. Author manuscript; available in PMC: 2019 Mar 21.

Published in final edited form as: Int Conf Comput Netw Commun. 2018 Jun 21;2018:912–916. doi: 10.1109/ICCNC.2018.8390419

Algorithm 1.

eFCM Algorithm

procedure eFCM(X, n)	▷ Where, X: Incomplete Data, n: Imputation Times
EM(X)	▷ Expectation Maximization
EM Posterior
for i = 1 : n do
Build Markov Chain
Between imputation steps
Interior Imputation Steps
Impute X to get Y_i
for cluster = 2 : maxCluster do	▷ Find Best
Clusters number
for m = 1 : 10 do
Initialize U⁽⁰⁾
InitializeCentroids(Y_i, ClusterNumber)
for r = 1 : MaxIteration do
Calculate V⁽^r⁾
Calculate U⁽^r⁾
if max\|U⁽^r⁾ − U⁽^r⁻¹⁾\| < ε then
Break
Update Xb Matrix and Lx Matrix
Per Xb matrix, extract best cluster no. and fuzzifier
return Lx, Cluster, Fuzzifier	▷ Output
End procedure