Wearable Technology for Detecting Significant Moments in Individuals with Dementia

Table 1

Creating an artifact-detection algorithm to score the signal quality of physiological data.

ANS signal	Feature extracted	Threshold	SQI
Electrodermal activity	First derivative of signal over 15 s sliding window, incremented in 0.5 s intervals	Positive or negative change >3 µs	0.4
	Flatness over 25 s sliding window, incremented in 0.5 s intervals	Difference between two consecutive points ≤0.001 µs	0.1
	Out of normal physiological range	≤0.02 µs	0
		>20 µs	0.65
		>30 µs	0
Skin temperature	Flatness over 25 s sliding window, incremented in 0.5 s intervals	Difference between two consecutive points ≤0.0001°C	0.5
	Out of normal physiological range	<15°C	0.5