Research on the Information Entropy Using Processing Square Matrix Method Based on Similarities Evaluation Model
Chupeng Cui, Zhendong Jia, Ke Gu · Journal of Physics Conference Series · 2021
Abstract In the music history, there are plenty of splendid music artists. musicians in a certain genre may bring some varieties other genres, or influenced by them. this paper constructs a complex network model based on directional weighted graph. Specifically, we calculate the edge of the graph by referring the ideology of information entropy to describe the direct influence on two certain artists. Then, we take the 100 most influential artists and analyze their influence to get a direct influence square matrix. After that, we utilize the DEMATEL method to process this square matrix, and calculate the scale of the comprehensive influence square matrix about these musicians. This article uses Euclidean distance as the similarity metric, and measures the similarity between artists through 11 indicators. In order to facilitate the calculation, this paper uses the principal component analysis method to reduce the dimensionality of these indicators. In order to determine the influence relationship between genres, this paper uses the k-means algorithm to compare and analyze the clusters of artists with more than 10 followers.