A Method for Recognition of Satellite Communication Interference Pattern Based on xgboost

Abstract

The invention belongs to the field of communication technology and artificial intelligence technology, and discloses a satellite communication interference pattern recognition method based on Xgboost; first, preprocessing the interference signal to be trained, extracting nine characteristic parameters of the signal, and constructing a training model The input matrix and output matrix; Then, create the Xgboost model, set the model parameter combination interval, and combine the Bayesian Optimization idea to train the model, find the optimal parameter combination, and get the final model; finally, extract the signal to be identified Nine kinds of characteristic parameters, input the extracted characteristic parameters into the trained model, and identify the pattern of the interference signal. The invention effectively solves the problems of low recognition rate, manual parameter adjustment and optimization, and poor stability of the existing recognition method in scenes with low interference-to-noise ratio, and provides a basis for interference suppression and interference elimination.

Description

technical field [0001] The invention belongs to the technical fields of communication technology and artificial intelligence, and in particular relates to an Xgboost-based satellite communication interference pattern recognition method. Background technique [0002] Today's era is an era of informatization. With the continuous development of wireless communication technology, the available spectrum resources are becoming more and more scarce, and the mutual interference is becoming more and more serious. At the same time, the satellite communication system is always subject to various human interference. How to provide high-quality, high-reliability, and high-security wireless communications has become a major research topic in the field of communications. [0003] At present, the closest existing technology: there are mainly two methods for identifying interference signals. One is the recognition method based on the maximum likelihood theory. First, the likelihood functio...

AI Technical Summary

Problems solved by technology

This method is simple to implement and low in complexity, but there are shortcomings: the decision-making effect mainly depends on the influence of the decision threshold, if the threshold is not selected properly, the recognition performance will be very low in scenes with low interference-to-noise ratio; in addition, the use of decision-making When the tree method is used to identify interference patterns, the recognition accuracy is also affected by the selection order of the feature parameters. If the performance of the feature attributes used as the first division is poor, it will directly affect the subsequent overall recognition performance.

Although this method has strong self-learning and self-adaptive capabilities, it has shortcomings: the neural network model is complex, the training efficiency is low, the parameter adjustment is complicated, and there is no theoretical basis for the selection of the number of hidden layers and hidden layer neurons.

[0007] (1) In the prior art, the decision-making effect of the interference identification method using the decision tree mainly depends on the influence of the decision threshold. If the threshold is not selected properly, the recognition performance is very low in the scene with a low interference-to-noise ratio; in addition, the decision tree method is used. When performing interference pattern recognition, the recognition accuracy is also affected by the selection order of the feature parameters. If the performance of the feature attributes used as the first division is poor, it will directly affect the subsequent overall recognition performance.

[0008] (2) The prior art adopts BP neural network to carry out the method for interference identification to have complex neural network model, low training efficiency, complicated parameter adjustment, and there is no theoretical basis for the selection of the number of hidden layers and the number of hidden layer neurons; in addition, the neural network model Relying on a large number of sample data, if the data sample is small, it is easy to perform well only on known samples, but the predictive ability for unknown data is insufficient, and the generalization ability is weak

[0010] In the prior art, for the decision tree, the effect mainly depends on the influence of the decision threshold, and the decision threshold needs to be set in advance, and there is no fixed standard for setting the threshold

For the neural network, although the recognition results are good, the network parameter settings are complicated, and there is no theoretical basis for parameter selection. Usually, a large number of experiments are required to obtain better parameters.

The training cost is high, the efficiency is low, and the interpretation is poor, so it is rarely directly applied to engineering

Images