English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a comprehensive evaluation of the robustness and explainability ofResNet-like models in the context of Unintended Radiated Emission (URE)classification and suggest a new approach leveraging Neural StochasticDifferential Equations (SDEs) to address identified limitations. We provide anempirical demonstration of the fragility of ResNet-like models to Gaussiannoise perturbations, where the model performance deteriorates sharply and itsF1-score drops to near insignificance at 0.008 with a Gaussian noise of only0.5 standard deviation. We also highlight a concerning discrepancy where theexplanations provided by ResNet-like models do not reflect the inherentperiodicity in the input data, a crucial attribute in URE detection from stabledevices. In response to these findings, we propose a novel application ofNeural SDEs to build models for URE classification that are not only robust tonoise but also provide more meaningful and intuitive explanations. Neural SDEmodels maintain a high F1-score of 0.93 even when exposed to Gaussian noisewith a standard deviation of 0.5, demonstrating superior resilience to ResNetmodels. Neural SDE models successfully recover the time-invariant or periodichorizontal bands from the input data, a feature that was conspicuously missingin the explanations generated by ResNet-like models. This advancement presentsa small but significant step in the development of robust and interpretablemodels for real-world URE applications where data is inherently noisy andassurance arguments demand interpretable machine learning predictions.

Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions