Acceleration model of online educational games based on improved ensemble ML algorithm

Abstract

Online educational games are easy to be affected by hardware and network status and have delay problems, which will affect students' learning interest and enthusiasm. Therefore, in this study, Bayesian optimization method is used to optimize the parameters of the “gradient boosting + category features” algorithm, and an improved “gradient boosting + categorical features” ensemble algorithm is designed using the integration framework of RF. And based on this, an online education game acceleration model is designed. The experimental results showed that the improved “gradient boosting + categorical features” algorithm, which combines Bayesian optimization and RF integration framework, was superior to the partially improved and traditional “gradient boosting + categorical features” algorithm in online education game recognition. The former's Accuracy mean and Precision mean in various online education games were 98.9 % and 99.3 %, respectively. Compared with other common ensemble algorithms and deep learning algorithms, the research outcomes expressed that the Accuracy of the algorithm designed in this study in the training phase and the F1 value in the testing phase were 98.6 % and 99.0 %. respectively, which were significantly higher than other intelligent algorithms. The test results of the game acceleration model constructed based on this algorithm and other comparative algorithms indicated that the online education game acceleration model constructed based on the improved “gradient boosting + categorical features” algorithm could minimize the delay phenomenon generated during game operation to the greatest extent. The model designed in this study has the potential to solve the problems of running lag and delay in online education games, which is beneficial for improving students' user experience and learning absorption effect in such game applications.