Design of passive filters for time-delay neural networks with quantized output

doi:10.1088/1674-1056/aba602

Abstract

Passive filtering of neural networks with time-invariant delay and quantized output is considered. A criterion on the passivity of a filtering error system is proposed by means of the Lyapunov–Krasovskii functional and the Bessel–Legendre inequality. Based on the criterion, a design approach for desired passive filters is developed in terms of the feasible solution of a set of linear matrix inequalities. Then, analyses and syntheses are extended to the time-variant delay situation using the reciprocally convex combination inequality. Finally, a numerical example with simulations is used to illustrate the applicability and reduced conservatism of the present passive filter design approaches.

Keywords: neural networks time delay quantization filtering

Received: 13 May 2020
Revised: 16 June 2020
Accepted manuscript online: 15 July 2020

Fund: the Excellent Youth Talent Support Program of Universities in Anhui Province, China (Grant No. GXYQZD2019021), the Major Research Project of Anhui Provincial Department of Education, China (Grant No. KJ2017ZD05), and the National Natural Science Foundation of China (Grant Nos. 61503002 and 61973199).

Corresponding Authors: ^†Corresponding author. E-mail: jpzhou0@gmail.com

Cite this article:

Jing Han(韩静), Zhi Zhang(章枝), Xuefeng Zhang(张学锋), and Jianping Zhou(周建平) Design of passive filters for time-delay neural networks with quantized output 2020 Chin. Phys. B 29 110201

Fig. 1.

State trajectories of x₁(t) and its estimation ${\mathop{x}\limits^{\unicode{x2323}}}_{1}(t)$.

Fig. 2.

State trajectories of x₂(t) and its estimation ${\mathop{x}\limits^{\unicode{x2323}}}_{2}(t)$.

Fig. 3.

State trajectories of filtering error λ(t).

1	Hopfield J J 1982 Proc. Natl. Acad. Sci. USA 79 2554 DOI: 10.1073/pnas.79.8.2554
2	Hu B, Guan Z, Chen G, Lewis F L 2019 IEEE Trans. Neural. Netw. Learn. Syst. 30 1537 DOI: 10.1109/TNNLS.2018.2870553
3	Wang W, Jia X, Luo X, Kurths J, Yuan M 2019 Chaos Soliton. Fract. 126 85 DOI: 10.1016/j.chaos.2019.05.041
4	Alimi A M, Aouiti C, Assali E A 2019 Neurocomputing 332 29 DOI: 10.1016/j.neucom.2018.11.020
5	Wei T, Lin P, Wang Y, Wang L 2019 Neural Netw. 116 35 DOI: 10.1016/j.neunet.2019.03.016
6	Chen L, Hao Y, Huang T, Yuan L, Zheng S, Yin L 2020 Neural Netw. 125 174 DOI: 10.1016/j.neunet.2020.02.008
7	Kwon O M, Park M J, Park J H, Lee S M, Cha E J 2013 Chin. Phys. B 22 110504 DOI: 10.1088/1674-1056/22/11/110504
8	Yang X, Song Q, Liang J, He B 2015 J. Franklin Inst. 352 4382 DOI: 10.1016/j.jfranklin.2015.07.001
9	Thuan M V, Tran H M, Trinh H 2018 Neural. Comput. Appl. 29 783 DOI: 10.1007/s00521-016-2580-5
10	Zhou J, Liu Y, Xia J, Wang Z, Arik S 2020 Neural Netw. 125 194 DOI: 10.1016/j.neunet.2020.02.015
11	Saravanakumar R, Stojanovic S B, Radosavljevic D D, Ahn C K, Karimi H R 2019 IEEE Trans. Neural Netw. Learn. Syst. 30 58 DOI: 10.1109/TNNLS.2018.2829149
12	Liu Y, Xuan Z, Wang Z, Zhou J, Liu Y 2020 Appl. Math. Comput. 385 125429 DOI: 10.1016/j.amc.2020.125429
13	Zhou J, Liu Y, Park J H, Kong Q, Wang Z 2020 Discrete & Continuous Dynamical Systems S in press DOI: 10.3934/dcdss.2020357
14	Wang Z, Ho D W C, Liu X 2005 IEEE Trans. Neural Netw. 16 279 DOI: 10.1109/TNN.2004.841813
15	Huang H, Feng G, Cao J 2008 IEEE Trans. Neural Netw. 19 1329 DOI: 10.1109/TNN.2008.2000206
16	Ahn C K 2010 Proc. Inst. Mech. Eng. I. J. Syst. Control. Eng. 224 1040 DOI: 10.1243/09596518JSCE1056
17	Shi P, Zhang Y, Chadli M, Agarwal R K 2016 IEEE Trans Neural Netw. Learn. Syst. 27 903 DOI: 10.1109/TNNLS.2015.2425962
18	Chang X, Wang Y 2018 IEEE Trans. Industr. Inform. 14 5378 DOI: 10.1109/TII.2018.2805707
19	Park J H, Shen H, Chang X, Lee T H Recent Advances in Control and Filtering of Dynamic Systems with Constrained Signals Berlin Springer DOI: 10.1016/j.neunet.2016.06.006
20	Liu J, Tang J, Fei S 2016 Neural Netw. 82 39 DOI: 10.1016/j.neunet.2016.06.006
21	Lu R, Tao J, Shi P, Su H, Wu Z, Xu Y 2018 IEEE Trans. Neural Netw. Learn. Syst. 29 1888 DOI: 10.1109/TNNLS.2017.2688582
22	Shen Y, Wu Z, Shi P, Su H, Huang T 2019 IEEE Trans. Syst. Man Cybern. Syst. 49 433 DOI: 10.1109/TSMC.2017.2789180
23	Zhou J, Wang Y, Zheng X, Wang Z, Shen H 2019 Nonlinear Dyn. 96 853 DOI: 10.1007/s11071-019-04826-9
24	Jia Y, Jiang G 2017 Acta Phys. Sin. 66 160501 in Chinese DOI: 10.7498/aps.66.160501
25	Liu H, Li S, Wang H, Li G 2017 Chin. Phys. B 26 030504 DOI: 10.1088/1674-1056/26/3/030504
26	Yang X, Li C, Song Q, Li H, Huang J 2019 IEEE Trans. Neural Netw. Learn. Syst. 30 2197 DOI: 10.1109/TNNLS.2018.2877152
27	Arik S 2020 IEEE Trans. Neural Netw. Learn. Syst. 31 1504 DOI: 10.1109/TNNLS.2019.2920672
28	Meng X, Kao Y, Karimi H R, Gao C 2020 Sci. China Inf. Sci. 63 132201 DOI: 10.1007/s11432-019-9946-6
29	Yan Z, Huang X, Fan Y, Xia J, Shen H 2020 IEEE Trans. Syst. Man Cybern. Syst. in press DOI: 10.1109/TSMC.2020.2964605
30	Chen C, Ding Z, Li S, Wang L 2020 Chin. Phys. B 29 040202 DOI: 10.1088/1674-1056/ab7803
31	Liu Y, Fang F, Park J H, Kim H, Yi X 2019 Nonlinear Anal: Hybrid Syst. 31 109 DOI: 10.1016/j.nahs.2018.08.006
32	Fu M, Xie L 2005 IEEE Trans. Auto. Contr. 50 1699 DOI: 10.1109/TAC.2005.858689
33	Seuret A, Gouaisbaut F 2015 Syst. Control. Lett. 81 1 DOI: 10.1016/j.sysconle.2015.03.007
34	Zhou K, Khargonekar P P 1988 Syst. Control. Lett. 10 17 DOI: 10.1016/0167-6911(88)90034-5
35	He Y, Wang Q, Xie L, Lin C 2007 IEEE Trans. Auto. Contr. 52 293 DOI: 10.1109/TAC.2006.887907
36	Park P G, Ko J W, Jeong C 2011 Automatica 47 235 DOI: 10.1016/j.automatica.2010.10.014
37	Yan Z, Huang X, Cao J 2019 Sci. China Inf. Sci. 63 212201 DOI: 10.1007/s11432-019-2664-7
38	Wang W, Zeng H, Teo K 2017 Chin. Phys. B 26 110503 DOI: 10.1088/1674-1056/26/11/110503
39	Sakthivel R, Wang C, Santra S, Kaviarasan B 2018 Nonlinear Anal: Hybrid Syst. 27 62 DOI: 10.1016/j.nahs.2017.08.005
40	Zhuang G, Xu S, Xia J, Ma Q, Zhang Z 2019 Appl. Math. Comput. 355 21 DOI: 10.1016/j.amc.2019.02.057
41	Bao H, Cao J, Kurths J, Alsaedi A, Ahmad B 2018 Neural Netw. 99 79 DOI: 10.1016/j.neunet.2017.12.014
42	Tai W, Teng Q, Zhou Y, Zhou J, Wang Z 2019 Appl. Math. Comput. 354 115 DOI: 10.1016/j.amc.2019.02.028
43	Chen W, Xu S, Li Y, Zhang Z 2020 J. Franklin Inst. 357 3721 DOI: 10.1016/j.jfranklin.2020.02.038
44	Wang X, Wang Z, Song Q, Shen H, Huang X 2020 Neural Netw. 121 329 DOI: 10.1016/j.neunet.2019.09.032
45	Liu K, Seuret A, Xia Y 2017 Automatica 76 138 DOI: 10.1016/j.automatica.2016.11.001
46	Chen Y, Zhang Z, Liu Y, Zhou J, Wang Z 2020 Commun. Nonlinear Sci. Numer. Simulat. 89 105335 DOI: 10.1016/j.cnsns.2020.105335

[1]	Meshfree-based physics-informed neural networks for the unsteady Oseen equations Keyi Peng(彭珂依), Jing Yue(岳靖), Wen Zhang(张文), and Jian Li(李剑). Chin. Phys. B, 2023, 32(4): 040208.
[2]	Hopf bifurcation and phase synchronization in memristor-coupled Hindmarsh-Rose and FitzHugh-Nagumo neurons with two time delays Zhan-Hong Guo(郭展宏), Zhi-Jun Li(李志军), Meng-Jiao Wang(王梦蛟), and Ming-Lin Ma(马铭磷). Chin. Phys. B, 2023, 32(3): 038701.
[3]	Effect of autaptic delay signal on spike-timing precision of single neuron Xuan Ma(马璇), Yaya Zhao(赵鸭鸭), Yafeng Wang(王亚峰), Yueling Chen(陈月玲), and Hengtong Wang(王恒通). Chin. Phys. B, 2023, 32(3): 038703.
[4]	Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks Jian Zhang(张健), Yiming Liu(刘一鸣), and Zhanchun Tu(涂展春). Chin. Phys. B, 2022, 31(9): 094502.
[5]	Review on typical applications and computational optimizations based on semiclassical methods in strong-field physics Xun-Qin Huo(火勋琴), Wei-Feng Yang(杨玮枫), Wen-Hui Dong(董文卉), Fa-Cheng Jin(金发成), Xi-Wang Liu(刘希望), Hong-Dan Zhang(张宏丹), and Xiao-Hong Song(宋晓红). Chin. Phys. B, 2022, 31(3): 033101.
[6]	Wire network behavior of superconducting films with lower symmetrical mesoscopic hole arrays Wei-Gui Guo(郭伟贵), Zi-Xi Pei(裴子玺), and Xiang-Gang Qiu(邱祥冈). Chin. Phys. B, 2022, 31(3): 037405.
[7]	Inferring interactions of time-delayed dynamic networks by random state variable resetting Changbao Deng(邓长宝), Weinuo Jiang(蒋未诺), and Shihong Wang(王世红). Chin. Phys. B, 2022, 31(3): 030502.
[8]	Iterative filtered ghost imaging Shao-Ying Meng(孟少英), Mei-Yi Chen(陈美伊), Jie Ji(季杰), Wei-Wei Shi(史伟伟), Qiang Fu(付强), Qian-Qian Bao(鲍倩倩), Xi-Hao Chen(陈希浩), and Ling-An Wu(吴令安). Chin. Phys. B, 2022, 31(2): 028702.
[9]	Bifurcation and dynamics in double-delayed Chua circuits with periodic perturbation Wenjie Yang(杨文杰). Chin. Phys. B, 2022, 31(2): 020201.
[10]	Parameter estimation of continuous variable quantum key distribution system via artificial neural networks Hao Luo(罗浩), Yi-Jun Wang(王一军), Wei Ye(叶炜), Hai Zhong(钟海), Yi-Yu Mao(毛宜钰), and Ying Guo(郭迎). Chin. Phys. B, 2022, 31(2): 020306.
[11]	Learnable three-dimensional Gabor convolutional network with global affinity attention for hyperspectral image classification Hai-Zhu Pan(潘海珠), Mo-Qi Liu(刘沫岐), Hai-Miao Ge(葛海淼), and Qi Yuan(袁琪). Chin. Phys. B, 2022, 31(12): 120701.
[12]	Finite-time Mittag—Leffler synchronization of fractional-order complex-valued memristive neural networks with time delay Guan Wang(王冠), Zhixia Ding(丁芝侠), Sai Li(李赛), Le Yang(杨乐), and Rui Jiao(焦睿). Chin. Phys. B, 2022, 31(10): 100201.
[13]	Spin transport properties for B-doped zigzag silicene nanoribbons with different edge hydrogenations Jing-Fen Zhao(赵敬芬), Hui Wang(王辉), Zai-Fa Yang(杨在发), Hui Gao(高慧), Hong-Xia Bu(歩红霞), and Xiao-Juan Yuan(袁晓娟). Chin. Phys. B, 2022, 31(1): 017302.
[14]	Approximate analytical solutions and mean energies of stationary Schrödinger equation for general molecular potential Eyube E S, Rawen B O, and Ibrahim N. Chin. Phys. B, 2021, 30(7): 070301.
[15]	Spectral filtering of dual lasers with a high-finesse length-tunable cavity for rubidium atom Rydberg excitation Yang-Yang Liu(刘杨洋), Zhuo Fu(付卓), Peng Xu(许鹏), Xiao-Dong He(何晓东), Jin Wang(王谨), and Ming-Sheng Zhan(詹明生). Chin. Phys. B, 2021, 30(7): 074203.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Design of passive filters for time-delay neural networks with quantized output

Cite this article:

Online attention