Integrating Enhanced Clustering Algorithms and Ensemble Techniques for Bigdata

Abstract

The proposed system introduces an enhanced clustering algorithm optimized for big data analytics, addressing challenges such as scalability, heterogeneity, and high dimensionality. Utilizing an ensemble clustering approach combined with a voting mechanism, the system generates robust and accurate cluster outcomes suitable for diverse applications. The invention leverages cloud-based platforms for efficient processing of large-scale datasets while ensuring adaptability to numerical, categorical, and mixed data types. Comprehensive performance evaluation metrics, including silhouette score and Davies-Bouldin index, provide insights into clustering quality and efficiency. The system's design supports real-time applications in healthcare, finance, IoT, and AI, emphasizing scalability and precision. This innovation contributes to the advancement of artificial intelligence and data mining technologies by delivering an adaptable, efficient, and scalable clustering solution tailored for big data environments.