Unit-Independent Low-Rate Wrist GSR Processing for Stress Detection Using Phasic nSCR Features

2026-07-08

AI Summary

This study addresses the challenge of unreliable absolute amplitude in wrist-worn galvanic skin response (GSR) signals due to inter-individual and device-related variability, which hinders robust stress detection. The authors propose a device-agnostic GSR processing pipeline operating at a low sampling rate of 25 Hz, incorporating signal cleaning, decomposition into skin conductance level (SCL) and skin conductance response (SCR), robust z-score normalization, and SCR peak detection. This approach enables, for the first time, the extraction of a unit-invariant feature—number of SCRs per minute (nSCR/min)—without reliance on high sampling rates or palmar measurements. Evaluated on a binary classification task distinguishing Trier Social Stress Test (TSST) from resting states, the method achieves balanced accuracies of 0.823 and 0.871, respectively, with performance at 25 Hz comparable to that of the original 100 Hz data.

Abstract

Galvanic skin response (GSR) is widely used for stress detection, but wrist-based GSR remains challenging because its absolute amplitude can differ substantially from laboratory-grade palmar measurements. In this paper, we propose a unit-independent low-rate wrist GSR processing pipeline to extract the number of skin conductance responses per minute (nSCR/min) as a stress-related feature. We collect paired wrist and palmar GSR recordings from 31 participants during sitting baseline, standing baseline, neutral speaking, and the Trier Social Stress Test (TSST), a laboratory social stressor task. The proposed pipeline cleans the raw GSR signal, decomposes it into tonic skin conductance level (SCL) and phasic skin conductance response (SCR), applies robust z-score normalization, and detects phasic SCR peaks to compute nSCR/min. Using random forest on 25Hz We-Be GSR, nSCR/min achieved balanced accuracies of 0.823 and 0.871 for binary classification between TSST and the sitting and standing baselines, respectively. Moreover, the 25Hz We-Be GSR features achieved comparable balanced accuracy to the original 100Hz features across the evaluated tasks. These results suggest the feasibility of low-rate, unit-independent wrist GSR processing for wearable stress detection.

Problem

• wrist GSR
• stress detection
• unit-independent
• low-rate
• phasic SCR

Innovation

• unit-independent
• low-rate GSR
• phasic nSCR
• wrist-based stress detection
• skin conductance response