SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 13 Sayı: 3

The detailed performance analysis of online censoring-based CLMK algorithms with step size, forgetting factor, and filter order

Çevrim içi sansürleme tabanlı CLMK algoritmalarının adım büyüklüğü, unutma faktörü ve filtre derecesine göre detaylı başarım analizi

Buket Çolak Güvenç(Kayseri University)0000-0003-0805-5885
Engin Cemal Mengüç(Kayseri University)0000-0002-0619-549X
Pages
892–904
Publication Date
2024-07-15
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Thus, a guiding study is presented to the end-users of online censoring-based CLMK algorithms regarding the parameter limits within which they should be worked.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Recently, complex-valued least mean kurtosis (CLMK) algorithms have become highly popular in the literature due to the advantages they offer.
📊
Key Findings & Data:This study provides a detailed performance analysis of OC-CLMK, OC-ACLMK, ROC-CLMK, and ROC-ACLMK algorithms previously proposed by Çolak Güvenç and Mengüç, focusing on step size, forgetting factor, and filter order.
💡
Conclusion & Impact:Thus, a guiding study is presented to the end-users of online censoring-based CLMK algorithms regarding the parameter limits within which they should be worked.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Parametre analizi · Çevrim içi sansürleme · Kompleks-değerli en küçük kurtosis

Abstract

Recently, complex-valued least mean kurtosis (CLMK) algorithms have become highly popular in the literature due to the advantages they offer. This study provides a detailed performance analysis of OC-CLMK, OC-ACLMK, ROC-CLMK, and ROC-ACLMK algorithms previously proposed by Çolak Güvenç and Mengüç, focusing on step size, forgetting factor, and filter order. Firstly, the performance analysis in this study is made by comparing parameter ranges with different values and three different censoring ratios on two different scenarios of the system identification problem used in the study in which the algorithms were proposed. Then, the dependencies of the proposed online censoring-based CLMK algorithms to these crucial parameters is presented in terms of steady-state mean square error (SS-MSE). Thus, a guiding study is presented to the end-users of online censoring-based CLMK algorithms regarding the parameter limits within which they should be worked.

Özet

Kompleks-değerli en küçük kurtosis tabanlı (complex-valued least mean kurtosis, CLMK) algoritmalar sağladığı avantajlar nedeniyle son zamanlarda literatürde oldukça popüler bir hale gelmiştir. Bu çalışmada, literatürde daha önce Çolak Güvenç ve Mengüç tarafından önerilen çevrim içi sansürleme tabanlı OC-CLMK, OC-ACLMK, ROC-CLMK ve ROC-ACLMK algoritmalarının adım büyüklüğü, unutma faktörü ve filtre derecesine göre detaylı başarım analizi sunulmuştur. İlk olarak, bu çalışmada yapılan başarım analizi, algoritmaların önerildiği çalışmada kullanılan sistem tanımlama problemine ait iki farklı senaryo üzerinde birbirinden farklı değerlere sahip parametre aralıklarında ve üç farklı sansürleme oranına göre kıyaslanarak yapılmıştır. Ardından, önerilen çevrim içi sansürleme tabanlı CLMK algoritmalarının bu önemli parametrelere olan duyarlılığı kararlı-durum ortalama kare hata (steady-state mean square error, SS-MSE) olarak verilmiştir. Böylece, çevrim içi sansürleme tabanlı CLMK algoritmalarının son kullanıcılarına hangi parametre sınırları içinde çalışılması gerektiğine ilişkin yol gösterici bir çalışma sunulmuştur.

🔖

Cite This Article

Güvenç, B. Ç., Mengüç, E. C. (2024). The detailed performance analysis of online censoring-based CLMK algorithms with step size, forgetting factor, and filter order. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 13 Sayı: 3, 892–904. https://doi.org/10.28948/ngumuh.1453683

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (31)

  1. E. C. Mengüç and N. Acir, Complex-valued least mean kurtosis adaptive filter algorithm. IEEE 23rd Signal Processing and Communications Applications Conference, pp. 325–328, 2016. https://doi.org/10. 1109/SIU.2016.7495743.
  2. E. C. Mengüç and N. Acır, An augmented complex-valued least-mean kurtosis algorithm for the filtering of noncircular signals. IEEE Transactions on Signal Processing, 66 (2), 438–448, 2018. https://doi.org/ 10.1109/TSP.2017.2768024.
  3. E. Zerdali and E. C. Mengüç, Novel complex-valued stator current-based MRAS estimators using different adaptation mechanisms. IEEE Transactions on Instrumentation and Measurement, 68 (10), 3793-3795, 2019. https://doi.org/10.1109/TIM.2019.2932161.
  4. N. Gebeyehu, H. Zhao, and Y. Xia, Robust frequency estimation of unbalanced power system using a phase angle error based least mean kurtosis algorithm. International Journal of Electrical Power & Energy Systems, 110, 795-808, 2019. https://doi.org/10.1016/ j.ijepes.2019.03.052.
  5. N. Gebeyehu L., H. Zhao, and Y. Xia, Widely linear least mean kurtosis-based frequency estimation of three-phase power system. IET Generation, Transmission & Distribution, vol. 14, no. 6, pp. 1159-1167, 2019. https://doi.org/10.1049/iet-gtd.2018.6498.
  6. N. Gebeyehu and H. Zhao, Magnitude-cum-phase angle error-based WL adaptation for frequency estimation of three-phase power system. Electronics Letters, 55 (4), pp 218-220, 2019. https://doi.org /10.1049/el.2018.6911.
  7. E. C. Mengüç¸ and N. Acır, Kurtosis-Based CRTRL Algorithms for Fully Connected Recurrent Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 29 (12), 6123–6131, 2018. https://doi.org/10.1109/TNNLS.2018.2826442.
  8. E. C. Mengüç, A Novel Fully Complex Nonlinear Adaptive Finite Impulse Response Filter Algorithm. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 7 (1), 1-11, 2019. https://doi.org/10.2910 9/gujsc.42527.
  9. O. Tanrikulu and A. G. Constantinides, Least-mean kurtosis: A novel higher-order statistics based adaptive filtering algorithm. Electronics Letters, 30 (3), 189–190, 1994. https://doi.org/10.1049/el:19940129.
  10. N. J. Bershad and J. C. Bermudez, Stochastic analysis of the least mean kurtosis algorithm for Gaussian inputs. Digital Signal Processing, 54, 35-45, 2016. https://doi.org/10.1016/j.dsp.2016.03.012.
  11. P. I. Hübscher and J. C. Bermudez, A model for the behavior of the least mean kurtosis (LMK) adaptive algorithm with Gaussian inputs. International Telecommunications Symposium, 2002.
  12. E. C. Mengüç, N. Acır and D. P. Mandic, Widely Linear Quaternion-Valued Least-Mean Kurtosis Algorithm. IEEE Transactions on Signal Processing, 68, 5914-5922, 2020. https://doi.org/10.1109/TSP. 2020.3029959.
  13. E. C. Mengüç, Novel quaternion-valued least-mean Kurtosis adaptive filtering algorithm based on the GHR calculus. IET Signal Processing, 12 (4), pp. 486-495, 2019. https://doi.org/10.1049/iet-spr.2017.0340.
  14. D.P. Mandic, V.S.L. Goh, Complex Valued Nonlinear Adaptive Filters: Noncircularity, Widely Linear and Neural Models. John Wiley & Sons, 2009. https://doi.org/10.1002/9780470742624.
  15. B. Çolak Güvenç and E. C. Mengüç, A novel family of online censoring based complex-valued least mean kurtosis algorithms. Signal Processing, 216, 109302, 2024. https://doi.org/10.1016/j.sigpro.2023.109302.
  16. D. Berberidis, V. Kekatos, G.B. Giannakis, Online censoring for large-scale regressions with application to streaming big data. IEEE Trans. Signal Process. 64 (15) 3854–3867, 2016 https://doi.org/10.1109/ TSP.2016.2546225.
  17. P.S.R. Diniz, On data-selective adaptive filtering, IEEE Trans. Signal Process. 66 (16), 4239–4252, 2018. https: //doi.org/10.1109/TSP.2018.2847657.
  18. E.C. Mengüç, M. Xiang, D.P. Mandic, Online censoring based complex-valued adaptive filters. Signal Processing, 200 108638, 2022 https://doi.org/ 10.1016/j.sigpro.2022.108638.
  19. Z. Wang, Z. Yu, Q. Ling, D. Berberidis, G.B. Giannakis, Decentralized RLS with data-adaptive censoring for regressions over large-scale networks, IEEE Trans. Signal Process. 66 (6), 1634–1648, 2018. https://doi.org/10.1109/TSP.2018.2795594.
  20. E. C. Mengüç, Large-scale regression in the complex domain: Performance analysis of CRLS algorithms censoring noninformative data in an online manner. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 12 (2), pp.349-359, 2023. https:// doi.org/10.28948/ngumuh.1234303.
  21. E. C. Mengüç, N. Acır and D.P. Mandic, A Class of Online Censoring Based Quaternion-Valued Least Mean Square Algorithms. IEEE Signal Processing Letters, 30, pp. 244-248, 2023. https://doi.org/10.11 09/LSP.2023.3255000.
  22. Y. Eren, B. Çolak Güvenç and E. C. Mengüç, An acoustic feedback canceler based on probe noise and informative data for hearing aids, Signal, Image and Video Processing, 18 (1), pp.703-714, 2024. https://doi.org/10.1007/s11760-023-02786-7.
  23. Y. Eren, B. Çolak Güvenç and E. C. Mengüç, Cost-Effective Acoustic Feedback Cancellers for Digital Hearing Aids, IEEE/ACM Transactions on Audio Speech and Language Processing, 2024. https://doi.org/10.1109/TASLP.2024.3389644.
  24. Y. Eren, B. Çolak Güvenç and E. C. Mengüç, Cost-Effective Adaptive Predictor for Large-Scale Wind Signal, 2023 46th International Conference on Telecommunications and Signal Processing (TSP), Praha, Czech Republic, pp. 221-224, 2023. https://doi.org/10.1109/TSP59544.2023.10197765.
  25. B. Çolak Güvenç, Y. Eren ve E.C. Mengüç, Adaptive Prediction of Financial Data with Complex-Valued Informative Data, 2022 Elektrik-Elektronik ve Biyomedikal Mühendisliği Konferansı (ELECO), Bursa, Turkey, pp.1-5, 2022.
  26. B. Çolak Güvenç, Y. Eren ve E.C. Mengüç, Novel Online Censoring Based Learning Algorithm for Complex-Valued Big Data Streams, IEEE 30. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2022), Karabük, Turkey, 15-18 Mayıs 2022. https:// doi.org/10.1109/SIU55565.2022.9864761.
  27. Y. Eren, B. Çolak Güvenç ve E. C. Mengüç, Online Censoring Based Acoustic Feedback Cancellation for Wearable Hearing Aids, IEEE 30. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2022), Karabük, Turkey, 15-18, 2022. https://doi.org/10.1109 /SIU55 565.2022.9864685.
  28. E. C. Mengüç, Novel quaternion-valued least-mean Kurtosis adaptive filtering algorithm based on the GHR calculus. IET Signal Processing, 12 (4), pp. 486-495, 2019. https://doi.org/10.1049/iet-spr.2017.0340.
  29. B. Çolak Güvenç and E. C. Mengüç, A novel family of online censoring based complex-valued least mean kurtosis algorithms. Signal Processing, 216, 109302, 2024. https://doi.org/10.1016/j.sigpro.2023.109302.
  30. P.S.R. Diniz, On data-selective adaptive filtering, IEEE Trans. Signal Process. 66 (16), 4239–4252, 2018. https: //doi.org/10.1109/TSP.2018.2847657.
  31. Y. Eren, B. Çolak Güvenç ve E. C. Mengüç, Online Censoring Based Acoustic Feedback Cancellation for Wearable Hearing Aids, IEEE 30. Sinyal İşleme ve İletişim Uygulamaları Kurultayı (SIU 2022), Karabük, Turkey, 15-18, 2022. https://doi.org/10.1109 /SIU55 565.2022.9864685.