Adversarial attacks and defenses for digital communication signals identification

As modern communication technology advances apace,the digital communication signals identification plays an important role in cognitive radio networks,the communication monitoring and management systems.AI has become a promising solution to this problem due to its powerful modeling capability,which has become a consensus in academia and industry.However,because of the data-dependence and inexplicability of AI models and the openness of electromagnetic space,the physical layer digital communication signals identification model is threatened by adversarial attacks.Adversarial examples pose a common threat to AI models,where well-designed and slight perturbations added to input data can cause wrong results.Therefore,the security of AI models for the digital communication signals identification is the premise of its efficient and credible applications.In this paper,we first launch adversarial attacks on the end-to-end AI model for automatic modulation classifi-cation,and then we explain and present three defense mechanisms based on the adversarial principle.Next we present more detailed adversarial indicators to evaluate attack and defense behavior.Finally,a demonstration verification system is developed to show that the adversarial attack is a real threat to the digital communication signals identification model,which should be paid more attention in future research.

A model for automatic identification of human pulse signals

This paper presents a quantitative method for automatic identification of human pulse signals. The idea is to start with the extraction of characteristic parameters and then to construct the recognition model based on Bayesian networks. To identify depth, frequency and rhythm, several parameters are proposed. To distinguish the strength and shape, which cannot be represented by one or several parameters and are hard to recognize, the main time-domain feature parameters are computed based on the feature points of the pulse signal. Then the extracted parameters are taken as the input and five models for automatic pulse signal identification are constructed based on Bayesian networks. Experimental results demonstrate that the method is feasible and effective in recognizing depth, frequency, rhythm, strength and shape of pulse signals, which can be expected to facilitate the modernization of pulse diagnosis.

Radar emitter signal recognition method based on improved collaborative semi-supervised learning

Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed.First,a small amount of labeled data are randomly sampled by using the bootstrap method,loss functions for three common deep learning net-works are improved,the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification.Subsequently,the dataset obtained after sam-pling is adopted to train three improved networks so as to build the initial model.In addition,the unlabeled data are preliminarily screened through dynamic time warping(DTW)and then input into the initial model trained previously for judgment.If the judg-ment results of two or more networks are consistent,the unla-beled data are labeled and put into the labeled data set.Lastly,the three network models are input into the labeled dataset for training,and the final model is built.As revealed by the simula-tion results,the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.

dentification of blasting vibration and coal-roc fracturing microseismic signals

A new method based on variational mode decomposition （VMD） is proposed to distinguish between coal-rock fracturing and blasting vibration microseismic signals. First, the signals are decomposed to obtain the variational mode components, which are ranked by frequency in descending order. Second, each mode component is extracted to form the eigenvector of the energy of the original signal and calculate the center of gravity coefficient of the energy distribution plane. Finally, the coal-rock fracturing and blasting vibration signals are classified using a decision tree stump. Experimental results suggest that VMD can effectively separate the signal components into coal-rock fracturing and blasting vibration signals based on frequency. The contrast in the energy distribution center coefficient after the dimension reduction of the energy distribution eigenvector accurately identifies the two types of microseismic signals. The method is verified by comparing it to EMD and wavelet packet decomposition.

Seismic signal recognition using improved BP neural network and combined feature extraction method

Seismic signal is generally employed in moving target monitoring due to its robust characteristic.A recognition method for vehicle and personnel with seismic signal sensing system was proposed based on improved neural network.For analyzing the seismic signal of the moving objects,the seismic signal of person and vehicle was acquisitioned from the seismic sensor,and then feature vectors were extracted with combined methods after filter processing.Finally,these features were put into the improved BP neural network designed for effective signal classification.Compared with previous ways,it is demonstrated that the proposed system presents higher recognition accuracy and validity based on the experimental results.It also shows the effectiveness of the improved BP neural network.

Modal identification based on Hilbert-Huang Transform of structural response with S VD preprocessing

In recent years, Empirical mode decomposition and Hilbert spectral analysis have been combined to identify system parameters. Singular-Value Decomposition is pro- posed as a signal preprocessing technique of Hilbert-Huang Transform to extract modal parameters for closely spaced modes and low-energy components. The proposed method is applied to a simulated airplane model built in Automatic Dynamic Analysis of Mechanical Systems software. The results demonstrate that the identified modal parameters are in good agreement with the baseline model.

Using Array Methods to Identify and Process Weak Signals Generated by the Brightlight(Ⅰ) 50t Explosion

Waveforms generated by the 50t explosion of project Brightlight （ I ） were recorded by HILR array. Using array techniques, the author performed identification, f-k analysis, velocity spectrum analysis, etc. of the weak signals. The analysis results show that the signal-to-noise ratio after beamforming was obviously enhanced, and the signal could be clearly shown. The energy from this explosion was mainly concentrated in the 1 -8Hz range from f-k analysis. The velocity spectrum gave clear positions of event phases, which could not be seen in the original weak signals. The maximum energy distribution obtained by the Beaman method is close to the theoretical value in the azimuth-slowness domain.

OFDM and FH Signal Recognition Based on Cumulants and SPWVD Spectrum Cancellation for Internet of Things

Considering the Gaussian asymptotic features of OFDM signals, the identification meth-od of it is proposed in this paper by using the cu-mulants of the wavelet transform coefficients in different layer in a low SNR circumstance. Further-more, taking the coexistence of the OFDM and Frequency Hopping （FH） signals into account, a new way to separate FH and OFDM signals is pro- posed based on SPWVD spectrum cancellation, and it can be used to estimate the FH parameters. The simulation resuks show that the OFDM and single-carrier signals can be identified with a high correct rate of 95% even at-6 dB SNR; mean-while, the separation of mixed OFDM and FH sig-nals can be achieved with a low SNR of-6 dB, and FH parameters can be estirmted accurately.It shows that the recognition performance is improved by about 5 dB compared with the traditional method.

Virtual electromagnetic environment modeling based data augmentation for drone signal identification

Radio frequency(RF)-based drone identification technologies have the advantages of long effective distances and low environmental dependence,which has become indispensable for drone surveillance systems.However,since drones operate in unlicensed frequency bands,a large number of co-frequency devices exist in these bands,which brings a great challenge to traditional signal identification methods.Deep learning techniques provide a new approach to complete endto-end signal identification by directly learning the distribution of RF data.In such scenarios,due to the complexity and high dynamics of the electromagnetic environments,a massive amount of data that can reflect the various propagation conditions of drone signals is necessary for a robust neural network(NN)for identifying drones.In reality,signal acquisition and labeling that meet the above requirements are too costly to implement.Therefore,we propose a virtual electromagnetic environment modeling based data augmentation(DA)method to improve the diversity of drone signal data.The DA method focuses on simulating the spectrograms of drone signals transmitted in real-world environments and randomly generates extra training data in each training epoch.Furthermore,considering the limited processing capability of RF receivers,we modify the original YOLOv5s model to a more lightweight version.Without losing the identification performance,more hardware-friendly designs are applied and the number of parameters decreases about 10-fold.For performance evaluation,we utilized a universal software radio peripheral(USRP)X310 platform to collect RF signals of four drones in an anechoic chamber and a practical wireless scenario.Experiment results reveal that the NN trained with augmented data performs as well as that trained with practical data in the complex electromagnetic environment.

Field PMU Test and Calibration Method——PartⅡ:Test Signal Identification Methods and Field Test Applications

Synchrophasor measurement units(PMUs)provide synchronized measurement data for wide-area applications.To improve the effectiveness of synchrophasor-based applications,field PMUs must be tested to ensure their performance and data quality.In the companion paper(Part I),we proposed a field PMU test and calibration framework consisting of a PMU calibrator and analysis center.Part I presents the development and test of the PMU calibrator.This paper focuses on the analysis center and field test applications.First,the critical component of the analysis center is the signal identification module,for which the step and oscillation signal identification methods are proposed.Here,the performance evaluation criteria of PMU in these two cases are different from others.The methods include a step signal detection method based on singular value decomposition(SVD),which has the capability of weak step detection to account for energy leakage of the signal during the step process,and an oscillation signal identification method based on SVD and fast Fourier transform,which can accurately extract oscillation components that benefit from the adaptive threshold setting method.Second,the analysis center software is implemented based on identification results.By integrating the PMU calibrator in Part I with the analysis center in Part II,we can examine in depth the field PMU test applications in three test scenarios,including standard,playback,and field signal test.Results demonstrate the effectiveness and applicability of the proposed field PMU test methods from both Parts I and II.

FOLMS-AMDCNet:an automatic recognition scheme for multiple-antenna OFDM systems

The existing recognition algorithms of space-time block code(STBC)for multi-antenna(MA)orthogonal frequencydivision multiplexing(OFDM)systems use feature extraction and hypothesis testing to identify the signal types in a complex communication environment.However,owing to the restrictions on the prior information and channel conditions,these existing algorithms cannot perform well under strong interference and noncooperative communication conditions.To overcome these defects,this study introduces deep learning into the STBCOFDM signal recognition field and proposes a recognition method based on the fourth-order lag moment spectrum(FOLMS)and attention-guided multi-scale dilated convolution network(AMDCNet).The fourth-order lag moment vectors of the received signals are calculated,and vectors are stitched to form two-dimensional FOLMS,which is used as the input of the deep learning-based model.Then,the multi-scale dilated convolution is used to extract the details of images at different scales,and a convolutional block attention module(CBAM)is introduced to construct the attention-guided multi-scale dilated convolution module(AMDCM)to make the network be more focused on the target area and obtian the multi-scale guided features.Finally,the concatenate fusion,residual block and fully-connected layers are applied to acquire the STBC-OFDM signal types.Simulation experiments show that the average recognition probability of the proposed method at−12 dB is higher than 98%.Compared with the existing algorithms,the recognition performance of the proposed method is significantly improved and has good adaptability to environments with strong disturbances.In addition,the proposed deep learning-based model can directly identify the pre-processed FOLMS samples without a priori information on channel and noise,which is more suitable for non-cooperative communication systems than the existing algorithms.

Research on Image Signal Identification Based on Adaptive Array Stochastic Resonance

Aiming at the problems of low accuracy of image signal identification and poor anti-noise signal interference ability under strong noise environment,a signal identification method of correlated noisy image based on adaptive array stochastic resonance(SR)is proposed in this paper.Firstly,the two-dimensional grayscale image is transformed to a one-dimensional binary pulse amplitude modulation(BPAM)signal with periodicity by the row or column scanning method,encoding and modulation.Then,the one-dimensional low signal-to-noise ratio BPAM signal can be applied to the saturating nonlinearity array SR module for image signal identification processing and part of the noise energy is converted into signal energy.Finally,the one-dimensional image signal processed by the nonlinearities is demodulated,decoded and reverse scanned to get the restored grayscale image.The simulation results show that the image signal identification method proposed in this paper is highly efficient and accurate for the identification of noisy image signals of different sizes,and the bit error rate(BER)is also significantly reduced.

Operational Modal Analysis of a Ship Model in the Presence of Harmonic Excitation

A ship is operated under an extremely complex environment, and waves and winds are assumed to be the stochastic excitations. Moreover, the propeller, host and mechanical equipment can also induce the harmonic responses. In order to reduce structural vibration, it is important to obtain the modal parameters information of a ship. However, the traditional modal parameter identification methods are not suitable since the excitation information is difficult to obtain. Natural excitation technique-eigensystem realization algorithm （NExT-ERA） is an operational modal identification method which abstracts modal parameters only from the response signals, and it is based on the assumption that the input to the structure is pure white noise. Hence, it is necessary to study the influence of harmonic excitations while applying the NExT-ERA method to a ship structure. The results of this research paper indicate the practical experiences under ambient excitation, ship model experiments were successfully done in the modal parameters identification only when the harmonic frequencies were not too close to the modal frequencies.

On measured-error pretreatment of bionic polarization navigation

A signal pre-treatment algorithm based on combination of 3-dimension system identification and Kalman filtering estimation（3DSKE）is proposed.The aim of designing the 3DSKE algorithm is to reduce errors caused by random noise,but leave the systematical errors caused by signal source remained to be solved by a special method.The 3DSKE algorithm is especially suitable for time series of pure measured data without dynamic equation and on-line real-time execution.The simulated result shows that the 3DSKE algorithm can help the basic theoretic calculation to realize feasible,stable,fast,high accurate and auto-executing computing process for the navigation applications.

Identification and characterization of genes involved in the jasmonate biosynthetic and signaling pathways in mulberry(Morus notabilis)

Jasmonate （JA） is an important phytohormone regulating growth, development, and environmental response in plants, particularly defense response against herbivorous insects. Recently, completion of the draft genome of the mulberry （Morus notabilis） in conjunction with genome sequencing of silkworm （Bombyx mori） provides an opportuni-ty to study this unique plant-herbivore interaction. Here, we identified genes involved in JA biosynthetic and signaling pathways in the genome of mulberry for the first time, with the majority of samples showing a tissue-biased expression pattern. The analysis of the representative genes 12-oxophy-todienoic acid reductase （OPRs） and jasmonate ZIM-domain （JAZs） was performed and the results indicated that the mulberry genome contains a relatively smal number of JA biosynthetic and signaling pathway genes. A gene encoding an＆amp;nbsp;important repressor, MnNINJA, was identified as an alternative splicing variant lacking an ethylene-responsive element binding factor-associated amphiphilic repression motif. Having this fundamental information wil facilitate future functional study of JA-related genes pertaining to mulberry-silkworm interactions.

Multi-function radar emitter identification based on stochastic syntax-directed translation schema

To cope with the problem of emitter identification caused by the radar words＇ uncertainty of measured multi-function radar emitters, this paper proposes a new identification method based on stochastic syntax-directed translation schema（SSDTS）. This method, which is deduced from the syntactic modeling of multi-function radars, considers the probabilities of radar phrases appearance in different radar modes as well as the probabilities of radar word errors occurrence in different radar phrases. It concludes that the proposed method can not only correct the defective radar words by using the stochastic translation schema, but also identify the real radar phrases and working modes of measured emitters concurrently. Furthermore, a number of simulations are presented to demonstrate the identification capability and adaptability of the SSDTS algorithm.The results show that even under the condition of the defective radar words distorted by noise,the proposed algorithm can infer the phrases, work modes and types of measured emitters correctly.