ospEDA decomposes EDA signals into tonic and phasic parts via valley detection, orthogonal subspace projection, and NNLS deconvolution, achieving lower RMSE and higher F1 scores than six prior methods across simulated noise levels and five real datasets.
Elevation of spectral components of electrodermal activity precedes central nervous system oxygen toxicity symptoms in divers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
eess.SP 2years
2026 2roles
background 2polarities
background 2representative citing papers
Knowledge distillation from a hybrid CNN-Transformer teacher to a depth-wise separable CNN student, combined with realistic motion and environmental augmentation, produces a 15x smaller EDA denoiser that cuts underwater reconstruction error from 2.809 to 0.215 MAE and raises downstream CNS-OT AUROC.
citing papers explorer
-
ospEDA: Orthogonal Subspace Projection for Electrodermal Activity Decomposition
ospEDA decomposes EDA signals into tonic and phasic parts via valley detection, orthogonal subspace projection, and NNLS deconvolution, achieving lower RMSE and higher F1 scores than six prior methods across simulated noise levels and five real datasets.
-
Memory-Efficient EDA Denoising via Knowledge Distillation for Wearable IoT Under Severe Motion Artifacts and Underwater Conditions
Knowledge distillation from a hybrid CNN-Transformer teacher to a depth-wise separable CNN student, combined with realistic motion and environmental augmentation, produces a 15x smaller EDA denoiser that cuts underwater reconstruction error from 2.809 to 0.215 MAE and raises downstream CNS-OT AUROC.