Research on K-Means Clustering Algorithm Based on Relational Database Management System

The K-means clustering algorithm holds a pivotal role in data mining due to its high computational efficiency and ease of implementation, making it widely applicable across various domains. This study investigates the methods for implementing the K-means algorithm within relational database management systems and conducts a thorough analysis. Initially, we present the fundamental principles and procedures of the K-means algorithm and explore its applicability and optimization strategies within a relational database environment. Subsequently, we perform a needs analysis based on MongoDB's relational database management system, including system functional requirements, non-functional requirements, and critical technical analyses. By implementing SSH connection protocols and a frequency-based data balancing algorithm (FODO), we enhance the system's security and performance. Finally, through the design and implementation of a MongoDB-based relational database management system, we conduct system experimentation to validate the effectiveness and reliability of the K-means algorithm in practical applications. This research offers a novel perspective and methodology for data mining in relational databases, carrying significant practical implications and reference value.