Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Frequency spectrum sensing algorithm based on FLOM covariance matrix and LSTM neural network

A technology of covariance matrix and neural network, which is applied in the field of spectrum sensing algorithm, can solve problems such as algorithm performance degradation, and achieve the effect of improving detection performance, improving spectrum sensing performance, and good performance

Pending Publication Date: 2021-08-27
NANJING UNIV OF TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: the purpose of the present invention is to provide a spectrum sensing algorithm based on FLOM covariance matrix and LSTM neural network to solve the problem that the performance of the algorithm is degraded or even invalid in non-Gaussian noise.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Frequency spectrum sensing algorithm based on FLOM covariance matrix and LSTM neural network
  • Frequency spectrum sensing algorithm based on FLOM covariance matrix and LSTM neural network
  • Frequency spectrum sensing algorithm based on FLOM covariance matrix and LSTM neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] Embodiment 1: as Figure 2-4 As shown, the detection probability (P d ) and false alarm probability (P f ) is the measure of the spectrum sensing algorithm. On the premise that the false alarm probability is fixed, if the detection probability is higher than 90%, it is considered that the performance of the perception algorithm is good. The experimental simulation is based on MATLAB and Pytorch. The training set and test set are generated by MATLAB. Under the ubuntu16.04 operating system, Pytorch is used, and the scikitlearn library is used to program the algorithm. The parameters of the simulation data set are shown in Table 1:

[0082] Table 1 Simulation data set parameters

[0083]

[0084] Firstly, the data preprocessed by FLOM are input into the improved LSTM neural network. When comparing the algorithm performance, we input the data without low-level preprocessing of scores and the data after low-level preprocessing of scores into the improved LSTM neural...

Embodiment 2

[0091] Embodiment 2: as Figure 5-6 As shown, compare the spectrum sensing algorithm based on FLOM matrix sensing LSTM neural network with FLOM matrix sensing based DNN, CNN spectrum sensing algorithm, LSTM spectrum sensing algorithm, DNN spectrum sensing algorithm, CNN spectrum sensing algorithm and energy detection algorithm:

[0092] In the simulation, the detection threshold was initially set to η = 0.5, and then a decision was made by comparing with this threshold. Finally, based on the Monte Carlo implementation, probabilistic detection values ​​can be obtained under different conditions.

[0093] Figure 5 It is the performance comparison of different algorithms under Alpha noise. from Figure 8 It can be seen that under the background of Alpha noise, the detection performance of the energy detection algorithm, the DNN algorithm, the CNN algorithm and the LSTM algorithm is almost invalid, and when the low-order processing is performed, the spectrum sensing performanc...

Embodiment 3

[0098] Embodiment 3: as Figure 8 As shown, considering the influence of the input signal on the performance of the algorithm, in order to verify the ability of the neural network model trained by several signal types to detect other types of untrained signals, this paper also simulates the signal data of 8PSK and QFSK modulation methods, and uses it as Test samples of unknown signals are input into the neural network for performance analysis. The result is as Figure 8 shown. from Figure 8 In this paper, the following two conclusions can be drawn:

[0099] One: When the sample size and network model parameters are the same, the detection performance of 8PSK modulated signal is the best. When the GSNR is -15dB, its P d It can still reach more than 0.8. The detection performance of QFSK modulated signal is slightly worse, when the GSNR is 15dB, P d Only 0.75. For example, when the GSNR is -15dB and p=0.7, the P of the 8PSK LSTM d is 80%, while QPSK-LSTM's P d Only 65%...

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

No PUM Login to View More

Abstract

The invention discloses a spectrum sensing algorithm based on an FLOM covariance matrix and an LSTM neural network, and belongs to the technical field of cognitive radio, and the algorithm comprises the steps: employing the FLOM to carry out the preprocessing of samples in a training set, building an LSTM neural network model, transmitting the training set for training to the LSTM neural network, carrying out the learning, inputting a test set into the learned LSTM neural network, and obtaining an output result by a softmax module, comparing the output result with a threshold value, and making a decision on whether the main user exists or not. The method is scientific and reasonable, is safe and convenient to use, and improves the detection performance through the powerful capability of the FLOM in the aspect of reducing the influence of non-Gaussian features and the powerful processing capability of the LSTM neural network in the aspect of extracting data time sequence features. The spectrum sensing under the conditions that non-Gaussian noise has no energy and other second-order statistics used for detection is effectively solved, the spectrum sensing performance is improved, and the spectrum sensing method has better performance compared with other networks under the low signal-to-noise ratio.

Description

technical field [0001] The invention relates to the field of cognitive radio technology, in particular to a spectrum sensing algorithm based on a FLOM covariance matrix and an LSTM neural network. Background technique [0002] Cognitive radio can make reasonable use of idle wireless channel resources, which is one of the important ways to solve the problem of wireless spectrum scarcity. Spectrum sensing is one of the key technologies of cognitive radio. The task of spectrum sensing is to identify suitable frequency bands for sub-users. In order to seek a more efficient cognitive radio resource allocation scheme, the use of machine learning methods to solve spectrum sensing problems has also received extensive attention. [0003] Currently, many model-driven spectrum sensing schemes have been proposed. However, most of the spectrum sensing algorithms are based on the Gaussian noise environment, but the performance is superior in the Gaussian noise environment. The actual wi...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04B17/382H04W72/04H04W16/14G06N3/04G06N3/08
CPCH04B17/382H04W72/0453H04W16/14G06N3/084G06N3/044G06N3/045H04W72/53Y02D30/70
Inventor 赵韵雪朱晓梅李义丰朱艾春
Owner NANJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com