Education and Training System Based on Fuzzy Random Forest Model

During the use of education and training systems, it is inevitable to encounter malfunctions. This article proposes a fault prediction model for education and training systems based on fuzzy random forests to improve the operational efficiency of the system. Combining IoT sensors with random forest algorithms, establish a fault prediction model for education and training systems based on fuzzy random forest. Obtain the operating parameters of the education and training system through wireless collection devices on the Internet of Things, and use fuzzy control algorithms to optimize the random forest algorithm to reduce interference from less important features. Using the optimized data as the input of the random forest algorithm and the degree of risk faults as the output, the effectiveness of the model is verified through examples. The experimental results indicate that: When the number of influencing factors is 5, the classification accuracy is the highest. According to the weight calculation and ranking of the influencing factors, the top 5 influencing factors are extracted. The model based on fuzzy random forest education and training has a higher prediction effect and accuracy, while the prediction accuracy of other models has a certain degree of difference compared to actual results.