Title: An abnormal behaviour recognition of MOOC online learning based on multidimensional data mining

Authors: Meng Qu

Addresses: Quality Control and Continuous Assessment Office, Qingdao Vocational and Technical College of Hotel Management, Qingdao, 266100, China

Abstract: To solve the problems of low recall rate, low recognition rate and the long time-consuming nature of the traditional massive open online learning (MOOC) online learning abnormal behaviour identification method, an abnormal behaviour recognition method of MOOC online learning based on multidimensional data mining is designed. The clustering by fast search and find of density peaks (CFSFDP) algorithm is used to mine MOOC online learning multidimensional data, the Lagrangian function is used to improve the support vector machine (SVM), and the improved SVM is used to classify the collected data. A neural network structure based on a multi-head self-attention mechanism is constructed, and the feature vector of each class of MOOC online learning data is extracted by this network, and the abnormal behaviour of MOOC online learning is identified according to the feature vector. The experimental results show that the recall rate of the method in this paper is always above 93%, the average recognition rate is 95.9%, and the maximum recognition time is only 0.4s.

Keywords: multidimensional data mining; MOOC; massive open online learning; online learning; abnormal behaviour recognition; multi-head self-attention mechanism; neural network structure; recogniser.

DOI: 10.1504/IJAACS.2024.139403

International Journal of Autonomous and Adaptive Communications Systems, 2024 Vol.17 No.4, pp.369 - 382

Received: 20 May 2022
Accepted: 18 Oct 2022
Published online: 02 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article