Multitask Multi attention Residual Shrinkage Convolutional Neural Network Personalized Assessment Model of Tennis Teaching Based on Data Mining and Intelligent Recommendation

Abstract

Tennis is highly explosive, continuous, intense sport that involves numerous continuous short-term explosive actions. This type of training is short-term, high-intensity, and focuses on competitive skills. Athletes must be physically fit and have long-term endurance to excel in technical and tactical skills during competition. In this manuscript, Multitask Multi attention Residual Shrinkage Convolutional Neural Network Personalized Assessment Model of Tennis Teaching Based on Data Mining and Intelligent Recommendation (MMARSCNN-PAM-TT-DM-IR) is proposed. The input data are collected from training levels of technical – sportive actions of 12-14 years old tennis players’ dataset. Initially the input data is preprocessed using Generalized Multi-kernel Maximum Correntropy Kalman Filter for exploring the data. The pre-processed data is given into Gradient Descent Namib Beetle Optimization (GDNBO) for choosing features from the dataset. Then, selected features are given to Dual Tree Complex Discrete Wavelet Transform to extract gray-scale statistical features such as Homogeneity, Entropy, Energy and Smoothness. Finally, the extracted feature attributes are given to MMARSCNN is used to Tennis Teaching Based on Data Mining. In general, MMARSCNN does not express some adaption of optimization strategies for determining optimal parameters to assure accurate Teaching of Tennis. Therefore, Zebra Optimization Algorithm (ZOA) is proposed to enhance weight parameter of MMARSCNN, which precisely Teaching of tennis depend on Data Mining. The proposed model is implemented, its efficacy is assessed utilizing some performance metrics such as accuracy, precision, F1-score, MSE, AUC. The proposed MMARSCNN-PAM-TT-DM-IR method provides 22.55%, 24.72% and 29.63% higher accuracy; 32.66%, 34.97% and 29.57% higher precision; 25.18%, 21.52% and 28.68% higher F1-Score is compared with existing method such as analysis characteristics of Tennis singles matches depend on 5G with data mining technology (AOC-TSM-DM), Tennis online teaching information platform depend on android mobile intelligent terminal (AMIT-TTP-DM), optimization analysis of Tennis players’ physical fitness index depend on data mining with mobile computing (OA-TP-DM-MC) respectively.