Kybernetika 58 no. 4, 498-521, 2022

Global stability of Clifford-valued Takagi-Sugeno fuzzy neural networks with time-varying delays and impulses

Ramalingam Sriraman and Asha NedunchezhiyanDOI: 10.14736/kyb-2022-4-0498


In this study, we consider the Takagi-Sugeno (T-S) fuzzy model to examine the global asymptotic stability of Clifford-valued neural networks with time-varying delays and impulses. In order to achieve the global asymptotic stability criteria, we design a general network model that includes quaternion-, complex-, and real-valued networks as special cases. First, we decompose the $n$-dimensional Clifford-valued neural network into $2^mn$-dimensional real-valued counterparts in order to solve the noncommutativity of Clifford numbers multiplication. Then, we prove the new global asymptotic stability criteria by constructing an appropriate Lyapunov-Krasovskii functionals (LKFs) and employing Jensen's integral inequality together with the reciprocal convex combination method. All the results are proven using linear matrix inequalities (LMIs). Finally, a numerical example is provided to show the effectiveness of the achieved results.


global stability, impulses, T-S fuzzy, Clifford-valued neural networks, Lyapunov-Krasovskii functionals


92B20, 34D08, 35R12, 03E72


  1. C. K. Ahn: Delay-dependent state estimation for T-S fuzzy delayed Hopfield neural networks. Nonlinear Dyn. 61 (2010), 483-489.   DOI:10.1007/s11071-010-9664-z
  2. C. K. Ahn: Some new results on stability of Takagi-Sugeno fuzzy Hopfield neural networks. Fuzzy Sets Syst. 179 (2011), 100-111.   DOI:10.1016/j.fss.2011.05.010
  3. C. Aouiti and F. Dridi: Weighted pseudo almost automorphic solutions for neutral type fuzzy cellular neural networks with mixed delays and $D$ operator in Clifford algebra. Int. J. Syst. Sci. 51 (2020), 1759-1781.   DOI:10.1080/00207721.2020.1777345
  4. C. Aouiti and I. B. Gharbia: Dynamics behavior for second-order neutral Clifford differential equations: inertial neural networks with mixed delays. Comput. Appl. Math. 39 (2020), 120.   DOI:10.1109/MCG.2019.2933374
  5. P. Balasubramaniam, V. Vembarasan and R. Rakkiyappan: Leakage delays in T-S fuzzy cellular neural networks. Neural Process. Lett. 33 (2011), 111-136.   DOI:10.1007/s11063-010-9168-3
  6. N. Boonsatit, R. Sriraman, T. Rojsiraphisal, C. P. Lim, P. Hammachukiattikul and G. Rajchakit: Finite-Time Synchronization of Clifford-valued neural networks with infinite distributed delays and impulses. IEEE Access. 9 (2021), 111050-111061.   DOI:10.1109/ACCESS.2021.3102585
  7. J. Cao and D. W. C. Ho: A general framework for global asymptotic stability analysis of delayed neural networks based on LMI approach. Chaos Solitons Fract. 24 (2005), 1317-1329.   DOI:10.1016/j.chaos.2004.09.063
  8. S. Chen, H. L. Li, Y. Kao, L. Zhang and C. Hu: Finite-time stabilization of fractional-order fuzzy quaternion-valued BAM neural networks via direct quaternion approach. J. Franklin Inst. 358 (2021), 7650-7673.   DOI:10.1016/j.jfranklin.2021.08.008
  9. W. K. Clifford: Applications of grassmann's extensive algebra. Amer. J. Math. 1 (1878), 350-358.   CrossRef
  10. K. Gopalsamy: Stability of artificial neural networks with impulses. Appl. Math. Comput. 154 (2004), 783-813.   DOI:10.1016/S0096-3003(03)00750-1
  11. Z. H. Guan and G. R. Chen: On delayed impulsive Hopfield neural networks. Neural Network 12 (1999), 273-280.   DOI:10.1016/S0893-6080(98)00133-6
  12. A. Hirose: Complex-valued Neural Networks: Theories and Applications. World Scientific 2003.   CrossRef
  13. E. Hitzer, T. Nitta and Y. Kuroe: Applications of Clifford's geometric algebra. Adv. Appl. Clifford Algebras 23 (2013), 377-404.   DOI:10.1007/s00006-013-0378-4
  14. J. J. Hopfield: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81 (1984), 3088-3092.   DOI:10.1073/pnas.81.10.3088
  15. T. Isokawa, H. Nishimura, N. Kamiura and N. Matsui: Associative memory in quaternionic Hopfield neural network. Int. J. Neural Syst. 18 (2008), 135-145.   DOI:10.1142/S0129065708001440
  16. J. Jian and P. Wan: Global exponential convergence of fuzzy complex-valued neural networks with time-varying delays and impulsive effects. Fuzzy Sets Syst. 338 (2018), 23-39.   DOI:10.1016/j.fss.2017.12.001
  17. B. Li and Y. Li: Existence and global exponential stability of almost automorphic solution for Clifford-valued high-order Hopfield neural networks with leakage delays. Complexity 2019 (2019), 6751806.   DOI:10.1155/2019/6751806
  18. X. Li and J. Wu: Stability of nonlinear differential systems with state-dependent delayed impulses. Automatica 64 (2016), 63-69.   DOI:10.1016/j.automatica.2015.10.002
  19. Y. Li and J. Xiang: Existence and global exponential stability of anti-periodic solution for Clifford-valued inertial Cohen-Grossberg neural networks with delays. Neurocomputing 332 (2019), 259-269.   DOI:10.1016/j.neucom.2018.12.064
  20. Y. Liu, Z. Wang and X. Liu: Global exponential stability of generalized recurrent neural networks with discrete and distributed delays. Neural Netw. 19 (2006), 667-675.   DOI:10.1016/j.neunet.2005.03.015
  21. Y. Liu, P. Xu, J. Lu and J. Liang: Global stability of Clifford-valued recurrent neural networks with time delays. Nonlinear Dyn. 84 (2016), 767-777.   DOI:10.1007/s11071-015-2526-y
  22. S. Long, Q. Song, X. Wang and D. Li: Stability analysis of fuzzy cellular neural networks with time delay in the leakage term and impulsive perturbations. J. Franklin Inst. 349 (2012), 2461-2479.   DOI:10.1016/j.jfranklin.2012.05.009
  23. D. P. Mandic, C. Jahanchahi and C. C. Took: A quaternion gradient operator and its applications. IEEE Signal Proc. Lett. 18 (2011), 47-50.   DOI:10.1109/LSP.2010.2091126
  24. C. M. Marcus and R. M. Westervelt: Stability of analog neural networks with delay. Phys. Rev. A 39 (1989), 347-359.   DOI:10.1103/PhysRevA.39.347
  25. N. Matsui, T. Isokawa, H. Kusamichi, F. Peper and H. Nishimura: Quaternion neural network with geometrical operators. J. Intell. Fuzzy Syst. 15 (2004), 149-164.   CrossRef
  26. T. Nitta: Solving the XOR problem and the detection of symmetry using a single complex-valued neuron. Neural Netw. 16 (2003), 1101-1105.   DOI:10.1016/S0893-6080(03)00168-0
  27. P. G. Park, J. W. Ko and C. Jeong: Reciprocally convex approach to stability of systems with time-varying delays. Automatica 47 (2011), 235-238.   DOI:10.1016/j.automatica.2010.10.014
  28. J. K. Pearson and D. L. Bisset: Neural networks in the Clifford domain. In: Proc. 1994 IEEE ICNN, Orlando 1994.   CrossRef
  29. G. Rajchakit, R. Sriraman, N. Boonsatit, P. Hammachukiattikul, C. P. Lim and P. Agarwal: Exponential stability in the Lagrange sense for Clifford-valued recurrent neural networks with time delays. Adv Differ. Equat. 2021 (2021), 1-21.   DOI:10.1016/j.amc.2021.126309
  30. G. Rajchakit, R. Sriraman, C. P Lim and B. Unyong: Existence, uniqueness and global stability of Clifford-valued neutral-type neural networks with time delays. Math. Comput. Simulat. (2021).   DOI:10.1016/j.matcom.2021.02.023
  31. G. Rajchakit, R. Sriraman, P. Vignesh and C. P. Lim: Impulsive effects on Clifford-valued neural networks with time-varying delays: An asymptotic stability analysis. Appl. Math. Comput. 407 (2021), 126309.   CrossRef
  32. R. Samidurai, R. Sriraman and S. Zhu: Leakage delay-dependent stability analysis for complex-valued neural networks with discrete and distributed time-varying delays. Neurocomputing 338 (2019), 262-273.   DOI:10.1016/j.neucom.2019.02.027
  33. R. Samidurai, S. Senthilraj, Q. Zhu, R. Raja and W. Hu: Effects of leakage delays and impulsive control in dissipativity analysis of Takagi-Sugeno fuzzy neural networks with randomly occurring uncertainties. J. Franklin Inst. 354 (2017), 3574-3593.   DOI:10.1016/j.jfranklin.2017.02.027
  34. S. Shen and Y. Li: $S^p$-Almost periodic solutions of Clifford-valued fuzzy cellular neural networks with time-varying delays. Neural Process. Lett. 51 (2020), 1749-1769.   DOI:10.1007/s11063-019-10176-9
  35. H. Shu, Q. Song, Y. Liu, Z. Zhao and F. E. Alsaadi: Global $\mu$-stability of quaternion-valued neural networks with non-differentiable time-varying delays. Neurocomputing 247 (2017), 202-212.   DOI:10.1016/j.neucom.2017.03.052
  36. Q. Song: Exponential stability of recurrent neural networks with both time-varying delays and general activation functions via LMI approach. Neurocomputing 71 (2008), 2823-2830.   DOI:10.1016/j.neucom.2007.08.024
  37. Q. Song, L. Long, Z. Zhao, Y. Liu and F. E. Alsaadi: Stability criteria of quaternion-valued neutral-type delayed neural networks. Neurocomputing 412 (2020), 287-294.   DOI:10.1016/j.neucom.2020.06.086
  38. Q. Song, Z. Zhao and Y. Liu: Stability analysis of complex-valued neural networks with probabilistic time-varying delays. Neurocomputing 159 (2015), 96-104.   DOI:10.1016/j.neucom.2015.02.015
  39. T. Takagi and M. Sugeno: Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybernet. 15 (1985), 116-132.   DOI:10.1109/TSMC.1985.6313399
  40. Y. Tan, S. Tang, J. Yang and Z. Liu: Robust stability analysis of impulsive complex-valued neural networks with time delays and parameter uncertainties. J. Inequal. Appl. 2017 (2017), 215.   CrossRef
  41. L. Wang and H. K. Lam: New stability criterion for continuous-time Takagi-Sugeno fuzzy systems with time-varying delay. IEEE Trans. Cybern. 49 (2019), 1551-1556.   DOI:10.1109/TCYB.2018.2801795
  42. Z. Zhang, X. Liu, D. Zhou, C. Lin, J. Chen and H. Wang: Finite-time stabilizability and instabilizability for complex-valued memristive neural networks with time delays. IEEE Trans. Syst. Man Cybern. Syst. 48 (2018), 2371-2382.   DOI:10.1109/TSMC.2017.2754508
  43. J. Zhu and J. Sun: Global exponential stability of Clifford-valued recurrent neural networks. Neurocomputing 173 (2016), 685-689.   DOI:10.1016/j.neucom.2015.08.016