Методи нейромережевої класифікації сигналів із розширеним спектром у системах радіомоніторингу

• Published in: Технологія та конструювання в електронній апаратурі
• Date: 2026
• Issue: 1
• Pages: 38-44
• ISSN: 3083-6549
• Author Affiliations: Ivan Horbatyi — Lviv Polytechnic National University, Ukraine — ORCID: 0000-0001-6495-192X; Oleksandr Usatyi — Lviv Polytechnic National University, Ukraine — ORCID: 0009-0007-3470-702X
• Keywords: радіомоніторинг, система обробки сигналу, common-mode noise, frequency and wave spectrum, класифікація радіочастотних сенсорів, transducer, формування сигнально-кодових послідовностей, radiometric receiver, обробка сигналів, методи аналізу сигналів
• Main Authors: Horbatyi, Ivan, Usatyi, Oleksandr
• Format: Article
• Language: Ukrainian
• Published: PE "Politekhperiodika", Book and Journal Publishers 2026
• Subjects: сигнали з розширеним спектром; цифрові радіосигнали; нейронні мережі; цілочисельна квантизація; радіомоніторинг; вбудовані системи
• Online Access: https://www.tkea.com.ua/index.php/journal/article/view/TKEA2026.1.38
• Journal Title: Technology and design in electronic equipment

Automatic classification of spread spectrum signals — frequency-hopping, direct-sequence, and chirp — is a key task in modern radio monitoring systems, particularly relevant for distributed sensor networks with constrained computational resources. A critical review of existing approaches shows that none of the three generations of classification methods — classical deterministic, feature-based machine learning, and deep learning on time-frequency representations — simultaneously meets three essential requirements: high accuracy at negative signal-to-noise ratios, computational complexity below 105 multiply–accumulate operations per realization, and compatibility with integer arithmetic for embedded deployment. This paper proposes a method that addresses this gap through a compact, informative feature vector combining frequency-domain, time-frequency, and statistical characteristics. The informativeness of Hjorth parameters is theoretically justified via their analytical link to spectral moments of the power spectral density, enabling O(N) time-domain computation equivalent to frequency-domain analysis. A formalized ablation analysis with three quantitative selection criteria (individual significance, pairwise correlation below 0.7, and absence of negative contribution) yields a reduced vector of five components. Complexity analysis confirms approximately 3·104 operations per realization and 2 kB model memory in integer configuration — four orders of magnitude less than convolutional network–based approaches. Experimental evaluation of a multilayer perceptron classifier demonstrates stable accuracy above 91% across a wide SNR range, 93.2% at 20 dB and 87% at −10 dB, with negligible degradation under integer quantization, confirming practical applicability to embedded and distributed radio monitoring systems.