Prediction Model of Piano Collective Class Teaching and Learning Effect Based on Deep Learning

Area of Science:

• Educational Technology
• Artificial Intelligence in Education
• Music Pedagogy

Background:

• Evaluating piano collective class teaching and learning effectiveness is crucial for improving instructional quality.
• Traditional assessment methods often suffer from subjectivity and lack precision.
• There is a need for objective and accurate models to predict and evaluate educational outcomes.

Purpose of the Study:

• To propose a novel prediction model for piano collective class teaching and learning effect using deep learning (DL) networks.
• To enable precise prediction and evaluation of instructional effects in piano collective classes.
• To promote the enhancement of piano collective class instructional quality through data-driven insights.

Main Methods:

• Quantifying instructional assessment indexes using specific input data and educational impact as output.
• Establishing several training networks corresponding to first-level evaluation indexes.
• Normalizing input samples and performing empirical research using MATLAB.

Main Results:

• The proposed DL-based prediction model achieved a prediction accuracy of 94.41%.
• This accuracy is approximately 10.22% higher than conventional methods.
• The model demonstrated feasibility and realism in predicting and assessing instructional quality.

Conclusions:

• The DL prediction model offers an objective alternative to expert-based evaluations, yielding satisfactory outcomes.
• The model provides valuable insights for teachers to identify weaknesses and enhance piano collective class teaching methods.
• This approach has broad applications for improving educational quality in music instruction.