F-Classify: Fuzzy Rule Based Classification Method for Privacy Preservation of Multiple Sensitive Attributes

. 2021 Jul 20;21(14):4933. doi: 10.3390/s21144933

Algorithm 1 F-Classify algorithm: Fuzzification.

Require:
Table T with m data attributes and n tuples
Ensure:
Release Table QT and ${S T_{1}, \dots, S T_{m}}$

Initialisation Split the table T into multiple sub-sets (One sub-set for QI and remaining sub-sets for SAs) from the data sets. multiple sub-sets = d1, d2, d3…dk data attributes (linguistic variables) = $l v_{1}, l v_{2}, \dots, l v_{m}$ Membership functions = $μ$ γ = number of attributes in one subset η = number of member-ship functions for lv α: Number of fuzzy rules ( $α = η^{γ}$ ) Rules R [] = ${R_{1}, \dots, R_{α}}$ Classes [] = ${C_{1}, \dots, C_{α}}$

1:
for $i = 1$ to m do
2:
define mfs for lvs
3:
end for
4:
for $i = 1$ to k do
5:
for $j = 1$ to $η$ do
6:
$R [i] \leftarrow A N D (l v [1] [j], l v [2] [j], \dots l v [γ] [j])$
7:
$C [i] \leftarrow R [i]$
8:
end for
9:
end for
10:
for $i = 1$ to n do
11:
for $j = 1$ to $α$ do
12:
if ( $T (T u p l e) \in (C [α])$ ) then
13:
Generate a new table according to Classes for QIs (QT) and SA $(S T_{1}, S T_{2}, \dots S T_{m})$
14:
end if
15:
end for
16:
end for
17:
return Tables QT and $S T_{1}, S T_{2}, \dots, S T_{m}$