Using Machine Learning Methods to Provision Virtual Sensors in Sensor-Cloud

. 2020 Mar 26;20(7):1836. doi: 10.3390/s20071836

Algorithm 1 Virtual sensor provisioning algorithm.

Input: Sample set X

1:
Step1:Classification
2:
Calculate the value of $ω$ for each attribute.
3:
$G = {G_{1}, G_{2}, \dots, G_{n}}$
4:
for $1 \leq i < j \leq n$ do
5:
if $Θ (G_{i}) = Θ (G_{j})$ then
6:
$G_{i} = G_{i} \cup G_{j}$
7:
end if
8:
end for
9:
Return $G = {G_{1}, G_{2}, \dots, G_{l}}$
10:
Step2:Clustering
11:
$C_{j} = \emptyset, (1 \leq j \leq k_{i})$
12:
$μ (G_{i}) = {μ_{1}, μ_{2}, \dots, μ_{k_{i}}}$
13:
$λ_{i} = arg min d_{i j}$
14:
$C_{λ_{i}} = C_{λ_{i}} ⋃ {x_{i}}$
15:
for $j = 1, j + +, j \leq k_{i}$ do
16:
$μ {(G_{i})}^{^{'}} = \frac{1}{∣ C_{j} ∣} \sum_{x_{i} \in C_{j}} x_{i}$ , then
17:
if $μ (G_{i}) \neq μ {(G_{i})}^{^{'}}$
18:
Update $μ (G_{i}) = μ {(G_{i})}^{^{'}}$
19:
end if
20:
end for

Output:

C^{*} = {C_{1}^{*}, C_{2}^{*}, \dots, C_{l}^{*}}