Data Sharing Method of College Dance Teaching Resource Database Based on PSO Algorithm.

Area of Science:

• Computer Science
• Data Science
• Educational Technology

Background:

• Traditional data sharing in college dance teaching resource databases suffers from long sharing times and suboptimal accuracy, recall, and F1 values.
• Existing methods struggle with data noise and incomplete datasets, hindering efficient resource utilization.

Purpose of the Study:

• To propose a novel data sharing method for college dance teaching resource databases.
• To improve the efficiency and accuracy of data sharing using the Particle Swarm Optimization (PSO) algorithm.

Main Methods:

• Data preprocessing using Multiple Regression KNN to handle missing values and noise.
• Establishing a data transmission self-service channel for statistical analysis.
• Feature extraction using Partial Least Squares (PLS) on preprocessed data.
• Implementing the Particle Swarm Optimization (PSO) algorithm for data sharing.

Main Results:

• The proposed PSO-based method demonstrates high accuracy, recall, and F1 values.
• The data sharing time is significantly reduced compared to traditional methods.
• Effective handling of data noise and incomplete data through preprocessing.

Conclusions:

• The PSO algorithm offers a superior approach for data sharing in college dance teaching resource databases.
• This method enhances data quality and accessibility, benefiting both educators and students.
• The findings suggest a scalable and efficient solution for managing educational resource databases.