Hierarchically Gated Recurrent Neural Network optimized with Tasmanian Devil Optimization for Piano Playing Based on Virtual Reality Technology

Abstract

Playing the piano is a beautiful and extremely technical art form in addition to an elegant performance art. The player's ability to execute with elegance and technicality which requires years of practice will be crucial. The success of a piano concert ultimately rests not only on the performing abilities of the pianist but also on the pianist's mental and psychological makeup. This manuscript presents a Hierarchically Gated Recurrent Neural Network (HGRNN) optimized with the Tasmanian Devil Optimization (TDO) for predicting the real time instruction for playing piano based on virtual reality (PPVR-HGRNN-TDO). Initially, the data is collected from MIDI dataset. Afterward, the data is fed to a Multi-domain collaborative Filter (MDCF) based preprocessing process. Then the preprocessed data’s are fed to Scaling-Basis Chirplet Transform (SBCT) for extracting features such as tone quality and loudness variations. The extracted features are fed to HGRNN to classify the piano playing performance such as good, normal and poor. The weight parameters of HGRNN are optimized using TDO. The proposed PPVR-HGRNN-TDO is implemented in python, effectiveness assessed by several performance metrics such as accuracy, precision, specificity, sensitivity, F1-score and ROC. The gained results of the proposed PPVR-HGRNN-TDO method attains higher accuracy 20.46%, 23.54%, 35.58%, higher precision 33.56%, 21.72%, 33.97% and higher sensitivity 32.54%, 22.76%, 36.97%. The proposed method shows better results in all existing systems like Dual Channel Convolutional Neural Network (DCCNN),Convolutional Neural Network (CNN), and Back Propagation Neural Network with Genetic Algorithm (BPNN-GA). From the result it is concludes that the proposed PPVR-HGRNN-TDO method based accuracy is higher than the existing methods.