Abstract
In recent years, emotional neural networks (ENNs) have been extensively used in the field of time series prediction. As a variant of ENN, the radial basis emotional neural network (RBENN) is chosen as the prediction model of time series in this paper, because it has a special type of structure that can preprocess the interference in the data. However, it is difficult for many existing methods to determine network structure automatically while adjusting network parameters. To solve this problem, an RBENN based on adaptive inertia weight comprehensive learning particle swarm optimization algorithm (ADw-CLPSO-RBENN) is designed. Firstly, an adaptive inertia weight adjustment strategy based on the CLPSO algorithm (ADw-CLPSO) is exploited to balance the global and local search ability of particles. Secondly, a particle-variable dimensional learning mechanism (PVDLM) is developed based on the ADw-CLPSO algorithm, which enables particles to find the appropriate network structure while searching for the optimal parameter solution. Finally, the proposed method is evaluated in two time series and a real wastewater treatment system. The simulation results demonstrate that the proposed ADw-CLPSO-RBENN can automatically adjust to a suitable network structure, and the prediction accuracy is also better than other methods. Therefore, the proposed method has higher superiority in time series prediction.
Similar content being viewed by others
References
Ragulskis M, Lukoseviciute K (2009) Non-uniform attractor embedding for time series forecasting by fuzzy inference systems. Neurocomputing 72(10):2618–2626. https://doi.org/10.1016/j.neucom.2008.10.010
Hu J, Wang X, Zhang Y, Zhang D, Zhang M, Xue J (2020) Time series prediction method based on variant LSTM recurrent neural network. Neural Process Lett 52(2):1485–1500. https://doi.org/10.1007/s11063-020-10319-3
Qiao J, Wang L, Yang C, Gu K (2018) Adaptive Levenberg-Marquardt algorithm based echo state network for chaotic time series prediction. IEEE Access 6:10720–10732. https://doi.org/10.1109/ACCESS.2018.2810190
Li D, Han M, Wang J (2012) Chaotic time series prediction based on a novel Robust echo state network. IEEE Trans Neural Netw Learn Syst 23(5):787–799
Shi Z, Han M (2007) Support Vector echo-state machine for chaotic time-series prediction. IEEE Trans Neural Netw 18(2):359–372
Yao X, Wang Z (2020) Fractional order echo state network for time series prediction. Neural Process Lett 52(1):603–614. https://doi.org/10.1007/s11063-020-10267-y
Min H, Jianhui X, Shiguo X, Fu-Liang Y (2004) Prediction of chaotic time series based on the recurrent predictor neural network. IEEE Trans Signal Process 52(12):3409–3416
Zhang R, Lan Y, Huang G, Xu Z, Soh YC (2013) Dynamic extreme learning machine and its approximation capability. IEEE Trans Cybern 43(6):2054–2065. https://doi.org/10.1109/TCYB.2013.2239987
Liu H, Mi Xw, Li Yf (2018) Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short term memory neural network and Elman neural network. Energy Convers Manage 156:498–514. https://doi.org/10.1016/j.enconman.2017.11.053
Zhou H, Zhang Y, Duan W, Zhao H (2020) Nonlinear systems modelling based on self-organizing fuzzy neural network with hierarchical pruning scheme. Appl Soft Comput 95:106516. https://doi.org/10.1016/j.asoc.2020.106516
Lotfi E, Akbarzadeh-T MR (2013) Brain emotional learning-based pattern recognizer. Cybern Syst 44(5):402–421. https://doi.org/10.1080/01969722.2013.789652
Lotfi E, Akbarzadeh TM (2014) Practical emotional neural networks. Neural Netw 59:61–72. https://doi.org/10.1016/j.neunet.2014.06.012
Lotfi E, Akbarzadeh-T MR (2014) Adaptive brain emotional decayed learning for online prediction of geomagnetic activity indices. Neurocomputing 126:188–196. https://doi.org/10.1016/j.neucom.2013.02.040
Lotfi E, Khazaei O, Khazaei F (2018) Competitive brain emotional learning. Neural Process Lett 47(2):745–764. https://doi.org/10.1007/s11063-017-9680-9
Baghbani F, Akbarzadeh-T MR, Sistani MBN (2018) Stable robust adaptive radial basis emotional neurocontrol for a class of uncertain nonlinear systems. Neurocomputing 309:11–26. https://doi.org/10.1016/j.neucom.2018.03.051
Parsa M, Bilstrup U (2013) Chaotic time series prediction using brain emotional learning-based recurrent fuzzy system (BELRFS). Int J Reasoning-based Intell Syst. https://doi.org/10.1504/IJRIS.2013.057273
Lotfi E, Khosravi A, Akbarzadeh-T M, Nahavandi S (2014) Wind power forecasting using emotional neural networks. In: 2014 IEEE International conference on systems, man, and cybernetics (SMC), pp 311–316, https://doi.org/10.1109/SMC.2014.6973926
Parsapoor M, Bilstrup U, Svensson B (2018) Forecasting solar activity with computational intelligence models. IEEE Access 6:70902–70909. https://doi.org/10.1109/access.2018.2867516
Baghbani F, Akbarzadeh-T MR, Naghibi-Sistani MB, Akbarzadeh A (2020) Emotional neural networks with universal approximation property for stable direct adaptive nonlinear control systems. Eng Appl Artif Intell 89:103447. https://doi.org/10.1016/j.engappai.2019.103447
Fakhrmoosavy SH, Setayeshi S, Sharifi A (2018a) An intelligent method for generating artificial earthquake records based on hybrid PSO-parallel brain emotional learning inspired model. Eng Comput 34(3):449–463. https://doi.org/10.1007/s00366-017-0551-9
Fakhrmoosavy SH, Setayeshi S, Sharifi A (2018b) A modified brain emotional learning model for earthquake magnitude and fear prediction. Eng Comput 34(2):261–276. https://doi.org/10.1007/s00366-017-0538-6
Lin BS, Lin BS, Chong FC, Lai F (2007) Higher-order-statistics-based radial basis function networks for signal enhancement. IEEE Trans Neural Netw 18(3):823–32. https://doi.org/10.1109/TNN.2007.891185
Xiao Y, Wang H, Xu W (2015) Parameter selection of Gaussian kernel for one-class SVM. IEEE Trans Cybern 45(5):941–953. https://doi.org/10.1109/TCYB.2014.2340433
Margoosian A, Abouei J, Plataniotis KN (2015) An accurate kernelized energy detection in gaussian and non-gaussian/impulsive noises. IEEE Trans Signal Process 63(21):5621–5636. https://doi.org/10.1109/tsp.2015.2457400
Ma L, Khorasani K (2004) New training strategies for constructive neural networks with application to regression problems. Neural Netw 17(4):589–609. https://doi.org/10.1016/j.neunet.2004.02.002
Lin CM, Ramarao R, Gopalai SH (2019) Self-organizing adaptive fuzzy brain emotional learning control for nonlinear systems. Int J Fuzzy Syst 21(7):1989–2007. https://doi.org/10.1007/s40815-019-00698-8
Le TL, Lin CM, Huynh TT (2018) Self-evolving type-2 fuzzy brain emotional learning control design for chaotic systems using PSO. Appl Soft Comput 73:418–433. https://doi.org/10.1016/j.asoc.2018.08.022
Babaie T, Karimizandi R, Lucas C (2007) Learning based brain emotional intelligence as a new aspect for development of an alarm system. Soft Comput 12(9):857–873. https://doi.org/10.1007/s00500-007-0258-8
Balkenius C, Moren J (2001) Emotional learning: a computational model of the amygdala. Cybern Syst 32(6):611–636. https://doi.org/10.1080/01969720118947
Abdi J, Moshiri B, Abdulhai B, Sedigh AK (2012) Forecasting of short-term traffic-flow based on improved neurofuzzy models via emotional temporal difference learning algorithm. Eng Appl Artif Intell 25(5):1022–1042. https://doi.org/10.1016/j.engappai.2011.09.011
Sharafi Y, Setayeshi S, Falahiazar A (2014) An improved model of brain emotional learning algorithm based on interval knowledge. J Math Comput Sci (JMCS) 14:42–53. https://doi.org/10.22436/jmcs.014.01.05
Falahiazar A, Setayeshi S, Sharafi Y (2014) Computational model of social intelligence based on emotional learning in the amygdala. J Math Comput Sci (JMCS). https://doi.org/10.13140/RG.2.2.28214.50248
Amani F, Amjadifard R (2019) Chaotic time series forecasting using emotional learning-based neural networks. In: 2019 6th international conference on control, instrumentation and automation (ICCIA), pp 1–6, https://doi.org/10.1109/ICCIA49288.2019.9030986
Parsapoor M (2019) An introduction to brain emotional learning inspired models (BELiMs) with an example of BELiMs applications. Artif Intell Rev 52(1):409–439. https://doi.org/10.1007/s10462-018-9638-y
Mei Y, Tan Gz (2018) An improved brain emotional learning algorithm for accurate and efficient data analysis. J Central South Univ 25(5):1084–1098. https://doi.org/10.1007/s11771-018-3808-6
Dorrah HT, El-Garhy AM, El-Shimy ME (2011) PSO-BELBIC scheme for two-coupled distillation column process. J Adv Res 2(1):73–83. https://doi.org/10.1016/j.jare.2010.08.004
Oldewage ET, Engelbrecht AP, Cleghorn CW (2020) Movement patterns of a particle swarm in high dimensional spaces. Inf Sci 512:1043–1062. https://doi.org/10.1016/j.ins.2019.09.057
Zamirpour E, Mosleh M (2018) A biological brain-inspired fuzzy neural network: fuzzy emotional neural network. Biol Inspir Cognit Arch 26:80–90. https://doi.org/10.1016/j.bica.2018.07.019
Hu W, Yan L, Liu K, Wang H (2016) A Short-term Traffic Flow Forecasting Method Based on the Hybrid PSO-SVR. Neural Process Lett 43(1):155–172. https://doi.org/10.1007/s11063-015-9409-6
Liang JJ, Qin AK, Suganthan PN, Baskar S (2006) Comprehensive learning particle swarm optimizer for global optimization of multimodal functions. IEEE Trans Evol Comput 10(3):281–295. https://doi.org/10.1109/tevc.2005.857610
Han HG, Chen QL, Qiao JF (2011) An efficient self-organizing RBF neural network for water quality prediction. Neural Netw 24(7):717–25. https://doi.org/10.1016/j.neunet.2011.04.006
Chauhan P, Deep K, Pant M (2013) Novel inertia weight strategies for particle swarm optimization. Memetic Comput 5(3):229–251. https://doi.org/10.1007/s12293-013-0111-9
Liang HT, Kang FH (2016) Adaptive mutation particle swarm algorithm with dynamic nonlinear changed inertia weight. Optik 127(19):8036–8042. https://doi.org/10.1016/j.ijleo.2016.06.002
Tran B, Xue B, Zhang M (2019) Variable-length particle swarm optimization for feature selection on high-dimensional classification. IEEE Trans Evol Comput 23(3):473–487. https://doi.org/10.1109/TEVC.2018.2869405
Shi Y, Eberhart R (1998) A modified particle swarm optimizer. In: 1998 IEEE international conference on evolutionary computation proceedings. IEEE world congress on computational intelligence (Cat. No.98TH8360), pp 69–73, https://doi.org/10.1109/ICEC.1998.699146
Xin J, Chen G, Hai Y (2009) A particle swarm optimizer with multi-stage linearly-decreasing inertia weight. In: 2009 International joint conference on computational sciences and optimization, vol 1, pp 505–508, https://doi.org/10.1109/CSO.2009.420
Lotfi E, Akbarzadeh-T MR (2016) A winner-take-all approach to emotional neural networks with universal approximation property. Inf Sci 346–347:369–388. https://doi.org/10.1016/j.ins.2016.01.055
Qiao J, Pan G, Han H (2015) Design and application of continuous deep belief network. Acta Autom Sin 41(12):2138–2146
Asadi R, Regan AC (2020) A spatio-temporal decomposition based deep neural network for time series forecasting. Appl Soft Comput 87:105963. https://doi.org/10.1016/j.asoc.2019.105963
Han H, Lu W, Hou Y, Qiao J (2018) An adaptive-PSO-based self-organizing RBF neural network. IEEE Trans Neural Netw Learn Syst 29(1):104–117. https://doi.org/10.1109/TNNLS.2016.2616413
Zhang L, Li J, Yang H (2019) T-S fuzzy model identification with sparse bayesian techniques. Neural Process Lett 50(3):2945–2962. https://doi.org/10.1007/s11063-019-10071-3
Han M, Xu M (2015) Predicting multivariate time series using subspace echo state network. Neural Process Lett 41(2):201–209. https://doi.org/10.1007/s11063-013-9324-7
Han H, Wu X, Zhang L, Tian Y, Qiao J (2019) Self-organizing RBF neural network using an adaptive gradient multiobjective particle swarm optimization. IEEE Trans Cybern 49(1):69–82. https://doi.org/10.1109/TCYB.2017.2764744
Yang C, Qiao J, Ahmad Z, Nie K, Wang L (2019) Online sequential echo state network with sparse RLS algorithm for time series prediction. Neural Netw 118:32–42. https://doi.org/10.1016/j.neunet.2019.05.006
Li D, Xu X, Li Z, Wang T, Wang C (2020) Detection methods of ammonia nitrogen in water: a review. TrAC, Trends Anal Chem 127:115890. https://doi.org/10.1016/j.trac.2020.115890
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grants 61533002, 61890930 and 61973010, the Major Science and Technology Program for Water Pollution Control and Treatment of China (2018ZX07111005), and the National Key Research and Development Project under Grants 2018YFC1900800-5.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Parameters Setting for ENN-GA, BELPR and WTAENN
Appendix: Parameters Setting for ENN-GA, BELPR and WTAENN
For the ENN-GA, the parameters of GA are given: the size of population is 4000 and the maximum generation is 4000. For BELPR, the method of initializing the weights V and W of the AMYG and OFC neurons is the same as in the original literature [11], in which V is randomly initialized in the range of [0, 1] and W is its opposite vector. In addition, the learning rate varies from 0.05 to 0.8 by step of 0.01, the decay rate varies from 0.001 to 0.01 by step of 0.001. For WTAENN, the number of competitive parts is 1, the parameters of the GA are given as: the size of population is 100 and the maximum generation is 400.
Rights and permissions
About this article
Cite this article
Zhang, H., Yang, C. & Qiao, J. Emotional Neural Network Based on Improved CLPSO Algorithm For Time Series Prediction. Neural Process Lett 54, 1131–1154 (2022). https://doi.org/10.1007/s11063-021-10672-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10672-x