Search

Multi-classification Twin Support Vector Machine model (MTWSVM) is put forward in order to solve the issues of low detection rates and weaken practicability in current network intrusion detection models. In the first place, the Adaptive Synthetic sampling method (ADASYN) is used to balance the dataset. And in the second place, the numerical and normalized methods are used to process the dataset. Ultimately, the data is balanced and simple enough to improve the calculability and convergence speed of the model. For the multi-classification problem, the classification strategy is used to build multi-classification model based on parameter optimization because the parameters have a greater impact on the model. The Improved Particle Swarm Optimization algorithm (IPSO) is used to find the global optimal parameters iteratively in the paper. The KDD’99 dataset is used to perform the network intrusion detection experiments. The experimental results show that the Multi-classification Twin Support Vector Machine model based on parameter optimization can effectively improve the detection performance compared with other models. At the same time, the experimental results show the overall detection accuracy and the detection accuracy of various attacks have been significantly improved. Therefore, the intrusion detection model proposed in the paper has validity and practicability in the network intrusion detection. [ABSTRACT FROM AUTHOR]

Online learning is becoming a common learning method in the field of education. The correct classification of online learners plays a vital role in solving the key issues such as low pass rates and high dropout rates. In this paper, we propose a improved ensemble algorithm for classifying learners, which integrates feature selection and the improved Stacking algorithm (Stacking-PMLR). One feature selection algorithm is Mean Decrease Impurity Algorithm based on Random Forest. It is used to investigate the learning behavior factors which contribute to class of learner. It is also used to select the most frequent features and to reduce the dimensions. Analyzing learners' behavior features by the feature selection algorithm, we know that a number of chapters, interaction days, interactions times and video viewed times are the most important factors. Learners' behavior features from feature selection are used as the attribute input of Stacking-PMLR for classifying learners. After that, we use the multilevel improved ensemble algorithm Stacking-PMLR to classify learners. We improve the Stacking algorithms in terms of its hierarchical structure, data features representation, combination strategy and classification algorithm according to its own characteristics. We use the improved Stacking algorithm to construct the classification model. In addition, fifteen real world different type datasets in UCI machine learning repository are applied. The experimental results show that the improved Stacking algorithm has better performance in accuracy, precision and F1. It also shows the feasibility of the Stacking-PMLR. Finally, we use feature selection and the Stacking-PMLR algorithm to classify the public dataset of the edX online learning platform. The experimental results show that the performance of Stacking-PMLR is better. It shows the practical value of the Stacking-PMLR in online learning prediction. [ABSTRACT FROM AUTHOR]