Least squares projection twin support vector clustering (LSPTSVC)

• Published in: Information sciences Vol. 533; pp. 1 - 23
• Main Authors: Richhariya, B., Tanveer, M.
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2020
• Subjects: Alzheimer’s disease; Clustering; Projection twin support vector machine; Unsupervised learning; Alzheimer’s disease; Clustering; Projection twin support vector machine; Unsupervised learning
• ISSN: 0020-0255; 1872-6291; 1872-6291
• DOI: 10.1016/j.ins.2020.05.001

•An efficient projection based clustering algorithm is presented.•Proposed technique is an alternative to plane based clustering algorithms.•Concave-convex procedure is utilized to solve the optimization problem.•Comparison on clustering performance is presented on large scale datasets.•Better generalization performance is achieved on real world applications. Clustering is a prominent unsupervised learning technique. In the literature, many plane based clustering algorithms are proposed, such as the twin support vector clustering (TWSVC) algorithm. In this work, we propose an alternative algorithm based on projection axes termed as least squares projection twin support vector clustering (LSPTSVC). The proposed LSPTSVC finds projection axis for every cluster in a manner that minimizes the within class scatter, and keeps the clusters of other classes far away. To solve the optimization problem, the concave-convex procedure (CCCP) is utilized in the proposed method. Moreover, the solution of proposed LSPTSVC involves a set of linear equations leading to very less training time. To verify the performance of the proposed algorithm, several experiments are performed on synthetic and real world benchmark datasets. Experimental results and statistical analysis show that the proposed LSPTSVC performs better than existing algorithms w.r.t. clustering accuracy as well as training time. Moreover, a comparison of the proposed method with existing algorithms is presented on biometric and biomedical applications. Better generalization performance is achieved by proposed LSPTSVC on clustering of facial images, and Alzheimer’s disease data.