Predicting the Results of LTL Model Checking using Multiple Machine Learning Algorithms

In this paper, we study how to predict the results of LTL model checking using some machine learning algorithms. Some Kripke structures and LTL formulas and their model checking results are made up data set. The approaches based on the Random Forest (RF), K-Nearest Neighbors (KNN), Decision tree (DT), and Logistic Regression (LR) are used to training and prediction. The experiment results show that the average computation efficiencies of the RF, LR, DT, and KNN-based approaches are 2066181, 2525333, 1894000 and 294 times than that of the existing approach, respectively.