Abstract
Artificial neural network models have been frequently used in time series forecasting problems as an alternative to many classical forecasting models. Although multi-layer perceptron neural networks are one of the most frequently used artificial neural networks in the literature, high-order neural networks using high-order combinations of inputs have superior performance compared to multi-layer perceptron artificial neural networks in recent years. Although there are many high-order artificial neural networks with different properties in the literature, one of the most important problems of these high-order artificial neural networks is to determine the optimization method to be used in the training of the network structure. Sigma-Pi artificial neural networks, one of the high-order artificial neural networks, have been used frequently in many problems in recent years. Like many artificial neural networks, the training of the Sigma-Pi neural network is one of the important factors affecting the performance of the network. In this study, the grey wolf optimization algorithm is used for the first time in the literature in the training of Sigma-Pi artificial neural networks. Thus, a training process that does not require complex derivative calculations in derivative-based algorithms is performed. In the evaluation of the performance of the proposed method, the closing prices of the FTSE and S&P 500 are analyzed for different years. According to the analysis results, the proposed method has a 60% success rate for both FTSE and S&P 500 time series. For the comparison of all methods, the mean rank calculation is made for each method. The proposed method took first place in this ranking and is determined as the best method among all methods.
Similar content being viewed by others
Data availability
The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
Code availability
Available upon request.
References
Arslan SN, Cagcag Yolcu O (2022) A hybrid sigma-pi neural network for combined intuitionistic fuzzy time series prediction model. Neural Comput Appl 34:12895–12917
Bas E, Egrioglu E, Karahasan O (2022a) A Pi-Sigma artificial neural network based on sine cosine optimization algorithm. Granul Comput 7:813–820
Bas E, Egrioglu E, Kolemen E (2022b) Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization. Granul Comput 7(2):411–420
Chen SM, Jian WS (2017) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups, similarity measures and PSO techniques. Inf Sci 391–392:65–79
Chen SM, Phuong BDH (2017) Fuzzy time series forecasting based on optimal partitions of intervals and optimal weighting vectors. Knowl-Based Syst 118:204–216
Chen SM, Wang NY (2010) Fuzzy forecasting based on fuzzy-trend logical relationship groups. IEEE Transa Syst Man Cybern Part B Cybern 40(5):1343–1358
Chen J, Yuan W, Cao J, Lv H (2020) Traffic-flow prediction via granular computing and stacked autoencoder. Granul Comput 5(4):449–459
Chow TWS, Cho SY (1997) Development of a recurrent Sigma-Pi neural network rainfall forecasting system in Hong Kong. Neural Comput Appl 5(2):66–75
Dash R, Rautray R, Dash R (2023) Utility of a shuffled differential evolution algorithm in designing of a Pi-Sigma Neural network-based predictor model. Appl Comput and Inform 19(1–2):22–40
Eğrioğlu E, Fildes R (2022) A new bootstrapped hybrid artificial neural network approach for time series forecasting. Comput Econ 59:1355–1383
Egrioglu E, Bas E, Karahasan O (2022) Winsorized dendritic neuron model artificial neural network and a robust training algorithm with Tukey’s biweight loss function based on particle swarm optimization. Granul Comput. https://doi.org/10.1007/s41066-022-00345-y
Fan MH, Chen MY, Liao EC (2021) A deep learning approach for financial market prediction: utilization of Google trends and keywords. Granul Comput 6(1):207–216
Fei G, Yu YL (1994) Modified sigma-pi BP network with self-feedback and its application in time series. In: Applications of artificial neural networks. SPIE, pp 508–515
Goyal G, Bisht DC (2022) Adaptive hybrid fuzzy time series forecasting technique based on particle swarm optimization. Granul Comput. https://doi.org/10.1007/s41066-022-00331-4
Gupta KK, Kumar S (2019) A novel high-order fuzzy time series forecasting method based on probabilistic fuzzy sets. Granul Comput 4(4):699–713
Gurney K (1989) Learning in nets of structured hypercubes. PhD Thesis, Department of Electrical Engineering, Brunel University, Middlesex, UK, available as: Technical Memo CN/R/144
Heywood MI, Noakes PD (1993) Simple addition to backpropagation learning for dynamic weight pruning, sparse network extraction and faster learning. In: Proceedings of IEEE ICNN, pp 620–625
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Holt CE (1957) Forecasting seasonals and trends by exponentially weighted averages (O.N.R. Memorandum No. 52). Carnegie Institute of Technology, Pittsburgh USA
Jiang F, Pourpanah F, Hao Q (2019) Design, implementation, and evaluation of a neural- network-based quadcopter UAV system. IEEE Trans Ind Electron 67(3):2076–2085
Khosravani MR (2012) Application of neural network on flight control. Int J Mach Learn Comput 2(6):882–885
Kim S, Horspool KR (2020) Aircraft speed/altitude control using a sigma-pi neural network. In: AIAA Scitech 2020 Forum, pp 1235
Kulishova N (2016) Emotion recognition using sigma-pi neural network. In: 2016 IEEE first international conference on data stream mining processing, pp 327–331
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61
Neville RS, Eldridge S (2002) Transformations of Sigma–Pi nets: obtaining reflected functions by reflecting weight matrices. Neural Netw 15(3):375–393
Neville RS, Glover RJ, Stonham TJ (1995) Evaluation of training and mapping sigma-pi networks to a massively parallel processor. In: International conference on neural networks, pp 1042–1047
Pant M, Kumar S (2021) Fuzzy time series forecasting based on hesitant fuzzy sets, particle swarm optimization and support vector machine-based hybrid method. Granul Comput 2021:1
Pant M, Kumar S (2022) Particle swarm optimization and intuitionistic fuzzy set-based novel method for fuzzy time series forecasting. Granul Comput 7(2):285–303
Pattanayak RM, Behera HS, Panigrahi S (2020) A novel hybrid differential evolution-PSNN for fuzzy time series forecasting. Adv Intell Syst Comput 990:675–687
Rumelhart DE, McClelland JL, PDP Research Group (1988) Parallel distributed processing. IEEE, New York, pp 354–362
Sahoo S, Mohanty SK, Pradhan SK (2019) Combining PI sigma neural network with multiple offspring genetic algorithm for stock market price prediction. Int J Eng Adv Technol 9(1):6934–6939
Shin Y, Gosh J (1991) The Pi-Sigma network: an efficient higher order neural network for pattern classification and function approximation. In: Proceedings of the international joint conference on neural networks, Seattle, pp 13–18
Yılmaz O, Bas E, Egrioglu E (2022) The training of Pi-Sigma artificial neural networks with differential evolution algorithm for forecasting. Comput Econ 59(4):1699–1711
Zhang BT, Muhlenbein H (1994) Synthesis of sigma-pi neural networks by the breeder genetic programming. In: Proceedings of the first IEEE conference on evolutionary computation, pp 318–323
Zhang C, Wu W, Xiong Y (2007) Convergence analysis of batch gradient algorithm for three classes of sigma-pi neural networks. Neural Process Lett 26(3):177–189
Author information
Authors and Affiliations
Contributions
Cansu Sarıkaya: Conceptualization, Methodology, Software, Writing- Original draft preparation, Writing- Reviewing and Editing, Visualization, Investigation, Data curation. Erol Egrioglu: Conceptualization, Methodology, Software, Writing- Original draft preparation, Writing- Reviewing and Editing, Visualization, Investigation, Data curation. Eren Bas: Conceptualization, Methodology, Software, Writing- Original draft preparation, Writing- Reviewing and Editing, Visualization, Investigation, Data curation.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Conflict of interest
The author declares that there is no conflict of interest toward the publication of this manuscript.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sarıkaya, C., Bas, E. & Egrioglu, E. Training Sigma-Pi neural networks with the grey wolf optimization algorithm. Granul. Comput. 8, 981–989 (2023). https://doi.org/10.1007/s41066-023-00368-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41066-023-00368-z