Research Article
Weak Signal Acquisition and Recognition Method for Mobile Communication Based on Information Fusion
@INPROCEEDINGS{10.1007/978-3-030-94554-1_6, author={Wu-lin Liu and Feng Jin and Hai-guang He and Yu-xuan Chen}, title={Weak Signal Acquisition and Recognition Method for Mobile Communication Based on Information Fusion}, proceedings={Advanced Hybrid Information Processing. 5th EAI International Conference, ADHIP 2021, Virtual Event, October 22-24, 2021, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2022}, month={1}, keywords={Information fusion Mobile communication Weak signal acquisition Recognition}, doi={10.1007/978-3-030-94554-1_6} }- Wu-lin Liu
Feng Jin
Hai-guang He
Yu-xuan Chen
Year: 2022
Weak Signal Acquisition and Recognition Method for Mobile Communication Based on Information Fusion
ADHIP PART 2
Springer
DOI: 10.1007/978-3-030-94554-1_6
Abstract
In traditional communication signal acquisition, the effect of weak signal recognition is poor. Therefore, a weak signal acquisition and recognition method for mobile communication based on information fusion is designed. The mobile communication signal location model is established; the TDOA algorithm is used to locate the mobile communication signal; the receiver is used to capture the mobile communication signal. M-QAM modulation technology is used to modulate the parameters of mobile communication signal transmission mode, and the feature classification model of mobile communication signal is established. The modulation types of mobile communication signals are identified by using cyclic spectrum, and the simulation is carried out. The modulation types are classified by using mobile communication signal feature classifier and information fusion technology, and the recognition of mobile communication signals is completed. Experimental results show that the recognition rate of this method is 24% higher than that of traditional method 1 and 34% higher than that of traditional method 2. This method is based on information fusion. The information is fused by combining classifiers to classify modulation types, which significantly improves the recognition accuracy.
