Title: Research on deep mining model of online learning data based on multiscale clustering

Authors: Lijuan Liu

Addresses: College of Computer Science, Neijiang Normal University, Neijiang, 641112, Sichuan, China

Abstract: Online learning data mining model does not consider the nonlinearity of data, and has the problems of low recall, precision and MMR. SVM is used to classify the online learning data, and hierarchical interpolation method is used to suppress the noise in the online learning data. This paper uses the multi-scale clustering algorithm to recursively process the data association rules, constructs the online learning data deep mining model through the regression classification tree, and solves the optimal solution of the deep mining model with the help of similar recursive function to complete the online learning data deep mining. The results show that this method has a high fitting degree with the ideal hierarchical result distribution, and the precision, recall and MRR of data mining are better than the traditional methods.

Keywords: multi scale clustering; SVM; inverse distance weighting method; layered interpolation method; regression classification tree; mining model.

DOI: 10.1504/IJICT.2023.134253

International Journal of Information and Communication Technology, 2023 Vol.23 No.3, pp.215 - 230

Received: 10 Jun 2021
Accepted: 27 Jul 2021
Published online: 15 Oct 2023 *

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