Tabu Search Particle Swarm Optimization used in Cluster Analysis

Yudong Zhang, Lenan Wu


In order to solve the cluster analysis problem more efficiently and quickly, we presented a hybrid method based on Tabu Search Particle Swarm Optimization (TSPSO) in this paper. First, we built the optimization model using the variance ratio criterion (VRC) as the fitness function. Second, TSPSO was introduced to find the maximal point of the VRC. TSPSO makes full use of the exploration ability of PSO and the exploitation ability of TS and offsets the weaknesses of each other. The experimental dataset contained 400 data of 4 groups with three different levels of overlapping degrees: non-overlapping, partial overlapping, and severely overlapping. We compared the TSPSO with genetic algorithm (GA) and combinatorial particle swarm optimization (CPSO). Each algorithm ran 20 times. The convergence results showed that TSPSO could found the largest VRC values among all three algorithms, and meanwhile it cost the least time. It can conclude that TSPSO is effective and rapid for the cluster analysis problem.


Particle Swarm Optimization; Tabu Search; Cluster Analysis

Full Text:



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

JOS ©: World Science Publisher United States