Scholarlink

<p>In the past, students in music colleges and universities were often taught through static teaching approaches, primarily centered on skills and knowledge, which resulted in disinterest and limited progress among students. Student preferences for learning and teaching methodologies vary dynamically. Hence, instructional decision making is needed to identify the dynamic needs of students’ music literacy skills. To achieve this goal, a deep fuzzy music training (DFMT) system is introduced in this study to innovate music training. Hence, this study proposes a novel deep learning (DL) algorithm called the recurrent neural network (RNN), which is used to predict sequential music teaching patterns from Kodaly-inspired methods. Features such as timing frequency, pitch accuracy, dynamism, and articulation of music performance are analyzed for this prediction. From the RNN, the student’s dynamic music learning abilities and preferences are predicted to enhance music performance. Then, a fuzzy decision system generates personalized teaching recommendations in music education. The associated fuzzy decision system helps assess student proficiency, music preferences, and learning styles predicted by the RNN. The proposed system is evaluated to make accurate decisions about the Kodaly instructional methods, assessments, and personalized critique feedback mechanisms that are most appropriate for each teaching method of university students.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Innovation of Music Teaching Methods in Universities Based on Fuzzy Decision Support Systems and Deep Learning

  • 期刊论文

  • 发表日期：

    2025年3月10日

查看全文
  • Yi Chen

摘要

In the past, students in music colleges and universities were often taught through static teaching approaches, primarily centered on skills and knowledge, which resulted in disinterest and limited progress among students. Student preferences for learning and teaching methodologies vary dynamically. Hence, instructional decision making is needed to identify the dynamic needs of students’ music literacy skills. To achieve this goal, a deep fuzzy music training (DFMT) system is introduced in this study to innovate music training. Hence, this study proposes a novel deep learning (DL) algorithm called the recurrent neural network (RNN), which is used to predict sequential music teaching patterns from Kodaly-inspired methods. Features such as timing frequency, pitch accuracy, dynamism, and articulation of music performance are analyzed for this prediction. From the RNN, the student’s dynamic music learning abilities and preferences are predicted to enhance music performance. Then, a fuzzy decision system generates personalized teaching recommendations in music education. The associated fuzzy decision system helps assess student proficiency, music preferences, and learning styles predicted by the RNN. The proposed system is evaluated to make accurate decisions about the Kodaly instructional methods, assessments, and personalized critique feedback mechanisms that are most appropriate for each teaching method of university students.