Title: Research on information popularity prediction of multimedia network based on fast K proximity algorithm

Authors: Hongtao Zhang

Addresses: Shangqiu Institute of Technology, Shangqiu, 476000, China

Abstract: In order to improve the accurate prediction ability of multimedia network information popularity, a multimedia network information popularity prediction algorithm based on fast K neighbour algorithm is proposed. Big data mining and feature extraction of multimedia network information popularity prediction are carried out by using discrete sequence analysis method. Based on the idea of fast K-neighbour clustering, the ordered clustering of the statistical feature series of multimedia network information flow is carried out. Combined with fuzzy autocorrelation fusion analysis method, the autocorrelation characteristics of multimedia network information flow statistical time series are extracted, the fuzzy correlation set of multimedia network information popularity is analysed by principal component analysis method, and the improved design of network information popularity prediction algorithm is realised based on fast K-neighbour algorithm. The simulation results show that the method has high accuracy and adaptability, and has good ability of information prediction and statistical analysis.

Keywords: fast K proximity algorithm; multimedia network; information popularity; prediction; discrete sequence analysis method; fast K-neighbour.

DOI: 10.1504/IJAACS.2020.109808

International Journal of Autonomous and Adaptive Communications Systems, 2020 Vol.13 No.2, pp.103 - 115

Received: 30 Sep 2019
Accepted: 20 Nov 2019
Published online: 24 Sep 2020 *

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