Stress Monitoring in Pandemic Screening: Insights from GSR Sensor and Machine Learning Analysis

Figures

• 

  Figure 1. (a) The GSR sensor; (b) individual wearing the GSR contacts.

• 

  Figure 2. The equivalent electrical circuit.

• 

  Figure 3. Galvanic skin response (GSR) signal characteristics following a stimulus. The red dot and vertical dashed line indicate the stimulus time (t). Key parameters include latency (time from stimulus to response onset), rise time (time from onset to peak), amplitude (peak GSR value minus baseline), and recovery time (time to reach 50% of the peak amplitude after the peak) [14].

• 

  Figure 4. GSR response of four individuals; (a) stressed response (1); (b) stressed response (2); (c) not stressed response; (d) invalid measurement.

• 

  Figure 5. GSR signal visualizations; (a) raw GSR signal; (b) phasic GSR signal; (c) GSR peaks and mean value; (d) combined GSR and phasic signal.

• 

  Figure 6. GSR data classification; (a) result of applying a K-means clustering algorithm to the GSR data. Yellow indicates subjects who showed elevated levels of anxiety. In purple are those who showed no noticeable change in GSR data; (b) classification results with SVM algorithm. The circle represents the training set data while the symbol “x” represents the test set data. The data categorized as unstressed are represented in blue while the test set categorized as stressed are represented in red.

• 

  Figure 7. SVM Classification; (a) using a linear kernel; (b) using Radial Basis Function (RBF) Kernel with gamma value equal to 2.0; (c) using NuSVM with RBF kernel and ν = 0.02; (d) using NuSVM with RBF kernel and ν = 0.2.