Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387156985> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4387156985 abstract "We present a comprehensive evaluation of the robustness and explainability of ResNet-like models in the context of Unintended Radiated Emission (URE) classification and suggest a new approach leveraging Neural Stochastic Differential Equations (SDEs) to address identified limitations. We provide an empirical demonstration of the fragility of ResNet-like models to Gaussian noise perturbations, where the model performance deteriorates sharply and its F1-score drops to near insignificance at 0.008 with a Gaussian noise of only 0.5 standard deviation. We also highlight a concerning discrepancy where the explanations provided by ResNet-like models do not reflect the inherent periodicity in the input data, a crucial attribute in URE detection from stable devices. In response to these findings, we propose a novel application of Neural SDEs to build models for URE classification that are not only robust to noise but also provide more meaningful and intuitive explanations. Neural SDE models maintain a high F1-score of 0.93 even when exposed to Gaussian noise with a standard deviation of 0.5, demonstrating superior resilience to ResNet models. Neural SDE models successfully recover the time-invariant or periodic horizontal bands from the input data, a feature that was conspicuously missing in the explanations generated by ResNet-like models. This advancement presents a small but significant step in the development of robust and interpretable models for real-world URE applications where data is inherently noisy and assurance arguments demand interpretable machine learning predictions." @default.
- W4387156985 created "2023-09-30" @default.
- W4387156985 creator A5014892277 @default.
- W4387156985 creator A5035902535 @default.
- W4387156985 creator A5067109059 @default.
- W4387156985 creator A5075978538 @default.
- W4387156985 date "2023-09-26" @default.
- W4387156985 modified "2023-10-14" @default.
- W4387156985 title "Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions" @default.
- W4387156985 doi "https://doi.org/10.48550/arxiv.2309.15386" @default.
- W4387156985 hasPublicationYear "2023" @default.
- W4387156985 type Work @default.
- W4387156985 citedByCount "0" @default.
- W4387156985 crossrefType "posted-content" @default.
- W4387156985 hasAuthorship W4387156985A5014892277 @default.
- W4387156985 hasAuthorship W4387156985A5035902535 @default.
- W4387156985 hasAuthorship W4387156985A5067109059 @default.
- W4387156985 hasAuthorship W4387156985A5075978538 @default.
- W4387156985 hasBestOaLocation W43871569851 @default.
- W4387156985 hasConcept C104317684 @default.
- W4387156985 hasConcept C11413529 @default.
- W4387156985 hasConcept C115961682 @default.
- W4387156985 hasConcept C119857082 @default.
- W4387156985 hasConcept C121332964 @default.
- W4387156985 hasConcept C153180895 @default.
- W4387156985 hasConcept C154945302 @default.
- W4387156985 hasConcept C163716315 @default.
- W4387156985 hasConcept C185592680 @default.
- W4387156985 hasConcept C28826006 @default.
- W4387156985 hasConcept C33923547 @default.
- W4387156985 hasConcept C41008148 @default.
- W4387156985 hasConcept C4199805 @default.
- W4387156985 hasConcept C50644808 @default.
- W4387156985 hasConcept C51955184 @default.
- W4387156985 hasConcept C55493867 @default.
- W4387156985 hasConcept C62520636 @default.
- W4387156985 hasConcept C63479239 @default.
- W4387156985 hasConcept C99498987 @default.
- W4387156985 hasConceptScore W4387156985C104317684 @default.
- W4387156985 hasConceptScore W4387156985C11413529 @default.
- W4387156985 hasConceptScore W4387156985C115961682 @default.
- W4387156985 hasConceptScore W4387156985C119857082 @default.
- W4387156985 hasConceptScore W4387156985C121332964 @default.
- W4387156985 hasConceptScore W4387156985C153180895 @default.
- W4387156985 hasConceptScore W4387156985C154945302 @default.
- W4387156985 hasConceptScore W4387156985C163716315 @default.
- W4387156985 hasConceptScore W4387156985C185592680 @default.
- W4387156985 hasConceptScore W4387156985C28826006 @default.
- W4387156985 hasConceptScore W4387156985C33923547 @default.
- W4387156985 hasConceptScore W4387156985C41008148 @default.
- W4387156985 hasConceptScore W4387156985C4199805 @default.
- W4387156985 hasConceptScore W4387156985C50644808 @default.
- W4387156985 hasConceptScore W4387156985C51955184 @default.
- W4387156985 hasConceptScore W4387156985C55493867 @default.
- W4387156985 hasConceptScore W4387156985C62520636 @default.
- W4387156985 hasConceptScore W4387156985C63479239 @default.
- W4387156985 hasConceptScore W4387156985C99498987 @default.
- W4387156985 hasLocation W43871569851 @default.
- W4387156985 hasOpenAccess W4387156985 @default.
- W4387156985 hasPrimaryLocation W43871569851 @default.
- W4387156985 hasRelatedWork W1980122758 @default.
- W4387156985 hasRelatedWork W2087200833 @default.
- W4387156985 hasRelatedWork W2089980404 @default.
- W4387156985 hasRelatedWork W2509835205 @default.
- W4387156985 hasRelatedWork W2604674416 @default.
- W4387156985 hasRelatedWork W2948805184 @default.
- W4387156985 hasRelatedWork W3115334024 @default.
- W4387156985 hasRelatedWork W3142326235 @default.
- W4387156985 hasRelatedWork W4288335398 @default.
- W4387156985 hasRelatedWork W4310428958 @default.
- W4387156985 isParatext "false" @default.
- W4387156985 isRetracted "false" @default.
- W4387156985 workType "article" @default.