Music Art Teaching Quality Evaluation System Based on Convolutional Neural Network.

Area of Science:

• Education
• Computer Science
• Artificial Intelligence

Background:

• Music and art education programs are expanding rapidly in higher education.
• Current teaching quality assessment (TQE) methods in these fields are underdeveloped and often borrowed from other disciplines, leading to ineffective evaluations.
• Existing TQE approaches lack rigor and fail to provide meaningful feedback for improvement in music and art education.

Purpose of the Study:

• To address the limitations of current TQE in music and art education.
• To develop a more appropriate and effective evaluation system for music and art teaching quality.
• To leverage advanced computational methods for improved educational assessment.

Main Methods:

• A comprehensive review of existing domestic and international TQE research and methods in music and art.
• Introduction and explanation of Convolutional Neural Network (CNN) principles and architecture.
• Construction of a TQE system specifically tailored for music and art education using CNN.

Main Results:

• The study introduces a novel TQE method based on Convolutional Neural Network (CNN).
• Experimental results indicate that the developed CNN model achieves higher accuracy and better performance compared to the traditional BP neural network.
• The CNN-based TQE system demonstrates effectiveness in evaluating music and art teaching quality.

Conclusions:

• The proposed CNN model offers a significant advancement in music and art teaching quality assessment.
• This approach provides a more rigorous and accurate evaluation framework than existing methods.
• The findings suggest that CNNs are well-suited for addressing nonlinear problems in educational TQE, offering improved feedback and advancement opportunities.