Discovering Human Activities from Binary Data in Smart Homes

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

Algorithm 13 computeInterClusters.

Input:

({\vec{P}}_{1}^{s}, \dots {\vec{P}}_{z}^{s}), ({\vec{T}}_{1}^{s}, \dots {\vec{T}}_{z}^{s}), ({\hat{\vec{c}}}_{1}^{s}, \dots {\hat{\vec{c}}}_{z}^{s})

Output: ${\vec{P}}_{1}^{s}, {\vec{T}}_{1}^{s}, {\hat{\vec{c}}}_{1}^{s}$

1:
for $a \leftarrow 1$ to z do
2:
compute cluster centroids for ${\vec{P}}_{a}^{s}$ and ${\vec{T}}_{a}^{s}$ as in Equation (11)
3:
end for
4:
for $a \leftarrow 2$ to z do
5:
$\hat{\vec{S}}, \hat{\vec{Z}} = c o m p u t e S i m i l a r i t y ({\vec{P}}_{1}^{s}, {\vec{T}}_{1}^{s}, {\hat{\vec{c}}}_{1}^{s}, {\vec{P}}_{a}^{s}, {\vec{T}}_{a}^{s}, {\hat{\vec{c}}}_{a}^{s}, T_{s}, N + 2)$ // Algorithm 8
6:
$\hat{\vec{k}} = c o m p u t e A v e r a g e R o w (\hat{\vec{S}})$ //Algorithm 9
7:
$\hat{\vec{Z}}, {\hat{\vec{c}}}_{1}^{s} = s o r t C l u s t e r s (\hat{\vec{Z}}, {\hat{\vec{c}}}_{1}^{s}, \hat{\vec{k}})$ //Algorithm 10
8:
$\hat{\vec{Z}} = r e m o v e D u p l i c a t e E n t r i e s (\hat{\vec{Z}})$ //Algorithm 11
9:
${\vec{P}}_{1}^{s}, {\vec{T}}_{1}^{s}, {\hat{\vec{c}}}_{1}^{s} = m e r g e C l u s t e r s (\hat{\vec{Z}}, {\vec{P}}_{1}^{s}, {\vec{T}}_{1}^{s}, {\hat{\vec{c}}}_{1}^{s}, {\vec{P}}_{a}^{s}, {\vec{T}}_{a}^{s}, {\hat{\vec{c}}}_{a}^{s})$ //Algorithm 12
10:
compute merged cluster centroids for ${\vec{P}}_{1}^{s}$ and ${\vec{T}}_{1}^{s}$ as in Equation (11)
11:
end for