Open Access

ARTICLE

An Improved Crow Search Based Intuitionistic Fuzzy Clustering Algorithm for Healthcare Applications

Parvathavarthini S^1,*, Karthikeyani Visalakshi N², Shanthi S³, Madhan Mohan J⁴

1 Kongu Engineering College, Department of Computer Technology, Perundurai, Erode, Tamilnadu, India, 638 060.
2 Government Arts & Science College, Department of Computer Science, Kangeyam, India.
3 Kongu Engineering College, Department of Computer Science and Engineering, Perundurai, Erode, India 638 060
4 Erode Sengunthar Engineering College, Department of Electronics and Communication, Perundurai, Erode, India

* Corresponding Author: Parvathavarthini S,

Intelligent Automation & Soft Computing 2020, 26(2), 253-260. https://doi.org/10.31209/2019.100000155

Abstract

Intuitionistic fuzzy clustering allows the uncertainties in data to be represented more precisely. Medical data usually possess a high degree of uncertainty and serve as the right candidate to be represented as Intuitionistic fuzzy sets. However, the selection of initial centroids plays a crucial role in determining the resulting cluster structure. Crow search algorithm is hybridized with Intuitionistic fuzzy C-means to attain better results than the existing hybrid algorithms. Still, the performance of the algorithm needs improvement with respect to the objective function and cluster indices especially with internal indices. In order to address these issues, the crow search algorithm is modified by introducing the genetic operators like cloning and mutation operators. In addition to that, an archive of memory is created to store the best solutions of the iterations and these values are used for updating the position when the acquired solutions are not feasible. The results obtained are compared with other hybrid Intuitionistic fuzzy C-means algorithms and the performance of ICrSA-IFCM is high in terms of the objective function and cluster validity indices.

---

Keywords

---