Abstract
This paper proposed a normalised spline adaptive filtering algorithm to improve the stability of spline adaptive filtering (SAF) algorithm against the eigenvalue spread of the autocorrelation matrix of the input signal. The new adaptive filtering algorithm is based on the normalised least mean square (NLMS) approach and the value range of the learning rate in this algorithm is specified. This algorithm is called SAF-NLMS. In this work, first the derivation of the SAF-NLMS algorithm is given. Second, detailed convergence and the computational complexity analyses are carried out. Finally, the performance of the proposed algorithm is tested according to artificial datasets and real datasets. The achieved results present actually good performance. So, in practical engineering, the algorithm can be used to solve the problem of modeling or identification of nonlinear systems.
References
Nerrand O, Roussel-Ragot P, Personnaz L, Dreyfus G (1993) Neural networks and nonlinear adaptive filtering: unifying concepts and new algorithms. Neural Comput 5(5):165–199
Barreto GA, Souza LG (2006) Adaptive filtering with the self-organizing map: a performance comparison. Neural Netw 19(6–7):785–798
Barreto GA, Barros ALBP (2014) On the design of robust linear pattern classifiers based on M-estimators. Neural Process Lett 42(1):1–19
Kong XY, Hu CH, Han CZ (2009) A self-stabilizing neural algorithm for total least squares filtering. Neural Process Lett 30(3):257–271
Widrow B, Lehr MA (1990) 30 years of adaptive neural network, perceptron, madaline, and back propagation. Proc IEEE 78(9):1415–1442
Kim JH, Zhang W, Ryu SK, Oh YS (2012) An ADALINE neural network with truncated momentum for system identification of linear time varying systems. IEEE Int Conf Ind Technol 2012:292–297
Aouiti C, M’Hamdi MS, Touati A (2016) Pseudo almost automorphic solutions of recurrent neural networks with time-varying coefficients and mixed delays. Neural Process Lett 45(1):121–140
Egrioglu E, Yolcu U, Aladag CH, Bas E (2015) Recurrent multiplicative neuron model artificial neural network for non-linear time series forecasting. Neural Process Lett 41(2):249–258
Ljung L (1999) System identification: theory for the user, 2nd edn. Prentice Hall, Englewood Cliffs
Prawin J, Rao ARM (2017) Nonlinear identification of MDOF systems using Volterra series approximation. Mech Syst Signal Process 84:58–77
LeCaillec J-M (2011) Spectral inversion of second order Volterra models based on the blind identification of Wiener models. Signal Process 91(11):2541–2555
Sicuranza GL, Carini A (2011) A generalized FLANN filter for nonlinear active noise control. IEEE Trans Audio Speech Lang Process 19(8):2412–2417
Richard C, Bermudez J, Honeine P (2009) Online prediction of time series data with kernels. IEEE Trans Signal Process 57(3):1058–1067
Engel Y, Mannor S, Meir R (2012) Kernel recursive least squares. IEEE Trans Signal Process 52(5):2275–2285
Liu W, Príncipe JC, Haykin S (2009) Extended kernel recursive least squares algorithm. IEEE Trans Signal Process 57(10):3801–3814
Liu W, Príncipe JC, Simon H (2008) Kernel affine projection algorithms. EURASIP J Adv Signal Process 2008(1):1–12
Chen B, Zhao S, Zhu P, Principe JC (2012) Quantized kernel least mean square algorithm. IEEE Trans Neural Netw Learn Syst 23(1):22–32
Parreira WD, Bermudez JCM, Richard C, Tourneret J-Y (2012) Stochastic behavior analysis of the Gaussian kernel least-mean-square algorithm. IEEE Trans Signal Process 60(5):2208–2222
Scarpiniti M, Comminiello D, Parisi R, Uncini A (2013) Nonlinear spline adaptive filtering. Signal Process 93(4):772–783
Scarpiniti M, Comminiello D, Parisi R, Uncini A (2015) Nonlinear system identification using IIR spline adaptive filters. Signal Process 108(108):30–35
Scarpiniti M, Comminiello D, Parisi R, Uncini A (2014) Hammerstein uniform cubic spline adaptive filters: learning and convergence properties. Signal Process 100(7):112–123
Patel V, George NV (2016) Compensating acoustic feedback in feed-forward active noise control systems using spline adaptive filters. Signal Process 120:448–455
Scarpiniti M, Comminiello D, Scarano G, Parisi R (2016) Steady-state performance of spline adaptive filters. IEEE Trans Signal Process 64(4):816–828
Scarpiniti M, Comminiello D, Parisi R, Uncini A (2015) Novel cascade spline architectures for the identification of nonlinear systems. IEEE Trans Circuits Syst I 62(7):1825–1835
Yin L, Astola J, Neuvo Y (1993) A new class of nonlinear filters-neural filters. IEEE Trans Signal Process 41(3):1201–1222
Widrow B (2005) Thinking about thinking: the discovery of the LMS algorithm. IEEE Signal Process Mag 22(1):100–106
Sayin MO, Vanli ND, Kozat SS (2013) A novel family of adaptive filtering algorithms based on the logarithmic cost. IEEE Trans Signal Process 62(17):4411–4424
Bershad NJ (1986) Analysis of the normalized LMS algorithm with Gaussian inputs. IEEE Trans Acoust Speech Signal Process 34(4):793–806
De Moor BLR (2006) DaISy: database for the identification of systems. Department of Electrical Engineering, ESAT/STADIUS, KU Leuven, Belgium. http://homes.esat.kuleuven.be/~smc/daisy/
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was partially supported by the National Natural Science Foundation of China (Grant: 61074120, 61673310) and the State Key Laboratory of Intelligent Control and Decision of Complex Systems of Beijing Institute of Technology.
Rights and permissions
About this article
Cite this article
Guan, S., Li, Z. Normalised Spline Adaptive Filtering Algorithm for Nonlinear System Identification. Neural Process Lett 46, 595–607 (2017). https://doi.org/10.1007/s11063-017-9606-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-017-9606-6