Uncovering Abnormal Behavior Patterns from Mobility Trajectories

. 2021 May 19;21(10):3520. doi: 10.3390/s21103520

Algorithm 2 Identifying mobility patterns.

Input:
$G r i d T_{k}$ : sequence of previously visited locations;
Output:
pattern type (“direct”, “random”, “lapping”, or “pacing”)
1:
if $\forall (g r i d T_{a} \neq g r i d T_{b})$ where $a \neq b$ then
2:
label “direct” for the $G r i d T_{k}$ ;
3:
else
4:
Find circles in $G r i d T_{k}$ ;
5:
label pacing for points in the circle whose length is 2;
6:
label lapping for points in the circle whose length is between 3 and $δ$ ;
7:
for each unlabeled sub-sequence $S_{i j}$ of $G r i d T_{k}$ do
8:
if $\forall (g r i d T_{i} \neq g r i d T_{j})$ where $i \neq j$ then
9:
label “direct” for $S_{i j}$ ;
10:
else
11:
label “random” for $S_{i j}$ ;
12:
end if
13:
end for
14:
$R_{a}, L_{a}, P_{a}$ = the number of sub-patterns labeled as “random”, “lapping”, and “pacing” respectively;
15:
$m a x = M a x (R_{a}, L_{a}, P_{a})$ ;
16:
if $m a x = = R_{a}$ then
17:
label “random” for the $G r i d T_{k}^{^{'}}$ ;
18:
else
19:
if $m a x = = L_{a}$ then
20:
label “lapping” for the $G r i d T_{k}^{^{'}}$ ;
21:
else
22:
label “pacing” for the $G r i d T_{k}^{^{'}}$ ;
23:
end if
24:
end if
25:
end if