What question did this study set out to answer?

The study aims to develop and evaluate TLPSC, an algorithm that enhances clustering performance through transfer learning.

April 13, 2026

A prototype-based transfer learning approach for the particle swarm clustering algorithm

Puntos clave

The study aims to develop and evaluate TLPSC, an algorithm that enhances clustering performance through transfer learning.
Developed TLPSC algorithm integrating Prototype-Based Transfer Learning and Particle Swarm Clustering.
Conducted experiments comparing TLPSC to traditional methods like K-Means and Gaussian Mixture Models.
Utilized various evaluation metrics including Normalized Mutual Information and Silhouette Score.
TLPSC outperformed traditional clustering methods across multiple evaluation metrics.
Improved cluster formation was noted in sparse and noisy data scenarios.
TLPSC effectively preserved the data structure and formed cohesive partitions.

Resumen

Abstract This paper introduces the Transfer Learning Particle Swarm for Clustering (TLPSC), a novel algorithm that integrates Particle Swarm Clustering (PSC) with Prototype-Based Transfer Learning to enhance clustering performance. By leveraging knowledge from a source domain, TLPSC improves cluster formation, particularly in sparse or noisy data scenarios. Experimental results show that TLPSC consistently outperforms traditional methods, including K-Means, Gaussian Mixture Models, and standard PSC, across multiple evaluation metrics, such as Normalized Mutual Information, Adjusted Rand Index, Silhouette Score, and Davies–Bouldin Index. TLPSC effectively preserves the structure of the data and forms cohesive partitions, highlighting its robustness and applicability to complex clustering tasks.

Me gusta

Guardar

Me gusta

Guardar

A prototype-based transfer learning approach for the particle swarm clustering algorithm

Puntos clave

Resumen

Cite This Study