Privacy-Preserving Approach for Early Detection of Long-Lie Incidents: A Pilot Study with Healthy Subjects

. 2025 Jun 19;25(12):3836. doi: 10.3390/s25123836

Algorithm 1: Long-lie Identification

1:
if Status == “Fall” then
2:
Count Fall_current_time
3:
$B o d y_o r t_c h a n g e \Leftarrow (|\frac{b o d y_o r t - b o d y_o r t_o l d}{b o d y_o r t_o l d}|) \times 100 %$
4:
if Fall_current_time ≥ LongLie_Time_Threshold then
5:
Longlie_Detected ⇐ True
6:
if Body_ort_change > 15% then
7:
LongLie_Current_time $\Leftarrow 0$
8:
Longlie_Detected ⇐ False
9:
Status ⇐ “Moving”
10:
end if
11:
end if
12:
else
13:
LongLie_Current_time $\Leftarrow 0$
14:
Fall_current_time $\Leftarrow 0$
15:
Longlie_Detected ⇐ False
16:
end if