Design and Implementation of Remote Piano Teaching Based on Attention-Induced Multi-Head Convolutional Neural Network Optimized with Hunter–Prey Optimization

Abstract

The continuous progress of multimedia technology in music educational institutions has led to the recognition of its importance in our country and society. The traditional approach to piano teaching has its limitations, which can be overcome by adopting alternative approaches to the instrument, using advances in science and technology. For pianist, expressing emotions and thoughts through music is crucial, and teachers can now use multimedia tools to exemplify their musical skills to students effectively. This manuscript proposes the Remote Piano Teaching Based on Attention-Induced Multi-Head Convolutional Neural Network Optimized with Hunter–Prey Optimization to improve the piano-teaching quality. At first, input data is taken from Piano Triad Wavset dataset. Afterward, the data are fed to preprocessing stage. The preprocessing stage involve data cleaning or scrubbing that is the process of identifying errors, inconsistencies, and incorrectness in a dataset with the help of adaptive distorted Gaussian matched filter. Then, the preprocessed output is fed to Attention-Induced Multi-Head Convolutional Neural Network (AIMCNN) for effectively predict the piano-teaching quality. The hunter–prey optimization (HPO) algorithm is proposed to optimize the parameters of Attention-Induced Multi-Head Convolutional Neural Network. The performance of the proposed technique is evaluated under performance metrics like accuracy, computational time, learning skill analysis, learning activity analysis, learning behavior analysis; student performance ratio and teaching evaluation analysis are evaluated. The proposed RPT-AIMCNN-HPO attains better prediction accuracy 12.566%, 12.075% and 15.993%, higher learning skill 15.86%, 15.26% and 16.25% compared with existing methods.