Design and Prediction of Deep Fuzzy Neural Network

doi:10.16182/j.issn1004731x.joss.24-0429

Abstract

Abstract:

A deep fuzzy neural network (DFNN) is proposed to solve the problem that the deep neural network has poor interpretability and the correction of the model is not targeted when dealing with the big data regression prediction problem. The proposed deep fuzzy neural network adopts an adaptive fuzzy C-means (AFCM)clustering algorithm in structural learning. The structure of the model, namely the number of rules and the antecedent parameters of the rules, is determined by calculating the introduced validity function. The identification of consequent parameters uses an improved grey wolf optimization (IGWO) algorithm. By replacing the linear decreasing strategy in the IGWO with an exponential convergence factor, and using an adaptive position update strategy combined with dynamic weight update, the consequent parameters of the deep fuzzy neural network and the initialization parameters in the adaptive fuzzy mean clustering are optimized. The proposed deep fuzzy neural network and related algorithms are applied to Box-Jenkins gas furnace and short-term traffic flow prediction problems. The experimental results prove the feasibility of the proposed model and algorithm.

Key words: deep fuzzy neural network(DFNN), adaptive clustering, grey wolf algorithm, Box-Jenkins gas furnace, traffic flow prediction

CLC Number:

TP273

Wei Chengbiao, Zhao Taoyan, Cao Jiangtao, Li Ping. Design and Prediction of Deep Fuzzy Neural Network[J]. Journal of System Simulation, 2025, 37(9): 2200-2210.

Figures/Tables 13

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Table 1

Fig. 10

Fig. 11

Table 2

References 28

[1]	Krizhevsky A, Sutskever I, Hinton G E. ImageNet Classification with Deep Convolutional Neural Networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2012: 1097-1105.
[2]	LeCun Y, Bengio Y, Hinton G. Deep Learning[J]. Nature, 2015, 521(7553): 436-444.
[3]	Silver D, Huang A, Maddison C J, et al. Mastering the Game of Go with Deep Neural Networks and Tree Search[J]. Nature, 2016, 529(7587): 484-489.
[4]	Raju G V S, Zhou Jun, Kisner R A. Hierarchical Fuzzy Control[J]. International Journal of Control, 1991, 54(5): 1201-1216.
[5]	Wang Lixin. Universal Approximation by Hierarchical Fuzzy Systems[J]. Fuzzy Sets and Systems, 1998, 93(2): 223-230.
[6]	Francois O. An Evolutionary Strategy for Global Minimization and Its Markov Chain Analysis[J]. IEEE Transactions on Evolutionary Computation, 1998, 2(3): 77-90.
[7]	Yao Xin, Liu Yong, Lin Guangming. Evolutionary Programming Made Faster[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(2): 82-102.
[8]	Kirkpatrick S, Gelatt C D Jr, Vecchi M P. Optimization by Simulated Annealing[J]. Science, 1983, 220(4598): 671-680.
[9]	Rashedi Esmat, Nezamabadi-pour Hossein, Saryazdi Saeid. GSA: A Gravitational Search Algorithm[J]. Information Sciences, 2009, 179(13): 2232-2248.
[10]	Hatamlou Abdolreza. Black Hole: A New Heuristic Optimization Approach for Data Clustering[J]. Information Sciences, 2013, 222: 75-184.
[11]	Mirjalili Seyedali, Seyed Mohammad Mirjalili, Hatamlou Abdolreza. Multi-verse Optimizer: A Nature-inspired Algorithm for Global Optimization[J]. Neural Computing and Applications, 2016, 27(2): 495-513.
[12]	Yang Xinshe. Harmony Search as a Metaheuristic Algorithm[M]//Geem Z W. Music-Inspired Harmony Search Algorithm: Theory and Applications. Berlin: Springer, 2009: 1-14.
[13]	Zhang Jinhao, Xiao Mi, Gao Liang, et al. Queuing Search Algorithm: A Novel Metaheuristic Algorithm for Solving Engineering Optimization Problems[J]. Applied Mathematical Modelling, 2018, 63: 464-490.
[14]	Shi Yuhui. Brain Storm Optimization Algorithm[C]//Advances in Swarm Intelligence. Berlin: Springer, 2011: 303-309.
[15]	Kennedy J, Eberhart R. Particle Swarm Optimization[C]//Proceedings of ICNN'95 — International Conference on Neural Networks. Piscataway: IEEE, 1995: 1942-1948.
[16]	Dorigo Marco, Birattari Mauro, Stutzle Thomas. Ant Colony Optimization[J]. IEEE Computational Intelligence Magazine, 2006, 1(4): 28-39.
[17]	Mirjalili S, Seyed Mohammad Mirjalili, Lewis A. Grey Wolf Optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.
[18]	Mohanty Satyajit, Subudhi Bidyadhar, Pravat Kumar Ray. A New MPPT Design Using Grey Wolf Optimization Technique for Photovoltaic System Under Partial Shading Conditions[J]. IEEE Transactions on Sustainable Energy, 2016, 7(1): 181-188.
[19]	Precup R E, David R C, Petriu E M. Grey Wolf Optimizer Algorithm-based Tuning of Fuzzy Control Systems with Reduced Parametric Sensitivity[J]. IEEE Transactions on Industrial Electronics, 2017, 64(1): 527-534.
[20]	Samanta S, Suresh S, Senthilnath J, et al. A New Neuro-fuzzy Inference System with Dynamic Neurons (NFIS-DN) for System Identification and Time Series Forecasting[J]. Applied Soft Computing, 2019, 82: 105567.
[21]	Samanta Subhrajit, Pratama Mahardhika, Sundaram Suresh. A Novel Spatio-temporal Fuzzy Inference System (SPATFIS) and Its Stability Analysis[J]. Information Sciences, 2019, 505: 84-99.
[22]	Subramanian K, Suresh S. A Meta-cognitive Sequential Learning Algorithm for Neuro-fuzzy Inference System[J]. Applied Soft Computing, 2012, 12(11): 3603-3614.
[23]	Pratama M, Anavatti S G, Angelov P P, et al. PANFIS: A Novel Incremental Learning Machine[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(1): 55-68.
[24]	Pratama M, Anavatti S G, Lughofer E. GENEFIS: Toward an Effective Localist Network[J]. IEEE Transactions on Fuzzy Systems, 2014, 22(3): 547-562.
[25]	Houcine L, Bouzbida M, Chaari A. Improved Fuzzy Clustering Algorithm Using Adaptive Particle Swarm Optimization for Nonlinear System Modeling and Identification[J]. Iranian Journal of Fuzzy Systems, 2021, 3(18): 179-196.
[26]	Burak Berk Ustundag, Kulaglic Ajla. High-performance Time Series Prediction with Predictive Error Compensated Wavelet Neural Networks[J]. IEEE Access, 2020, 8: 210532-210541.
[27]	Samanta S, Pratama M, Sundaram S. Bayesian Neuro-fuzzy Inference System for Temporal Dependence Estimation[J]. IEEE Transactions on Fuzzy Systems, 2021, 29(9): 2479-2490.
[28]	王小川, 史峰, 郁磊, 等. MATLAB神经网络43个案例分析[M]. 北京: 北京航空航天大学出版社, 2013: 281-282.

模型	RMSE	MSE	MAE
NFIS-DN	0.046	0.002	0.033
SPATFIS	0.050	0.003	0.036
McFIS	0.045	0.002	0.028
PANFIS	0.070	0.005	0.048
GENEFIS	0.050	0.003	0.034
Type2-PCM	0.142 5	0.014	—
Type2-PCM-IAPSO	0.108 9	0.013	—
PEC-WNN	0.059	—	—
BaNFIS	0.063	0.004	—
DFNN	0.043	0.002	0.029

模型	规则数	训练误差	测试误差
WNN	6	29.154 2	27.043 0
FNN	11	30.519 4	28.818 2
FWNN	8	29.956 2	27.956 8
GRNN	10	30.786 1	28.276 0
IT2FNN	6	26.846 3	25.621 5
DFNN	5	24.614 2	25.194 0