MATLAB Implementation of K-Means Clustering Algorithm

I implemented and tested the K-means clustering algorithm using MATLAB on the Iris dataset, conducting thorough debugging to ensure optimal performance. During testing, I experimented with multiple parameter configurations including cluster initialization methods and convergence thresholds to validate result stability. The implementation utilizes MATLAB's vectorization capabilities for efficient distance calculations and centroid updates. Key functions employed include kmeans() for core algorithm execution and pdist2() for pairwise distance computations. I performed comprehensive performance analysis on computational efficiency and clustering accuracy, while exploring optimization techniques such as k-means++ initialization for improved convergence. The findings regarding algorithm performance and optimization strategies have been documented in the experimental report, including comparative analysis of different parameter settings on clustering quality metrics.