Residual Neural Network for the Accurate Recognition of Human Action and Compared with Bayesian Regression

Aim: In this research article, the aim is to analyze and compare performance of Residual Neural Network Bayesian Regression for accurate recognition human actions. Materials Methods: The proposed machine learning classifier model uses 80% UCF101 dataset training remaining 20% testing. For SPSS analysis, results two classifiers are grouped with 20 samples in each group. sample size determined using a pretest G-power, 80%, confidence interval 95%, significance level 0.014 (p<0.05). Result: findings suggest that novel residual neural network regression achieved accuracy rates 95.63% 93.97%, respectively, identifying activities accurately.The statistical value between networks has been calculated be p=0.014 (independent t-test p<0.05), indicating statistically significant difference classifiers.