Table 4.

Smart phone usage features

Parent feature	Description	Statistical features	No. of
		extracted	features
Accelerometer probe	To measure acceleration (the rate of change of velocity). We approximated accelerometer magnitudes using (1).	Mean of the accelerometer magnitude was computed	1
Gyroscope probe	To measure orientation of the phone.	Axis-wise variance of entries were calculated	3
Application Usage probe	App categories were extracted using their package references from play store	Average amount of hours per day spent on each application category by the user	36
Location probe	Raw readings were used to calculate location variance (2), speed mean (3) total distance (4).	location variance (2) and its mean, Variance and mean of the instantaneous speed (3) and total distance (4) were calculated.	6
Bluetooth probe	The entries are grouped day wise and the number of unique encounters were calculated using the Address entry.	Day-wise mean, Variance and Standard Deviation of entries	3
Light (brightness) probe	To measure the illumination of the device(user). Brightness probe readings are used here	Mean, Variance and Standard Deviation of readings	3
Screen unlock probe	The entries were divided on the basis of binary readings provided by the probe	The percentage of entries where the screen_on entry is True with respect to the total number of entries was calculated	1