Tytuł:

Machine Learning Based System Identification with Binary Output Data Using Kernel Methods,Journal of Telecommunications and Information Technology, 2024, nr 1

Tytuł publikacji grupowej:

2024, nr 1, JTIT-artykuły

Autor:

Fateh, Rachid ; Oualla, Hicham ; Azougaghe, Es-said ; Darif, Anouar ; Boumezzough, Ahmed ; Safi, Said ; Pouliquen, Mathieu ; Frikel, Miloud

Temat i słowa kluczowe:

finite impulse response ; kernel adaptive filtering ; nonlinear systems identification ; Proakis C channe

Abstrakt:

Within the realm of machine learning, kernel meth-ods stand out as a prominent class of algorithms with widespreadapplications, including but not limited to classification, regres-sion, and identification tasks. Our paper addresses the chal-lenging problem of identifying the finite impulse response (FIR)of single-input single-output nonlinear systems under the in-fluence of perturbations and binary-valued measurements. Toovercome this challenge, we exploit two algorithms that leveragethe framework of reproducing kernel Hilbert spaces (RKHS) toaccurately identify the impulse response of the Proakis C chan-nel. Additionally, we introduce the application of these kernelmethods for estimating binary output data of nonlinear systems.We showcase the effectiveness of kernel adaptive filters in identi-fying nonlinear systems with binary output measurements, asdemonstrated through the experimental results presented in thisstudy.

Wydawca:

National Institute of Telecommunications

Data wydania:

2024

Typ zasobu:

artykuł

Identyfikator zasobu:

ISSN 1509-4553, on-line: ISSN 1899-8852

DOI:

10.26636/jtit.2024.1.143

ISSN:

1509-4553

eISSN:

1899-8852

Źródło:

Journal of Telecommunications and Information Technology

Język:

ang

Licencja:

CC BY 4.0

Właściciel praw:

Instytut Łączności - Państwowy Instytut Badawczy