Pseudo Wigner-Ville Distribution Research Articles

Diagnosis of Al-CFRTP TA-FSLW defect using acoustic emission signal based on SPWVD and ResNet

As one of the important development directions in modern railway and automobile, lightweight requires reliable connection technology of dissimilar materials. Thermal-assisted friction stir lap welding (TA-FSLW) is an available welding technology for the joining of dissimilar materials, which can solve the problems of physical and chemical properties in the welding process of dissimilar materials. Unfortunately, defects may occur during the welding process. This paper proposes a defect diagnosis method based on smooth pseudo Wigner-Ville distribution (SPWVD) and ResNet18 for Al-CFRTP TA-FSLW. Firstly, the acoustic emission (AE) signal and the temperature of the weld nugget are acquired by the AE sensor and thermography camera in the FSLW process. Then, the time–frequency domain features of AE signal are extracted by SPWVD, and the maximum temperature of the weld nugget is extracted by exponential moving average (EMA) from thermography. Moreover, the dataset is established by SPWVD features, maximum temperature of welding nugget, and several time–frequency features. Finally, the ResNet18-attention network is employed to classify welding defects and stages. The Al-CFRTP TA-FSLW experiments are carried out based on the proposed method. Experimental result indicates that the SPWVD spectrum can effectively extract the feature frequency of deep and shallow hole defects in the welding process. In the section of classification, the accuracy of the dataset with SPWVD features is improved by 2% to 4% compared to other methods, which demonstrates that the SPWVD feature is superior in defect feature extraction.

Online detection and assessment of cable insulation fault based on time–frequency domain reflectometry

The insulation performance of cables plays an important role in the safe and stable operation of aircraft. Time–frequency domain reflectometry (TFDR) is an effective method to detect the local insulation faults of cables. Usually, Wigner–Ville distribution (WVD) is used to analyze the energy distribution of reflected signals in TFDR. However, WVD can easily introduce cross-term interference to the detection results. In addition, most of the current studies have used TFDR to perform offline detection of cable insulation fault, and the performance of TFDR for online operation is unclear. In order to solve the above problems, first, this paper eliminates the interference of cross-term based on smoothed pseudo-Wigner–Ville distribution. Then, an online cable insulation fault detection platform based on non-contact signal injection is built. According to the requirements of the standard GJB181A, the interference degree of the incident signal of TFDR to the original signal of cable is analyzed, and the feasibility of using TFDR method to perform online detection is proved. Finally, the correlation between different features of reflected signals under different fault degrees of cable is analyzed. It is proved that time-domain correlation has a better correlation with the fault degree of cable compared to other four features.

Radar Signal Recognition Based on Bagging SVM

Radar signal recognition under low signal-to-noise ratio (SNR) conditions is a critical issue in modern electronic reconnaissance systems, which face significant challenges in recognition accuracy due to signal diversity. A novel method for radar signal detection based on the bagging support vector machine (SVM) is proposed in this paper.This method firstly utilizes the Choi–Williams distribution (CWD) and the smooth pseudo Wigner-Ville distribution (SPWVD) to obtain different time–frequency images of radar signals, which effectively leverages CWD’s strong time–frequency aggregation and SPWVD’s robust cross-interference resistance. Moreover, histograms of oriented gradient (HOG) features are extracted from time–frequency images to train multiple SVM classifiers by bootstrap sampling. Finally, the performance of each SVM classifier is aggregated using plurality voting to reduce the risk of model overfitting and improve recognition accuracy. We evaluate the effectiveness of the proposed method using 12 different types of radar signals. The experimental results demonstrate that its overall identification rate reaches around 79% at an SNR of −10 dB, and it improves the recognition rate by 5% compared with a single classifier.

Underwater target material classification based on feature extraction of finite element simulated signal

Feature extraction is crucial for underwater target classification and recognition, and this paper aims to propose a scheme for accurately classifying the material features of underwater targets. Finite element simulation software COMSOL is used to obtain echo signals, and then Auto Regressive (AR) coefficient, cepstrum feature, spectral peak and its frequency of Smoothing Pseudo Wigner-Ville Distribution (SPWVD) of echo signals are extracted as the input of the pattern recognition network. The classification results show that the proposed scheme is able to effectively differentiate among four types of materials: metal, brick, plastic and rubber. The scheme also shows good robustness for the target size and shape, and the proposed scheme has the potential to be applied to the practical underwater target classification.

Sea Clutter Suppression Using Smoothed Pseudo-Wigner–Ville Distribution–Singular Value Decomposition during Sea Spikes

The detection of small targets within the background of sea clutter is a significant challenge faced in radar signal processing. Small target echoes are weak in energy, and can be submerged by sea clutter and sea spikes, which are caused by overturning waves and breaking waves. This severely affects the radar target detection performance. This paper proposes a smoothed pseudo-Wigner–Ville distribution–singular value decomposition (SPWVD-SVD) method for sea clutter suppression. This method determines the instantaneous frequency range of the target by contrasting the time–frequency characteristics of the sea spike and the target. Subsequently, it employs a singular value difference spectrum to reduce the rank of the Hankel matrix, thereby reducing the computational burden of the instantaneous frequency estimation step in the experiment. Based on the instantaneous frequency range of the target in the time–frequency domain, the singular values of the target signal are retained, while the singular values of clutter are set to zero. This process accomplishes the reconstruction of radar echo signals and effectively achieves the suppression of sea clutter. The suppression effect is verified using simulation data alongside ten sets of Intelligent Pixel processing X-band (IPIX) radar data against the background of sea spikes. By contrasting the clutter amplitudes before and after suppression, the SPWVD-SVD algorithm demonstrated an average clutter suppression of 15.06 dB, which proves the effectiveness of the proposed algorithm in suppressing sea clutter.

Identification of S2 Paradoxical Splitting in Aortic Stenosis Subjects via Seismocardiogram Signals From a Wearable Accelerometer Contact Microphone

Second heart sound (S2) splitting can be used as an indicator for diagnosis of cardiovascular diseases; specifically, paradoxical S2 splitting is an indicator of aortic stenosis. We present that S2 acoustic signatures can be captured accurately from the seismocardiogram (SCG) signals of a sensitive wearable accelerometer contact microphone (ACM) and validated by comparing with digital stethoscope phonocardiogram (PCG) signals. The ACM was placed on the pulmonic region of 18 subjects, 10 with no known heart disease and 8 with known heart disease, for 60 seconds of SCG data collection. Smoothed Pseudo Wigner-Ville distribution is used to extract S2 time split and to identify S2 paradoxical splitting. Healthy subjects had SCG S2 time splits range agreeing with S2 time splits from past literature from PCG signals. The ACM SCG signal was al-so used to identify and capture paradoxical splitting from subjects with known valvular heart diseases such as aortic stenosis, from subjects with mild to severe diagnosis. In conclusion, a wearable ACM can be used to detect paradoxical splitting in subjects suspected with aortic valvular heart disease and shows high fidelity of capturing S2 time split through SCG signals.

Research on Intelligent Monitoring of Boring Bar Vibration State Based on Shuffle-BiLSTM.

Due to its low stiffness, the boring bar used in deep-hole-boring is prone to violent vibration during the cutting process. It is often inaccurate and inefficient to judge the vibration state of the boring bar through artificial experience. To detect the change of the vibration state of the boring bar over time, guide the adjustment of the processing parameters, and avoid wastage of the workpiece and the loss of equipment, it is particularly important to intelligently monitor the vibration state of the boring bar during processing. In this paper, the boring bar is taken as the research object, and an intelligent monitoring technology of the boring bar's vibration state based on deep learning is proposed. Based on grouping convolution, channel shuffle, and BiLSTM, a shuffle-BiLSTM NET model is constructed, which is both lightweight and has a high classification accuracy. The boring experiment platform is built, and 192 groups of cutting experiments are carried out. The three-way acceleration and sound pressure signals are collected, and the signals are processed by smoothed pseudo-Wigner-Ville distribution. The original signals are transformed into a 256 × 256 × 3 matrix obtained by a two-dimensional time-frequency spectrum diagram. The matrix is input into the model to recognize the boring bar's vibration state. The final classification accuracy is 91.2%. A variety of typical deep learning models are introduced for performance comparison, which proves the superiority of the models and methods used in this paper.

Post-Earthquake Damage Identification of Buildings with LMSST

The structure is said to be damaged if there is a permanent shift in the post-event natural frequency of a structure as compared with the pre-event frequency. To assess the damage to the structure, a time-frequency approach that can capture the pre-event and post-event frequency of the structure is required. In this study, to determine these frequencies, a local maximum synchrosqueezing transform (LMSST) method is employed. Through the simulation results, we have shown that the traditional methods such as the Wigner distribution, Wigner–Ville distributions, pseudo-Wigner–Ville distributions, smoothed pseudo-Wigner–Ville distribution, and synchrosqueezing transforms are not capable of capturing the pre-event and post-event frequency of the structure. The amplitude of the signal captured by sensors during those events is very small compared with the signal captured during the seismic event. Thus, traditional methods cannot capture the frequency of pre-event and post-event, whereas LMSST employed in this work can easily identify these frequencies. This attribute of LMSST makes it a very attractive method for post-earthquake damage detection. In this study, these claims are qualitatively and quantitatively substantiated by comprehensive numerical analysis.

Spatial multifractal spectrum distribution method for breast ultrasonic image classification

The point-wise multifractal spectrum (MFS) of the ultrasonic image in the time-frequency domain is studied in this paper. With the theoretical derivation, the spatial multifractal spectrum (SMFS) distribution, as an extension of the conventional MFS, is proposed to analyze and characterize the spatial multiscale multifractal feature. Furthermore, the homogeneous region statistical MFS (HRS-MFS) with respect to different physical regions and the singularity-exponent-domain statistical multi-resolution (SSMR) feature image can be extracted from the renormalized SMFS data cube. The SMFS is rigorously derived from the two-dimensional multifractal spectrum and the Pseudo Wigner-Ville distribution (PWVD). In addition, both the SSMR feature images based on the SMFS and the singularity exponent of the 2D-PWVD is proved to be the SNR independence in the Gaussian white noise (GWN) background, which ensures the robust estimation of SMFS features of images under low SNR conditions. Furthermore, the HRS-MFS and the SSMR feature images of the breast ultrasound images (BUSI) are extracted to discriminate the specificity of the tumor regions. Then, a novel BUSI classification method based on the SMFS and deep learning network is proposed and tested on the public BUSI datasets. The experiment results indicate that the SMFS method can significantly reduce the risk of the ‘intermediate effects’. In fact, the classification accuracy of the original deep network is considerately improved by 9.3 % with the SMFS method, and 94.8 % classification accuracy is achieved, which is superior by 3.3 % to the state-of-art method.

Automated extraction of baleen whale calls based on the pseudo-Wigner–Ville distribution

Baleen whales produce a wide variety of frequency-modulated calls. Extraction of the time-frequency (TF) structures of these calls forms the basis for many applications, including abundance estimation and species recognition. Typical methods to extract the contours of whale calls from a spectrogram are based on the short-time Fourier transform and are, thus, restricted by a fixed TF resolution. Considering the low-frequency nature of baleen whale calls, this work represents the contours using a pseudo-Wigner-Ville distribution for a higher TF resolution at the cost of introducing cross terms. An adaptive threshold is proposed followed by a modified Gaussian mixture probability hypothesis density filter to extract the contours. Finally, the artificial contours, which are caused by the cross terms, can be removed in post-processing. Simulations were conducted to explore how the signal-to-noise ratio influences the performance of the proposed method. Then, in experiments based on real data, the contours of the calls of three kinds of baleen whales were extracted in a highly accurate manner (with mean deviations of 5.4 and 0.051 Hz from the ground-truth contours at sampling rates of 4000 and 100 Hz, respectively) with a recall of 75% and a precision of 78.5%.

Discriminative sEMG-based features to assess damping ability and interpret activation patterns in lower-limb muscles of ACLR athletes

ObjectiveThe main goal of the athletes who undergo anterior cruciate ligament reconstruction (ACLR) surgery is a successful return-to-sport. At this stage, identifying muscular deficits becomes important. Hence, in this study, three discriminative features based on surface electromyographic signals (sEMG) acquired in a dynamic protocol are introduced to assess the damping ability and interpret activation patterns in lower-limb muscles of ACLR athletes. MethodsThe features include the median frequency of the power spectrum density (PSD), the relative percentage of the equivalent damping or equivalent stiffness derived from the median frequency, and the energy of the signals in the time–frequency plane of the pseudo-Wigner-Ville distribution (PWVD). To evaluate the features, 11 healthy and 11 ACLR athletes (6 months post-reconstruction surgery) were recruited to acquire the sEMG signals from the medial and the lateral parts of the hamstrings, quadriceps, and gastrocnemius muscles in pre- and post-fatigue single-leg landings. ResultsA significant damping deficiency is observed in the hamstring muscles of ACLR athletes by evaluating the proposed features. This deficiency indicates that more attention should be paid to this muscle of ACLR athletes in pre-return-to-sport rehabilitations. ConclusionThe quality of electromyography-based pre-return-to-sport assessments on ACLR subjects depends on the sEMG acquisition protocol, as well as the type and nature of the extracted features. Hence, combinatorial application of both energy-based features (derived from the PWVD) and power-based features (derived from the PSD) could facilitate the assessment process by providing additional biomechanical information regarding the behavior of the muscles surrounding the knee.

Parallel LSTM-CNN Network With Radar Multispectrogram for Human Activity Recognition

Owing to the ability of automatic feature extraction, deep learning is extensively applied in human activity recognition (HAR) based on radar. In this article, a recognition method based on a multispectrogram and deep-learning model is proposed. The radar echo data are transformed into spectrograms with different feature expressions by performing three time–frequency analyses, including short-time Fourier transform (STFT), reduced interference distribution with Hanning kernel (RIDHK), and smoothed pseudo-Wigner–Ville distribution (SPWVD), and then the spectrograms are sent to deep-learning model to realize HAR. The model employs three long short-term memory (LSTM) networks to learn the temporal features of the spectrograms and uses a 3-D convolutional neural network (3-DCNN) to extract the independent spatial features of a single spectrogram and the spatial correlation features between different kinds of spectrograms, named parallel LSTM-CNN network (PLCN). The PLCN is capable of effectively improving the degree of feature utilization in the spectrogram and the accuracy of human activity classification by fusing both temporal and spatial features. The final experimental results show that the average recognition accuracy of the method based on the PLCN for eight human activities reaches 94.75%, which is significantly higher than that of the three parallel LSTMs and the single 3-DCNN.

Exploration of Effective Time-Velocity Distribution for Doppler-Radar-Based Personal Gait Identification Using Deep Learning.

Personal identification based on radar gait measurement is an important application of biometric technology because it enables remote and continuous identification of people, irrespective of the lighting conditions and subjects' outfits. This study explores an effective time-velocity distribution and its relevant parameters for Doppler-radar-based personal gait identification using deep learning. Most conventional studies on radar-based gait identification used a short-time Fourier transform (STFT), which is a general method to obtain time-velocity distribution for motion recognition using Doppler radar. However, the length of the window function that controls the time and velocity resolutions of the time-velocity image was empirically selected, and several other methods for calculating high-resolution time-velocity distributions were not considered. In this study, we compared four types of representative time-velocity distributions calculated from the Doppler-radar-received signals: STFT, wavelet transform, Wigner-Ville distribution, and smoothed pseudo-Wigner-Ville distribution. In addition, the identification accuracies of various parameter settings were also investigated. We observed that the optimally tuned STFT outperformed other high-resolution distributions, and a short length of the window function in the STFT process led to a reasonable accuracy; the best identification accuracy was 99% for the identification of twenty-five test subjects. These results indicate that STFT is the optimal time-velocity distribution for gait-based personal identification using the Doppler radar, although the time and velocity resolutions of the other methods were better than those of the STFT.

Gray-level co-occurrence matrix of Smooth Pseudo Wigner-Ville distribution for cognitive workload estimation

Automatic, cost-effective, and reliable cognitive workload estimation (CWE) is one of the important issues in diagnosis and treatment of neurocognitive diseases, cognitive performance improvement and error preventive strategies. To address this issue, this paper has proposed a novel and robust CWE method by detecting the time–frequency (TF) changes of electrodermal activities (EDA). Firstly, the local and global properties of the time-variant characteristics of EDA have been presented using Smooth Pseudo Wigner-Ville distribution with enhanced TF resolution. Then, the transient changes in TF images of EDA signals have been quantified using a set of textural features based on Gray Level Co-occurrence Matrix descriptor (GLCM). Several static and dynamic classifiers, such as support vector machine, K- k-nearest neighbor, cascade forward neural network, and recurrent neural network have been explored. A real EDA data experiment recorded during arithmetic task with different workload levels have been used to evaluate the performance of the proposed method. The obtained results have confirmed that it can achieve a high estimation performance of 97.71% using contrast feature for discrimination of three workload levels. Further analysis has also suggested that the model is robust to GLCM parameters and classifiers and can provide a better tradeoff between computational complexity and high performance using minimum number of textural features in comparison with previous studies.

Deep-Learning-Based BCI for Automatic Imagined Speech Recognition Using SPWVD

The electroencephalogram (EEG)-based brain–computer interface (BCI) has potential applications in neuroscience and rehabilitation. It benefits a person with neurological impairment to communicate their thoughts to the external world without using any appendages. Decoding imagined speech had limited success, mainly because neural signals are weak and more variable than overt speech, hence challenging to decode by machine-learning (ML)-based algorithms. In recent years, deep learning (DL) with convolutional neural networks (CNNs) has transformed computer vision and can perform pattern recognition better than the traditional ML-based algorithms. The objective of this article is to design a smoothed pseudo-Wigner–Ville distribution (SPWVD) and CNN-based automatic imagined speech recognition (AISR) system to recognize imagined words. This article uses a publically available 64-channel EEG dataset, collected from 15 healthy subjects for three categories: long words, short words, and vowels. The EEG signals were transformed into time–frequency representation (TFR) using SPWVD, which are used as an input to CNN such that the EEG dataset was identified and classified into binary and multiclass categories. In addition, the CNN model was optimized using a recently developed Keras-tuner library to achieve optimal performance. The performance of the SPWVD-CNN-driven AISR system is evaluated using seven performance evaluation metrics: accuracy (ACC), recall (REC), precision (PREC), Mathew’s correlation coefficient (MCC), Cohen’s kappa ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\kappa $ </tex-math></inline-formula> ), F1-score, and area under the curve (AUC). It is found that the proposed system achieved the maximum classification ACCs of 94.82%, 94.26%, 94.68%, and 84.50% for long words, short–long words, short words, and vowels, respectively. The proposed AISR strengthens the possibility of using imagined speech recognition as a future BCI application.

A Transferable Thruster Fault Diagnosis Approach for Autonomous Underwater Vehicle under Different Working Conditions with Insufficient Labeled Training Data

Existing thruster fault diagnosis methods for AUV (autonomous underwater vehicle) usually need sufficient labeled training data. However, it is unrealistic to get sufficient labeled training data for each working condition in practice. Based on this challenge, a transferable thruster fault diagnosis approach is proposed. In the approach, an IPSE (instantaneous power spectrum entropy) and a STNED (signal-to-noise energy difference) are added to SPWVD (smoothed pseudo Wigner-Ville distribution) to identify time and frequency boundaries of the local region in the time-frequency power spectrum caused by thruster fault, forming a TFE (time-frequency energy) method for feature extraction. In addition, the RCQFFV (relative change quantity of the fault feature value), an MSN (multiple scale normalization) and a LSP (least square prediction) are added to SVDD (support vector data description) to align distributions of fault samples, contributing a TSVDD (transferable SVDD) for classification of fault samples. The experimental results of a prototype AUV indicate that the fault feature is monotonic to the percentage of thrust loss for the proposed TFE but not for the SPWVD. The TSVDD has a higher overall classification accuracy in comparison to conventional SVDD under working conditions with no labeled training data.

Multimodal attention-based deep learning for automatic modulation classification

Wireless Internet of Things (IoT) is widely accepted in data collection and transmission of power system, with the prerequisite that the base station of wireless IoT be compatible with a variety of digital modulation types to meet data transmission requirements of terminals with different modulation modes. As a key technology in wireless IoT communication, Automatic Modulation Classification (AMC) manages resource shortage and improves spectrum utilization efficiency. And for better accuracy and efficiency in the classification of wireless signal modulation, Deep learning (DL) is frequently exploited. It is found in real cases that the signal-to-noise ratio (SNR) of wireless signals received by base station remains low due to complex electromagnetic interference from power equipment, increasing difficulties for accurate AMC. Therefore, inspired by attention mechanism of multi-layer perceptron (MLP), AMC-MLP is introduced herein as a novel AMC method for low SNR signals. Firstly, the sampled I/Q data is converted to constellation diagram, smoothed pseudo Wigner-Ville distribution (SPWVD), and contour diagram of the spectral correlation function (SCF). Secondly, convolution auto-encoder (Conv-AE) is used to denoise and extract image feature vectors. Finally, MLP is employed to fuse multimodal features to classify signals. AMC-MLP model utilizes the characterization advantages of feature images in different modulation modes and boosts the classification accuracy of low SNR signals. Results of simulations on RadioML 2016.10A public dataset prove as well that AMC-MLP provides significantly better classification accuracy of signals in low SNR range than that of other latest deep-learning AMC methods.

Radar Moving Target Detection Method Based on SET2 and AlexNet

Aiming at the nonstationary characteristics of echo signal for a high-speed maneuvering target, a signal feature extraction method is proposed by combining the time-frequency analysis and convolution neural network, and then the automatic detection of radar moving target in a noisy environment is realized. Firstly, the echo signal is modelled as a more accurate Gaussian modulation-linear frequency modulation (GM-LFM) signal and converted into the time-frequency image by a second-order synchroextracting transform (SET2). Then, ridge extraction is applied to extract the maximum energy ridge from the time-frequency distribution, and the data set is constructed by the maximum energy ridge. Finally, the data set is input into AlexNet for training, and the deep-level features of echo signal are extracted to realize the automatic moving targets detection. Simulation results show that SET2 and RE can effectively enhance the time-frequency characteristics of echo signal under the noisy environment, and the detection accuracy and noise robustness of the proposed method are better than that of SET1 and smooth pseudo-Wigner–Ville distribution (SPWVD).

Pseudo Wigner-Ville distribution for 3D white light scanning interferometric measurement.

White light scanning interferometry is a commonly used optical measurement method for three-dimensional (3D) surface profiles. In the case of large phase errors, accurate height values can generally be obtained indirectly from the interferometric signal envelope information derived using various envelope extraction methods. However, the current envelope extraction algorithms have the disadvantages of low robustness, increasing the half-width of the envelope information, and requiring correct parameter settings in advance. In this study, the pseudo Wigner-Ville distribution is modified and applied to white light scanning interferometric 3D measurement to avoid the above-mentioned drawbacks. Simulations and experiments are performed in a single-frequency mode (only the approximate central wave-number is used to guide both the proposed and wavelet transform methods). The simulation results prove that the proposed method has a 31.7% higher reconstruction accuracy than the wavelet transform method under a 25 dB signal to noise ratio condition. Concurrently, the proposed method is insensitive to the change in the central wavelength with a constant central wave-number parameter and has a good extraction effect for a long coherent length. The experiments measure standard step objects (VLSI standard, 1.761 ± 0.01 µm), and the reconstruction height error of the proposed method is 0.0035 µm. Simulations and experiments show that the proposed method can adaptively provide accurate envelope information after half-width reduction under the condition that only the approximate central wave-number a priori knowledge is used. Simultaneously, the proposed method is shown to be robust and effective.

Signal fingerprint feature extraction and recognition method for communication satellite

ABSTRACT Due to the complex maritime environment, communication satellite signals are inevitably subjected to various unpredictable situations which results in the noisy signal. To tackle the fickle ocean environment, we propose a novel scheme to extract and identify the fingerprint feature of communication satellite signals. K-means clustering algorithm is utilised to optimise the conventional Smooth Pseudo Wigner-Ville Distribution (SPWVD), which makes the final result of SPWVD closer to the feature of the original data and improves the accuracy of signal fingerprinting. Basing on the improved SPWVD, the singular value entropy is calculated by time-frequency analysis. Then, the entropy of diagonal slices is generated by the ameliorated bispectrum method which is enhanced by using the fractional low-order covariance method. Consequently, a two-dimensional signal fingerprint feature vector can be calculated. For the fingerprint feature recognition, the XGBoost classifier which is more efficient in machine learning classification is employed. Finally, we simulate the Iridium satellite signal for experiments with MATLAB. The experimental result shows the superiority of the improved SPWVD method and the improved bispectrum method, which proves the scheme's feasibility.