Unknown-class signal detection method based on monitored learning classification model

Abstract

The invention belongs to the signal detection and depth learning technology field and discloses an unknown-class signal detection method based on a monitored learning classification model. The CNN istrained through a tagged data set, and the monitored learning classification model is established; the last SoftMax layer is dropped, and the classification model is utilized to carry out characteristic extraction; the characteristics extracted by the CNN are utilized, the t-SNE dimensional reduction algorithm is utilized to visually detect the classification effect and obtain low-dimensional characteristic data; the two-dimensional data after dimensional reduction is utilized, and frame detection accuracy is calculated through utilizing a distance-based calculation formula. The method is advantaged in that the CNN+t-SNE detection method is creatively proposed, the high-dimensional data is mapped to the low-dimensional space, the more intelligible result is acquired, calculation is convenient, added unknown-class signals can further have their own center to be gathered in one position, essential characteristics of the input data can be excellently extracted through the classificationmodel, and the unknown-class signals can be effectively detected.

Description

technical field [0001] The invention belongs to the technical fields of signal detection and deep learning, and in particular relates to a detection method of an unknown category signal based on a supervised learning classification model. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: [0003] With the development of communication technology and the national economy, the communication environment is becoming more and more complex. Within the limited frequency band, in order to make full use of resources, a large number of signals with different modulation methods have sprung up like mushrooms after rain. In the field of communication countermeasures, facing the problem of receiving a large amount of signal data of unknown categories, the proposed A common challenge. In the existing research, the detection of unknown types of data mostly appears in network intrusion detection and fault detection, but there ...

AI Technical Summary

Problems solved by technology

[0007] (1) In real life, the communication environment is becoming more and more complex, and the communication signal is more diverse and complex in terms of system and modulation style, so it is faced with the problem of receiving a large amount of modulation signal data of unknown types

[0008] (2) The existing technical method is to use the instantaneous information of the signal, including instantaneous amplitude (Instantaneous Amplitude), instantaneous frequency (Instantaneous Frequency), instantaneous phase (Instantaneous Phase) and other statistical feature values ​​from different angles to classify and identify, different expert features and The number of expert features will have a great impact on the final result

Although deep learning is introduced, the lower layer neurons and all upper layer neurons in the fully connected DNN structure can form connections. The potential problem brought about is the expansion of the number of parameters, resulting in local optimal values, which makes the final detection results unsatisfactory.

Images