MDPI - Publisher of Open Access Journals

26 pages, 9222 KB

Open AccessArticle

Evaluation of Confusion Behaviors in SEI Models

by Brennan Olds, Ethan Maas and Alan J. Michaels

Sensors 2025, 25(13), 4006; https://doi.org/10.3390/s25134006 - 27 Jun 2025

Viewed by 742

Radio Frequency Machine Learning (RFML) has in recent years become a popular method for performing a variety of classification tasks on received signals. Among these tasks is Specific Emitter Identification (SEI), which seeks to associate a received signal with the physical emitter that transmitted it. Many different model architectures, including individual classifiers and ensemble methods, have proven their capabilities for producing high accuracy classification results when performing SEI. Though the works studying different model architectures report on successes, there is a notable absence regarding the examination of systemic failures and negative traits associated with learned behaviors. This work studies those failure patterns for a 64-radio SEI classification problem by isolating common patterns in incorrect classification results across multiple model architectures and two distinct control variables: Signal-to-Noise Ratio (SNR) and the quantity of training data utilized. This work finds that many of the RFML-based models devolve to selecting from amongst a small subset of classes (≈10% of classes) as SNRs decrease and that observed errors are reasonably consistent across different SEI models and architectures. Moreover, our results validate the expectation that ensemble models are generally less brittle, particularly at a low SNR, yet they appear not to be the highest-performing option at a high SNR. Full article

(This article belongs to the Special Issue Sensors for Enabling Wireless Spectrum Access)

► Show Figures

Figure 1

21 pages, 3362 KB

Open AccessArticle

Assessing the Value of Transfer Learning Metrics for Radio Frequency Domain Adaptation

by Lauren J. Wong, Braeden P. Muller, Sean McPherson and Alan J. Michaels

Mach. Learn. Knowl. Extr. 2024, 6(3), 1699-1719; https://doi.org/10.3390/make6030084 - 25 Jul 2024

Cited by 1 | Viewed by 2213

Abstract

The use of transfer learning (TL) techniques has become common practice in fields such as computer vision (CV) and natural language processing (NLP). Leveraging prior knowledge gained from data with different distributions, TL offers higher performance and reduced training time, but has yet to be fully utilized in applications of machine learning (ML) and deep learning (DL) techniques and applications related to wireless communications, a field loosely termed radio frequency machine learning (RFML). This work examines whether existing transferability metrics, used in other modalities, might be useful in the context of RFML. Results show that the two existing metrics tested, Log Expected Empirical Prediction (LEEP) and Logarithm of Maximum Evidence (LogME), correlate well with post-transfer accuracy and can therefore be used to select source models for radio frequency (RF) domain adaptation and to predict post-transfer accuracy. Full article

(This article belongs to the Section Learning)

► Show Figures

Figure 1

33 pages, 5392 KB

Open AccessArticle

An Analysis of Radio Frequency Transfer Learning Behavior

by Lauren J. Wong, Braeden Muller, Sean McPherson and Alan J. Michaels

Mach. Learn. Knowl. Extr. 2024, 6(2), 1210-1242; https://doi.org/10.3390/make6020057 - 3 Jun 2024

Cited by 3 | Viewed by 2738

Abstract

Transfer learning (TL) techniques, which leverage prior knowledge gained from data with different distributions to achieve higher performance and reduced training time, are often used in computer vision (CV) and natural language processing (NLP), but have yet to be fully utilized in the field of radio frequency machine learning (RFML). This work systematically evaluates how the training domain and task, characterized by the transmitter (Tx)/receiver (Rx) hardware and channel environment, impact radio frequency (RF) TL performance for example automatic modulation classification (AMC) and specific emitter identification (SEI) use-cases. Through exhaustive experimentation using carefully curated synthetic and captured datasets with varying signal types, channel types, signal to noise ratios (SNRs), carrier/center frequencys (CFs), frequency offsets (FOs), and Tx and Rx devices, actionable and generalized conclusions are drawn regarding how best to use RF TL techniques for domain adaptation and sequential learning. Consistent with trends identified in other modalities, our results show that RF TL performance is highly dependent on the similarity between the source and target domains/tasks, but also on the relative difficulty of the source and target domains/tasks. Results also discuss the impacts of channel environment and hardware variations on RF TL performance and compare RF TL performance using head re-training and model fine-tuning methods. Full article

(This article belongs to the Section Learning)

► Show Figures

Figure 1

17 pages, 943 KB

Open AccessArticle

Transferring Learned Behaviors between Similar and Different Radios

by Braeden P. Muller, Brennan E. Olds, Lauren J. Wong and Alan J. Michaels

Sensors 2024, 24(11), 3574; https://doi.org/10.3390/s24113574 - 1 Jun 2024

Cited by 1 | Viewed by 1280

Abstract

Transfer learning (TL) techniques have proven useful in a wide variety of applications traditionally dominated by machine learning (ML), such as natural language processing, computer vision, and computer-aided design. Recent extrapolations of TL to the radio frequency (RF) domain are being used to increase the potential applicability of RFML algorithms, seeking to improve the portability of models for spectrum situational awareness and transmission source identification. Unlike most of the computer vision and natural language processing applications of TL, applications within the RF modality must contend with inherent hardware distortions and channel condition variations. This paper seeks to evaluate the feasibility and performance trade-offs when transferring learned behaviors from functional RFML classification algorithms, specifically those designed for automatic modulation classification (AMC) and specific emitter identification (SEI), between homogeneous radios of similar construction and quality and heterogeneous radios of different construction and quality. Results derived from both synthetic data and over-the-air experimental collection show promising performance benefits from the application of TL to the RFML algorithms of SEI and AMC. Full article

(This article belongs to the Section State-of-the-Art Sensors Technologies)

► Show Figures

Figure 1

16 pages, 2692 KB

Open AccessArticle

Clustering Method for Signals in the Wideband RF Spectrum Using Semi-Supervised Deep Contrastive Learning

by Adam Olesiński and Zbigniew Piotrowski

Appl. Sci. 2024, 14(7), 2990; https://doi.org/10.3390/app14072990 - 2 Apr 2024

Cited by 2 | Viewed by 3239

Abstract

This paper presents the application of self-supervised deep contrastive learning in clustering signals detected in the wideband RF spectrum, presented in the form of spectrograms. Radio clustering is a method of searching for similar signals within the analyzed part of the radio spectrum. Typically, it is based on one or several specific parameters processed from the signal in a given channel. The authors propose a slightly different, innovative approach; thanks to the self-supervised learning of neural networks, there is no need to define specific parameters, and the feature vector, enabling comparison of Euclidean distances between signals, is generated by a deep neural network trained using a contrastive loss function on a dataset containing different radio modulations. The authors describe self-supervised solutions based on contrastive learning and the methods of signal segmentation and augmentation. The training process utilizes a custom database and the Resnet-50 network with a contrastive cost function. Radio clustering is used for autonomous spectrum analysis across wide frequency ranges and enables, among other things, the detection of tactical radio stations operating with widely dispersed frequency-hopping or a significant reduction in computational power required for real-time analysis of a large number of radio signals. Full article

(This article belongs to the Section Electrical, Electronics and Communications Engineering)

► Show Figures

Figure 1

18 pages, 24317 KB

Open AccessArticle

A Radio Frequency Region-of-Interest Convolutional Neural Network for Wideband Spectrum Sensing

by Adam Olesiński and Zbigniew Piotrowski

Sensors 2023, 23(14), 6480; https://doi.org/10.3390/s23146480 - 18 Jul 2023

Cited by 13 | Viewed by 3566

Abstract

Wideband spectrum sensing plays a crucial role in various wireless communication applications. Traditional methods, such as energy detection with thresholding, have limitations like detecting signals with low signal-to-noise ratio (SNR). This article proposes a novel deep learning-based approach for RF signal detection in the wideband spectrum. The objective is to accurately estimate the noise distribution in a wideband radio spectrogram and improve the detection performance by substracting it. The proposed method utilizes convolutional neural networks to analyze radio spectrograms. Model evaluation demonstrates that the RFROI-CNN approach outperforms the traditional energy detection with thresholding method by achieving significantly better detection results, even up to 6 dB, and expanding the capabilities of wideband spectrum sensing systems. The proposed approach, with its precise estimation of noise distribution and consideration of neighboring signal power values, proves to be a promising solution for RF signal detection. Full article

(This article belongs to the Section Communications)

► Show Figures

Figure 1

14 pages, 341 KB

Open AccessArticle

Transfer Learning for Radio Frequency Machine Learning: A Taxonomy and Survey

by Lauren J. Wong and Alan J. Michaels

Sensors 2022, 22(4), 1416; https://doi.org/10.3390/s22041416 - 12 Feb 2022

Cited by 32 | Viewed by 6273

Abstract

Transfer learning is a pervasive technology in computer vision and natural language processing fields, yielding exponential performance improvements by leveraging prior knowledge gained from data with different distributions. However, while recent works seek to mature machine learning and deep learning techniques in applications related to wireless communications, a field loosely termed radio frequency machine learning, few have demonstrated the use of transfer learning techniques for yielding performance gains, improved generalization, or to address concerns of training data costs. With modifications to existing transfer learning taxonomies constructed to support transfer learning in other modalities, this paper presents a tailored taxonomy for radio frequency applications, yielding a consistent framework that can be used to compare and contrast existing and future works. This work offers such a taxonomy, discusses the small body of existing works in transfer learning for radio frequency machine learning, and outlines directions where future research is needed to mature the field. Full article

(This article belongs to the Special Issue Radio Frequency Machine Learning (RFML) Applications)

► Show Figures

Figure 1

Search Results (7)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (7)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI