Skip to main content

Winsorized dendritic neuron model artificial neural network and a robust training algorithm with Tukey’s biweight loss function based on particle swarm optimization

Abstract

Multilayer perceptron artificial neural networks, which are one of the most popular artificial neural network models, are affected by outliers in the data set because they have both additive and multiplicative aggregation functions. From this point of view, neural networks such as Pi-Sigma and multiplicative neuron model artificial neural networks, which have either or both of these functions and have fewer parameters than the multilayer perceptron, are also affected by outliers. It is inevitable that dendritic neuron model artificial neural networks will also be affected by outliers because they also have additive and multiplicative aggregation functions. In this study, a new winsorized dendritic neuron model artificial neural network is proposed. In this new neural network, the winsorized mean in the dendrite layer of the dendritic neuron model artificial neural network is used to reduce the outlier effect in the output. Moreover, a robust learning algorithm based on Tukey’s biweight loss function is proposed for the first time in the literature for a winsorized dendritic neuron model artificial neural network. For the model to work even better in the presence of outliers, a robust standardization method is used to reduce the outlier effect in the input. Besides, the particle swarm optimization method is used in the training of the proposed artificial neural network. The performance of proposed method is performed by analyzing the opening values of the S&P 500 time series in different years for both the original state and the outlier state. As a result of the analyses made, it is concluded that the proposed method is not affected by the outliers in the data set, but the other methods compared with the proposed method are affected by the outliers in the data set.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

Data availability

All data analysed during this study are included in this published article’s supplementary files.

References

  • Ahmed U, Lin JCW, Srivastava G, Yasin R, Djenouri Y (2020) An evolutionary model to mine high expected utility patterns from uncertain databases. IEEE Trans Emerg Topics Computational Intell 5(1):19–28

    Article  Google Scholar 

  • Bas E, Egrioglu E, Yolcu U, Grosan C (2019) Type 1 fuzzy function approach based on ridge regression for forecasting. Granul Computing 4(4):629–637

    Article  Google Scholar 

  • Bas E, Yolcu U, Egrioglu E (2021) Intuitionistic fuzzy time series functions approach for time series forecasting. Granul Computing 6(3):619–629

    Article  Google Scholar 

  • Bas E, Egrioglu E, Kolemen E (2022) Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization. Granul Computing 7(2):411–420

    Article  Google Scholar 

  • Bisht K, Kumar S (2019) Hesitant fuzzy set based computational method for financial time series forecasting. Granul Computing 4(4):655–669

    Article  Google Scholar 

  • Chen W, Sun J, Gao S, Cheng JJ, Wang J, Todo Y (2017) Using a single dendritic neuron to forecast tourist arrivals to Japan. IEICE Trans Inf Syst 100(1):190–202

    Article  Google Scholar 

  • Egrioglu E, Bas E (2022) Modified Pi sigma artificial neural networks for forecasting. Granul Comput. https://doi.org/10.1007/s41066-022-00320-7

    Article  Google Scholar 

  • Egrioglu E, Yolcu U, Bas E (2019) Intuitionistic high-order fuzzy time series forecasting method based on Pi–Sigma artificial neural networks trained by artificial bee colony. Granul Comput 4(4):639–654

    Article  Google Scholar 

  • Egrioglu E, Fildes R, Bas E (2022) Recurrent fuzzy time series functions approaches for forecasting. Granul Computing 7(1):163–170

    Article  Google Scholar 

  • Gao S, Zhou M, Wang Y, Cheng J, Yachi H, Wang J (2018) Dendritic neuron model with effective learning algorithms for classification, approximation, and prediction. IEEE Trans Neural Netw Learn Syst 30(2):601–614

    Article  Google Scholar 

  • Goyal G, Bisht DCS (2022) Adaptive hybrid fuzzy time series forecasting technique based on particle swarm optimization. Granular Computing. https://doi.org/10.1007/s41066-022-00331-4

    Article  Google Scholar 

  • Gupta KK, Kumar S (2019) A novel high-order fuzzy time series forecasting method based on probabilistic fuzzy sets. Granul Computing 4(4):699–713

    Article  Google Scholar 

  • Han Z, Shi J, Todo Y, Gao S. (2020) Training dendritic neuron model with whale optimization algorithm for classification. In 2020 IEEE International Conference on Progress in Informatics and Computing (PIC), IEEE, pp 11–15

  • He H, Gao S, Jin T, Sato S, Zhang X (2021) A seasonal-trend decomposition-based dendritic neuron model for financial time series prediction. Appl Soft Comput 108:107488

    Article  Google Scholar 

  • Hou C, Shi J, Zhang B. (2021) Evolving dendritic neuron model by equilibrium optimizer algorithm. In 2021 IEEE International Conference on Progress in Informatics and Computing (PIC), IEEE, pp 14–18

  • Ji J, Song Z, Tang Y, Jiang T, Gao S. (2016) Training a dendritic neural model with genetic algorithm for classification problems. In 2016 International Conference on Progress in Informatics and Computing (PIC), IEEE, pp 47–50

  • Kennedy J, Eberhart R. (1995) Particle swarm optimization. In: Proceedings of ICNN’95-International Conference on Neural Networks, IEEE, pp 1942–1948

  • Lin JCW, Liu Q, Fournier-Viger P, Hong TP, Voznak M, Zhan J (2016a) A sanitization approach for hiding sensitive itemsets based on particle swarm optimization. Eng Appl Artif Intell 53:1–18

    Article  Google Scholar 

  • Lin JCW, Yang L, Fournier-Viger P, Wu JMT, Hong TP, Wang LSL, Zhan J (2016b) Mining high-utility item sets based on particle swarm optimization. Eng Appl Artif Intell 55:320–330

    Article  Google Scholar 

  • Maciel L, Ballini R, Gomide F (2016) Evolving granular analytics for interval time series forecasting. Granul Computing 1(4):213–224

    Article  Google Scholar 

  • 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. https://doi.org/10.1007/s41066-021-00300-3

    Article  Google Scholar 

  • Qian X, Tang C, Todo Y, Lin Q, Ji J (2020) Evolutionary dendritic neural model for classification problems. Complexity 2019; Article ID 6296209. https://doi.org/10.1155/2020/6296209

    Article  Google Scholar 

  • Rumelhart E, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. The M.I.T. Press, Cambridge, pp 318–362

    Google Scholar 

  • Shao Y, Lin JCW, Srivastava G, Guo D, Zhang H, Yi H, Jolfaei A (2021) Multi-objective neural evolutionary algorithm for combinatorial optimization problems. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2021.3105937

    Article  Google Scholar 

  • 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, 13–18

  • Song S, Chen X, Tang C, Song S, Tang Z, Todo Y (2019) Training an approximate logic dendritic neuron model using social learning particle swarm optimization algorithm. IEEE Access 7:141947–141959

    Article  Google Scholar 

  • Song Z, Tang Y, Ji J, Todo Y (2020a) Evaluating a dendritic neuron model for wind speed forecasting. Knowl-Based Syst 201:106052

    Article  Google Scholar 

  • Song Z, Zhou T, Yan X, Tang C, Ji J. (2020b) Wind speed time series prediction using a single dendritic neuron model. In 2020b 2nd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), IEEE, pp 140–144

  • Tang C, Todo Y, Ji J, Lin Q, Tang Z (2021) Artificial immune system training algorithm for a dendritic neuron model. Knowl-Based Syst 233:107509

    Article  Google Scholar 

  • Todo Y, Tamura H, Yamashita K, Tang Z (2014) Unsupervised learnable neuron model with nonlinear interaction on dendrites. Neural Netw 60:96–103

    Article  Google Scholar 

  • Wang S, Yu Y, Zou L, Li S, Yu H, Todo Y, Gao S (2020a) A novel median dendritic neuron model for prediction. IEEE Access 8:192339–192351

    Article  Google Scholar 

  • Wang Z, Gao S, Wang J, Yang H, Todo Y (2020b) A dendritic neuron model with adaptive synapses trained by differential evolution algorithm. Comput Intell Neurosci. https://doi.org/10.1155/2020/2710561

    Article  Google Scholar 

  • Wang S, Sugiyama D, Sun J, Yang L, Gao S. (2018) Dendritic neuron model trained by biogeography-based optimization for crude oil price forecasting. In 2018 10th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), IEEE, 1 36–40

  • Xu Z, Wang Z, Li J, Jin T, Meng X, Gao S (2021a) Dendritic neuron model trained by information feedback-enhanced differential evolution algorithm for classification. Knowl-Based Syst 233:107536

    Article  Google Scholar 

  • Xu W, Li C, Dou Y, Zhang M, Dong Z, Jia D, Ban X (2021b) Optimizing the weights and thresholds in dendritic neuron model using the whale optimization algorithm. J Phys: Conf Series 2025(1):012037 (IOP Publishing)

    Google Scholar 

  • Xu W, Li C, Zhang M, Dong Z, Dou Y, Jia D. (2021c) A dendritic neuron model for breast cancer classification. In 2021a 7th International Conference on Computer and Communications (ICCC), IEEE, pp 826–830

  • Yadav RN, Kalra PK, John J (2007) Time series prediction with single multiplicative neuron model. Appl Soft Comput 7:1157–1163

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • Yilmaz A, Yolcu U (2022) Dendritic neuron model neural network trained by modified particle swarm optimization for time-series forecasting. J Forecast 41(4):793–809

    MathSciNet  Article  Google Scholar 

  • Yu Y, Wang Y, Gao S, Tang Z (2017) Statistical modeling and prediction for tourism economy using dendritic neural network. Comput Intell Neurosci. https://doi.org/10.1155/2017/7436948

    Article  Google Scholar 

  • Yu Y, Lei Z, Wang Y, Zhang T, Peng C, Gao S (2021) Improving dendritic neuron model with dynamic scale-free network-based differential evolution. IEEE/CAA J Automatica Sinica 9(1):99–110

    Article  Google Scholar 

  • Yu Y, Song S, Zhou T, Yachi H, Gao S. (2016) Forecasting house price index of China using dendritic neuron model. In 2016 International Conference on Progress in Informatics and Computing (PIC), IEEE, pp 37–41

  • Yu J, Shi J, Li Z, He H, Gao S. (2020) Single dendritic neuron model trained by spherical search algorithm for classification. In 2020 IEEE International Conference on Progress in Informatics and Computing (PIC) IEEE, pp 30–33

  • Zhao L, Yang Y (2009) PSO-based single multiplicative neuron model for time series prediction. Expert Syst Appl 36:2805–2812

    Article  Google Scholar 

  • Zhao K, Zhang T, Lai X, Dou C, Yue D. (2018) A dendritic neuron based very short-term prediction model for photovoltaic power. In 2018 Chinese Control and Decision Conference (CCDC), IEEE, pp 1106–1110

  • Zhou T, Gao S, Wang J, Chu C, Todo Y, Tang Z (2016) Financial time series prediction using a dendritic neuron model. Knowl-Based Syst 105:214–224

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Erol Egrioglu.

Ethics declarations

Conflict of interest

The author declares that there is no conflict of interest in the publication of this manuscript.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor 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.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Egrioglu, E., Bas, E. & Karahasan, O. 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. (2022). https://doi.org/10.1007/s41066-022-00345-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s41066-022-00345-y

Keywords

  • Dendritic neuron model
  • Particle swarm optimization
  • Robust training algorithm
  • Outlier
  • Forecasting