Time Series Prediction Using Emotional Neural Networks

Document Type : Research Paper


Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran.


Time series forecasting is important in many fields including energy management, power market, and engineering. Therefore, it is vital to introduce new algorithms that can predict time series with high accuracy. Emotional networks have recently been introduced based on emotional processes occurring in the mammalian brain. They have shown desirable numerical properties such as fast response, simple structure, learning capability, and the ability to accurately approximate and address time and complexity issues. However, their use in time-series prediction is at the primary stages. Therefore, we are inspired to use emotional models in the time-series prediction problems. Specifically, we propose to use a continuous radial basis emotional neural network (CRBENN) for time-series prediction. The normal rules of the emotional brain are used to update the network weights and the gradient descent algorithm is used to update the radial basis parameters. The proposed method is compared with two neuro and fuzzy methods in three benchmark problems. The results show the lower prediction error of the proposed method.


Main Subjects

[1]   M. Ragulskis and K. Lukoseviciute, ‘Non-uniform attractor embedding for time series forecasting by fuzzy inference systems’, Neurocomputing, vol. 72, no. 10–12, pp. 2618–2626, 2009, doi: 10.1016/j.neucom.2008.10.010.
[2]   J. Hu, X. Wang, Y. Zhang, D. Zhang, M. Zhang, and J. Xue, ‘Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network’, Neural Process. Lett., vol. 52, no. 2, pp. 1485–1500, 2020, doi: 10.1007/s11063-020-10319-3.
[3]   C. Balkenius and J. MorEn, ‘Emotional Learning: A Computational model of the amygdala’, Cybern. Syst., vol. 32, no. 6, pp. 611–636, Sep. 2001, doi: 10.1080/01969720118947.
[4]   F. Baghbani, M.-R. Akbarzadeh-T, M.-B. Naghibi-Sistani, and A. Akbarzadeh, ‘Emotional neural networks with universal approximation property for stable direct adaptive nonlinear control systems’, Eng. Appl. Artif. Intell., vol. 89, no. June 2020, p. 103447, Mar. 2020, doi: 10.1016/j.engappai.2020.103447.
[5]   S. M. Tahamipour-Z., M. R. Akbarzadeh-T., and F. Baghbani, ‘Interval type-2 generalized fuzzy hyperbolic modeling and control of nonlinear systems[Formula presented]’, Appl. Soft Comput., vol. 123, 2022, doi: 10.1016/j.asoc.2022.108859.
[6]   C. J. Lin, S. Y. Jeng, H. Y. Lin, and C. Y. Yu, ‘Design and verification of an interval type-2 fuzzy neural network based on improved particle swarm optimization’, Applied Sciences (Switzerland), vol. 10, no. 9. 2020, doi: 10.3390/app10093041.
[7]   H. Rafiei, A. Salehi, F. Baghbani, P. Parsa, and M. R. Akbarzadeh-T., ‘Interval type-2 Fuzzy control and stochastic modeling of COVID-19 spread based on vaccination and social distancing rates’, Comput. Methods Programs Biomed., vol. 232, 2023, doi: 10.1016/j.cmpb.2023.107443.
[8]   M. Gollapalli et al., ‘A Neuro-Fuzzy Approach to Road Traffic Congestion Prediction’, Comput. Mater. Contin., vol. 73, no. 1, pp. 295–310, 2022, doi: 10.32604/cmc.2022.027925.
[9]   E. I. Papageorgiou and K. Poczęta, ‘A two-stage model for time series prediction based on fuzzy cognitive maps and neural networks’, Neurocomputing, vol. 232, pp. 113–121, 2017, doi: 10.1016/j.neucom.2016.10.072.
[10] R. H. Abiyev, ‘Fuzzy wavelet neural network based on fuzzy clustering and gradient techniques for time series prediction’, Neural Comput. Appl., vol. 20, no. 2, pp. 249–259, 2011, doi: 10.1007/s00521-010-0414-4.
[11] W. Cheng et al., ‘High-efficiency chaotic time series prediction based on time convolution neural network’, Chaos, Solitons and Fractals, vol. 152, p. 111304, 2021, doi: 10.1016/j.chaos.2021.111304.
[12] T. Liu, S. Chen, S. Liang, S. Gan, and C. J. Harris, ‘Fast Adaptive Gradient RBF Networks For Online Learning of Nonstationary Time Series’, IEEE Trans. Signal Process., vol. 68, pp. 2015–2030, 2020, doi: 10.1109/TSP.2020.2981197.
[13] H. Gholizade-Narm and M. R. Shafiee Chafi, ‘Using repetitive fuzzy method for chaotic time series prediction’, J. Intell. Fuzzy Syst., vol. 28, no. 4, pp. 1937–1946, 2015, doi: 10.3233/IFS-141481.
[14] G. Heydari, M. Vali, and A. A. Gharaveisi, ‘Chaotic time series prediction via artificial neural square fuzzy inference system’, Expert Syst. Appl., vol. 55, pp. 461–468, Aug. 2016, doi: 10.1016/j.eswa.2016.02.031.
[15] D. Li, M. Han, and J. Wang, ‘Chaotic time series prediction based on a novel robust echo state network’, IEEE Trans. Neural Networks Learn. Syst., vol. 23, no. 5, pp. 787–797, 2012, doi: 10.1109/TNNLS.2012.2188414.
[16] Z. Shi and M. Han, ‘Support vector echo-state machine for chaotic time-series prediction’, IEEE Trans. Neural Networks, vol. 18, no. 2, pp. 359–372, 2007, doi: 10.1109/TNN.2006.885113.
[17] X. Yao and Z. Wang, ‘Fractional Order Echo State Network for Time Series Prediction’, Neural Process. Lett., vol. 52, no. 1, pp. 603–614, 2020, doi: 10.1007/s11063-020-10267-y.
[18] H. Zhou, Y. Zhang, W. Duan, and H. Zhao, ‘Nonlinear systems modeling based on self-organizing fuzzy neural network with hierarchical pruning scheme’, Appl. Soft Comput. J., vol. 95, p. 106516, 2020, doi: 10.1016/j.asoc.2020.106516.
[19] J. E. LeDoux, V. B. Mountcastle, and F. Plum, ‘Handbook of Physiology: Section I. The nervous system’, 1987.
[20] R. Webb, ‘The Emotional’, in Agency, 2015, pp. 103–109.
[21] J. Morén and C. Balkenius, ‘A computational model of emotional learning in the amygdala’, From Anim. to Animat., vol. 6, pp. 115–124, 2000.
[22] J. Moren, ‘Emotion and Learning- A computational model of the Amygdala’, Lund University, Lund, Sweden., 2002.
[23] M. Parsapoor, ‘An introduction to brain emotional learning inspired models (BELiMs) with an example of BELiMs’ applications’, Artif. Intell. Rev., vol. 52, no. 1, pp. 409–439, 2019, doi: 10.1007/s10462-018-9638-y.
[24] T. Babaie, R. Karimizandi, and C. Lucas, ‘Learning based brain emotional intelligence as a new aspect for development of an alarm system’, Soft Comput., vol. 12, no. 9, pp. 857–873, 2008, doi: 10.1007/s00500-007-0258-8.
[25] A. R. Mehrabian, C. Lucas, and J. Roshanian, ‘Aerospace launch vehicle control : an intelligent adaptive approach’, Aerosp. Sci. Technol., vol. 10, pp. 149–155, 2006.
[26] C. Lucas, D. Shahmirzadi, and N. Sheikholeslami, ‘Introducing belbic: Brain emotional learning based intelligent controller’, Intell. Autom. Soft Comput., vol. 10, no. 1, pp. 11–21, 2004, doi: 10.1080/10798587.2004.10642862.
[27] H. Rouhani, M. Jalili, B. N. Araabi, W. Eppler, and C. Lucas, ‘Brain emotional learning based intelligent controller applied to neurofuzzy model of micro-heat exchanger’, Expert Systems with Applications, vol. 32, no. 3. pp. 911–918, 2007, doi: 10.1016/j.eswa.2006.01.047.
[28] E. Lotfi, O. Khazaei, and F. Khazaei, ‘Competitive Brain Emotional Learning’, Neural Process. Lett., vol. 47, no. 2, pp. 745–764, Aug. 2018, doi: 10.1007/s11063-017-9680-9.
[29] O. K. Oyedotun and A. Khashman, ‘Prototype-incorporated emotional neural network’, IEEE Trans. Neural Networks Learn. Syst., vol. 29, no. 8, pp. 3560–3572, 2018, doi: 10.1109/TNNLS.2017.2730179.
[30] S. I. Abba et al., ‘Integrating feature extraction approaches with hybrid emotional neural networks for water quality index modeling’, Appl. Soft Comput., vol. 114, 2022, doi: 10.1016/j.asoc.2021.108036.
[31] E. Lotfi and M. R. Akbarzadeh-T., ‘Practical emotional neural networks’, Neural Networks, vol. 59, pp. 61–72, Nov. 2014, doi: 10.1016/j.neunet.2014.06.012.
[32] Y. Chu, S. Fu, S. Hou, and J. Fei, ‘Intelligent Terminal Sliding Mode Control of Active Power Filters by Self-Evolving Emotional Neural Network’, IEEE Trans. Ind. Informatics, vol. 19, no. 4, pp. 6138–6149, 2023, doi: 10.1109/TII.2022.3168654.
[33] E. Lotfi and M. R. Akbarzadeh-T., ‘A winner-take-all approach to emotional neural networks with universal approximation property’, Information Sciences, vol. 346–347. pp. 369–388, 2016, doi: 10.1016/j.ins.2016.01.055.
[34] M. Parsapoor and U. Bilstrup, ‘Chaotic time series prediction using Brain Emotional Learning-based Recurrent Fuzzy System (BELRFS)’, Int. J. Reason. Intell. Syst., vol. 5, no. 2, pp. 113–126, 2013, doi: 10.1504/IJRIS.2013.057273.
[35] H. Zhang, C. Yang, and J. Qiao, ‘Emotional Neural Network Based on Improved CLPSO Algorithm For Time Series Prediction’, Neural Process. Lett., 2021, doi: 10.1007/s11063-021-10672-x.
[36] F. Baghbani, M. R. Akbarzadeh-T, and M. B. N. Sistani, ‘Stable robust adaptive radial basis emotional neurocontrol for a class of uncertain nonlinear systems’, Neurocomputing, vol. 309, pp. 11–26, 2018, doi: 10.1016/j.neucom.2018.03.051.
[37] H. S. A. Milad and J. Gu, ‘Expanded Neo-Fuzzy Adaptive Decayed Brain Emotional Learning Network for Online Time Series Predication’, IEEE Access, vol. 9, pp. 65758–65770, 2021, doi: 10.1109/ACCESS.2021.3076668.
[38] E. Lotfi and M. R. Akbarzadeh-T, ‘Brain emotional learning-based pattern recognizer’, Cybern. Syst., vol. 44, no. 5, pp. 402–421, Jul. 2013, doi: 10.1080/01969722.2013.789652.