Multi-Objective Clustering Based on Hybrid Optimization Algorithm (MO-CS-PSO) and It's Application to Health Data

Data clustering as one of the important data mining techniques is a fundamental and widely used method to achieve useful information about data. Most of the clustering algorithms operate by any single measure to make the partitions and such methods may perform well on some data sets. However, many of the datasets lack robustness in the result of using single measures. To solve this problem, here we have provided a technique as multi-objective clustering based on hybrid optimization algorithm (MO-CS-PSO). We utilize the two objectives such as cluster validity index (I-index) and stability. The multi-objectives are incorporate in the fitness function of the hybrid optimization algorithm to improve the performance of the clustering in terms of accuracy. Finally, the experimentation analysis is carried out to evaluate the feasibility of the proposed approach in different plants, animal data along with the health data, namely blood transfusion data. The new MO-CS-PSO algorithm is tested on several data sets, and its performance is compared with Genetic-K means, cuckoo search, and Fuzzy-PSO. The simulation results show that the new method carries out better results than the Cuckoo search (4.70%), Genetic-K means (5.70%) and Fuzzy-PSO (3.48%).