Discovering Human Activities from Binary Data in Smart Homes

. 2020 Apr 29;20(9):2513. doi: 10.3390/s20092513

Algorithm 10 sortClusters.

Input:

\hat{\vec{Z}}, {\hat{\vec{c}}}_{i}^{s}, \hat{\vec{k}}

Output: $\hat{\vec{Z}}, {\hat{\vec{c}}}_{i}^{s}$

1:
$s c o r e = 0, i n d e x = 0, \vec{r o w}, f l a g = 1$
2:
for $h \leftarrow 1$ to $| {\hat{\vec{P}}}_{i}^{s} |$ do
3:
$f l a g = 0$
4:
for $g \leftarrow 2; g < | {\hat{\vec{P}}}_{i}^{s} | \land f l a g; g \leftarrow g + 1$ do
5:
if ${\hat{k}}_{g} < {\hat{k}}_{g - 1}$ then
6:
$i n d e x = {\hat{o}}_{g - 1}^{s}$ //swap elements
7:
${\hat{o}}_{g - 1}^{s} = {\hat{o}}_{g}^{s}$
8:
${\hat{o}}_{g}^{s} = i n d e x$
9:
$\vec{r o w} = {\hat{\vec{Z}}}_{(g - 1, *)}$ //swap elements
10:
${\hat{\vec{Z}}}_{(g - 1, *)} = {\hat{\vec{Z}}}_{(g, *)}$
11:
${\hat{\vec{Z}}}_{(g, *)} = \vec{r o w}$
12:
$f l a g = 1$ // indicates that a swap occurred.
13:
end if
14:
end for
15:
end for