Research Article
Wearable Technology for Detecting Significant Moments in Individuals with Dementia
Table 4
Creating customized algorithms for dementia participants from ANS signals.
| ANS signal | Feature extracted | Thresholds | Scaling factor |
| (A) Dyad 1 dementia participant Mary | Electrodermal activity | First derivative of signal over 10 s sliding window, incremented in 0.5 s intervals | Positive EDA change of 0.24 µs | 5 | Heart rate | Local maxima and minima | Peak prominence of 20 bpm | 0.05 | Skin temperature | First derivative of signal over 15 s sliding window, incremented in 0.5 s intervals | Positive or negative temperature change of 0.05°C | 1 |
| (B) Dyad 2 dementia participant Elisa | Electrodermal activity | First derivative of signal over 20 s sliding window, incremented in 0.5 s intervals | Positive EDA change of 0.25 µs | 4 | Heart rate | Local maxima and minima | Peak prominence of 25 bpm | 0.96 | Skin temperature | First derivative of signal over 15 s sliding window, incremented in 0.5 s intervals | Positive or negative temperature change of 0.11°C | 8.4 |
| (C) Dyad 3 dementia participant Irene | Electrodermal activity | First derivative of signal over 10 s sliding window, incremented in 0.5 s intervals | Positive EDA change of 0.25 µs | 4 | Heart rate | Local maxima and minima | Peak prominence of 35 bpm | 0.06 | Skin temperature | First derivative of signal over 25 s sliding window, incremented in 0.5 s intervals | Positive or negative temperature change of 0.02°C | 9 |
|
|