scholarly journals Spatial Transformer Network-Based Automatic Modulation Recognition of Blind Signals

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Yuxin Huang
Keyword(s):  
Time Scale ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Spatial Transformation ◽  
Modulation Recognition ◽  
Training Time ◽  
Communication Signals ◽  
Frequency Offsets ◽  
Time Required ◽  
High Level

Modulation recognition of communication signals plays an important role in both civil and military uses. Neural network-based modulation recognition methods can extract high-level abstract features which can be adopted for classification of modulation types. Compared with traditional recognition methods based on manually defined features, they have the advantage of higher recognition rate. However, in actual modulation recognition scenarios, due to inaccurate estimation of receiving parameters and other reasons, the input signal samples for modulation recognition may have large phase, frequency offsets, and time scale changes. Existing deep learning-based modulation recognition methods have not considered the influences brought by the above issues, thus resulting in a decreased recognition rate. A modulation recognition method based on the spatial transformation network is proposed in this paper. In the proposed network, some prior models for synchronization in communication are introduced, and the priori models are realized through the spatial transformation subnetwork, so as to reduce the influence of phase, frequency offsets, and time scale differences. Experiments on simulated datasets prove that compared with the traditional CNN, ResNet, and the CLDNN, the recognition rate of the proposed method has increased by 8.0%, 5.8%, and 4.6%, respectively, when the signal-to-noise ratio is greater than 0. Moreover, the proposed network is also easier to train. The training time required for convergence has reduced by 4.5% and 80.7% compared to the ResNet and CLDNN, respectively.

scholarly journals Research on signal modulation based on machine learning intelligent algorithm and computer automatic identification

2021 ◽  
Vol 2083 (4) ◽  
pp. 042092
Author(s):  
Zixi Li
Keyword(s):  
Neural Network ◽  
Signal To Noise Ratio ◽  
Feature Representation ◽  
Automatic Identification ◽  
Signal Recognition ◽  
Modulation Recognition ◽  
Data Set ◽  
Communication Signals ◽  
Communication Signal ◽  
Automatic Modulation Recognition

Abstract In the process of communication, modulation signal recognition and classification are an important part of non-cooperative communication. Automatic modulation recognition technology of communication signals based on feature extraction and pattern recognition is a key research object in the radio field. The use of neural network can achieve automatic recognition of a variety of modulation signals and achieve good results. In this method, the received signal is preprocessed to obtain the complex baseband signal including in-phase component and orthogonal component. As the data set of the input convolution neural network model, the signal further optimizes the traditional method of manual extraction of expert features for communication signal recognition, which has great limitations and low accuracy under low signal-to-noise ratio, and the simulation results are verified. The results show that the proposed method has stronger feature representation ability and competitiveness in automatic modulation recognition, and is helpful to promote the application of deep learning in the field of automatic modulation recognition.

scholarly journals Communication Signal Modulation Mechanism Based on Artificial Feature Engineering Deep Neural Network Modulation Identifier

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Fei Lu ◽  
Zhenjiang Shi ◽  
Rijian Su
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Deep Neural Network ◽  
Recognition Rate ◽  
Modulation Recognition ◽  
Signal Modulation ◽  
Communication Signals ◽  
Communication Signal ◽  
Neuron Activation ◽  
The Neural Network

Based on the characteristics of time domain and frequency domain recognition theory, a recognition scheme is designed to complete the modulation identification of communication signals including 16 analog and digital modulations, involving 10 different eigenvalues in total. In the in-class recognition of FSK signal, feature extraction in frequency domain is carried out, and a statistical algorithm of spectral peak number is proposed. This paper presents a method to calculate the rotation degree of constellation image. By calculating the rotation degree and modifying the clustering radius, the recognition rate of QAM signal is improved significantly. Another commonly used method for calculating the rotation of constellations is based on Radon transform. Compared with the proposed algorithm, the proposed algorithm has lower computational complexity and higher accuracy under certain SNR conditions. In the modulation discriminator of the deep neural network, the spectral features and cumulative features are extracted as inputs, the modified linear elements are used as neuron activation functions, and the cross-entropy is used as loss functions. In the modulation recognitor of deep neural network, deep neural network and cyclic neural network are constructed for modulation recognition of communication signals. The neural network automatic modulation recognizer is implemented on CPU and GPU, which verifies the recognition accuracy of communication signal modulation recognizer based on neural network. The experimental results show that the communication signal modulation recognizer based on artificial neural network has good classification accuracy in both the training set and the test set.

Signals Modulation Recognition Based on Efficient Attribute Reduction with Neighborhood Rough Set

2012 ◽  
Vol 220-223 ◽  
pp. 2301-2307
Author(s):  
Ying Zheng Han ◽  
Juan Ping Wu ◽  
Xiao Fang Liang
Keyword(s):  
Rough Set ◽  
Attribute Reduction ◽  
Recognition Rate ◽  
Modulation Recognition ◽  
Signal Modulation ◽  
Communication Signals ◽  
Time Frequency ◽  
Feature Parameters ◽  
Neighborhood Rough Set ◽  
Propagation Network

The purpose of communication signals automatic modulation recognition is to judge signal modulation styles and estimate signal modulation parameters on the precondition of unknown modulation information. According to the seven kinds communication modulation signals studied in this paper, select a group of feature parameters based on the time-frequency characteristics of communication signals. The fast algorithm for attribute reduction based on neighborhood rough set using feature selection is introduced in detail. Then, using back propagation network as classification instruments to identify signals. The simulation shows that the method can not only reduce the number of feature parameters, but also improve the recognition rate.

Based on the Singular Value Decomposition Fast Wavelet Ridge Intra Pulse Modulation Recognition

2014 ◽  
Vol 556-562 ◽  
pp. 4933-4940
Author(s):  
Shu Ge Yin ◽  
Wei Liu ◽  
Chao Wang
Keyword(s):  
Singular Value Decomposition ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Singular Value ◽  
Good Time ◽  
Modulation Recognition ◽  
Pulse Modulation ◽  
Fast Wavelet ◽  
Value Decomposition ◽  
Wavelet Ridge

As a good time and frequency domain localization features, the method of wavelet ridge became one of effective ways to identify the pulse modulation. Aiming at the problem of the low intra pulse recognition rate of the wavelet ridge method in the situation of low signal-to-noise ratio, this paper presented a method of fast wavelet ridge intra pulse modulation based on singular value decomposition. The basic idea of this method:The first signal for fast Morlet wavelet transform; determined the singular value decomcomposition filtering threshold; According to the iterative method to extract the wavelet ridge was to calculate the instantaneous signal teristics; then to identify signal according to the different characteristics of signal instantaneous frequency. The simulation results show that: In less than or equal 0dB SNR situation, this method can improve the recognition rate of common pulse modulation.

Design and Implementation of Modulation Recognition Algorithm Based on Monitoring Receiver

2013 ◽  
Vol 411-414 ◽  
pp. 898-902
Author(s):  
Peng Zhou ◽  
Qi An ◽  
Wei Xia ◽  
Zi Shu He
Keyword(s):  
Digital Signal Processor ◽  
Signal To Noise Ratio ◽  
Digital Signal ◽  
Recognition Algorithm ◽  
Modulation Recognition ◽  
Signal To Noise ◽  
Communication Signals ◽  
Design And Implementation ◽  
Modulation Type ◽  
The Right

In order to recognize the modulation type of common communication signals, an automatic recognition algorithm based on decision theory is designed and introduced. Combined with engineering realization, an adjustment is made to the algorithm. Then, a recognition scheme is proposed and realized on Digital Signal Processor (DSP), which is the key module in monitoring receiver. When the signal-to-noise ratio is not less than 12 dB, the experimental results show that the right recognition rates of eight common communication signals are above 90%. The algorithm proposed can result in a good case, and the smaller calculated complexity compared with its counterparts makes it could better reach the real-time requirement of engineering realization.

scholarly journals Train Fast While Reducing False Positives: Improving Animal Classification Performance Using Convolutional Neural Networks

Geomatics ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 34-49
Author(s):  
Mael Moreni ◽  
Jerome Theau ◽  
Samuel Foucher
Keyword(s):  
False Positive ◽  
Classification Performance ◽  
Large Datasets ◽  
False Positives ◽  
Fine Tuning ◽  
Training Time ◽  
In The Wild ◽  
Test Sets ◽  
High Level ◽  
Time Decrease

The combination of unmanned aerial vehicles (UAV) with deep learning models has the capacity to replace manned aircrafts for wildlife surveys. However, the scarcity of animals in the wild often leads to highly unbalanced, large datasets for which even a good detection method can return a large amount of false detections. Our objectives in this paper were to design a training method that would reduce training time, decrease the number of false positives and alleviate the fine-tuning effort of an image classifier in a context of animal surveys. We acquired two highly unbalanced datasets of deer images with a UAV and trained a Resnet-18 classifier using hard-negative mining and a series of recent techniques. Our method achieved sub-decimal false positive rates on two test sets (1 false positive per 19,162 and 213,312 negatives respectively), while training on small but relevant fractions of the data. The resulting training times were therefore significantly shorter than they would have been using the whole datasets. This high level of efficiency was achieved with little tuning effort and using simple techniques. We believe this parsimonious approach to dealing with highly unbalanced, large datasets could be particularly useful to projects with either limited resources or extremely large datasets.

Research on Modulation Recognition Algorithm of Digital Communication Signal Based on Wavelet Denoising

2014 ◽  
Vol 608-609 ◽  
pp. 459-467 ◽  
Author(s):  
Xiao Yu Gu
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Decision Theory ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Modulation Recognition ◽  
The Core ◽  
Feature Parameters ◽  
Communication Signal ◽  
Modulation Signal

The paper researches a recognition algorithm of modulation signal and modulation modes. The modulation modes to be recognized include 2ASK, 2FSK, 2PSK, 4ASK, 4FSK and 4PSK modulation. There are two methods recognizing modulation modes of digital signal, method based on decision theory and pattern-recognition method based on feature extraction. The method based on decision theory is not suitable for recognition with multiple modulation modes. The core of pattern recognition based on feature extraction is selection of feature parameters. So the paper uses the feature parameters with simple calculation, easy to be implemented and high recognition rate as the core. The extraction of feature parameters is based on instant feature of modulation signal after Hilbert transformation.

Design for Assembly Evaluation of Orientation Difficulty Features

1992 ◽  
Author(s):  
Robert H. Sturges ◽  
Jui-Te Yang
Keyword(s):  
Geometric Modeling ◽  
Boundary Representation ◽  
Design For Assembly ◽  
Assembly Process ◽  
Assembly Evaluation ◽  
Index Of Difficulty ◽  
Analysis System ◽  
Time Required ◽  
High Level ◽  
Geometric Modeling System

Abstract In support of the effort to bring downstream issues to the attention of the designer as parts take shape, an analysis system is being built to extract certain features relevant to the assembly process, such as the dimension, shape, and symmetry of an object. These features can be applied to a model during the downstream process to evaluate handling and assemblability. In this paper, we will focus on the acquisition phase of the assembly process and employ a Design for Assembly (DFA) evaluation to quantify factors in this process. The capabilities of a non-homogeneous, non-manifold boundary representation geometric modeling system are used with an Index of Difficulty (ID) that represents the dexterity and time required to assemble a product. A series of algorithms based on the high-level abstractions of loop and link are developed to extract features that are difficult to orient, which is one of the DFA criteria. Examples for testing the robustness of the algorithms are given. Problems related to nearly symmetric outlines are also discussed.

The estimation of temporal processes in tropical rain forest: a study of primary mixed dipterocarp forest in Indonesia

1985 ◽  
Vol 1 (2) ◽  
pp. 171-182 ◽  
Author(s):  
Soedarsono Riswan ◽  
J. B. Kenworthy ◽  
Kuswata Kartawinata
Keyword(s):  
Time Scale ◽  
Rain Forest ◽  
Tropical Rain Forest ◽  
Gap Formation ◽  
Growth Rings ◽  
Secondary Species ◽  
East Kalimantan ◽  
Forest Sites ◽  
Time Required ◽  
Individual Trees

ABSTRACTIn the absence of growth rings it is difficult to give a precise time scale for processes associated with the re-establishment of tropical rain forest. This paper explores other methods by which a time scale may be constructed. The proportions of primary and secondary species, an index of similarity, biomass measurements, girth dimensions and gap size are all considered from sites in East Kalimantan, Indonesia. Data from primary, secondary and experimentally cleared forest sites are compared to estimate the minimum time required for various phases involved in the re-establishment of tropical rain forest after disturbance. A simple model is proposed to accommodate the data and other estimates in the literature. The model predicts a minimum period for the stablization of secondary species numbers as 60–70 years and the replacement of primary species as 150 years at which point gap formation is initiated. After approximately 220–250 years biomass stabilizes while individual trees exist for over 500 years.

scholarly journals Fabric Vest Socket with Embroidered Electrodes for Control of Myoelectric Prosthesis

Sensors ◽  
2020 ◽  
Vol 20 (4) ◽  
pp. 1196 ◽  
Author(s):  
Seulah Lee ◽  
Babar Jamil ◽  
Sunhong Kim ◽  
Youngjin Choi
Keyword(s):  
Signal To Noise Ratio ◽  
Cost Effective ◽  
Electrode Impedance ◽  
Rigid Support ◽  
Daily Lives ◽  
Myoelectric Prosthesis ◽  
Myoelectric Prostheses ◽  
Average Classification Accuracy ◽  
High Level ◽  
Semg Signals

Myoelectric prostheses assist users to live their daily lives. However, the majority of users are primarily confined to forearm amputees because the surface electromyography (sEMG) that understands the motion intents should be acquired from a residual limb for control of the myoelectric prosthesis. This study proposes a novel fabric vest socket that includes embroidered electrodes suitable for a high-level upper amputee, especially for shoulder disarticulation. The fabric vest socket consists of rigid support and a fabric vest with embroidered electrodes. Several experiments were conducted to verify the practicality of the developed vest socket with embroidered electrodes. The sEMG signals were measured using commercial Ag/AgCl electrodes for a comparison to verify the performance of the embroidered electrodes in terms of signal amplitudes, the skin-electrode impedance, and signal-to-noise ratio (SNR). These results showed that the embroidered electrodes were as effective as the commercial electrodes. Then, posture classification was carried out by able-bodied subjects for the usability of the developed vest socket. The average classification accuracy for each subject reached 97.92%, and for all the subjects it was 93.2%. In other words, the fabric vest socket with the embroidered electrodes could measure sEMG signals with high accuracy. Therefore, it is expected that it can be readily worn by high-level amputees to control their myoelectric prostheses, as well as it is cost effective for fabrication as compared with the traditional socket.

Sign in / Sign up

Export Citation Format

Share Document