With the development of wireless communication technology, the structure of wireless communication networks is becoming increasingly complex, and there are various factors that can affect the performance of a wireless communication network. Therefore, we first construct a knowledge graph of wireless communication network. Then, combined with mutual information and the constructed knowledge graph, the factors that have a greater impact on the efficiency of key performance indicators are effectively screened. Finally, a Multi-layer Perceptron (MLP) is used to fit the screening results to verify the effectiveness of the proposed scheme. Based on the data set collected in the real communication scenario, after fitting the first 20 selected factors, the accuracy of the scheme proposed in this paper in the test set is 9.56% higher than that of the Bayesian network and 18.8% higher than that of the PageRank algorithm. On the fitting results of the first 30 selection factors, our method is 1.11% and 1.84% higher than the two methods respectively. Experimental results show that the method in this paper outperforms the Bayesian network as well as PageRank algorithm.
A Knowledge Graph Based Factor Screening Approach for Wireless Communication Networks
2024-06-24
1832104 byte
Conference paper
Electronic Resource
English
Knowledge Graph-Based Methods for Automated Driving
TIBKAT | 2025
|WIRELESS CLUSTER BASED SYSTEM FOR COMMUNICATION BETWEEN SENSOR NETWORKS
European Patent Office | 2017
|