"Replication Data for: Mixture Density Function Estimation in Shape Clustering"

"This dataset provides a complete collection of R programs and preprocessed text datasets used to reproduce the experiments reported in the research paper \"Mixture Density Function Estimation in Shape Clustering\" (IEEE Transactions on Artificial Intelligence, 2025, DOI: 10.1109\/TAI.2025.3543815). It includes implementations of the proposed mixture density function estimation framework based on the Expectation-Maximization (EM) algorithm, along with executable code for several baseline shape clustering methods, including K-means, fuzzy c-means, spectral clustering, and mean-shift clustering. The bundled preprocessed datasets allow users to replicate the empirical results without performing complex data extraction. These datasets include the Great Ape skulls dataset, subsets of the NFL Big Data Bowl 2020 player-tracking data, and subsets of MLB Shohei Ohtani's 2023 pitch-trajectory data. Additional R scripts demonstrate how raw CSV files can be converted into configuration matrices required by the clustering algorithms."