Cognitive recognition method of radio signal based on lightweight deep network
A radio signal and deep network technology, applied in the field of radio signal cognitive recognition, can solve problems such as complex models, complex artificial feature extraction, and relying on artificial feature extraction to achieve the effects of improving efficiency, increasing diversity, and reducing the number of parameters
Active Publication Date: 2019-11-26
XIDIAN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although this method proposes a graph-domain communication signal modulation recognition method based on fractional low-order cyclic spectrum, the method still has shortcomings: the method needs to convert the signal to graph-domain before it can be recognized, and it relies too much on Due to manual feature extraction, the model is complex
The shortcomings of this method are: although this method proposes a channel coding identification method, it needs to know a lot of signal prior knowledge, and can only identify the channel coding type of the signal alone, but cannot identify the modulation mode of the signal, and Requires complex manual feature extraction
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] The invention will be further described below in conjunction with the accompanying drawings.
[0036] Refer to attached figure 1 , to further describe the specific steps of the present invention.
[0037] Step 1: Construct a coded-modulated joint signal.
[0038] In the first step, each information sequence in the received information sequence set is sequentially subjected to four kinds of channel coding to generate different coded signals.
[0039] The four kinds of channel coding refer to Hamming code channel coding, 216 non-systematic convolutional code channel coding with a code rate of 1 / 2, 216 non-systematic convolutional code channel coding with a code rate of 2 / 3, and 3 / 4 Code rate 432 non-systematic convolutional code channel coding.
[0040] In the second step, each coded signal is sequentially subjected to six modulations to obtain a coded-modulated joint signal.
[0041] The six modulations refer to binary phase shift keying modulation, quaternary phase ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a radio signal cognitive recognition method based on a lightweight deep network. The method includes the following implementation steps: (1) constructing a coded modulation joint signal; (2) generating a training sample set and a test sample set; (3) constructing a lightweight deep network; (4) setting parameters of the lightweight deep network; (5) training the lightweightdeep network; and (6) obtaining a cognitive recognition accuracy rate. The scheme of the invention has strong universality, can directly process one-dimensional radio signals, does not require artificial feature extraction and prior knowledge, can simultaneously perform cognitive recognition on a channel coding mode and a modulation recognition mode of the radio signals, has the advantages of lowcomplexity, lightweight model and accurate and stable classification result, and can be used in the technical field of radio signal cognitive recognition.
Description
technical field [0001] The invention belongs to the technical field of communication, and further relates to a radio signal cognitive recognition method of a lightweight deep network in the technical field of signal processing. The invention simulates the cognitive recognition process of the biological brain, can automatically extract the hierarchical semantic features of various radio signals in a complex electromagnetic environment, and realize the joint cognitive recognition of the automatic channel coding type and the modulation mode type of the radio signal. Compared with the existing deep learning models, the present invention not only has the characteristics of low computational complexity, small parameter scale, and easy hardware implementation, but also can obtain accurate cognitive recognition results at a lower signal-to-noise ratio. Background technique [0002] Radio signal coding and modulation joint recognition plays an important role in military electronic co...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L27/00H04L1/00H04B17/391
CPCH04B17/391H04B17/3912H04L1/0059H04L27/0012
Inventor 杨淑媛焦李成黄震宇王敏吴亚聪王喆李兆达张博闻宋雨萱李治王翰林王俊骁
Owner XIDIAN UNIV