aiqbench analysis
This research demonstrates that fusing multiple visual representations of electrodermal activity (EDA) signals, such as spectrograms and scalograms, alongside raw waveforms, yields measurable improvements in automated stress detection accuracy. By employing a shared asymmetric-attention architecture to process these complementary inputs, the study achieves higher classification performance than using raw data alone while offering insights into efficient feature selection.
Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection
arXiv:2609.22095v1 Announce Type: cross Abstract: Electrodermal activity (EDA) is widely used in automatic stress detection, yet most pipelines treat it only as a raw one-dimensional waveform. This study examines whether complementary visual representations of EDA provide useful information for stress classification and whether their fusion im- proves recognition performance. Six image-based representations are derived from each EDA recording: an unwrapped short-time Fourier transform (STFT) phase spectrogram, an instantaneous-frequency map computed from that phase, a power spectral density (PSD) spectrogram, a continuous wavelet transform scalogram, a recurrence plot, and a rendered waveform trace. The selected representations are stacked as channels of a single multichannel input, together with the raw waveform, and processed by a shared asymmetric-attention architecture. Experiments on a 58-subject stress dataset show that representation fusion improves over the raw waveform. The best configuration, which combines five representations while excluding the unwrapped phase spectrogram, reaches 70.97% test accuracy, compared with 67.36% for the raw waveform. The single PSD spectrogram achieves 69.44%, remaining close to the best-fused configuration at a lower computational cost. The results show that alternative visual forms of the same EDA signal can provide useful inductive biases for stress detection, and that a compact selection of complementary representations can be more effective than the raw waveform alone.
Abstract:Electrodermal activity (EDA) is widely used in automatic stress detection, yet most pipelines treat it only as a raw one-dimensional waveform. This study examines whether complementary visual representations of EDA provide useful information for stress classification and whether their fusion im- proves recognition performance. Six image-based representations are derived from each EDA recording: an unwrapped short-time Fourier transform (STFT) phase spectrogram, an instantaneous-frequency map computed from that phase, a power spectral density (PSD) spectrogram, a continuous wavelet transform scalogram, a recurrence plot, and a rendered waveform trace. The selected representations are stacked as channels of a single multichannel input, together with the raw waveform, and processed by a shared asymmetric-attention architecture. Experiments on a 58-subject stress dataset show that representation fusion improves over the raw waveform. The best configuration, which combines five representations while excluding the unwrapped phase spectrogram, reaches 70.97% test accuracy, compared with 67.36% for the raw waveform. The single PSD spectrogram achieves 69.44%, remaining close to the best-fused configuration at a lower computational cost. The results show that alternative visual forms of the same EDA signal can provide useful inductive biases for stress detection, and that a compact selection of complementary representations can be more effective than the raw waveform alone.
Signal Processing (eess.SP); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
arXiv:2609.22095 [eess.SP]
(or arXiv:2609.22095v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2609.22095 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 306 words
Related coverage
End-to-End Cell Detection via Instance-aware Graph Modeling
arXiv · Sep 16, 2026
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026
Why do models task game?
AI Alignment Forum · Aug 6, 2026
FUSE: Frame-Unified Stress Estimation from Facial Video
arXiv · Aug 19, 2026