Improving K-Means Effectiveness and Efficiency with Initialization Estimates of Cluster Centroids

• Published in: 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC) pp. 1086 - 1091
• Main Authors: Ojha, Rajesh Kumar, Srivastava, Sandeep, Goyal, Mohit, Kumar, Lalan, Kumar, Amit, Prasad, Chitturi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07-10-2021
• Subjects: Autodesk 3D Max software; Clustering algorithms; Costs; Electromyography; EMG MyoWare Muscle Sensor; Hand gestures; K-nearest Neighbor (KNN); Muscles; Prosthetic; Support Vector Machine (SVM); Support vector machines; Three-dimensional displays
• DOI: 10.1109/ICOSEC51865.2021.9591948

K-Means is known both for its usefulness in finding clusters of related data as well as its fragility with respect to initialization choices. This paper introduces a 95% more effective and 50% more efficient initialization methods, that could eliminate the need for multiple executions of K-Means to find high quality clustering. To initialize the centroids, it selects a multiple, m, of K real data points, computes (mK) 2 distances and keeps only the K maximum( minimum( distance ) ) points. A consequence of this technique enables O(lnK) binary search to find the optimal K on 'linearly' separable clusters. The effectiveness claim applies both to separable and intertwined clusters although the efficiency is lost on intertwined clusters.