Anomalous behaviour recognition in MOOC learning based on local intuitionistic fuzzy support vector machine

In order to improve the accuracy and efficiency of MOOC learning anomalous behaviour recognition, a MOOC learning anomalous behaviour recognition method based on local intuitionistic fuzzy support vector machine is proposed. Firstly, construct a sliding filter for MOOC learning video image grids and filter the MOOC learning video image channels. Secondly, using the key points of the student skeleton as behavioural posture features, the detection of anomalous behaviour in MOOC learning is carried out. Finally, based on the theory of local intuitionistic fuzzy sets, the local intuitionistic indices of positive and negative samples in MOOC learning behaviour are calculated, and a decision function for classifying and recognising MOOC learning anomalous behaviours is constructed to complete the classification and recognition of MOOC learning anomalous behaviours. The results show that the recognition accuracy of the method proposed in this paper is consistently above 90%, and the recognition time does not exceed 3 s.