Optimized Hamiltonian Deep Neural Network-Based Art Education Teaching Content and Evaluation System

Abstract

The organized educational processes and experiences created to promote a comprehension and appreciation of the visual arts are referred to as art education. It includes a variety of exercises designed to foster artistic abilities, the ability to express oneself creatively, and a greater understanding of artistic ideas and background. There are several places where art instruction can take place, such as private studios, museums, community centers, and schools. In this manuscript, Optimized Hamiltonian Deep Neural Network-Based Art Education Teaching Content and Evaluation System (HDNN-AETC-ES) is proposed. Initially the data is collect from MADS dataset. To execute this, input data is pre-processed using Adaptive Distorted Gaussian Matched Filter (ADGMF) and it removes the noise from collected data. Then, data is fed to Hamiltonian Deep Neural Network (HDNN)for effectively categorized Technology-Based Art Teaching Platform. Generally, HDNN doesn’t express adapting optimization approaches to determine optimal parameters to ensure accurate art teaching. Hence, the Tasmanian Devil Optimization Algorithm (TDOA) to optimize Hamiltonian Deep Neural Network which accurately evaluated the art teaching. Then the proposed HDNN-AETC-ES is implemented and the performance metrics likes accuracy, precision, recall, F1-score, computation time, ROC are analyzed. Performance of the HDNN-AETC-ES approach attains 18.41%, 24.08% and 32.57% higher accuracy, 20.31%, 21.08% and 22.57% higher Precision and 21.41%, 22.08% and 23.55% higher recall when analyzed through existing techniques like art education teaching content using optimization of digital art teaching platform depend on information technology with deep learning (DAT-IT-DL), building arts education policy utilizing tools of out-of-school time youth arts organizations (BAEP-ST-YAO) and investigating arts education effects on school engagement with climate (IAE-ES-EC) methods respectively.