Comparison of algorithms for AR system modeling

Objective & Hypothesis:In this paper, performance of numeric tabu search algorithm developed by authors on AR (Auto Regressive) system modeling was compared to adaptive methods and artificial neural networks.

📊

Key Findings & Data:The performances of total 16 algorithms were tested on two AR systems having 4th and 6th orders.

💡

Conclusion & Impact:The numeric tabu search algorithm was found the most successful algorithm on linear AR systems.

🔬Design:Modeling & Simulation

📍Scope:Comprehensive Sample

⚙️Variables:Domain Parameters

Abstract

In this paper, performance of numeric tabu search algorithm developed by authors on AR (Auto Regressive) system modeling was compared to adaptive methods and artificial neural networks. The adaptive methods are Least Squares Lattice, Doubje Lattice, Affine Projection algorithm, Least Mean Squares (LMS), Normalized LMS and Recursive Least Squares (RLS). Artificial neural networks trained with eight learning algorithms and classic and numeric tabu search algorithms were the rest of algorithms compared with. The performances of total 16 algorithms were tested on two AR systems having 4th and 6th orders. The numeric tabu search algorithm was found the most successful algorithm on linear AR systems.

Özet

Bu makalede, yazarlar tarafından geliştirilen sayısal tabu araştırma algoritmasının, AR (Auto Regressive) sistem modelleme performansı analiz edilmiş ve karşılaştırılmıştır. Bu karşılaştırmada, en küçük kafes kareler, çift kafes, "affine" projeksiyon, en küçük ortalama kareler, normalize edilmiş en küçük ortalama kareler ve özyineli (recursive) en küçük kareler, uyarlanabilir klasik metotlar iken 8 farklı eğitim algoritması ile eğitilmiş yapay sinir ağları, klasik ve sayısal (nümerik) tabu araştırma algoritması kullanılmıştır. Bu çalışmada, 16 farklı algoritmanın modelleme performansı 4.ve 6. dereceden iki farklı AR sistem üzerinde test edilmiştir. Genel olarak, yazarlar tarafından geliştirilen sayısal tabu araştırma algoritmasının, doğrusal AR sistem modellemede daha başarılı olduğu anlaşılmıştır.

🔖

Cite This Article

KAPLAN, A., SAĞIROĞLU, Ş., ÖZER, Ş. (2022). Comparison of algorithms for AR system modeling. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, Cilt: 19 - Sayı: 4, 431–436. https://ajindex.com/articles/524235

📄 Full Text PDF Viewer

Open in New Tab ↗

↗New Tab

📄

PDF görüntüleyici hazırlanıyor...

References (1)

Haykin, S., Adaptive Filter Theory, 3rd ed., Englewood Cliffs, NJ, Prentice-Hall, 1996. 2.Widrow, B. ve Stearns, S.D., Adaptive Signal Processing. Englewood Cliffs, Prentice- Hall,NJ, 1985. 3.Macchi, O., The Least Mean Squares Approach with Applications in Transmission. Wiley, New York, 1995. 4.Eleftheriou, E. ve Falconer, D., Tracking properties and steady-state performance of RLS adaptive filter algorithms, IEEE Trans. Acoust., Speech, Signal Processing, Cilt ASSP-34, 1097- 1110, Oct. 1986. 5.Friedlander, B., Lattice filter for adaptive processing, Proc. IEEE, Cilt 70, 829-867, Aug. 1982. 6.Tanaka, M., Kaneda, Y. Makino, S. ve Kojima,J., A Block Exact Fast Affine Projection Algorithm, IEEE Trans. Speech and Audio; Processing, Cilt 7, 79-87, Jan. 1999. 7.Özer, Ş., Güney, K. ve Kaplan, A., AR model parametrelerini ve derecesini tahmin. etme metodları, Politeknik Dergisi, Cilt 3, No 3, 67-76,2000. 8.Peters, S. D. ve Antoniu, A., A Self-Tuning NLMS Adaptive Filter Using Parallel Adaptation, IEEE Trans, on Circuits & Systems-II Analog and Digital Signal Processing, Cilt 44, No 1,11-21, January 1997. 9.Chansarkar, M. M. ve Desai, U.B., A Robust Recursive Least Squares Algorithm, IEEE Trans, on Signal Processing, Cilt 45, No 7, 1726-1735, July 1997. 10.Goodwin, K. Adaptive Filtering, Prediction and Control, Prentice-Hall, 1990. 11.Swami, A. ve Mendel, J.M., Lattice Algorithms For Recursive Instrumental Variable Methods, International Journal Of Adaptive Control and Signal Processing, 1996. 12.Farhang-Boroujeny, B., Fast LMS/Newton Algorithms Based on Autoregressive Modelling ve Their Application To Acoustic Echo Cancellation,IEEE Trans,on Signal Processing, Cilt 45, No 8, 1987-2000, August 1997. 13.Haykin, S.,Neural Networks:A Comprehensive Foundation, Macmillan College Publishing Company, New York, USA, ISBN 0-02-352761-7, 1994. 14.Rumelhart, D. E. ve McClelland, J. L., Parallel Distributed Processing. Cilt 1, The MIT Press, Cambridge, 1986. 15.Battiti, R., First and Second Order Methods for Learning: Between Steepest Descent and Newton's Method, Neural Computation, Cilt 4,No 2, 141-166, 1992. 16.Gill, P. E., Murray, W. ve Wright, M. H.,Practical Optimization, Academic Press, New York, 1981. 17.Levenberg, K., A Method For the Solution of Certain Nonlinear Problems in Least Squares, Quart. Appl. Math., Cilt 2,164-168, 1944. 18.Marquardt, D. W., An Algorithm For Least- Squares Estimation of Nonlinear Parameters, J. Soc. Ind. Appl. Math., Cilt 11, 431-441,196