A Parallel Multiobjective PSO Weighted Average Clustering Algorithm Based on Apache Spark

. 2023 Jan 31;25(2):259. doi: 10.3390/e25020259

Algorithm 2 calFitness Algorithm.

Input: $l o c a l D a t a_{c}, p a r t i c l e S w a r m B C$

Output: particleSwarmFitness

1:
// Run in worker Node c
2:
functioncalFitness( $l o c a l D a t a_{c}, p a r t i c l e S w a r m B C$ )
3:
particleSwarmBCValue = particleSwarmBC.value
4:
for 1 ≤ i ≤ particleSwarmBCValue do
5:
dataWithClusterK ← K-means clustering with $p a r t i c l e_{i}$ .position as the cluster center using $l o c a l D a t a_{c}$
6:
Calculate the objective function value as the local fitness value based on (2) and the dataWithClusterK
7:
Calculate the objective function value as the local fitness value based on (3) and the dataWithClusterK
8:
end for
9:
return particleSwarmFitness
10:
end function