Decision-Level Fusion for Robust Wearable Affect Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Singh, Lokesh, Georgara, Athina, Deshmukh, Jayati, Nguyen, Tan Viet Tuyen, Ramchurn, Sarvapali D.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909043859128320
author Singh, Lokesh
Georgara, Athina
Deshmukh, Jayati
Nguyen, Tan Viet Tuyen
Ramchurn, Sarvapali D.
author_facet Singh, Lokesh
Georgara, Athina
Deshmukh, Jayati
Nguyen, Tan Viet Tuyen
Ramchurn, Sarvapali D.
contents Automatic recognition of affective state from wearable physiology has clear societal impact for public health, preventive care, and stress-aware interventions, but real deployments require robustness to non-stationary dynamics, artefacts, and missing sensors. We study this problem on WESAD, using baseline, stress, and amusement conditions, where common fixed-basis spectral features such as FFT bandpower and Welch PSD can oversmooth short-lived discriminative patterns. We propose a non-stationary pipeline that combines Fourier-Bessel Series Expansion (FBSE) with EWT data-driven spectral segmentation to extract mode-wise transient descriptors. For multimodal integration, we adopt decision-level aggregation over per-modality predictors and weight each modality by predictive uncertainty and modality reliability. Results on WESAD, using 15 subjects and ECG, EDA, BVP, EMG, and ACC signals across three classes, indicate that decision-level aggregation is approximately 84 percent of the time at least as good as feature-level aggregation, and approximately 48 percent of the time strictly better, suggesting improved robustness under heterogeneous and partially reliable sensing.
format Preprint
id arxiv_https___arxiv_org_abs_2605_14878
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Decision-Level Fusion for Robust Wearable Affect Recognition
Singh, Lokesh
Georgara, Athina
Deshmukh, Jayati
Nguyen, Tan Viet Tuyen
Ramchurn, Sarvapali D.
Multiagent Systems
Automatic recognition of affective state from wearable physiology has clear societal impact for public health, preventive care, and stress-aware interventions, but real deployments require robustness to non-stationary dynamics, artefacts, and missing sensors. We study this problem on WESAD, using baseline, stress, and amusement conditions, where common fixed-basis spectral features such as FFT bandpower and Welch PSD can oversmooth short-lived discriminative patterns. We propose a non-stationary pipeline that combines Fourier-Bessel Series Expansion (FBSE) with EWT data-driven spectral segmentation to extract mode-wise transient descriptors. For multimodal integration, we adopt decision-level aggregation over per-modality predictors and weight each modality by predictive uncertainty and modality reliability. Results on WESAD, using 15 subjects and ECG, EDA, BVP, EMG, and ACC signals across three classes, indicate that decision-level aggregation is approximately 84 percent of the time at least as good as feature-level aggregation, and approximately 48 percent of the time strictly better, suggesting improved robustness under heterogeneous and partially reliable sensing.
title Decision-Level Fusion for Robust Wearable Affect Recognition
topic Multiagent Systems
url https://arxiv.org/abs/2605.14878