, Vietnam

Pham Chi Cong received the B.S. degree in Information Technology Engineer at Saigon Technology University in 2008, the M.S. degree in Economic management at Hanoi University of Mining and Geology in 2013, and the M.S. degree in Computer Science at HCMC University of Technology and Education in 2021. From 2008 to 2022, he was a lecturer in Computer Science at the Southeast Asia Institute for Cultural and Educational Development Research. From 2022 up to now, he is a lecturer in Computer Science at the Ho Chi Minh City Open University. His research interest is time series datamining. He can be contacted at email: cong.pc@ou.edu.vn

Tài liệu tham khảo

A. T. Lora, J. C. Riquelme, J. L. M. Ramos, J. M. R. Santos, and A. G. Expósito, "Influence of kNN-Based Load Forecasting Errors on Optimal Energy Production," Progress in Artificial Intelligence, Lecture Notes in Computer Science, vol. 2902, pp. 189-203, 2003. ISSN: 0302-9743. DOI: https://doi.org/10.1007/978-3-540-24580-3_26

F. M. Alvarez, A. T. Lora, J. C. Riquelme, and J. S. A. Ruiz, "Energy Time Series Forecasting Based on Pattern Sequence Similarity," IEEE Trans. on Knowledge and Data Engineering, vol. 23, no. 8, pp. 1230–1243, 2011. DOI: https://doi.org/10.1109/TKDE.2010.227

R. Nayak and T. Braak, "Temporal Pattern Matching for the Prediction of Stock Prices," in Proceedings 2nd International Workshop on Integrating Artificial Intelligence and Data Mining (AIDM 2007), vol. 84, pp. 95-103.

Y. Jiang, C. Li, and J. Han, "Stock temporal prediction based on time series motifs," in Proceedings of 8th International Conference on Machine Learning and Cybernetics, 2009, vol. 6, pp. 3550-3555.

L. Zhang et al., "An Improved K-nearest Neighbor Model for Short-term Traffic Flow Prediction," in Intelligent and Integrated Sustainable Multimodal Transportation Systems Proceedings from the 13th COTA International Conference of Transportation Professionals (CICTP2013), vol. 96, pp. 653–662. DOI: https://doi.org/10.1016/j.sbspro.2013.08.076

G. Rigopoulos, "Univariate Time Series Forecasting Using k-Nearest Neighbors Algorithm: A Case for GDP," International Journal of Scientific Research and Management (IJSRM), vol. 10, no. 09, pp. EM01, Sep. 2022, doi: 10.18535/ijsrm/v10i9.em01. DOI: https://doi.org/10.18535/ijsrm/v10i9.em01

N. T. Son, N. H. Le, and D. T. Anh, "Time Series Prediction Using Pattern Matching," in Proc. of International Conference on Computating, Management and TeleCommunications (ComManTel 2013), Ho Chi Minh City, Vietnam, Jan. 21-24, 2013, pp. 401-406. DOI: https://doi.org/10.1109/ComManTel.2013.6482428

Z. Ivanovski, A. Milenkovski, and Z. Narasanov, "Time Series Forecasting Using a Moving Average Model for Extrapolation of Number of Tourist," UTMS Journal of Economics, vol. 9, no. 2, pp. 121–132, 2018.

M. Sreemalli, P. Chaitanya, and K. Srinivas, "Comparative Analysis of Machine Learning Techniques on Stock Market Prediction," in Vol. 14 ICETCSE 2016 Special Issue International Journal of Computer Science and Information Security (IJCSIS), ISSN 1947-5500 [Online]. Available: https://sites.google.com/site/ijcsis/.

B. M. Pavlyshenko, "Machine-Learning Models for Sales Time Series Forecasting," Data, vol. 4, no. 1, p. 15, Jan. 2019, doi: 10.3390/data4010015. DOI: https://doi.org/10.3390/data4010015

J. C. Brocklebank, D. A. Dickey, and B. S. Choi, SAS for Forecasting Time Series, 3rd ed. Cary, NC: SAS Institute Inc., 2018.

J. H. Kim, "Forecasting autoregressive time series with bias corrected parameter estimators," International Journal of Forecasting, vol. 19, pp. 493-502, 2003. DOI: https://doi.org/10.1016/S0169-2070(02)00062-6

D. C. Montgomery, C. L. Jennings, and M. Kulahci, Introduction to Time Series Analysis and Forecasting. John Wiley & Sons, 2015.

S. D. Balkin and J. K. Ord, "Automatic neural network modeling for univariate time series," International Journal of Forecasting, vol. 16, pp. 509-515, 2000. DOI: https://doi.org/10.1016/S0169-2070(00)00072-8

E. Cadenas and W. Rivera, "Short-term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural network," Renewable Energy, vol. 34, pp. 274-278, 2009. DOI: https://doi.org/10.1016/j.renene.2008.03.014

M. Ghiassi, H. Saidane, and D. K. Zimbra, "A dynamic artificial neural network for forecasting series events," International Journal of Forecasting, vol. 21, pp. 341-362, 2005. DOI: https://doi.org/10.1016/j.ijforecast.2004.10.008

S. Heravi, D. R. Osborn, and C. R. Birchenhall, "Linear versus neural network forecasting for European industrial production series," International Journal of Forecasting, vol. 20, no. 3, pp. 435-446, 2004. DOI: https://doi.org/10.1016/S0169-2070(03)00062-1

G. Tkacz, "Neural network forecasting of Canadian GDP growth," International Journal of Forecasting, vol. 17, pp. 57-69, 2001. DOI: https://doi.org/10.1016/S0169-2070(00)00063-7

G. P. Zhang and M. Qi, "Neural network forecasting for seasonal and trend time series," European Journal of Operational Research, vol. 160, no. 2, pp. 501–514, 2005. DOI: https://doi.org/10.1016/j.ejor.2003.08.037

K. Lai et al., "Hybridizing exponential smoothing and neural network for financial time series prediction," in Proceedings of 6th International Conference on Computational Science (ICCS'06), vol. 4, pp. 493–500, 2006. DOI: https://doi.org/10.1007/11758549_69

C. D. Truong, H. N. Tin, and D. T. Anh, "Combining motif information and neural network for time series prediction," Int. J. Business Intelligence and Data Mining, vol. 7, no. 4, pp. 318–339, 2012. DOI: https://doi.org/10.1504/IJBIDM.2012.051734

D. N. Bao, N. D. K. Vy, and D. T. Anh, "A hybrid method for forecasting trend and seasonal time series," in Proc. of 2013 IEEE RIVF International Conference on Information and Communication Technologies, Hanoi, Vietnam, Nov. 10–13, 2013, pp. 203–208.

N. T. Son and D. T. Anh, "Hybridizing pattern matching and neural network for time series prediction," in Proc. of 2013 World Congress on Information and Communication Technologies (WICT 2013), Hanoi, Vietnam, pp. 19–24.

S. A. Mangai et al., "Hybrid ARIMA-HyFIS model for forecasting univariate time series," International Journal of Computer Applications, vol. 91, no. 5, pp. 38–44, 2014. DOI: https://doi.org/10.5120/15880-4852

S. M. Pandhiani and A. B. Shabri, "Time series forecasting by using hybrid models for monthly streamflow data," Applied Mathematical Sciences, vol. 9, no. 57, pp. 2809–2829, 2015. DOI: https://doi.org/10.12988/ams.2015.52164

J. S. Vaiz and M. Ramaswami, "A Hybrid Model to Forecast Stock Trend Using Support Vector Machine and Neural Networks," International Journal Of Engineering Research And Development, vol. 13, no. 9, pp. 52-59, Sep. 2017.

L. Zhang, G. X. Zhang, and R. R. Li, "Water quality analysis and prediction using hybrid time series and neural network models," J. Agr. Sci. Tech., vol. 18, pp. 975-983, 2018.

S. Agarwal and S. Tarar, "A Hybrid Approach For Crop Yield Prediction Using Machine Learning And Deep Learning Algorithms," J. Phys.: Conf. Ser., vol. 1714, p. 012012, 2021. DOI: https://doi.org/10.1088/1742-6596/1714/1/012012

A. A. Alsuwaylimi, "Comparison of ARIMA, ANN and Hybrid ARIMA-ANN Models for Time Series Forecasting," Inf. Sci. Lett., vol. 12, no. 2, pp. 1003-1016, 2023. DOI: https://doi.org/10.18576/isl/120238

S. Nosratabadi et al., "Hybrid Machine Learning Models for Crop Yield Prediction," arXiv:2005.04155 [cs.NE], 2020.

D. Batool et al., "A Hybrid Approach to Tea Crop Yield Prediction Using Simulation Models and Machine Learning," Plants, vol. 11, no. 9, p. 1925, Sep. 2022, doi: 10.3390/plants11151925. DOI: https://doi.org/10.3390/plants11151925

J. H. Cochrane, "Time Series for Macroeconomics and Finance," Graduate School of Business, University of Chicago, Spring 1997.

K. W. Hipel and A. I. McLeod, Time Series Modelling of Water Resources and Environmental Systems, Amsterdam, Elsevier, 1994.

Z. Q. Zhao and D. Huang, "A mended hybrid learning algorithm for radial basis function neural networks to improve generalization capability," Applied Mathematical Modelling, vol. 31, no. 7, pp. 1271-1281, 2007. DOI: https://doi.org/10.1016/j.apm.2006.04.014

P. G. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model," Neurocomputing, vol. 50, pp. 159–175, 2003. DOI: https://doi.org/10.1016/S0925-2312(01)00702-0

Tải xuống

Đã Xuất bản

2024-02-28

Cách trích dẫn

[1]
T. S. Nguyen và C. C. Pham, “Đánh giá bằng thực nghiệm phương pháp dự báo lai ghép giữa ARIMA và RBFNN theo mô hình tuần tự cộng”, JTE, vol 19, số p.h Special Issue 01, tr 1–7, tháng 2 2024.

Số

Chuyên mục

Bài báo khoa học

Categories