Feature Vector Of Signal Research Articles

Research on modulation recognition method of electromagnetic signal based on wavelet transform convolutional neural network

The method of electromagnetic signal modulation recognition based on wavelet transform convolutional neural network is studied to improve the effect of electromagnetic signal modulation recognition. By analyzing the electromagnetic signal modulation model, the original electromagnetic signal is preprocessed by wavelet transform to remove the noise of the original electromagnetic signal. The processed electromagnetic signal is used as the input of convolutional neural network, and the electromagnetic signal feature vector is extracted through the convolution layer of convolutional neural network. By using full connection operation, the advanced feature vector of electromagnetic signal is integrated, and the electromagnetic signal is classified by softmax function, and the electromagnetic signal modulation recognition result is output, thus realizing the electromagnetic signal modulation recognition. The experimental results show that when the number of layers of wavelet decomposition is 7 and the wavelet function is Db9, the wavelet transform has the best denoising effect on electromagnetic signal data. At the same time, the network training efficiency of this method is high, and the accuracy of electromagnetic signal modulation recognition is as high as 97.2 %, which improves the effect of electromagnetic signal modulation recognition and is suitable for various types of electromagnetic signal modulation recognition.

Nonlinear characterization of enhanced and generalized Hjorth’s feature space for bearing condition monitoring

The degradation assessment of rolling bearings provides a reasonable maintenance plan for the safe operation of mechanical equipment. The general strategy for bearing condition monitoring is to construct a health indicator (HI) to characterize different degradation stages. A preferable HI that can sensitively detect initial faults and track machine degradation is crucial to developing timely maintenance strategies for mechanical equipment to avoid catastrophic accidents. However, many developed and reported HIs are still insensitive to early faults, resulting in delayed maintenance schedules. To identify the incipient defects as early as possible, a novel HI constructed by nonlinear characterization of enhanced and generalized Hjorth’s feature space based on extended probability entropy is proposed in this paper. Firstly, the time-frequency spectral amplitude modulation helps to enhance the characteristics of the original signal with the amplitude editing in the time-frequency domain. Then, three new features of generalized Hjorth’s parameter combinations are designed and combined with other similar feature combinations to construct a high-dimensional enhanced and generalized Hjorth’s feature space. On this basis, a set of low-dimensional sensitive features is obtained by nonlinearly characterizing high-dimensional features through extended probability entropy after these features are standardized. Finally, a novel HI is developed by calculating the distance between the minimum volume ellipse (MVE) center of the low-dimensional feature subspace based on nonlinear characterization and the low-dimensional feature vector of the real-time monitoring signal. The performance of the proposed approach is verified in three cases, whose experimental results indicate that the proposed HI is more sensitive and significant in detecting early faults compared to some current HIs.

Research on Electric Vehicle Braking Intention Recognition Based on Sample Entropy and Probabilistic Neural Network

The accurate identification of a driver’s braking intention is crucial to the formulation of regenerative braking control strategies for electric vehicles. In this paper, a braking intention recognition model based on the sample entropy of the braking signal and a probabilistic neural network (PNN) is proposed to achieve the accurate recognition of different braking intentions. Firstly, the brake pedal travel signal is decomposed to extract the effective components via variational modal decomposition (VMD); then, the features of the decomposed signal are extracted using sample entropy to obtain the multidimensional feature vector of the braking signal; finally, the sparrow search algorithm (SSA) and probabilistic neural network are combined to optimize the smoothing factor with the sparrow search algorithm and the cross-entropy loss function as the fitness function to establish a braking intention recognition model. The experimental validation results show that combining the sample entropy features of the braking signal with the probabilistic neural network can effectively identify the braking intention, and the SSA-PNN algorithm has higher recognition accuracy compared with the traditional machine learning algorithm.

Big data-based method for automatic localization of power quality disturbance signal of PV access distribution network

At present, the conventional automatic localization method of the power quality disturbance signal of the distribution network mainly extracts the feature vector of the disturbance signal. It constructs the target localization function, which leads to poor localization accuracy because the noise part of the disturbance signal is ignored. In this regard, the automatic localization method of PV access power quality disturbance signal based on big data is proposed. By using the wavelet decomposition algorithm, the noise part of the power quality disturbance signal is removed, and the measurement matrix and reconstruction function are combined with compressing and reconstructing the disturbance signal. Finally, the automatic positioning of the disturbance signal is achieved by extracting the characteristics of the disturbance signal data and clustering analysis processing. In the experiment, the designed signal localization method is tested for the localization effect. The results can prove that when the proposed method is used to automatically localize the disturbed signal, the localization results are consistent with the spatial feature distribution of the signal and have a more desirable automatic localization effect.

Application of self-attention conditional deep convolutional generative adversarial networks in the fault diagnosis of planetary gearboxes

The Generative Adversarial Network (GAN) can generate samples similar to the original data to solve the problem of fault sample imbalance in planetary gearbox fault diagnosis. Most of models rely heavily on convolution to model the dependencies across feature vectors of vibration signals. However, the characterization ability of convolution operator is limited by the size of convolution kernel and it cannot capture the long-distance dependence in the original data. In this paper, self-attention is introduced into Conditional Deep Convolutional Generative Adversarial Networks (C-DCGAN). In the model, vibration features are dynamically weighted and merged, so that it can adaptively focus “attention” on different times to solve the problem of sample differences caused by time-varying vibration signals. Finally, the proposed method is verified on the planetary gearbox experiment and the quality of the generated signal samples is evaluated with Dynamic Time Warping (DTW) algorithm. The visual experimental results indicated that the proposed model performed better than conditional deep convolutional generative adversarial networks (C-DCGAN) and could accurately diagnose various working states of planetary gearboxes.

Identification of Vibration Signal for Residual Pressure Utilization Hydraulic Unit Using MRFO-BP Neural Network

Combined with wavelet threshold denoising and Ensemble Empirical Mode Decomposition (EEMD) decomposition, an identification method based on Manta Ray Foraging Optimization-BP (MRFO-BP) neural network for vibration signals of residual pressure utilization hydraulic units is proposed to distinguish the vibration signal of each unit. The feature vectors of vibration signals are extracted by wavelet denoising and EEMD decomposition. The weights and thresholds in BP neural network are optimized by the MRFO algorithm. The feature vectors are input into the optimized BP neural network to realize the identification and classification of vibration signals. Compared with Particle Swarm Optimization-BP (PSO-BP) neural network, Bat Algorithm-BP (BA-BP) neural network, and BP neural network, the results show that the identification rate of each measuring point from the MRFO-BP neural network is greatly improved. The average identification rate of other measuring points is 98.514%, except the identification rate of the generator, which is 85.389%. Therefore, the MRFO-BP neural network has better stability and higher identification accuracy and can identify and classify vibration signals more accurately. The conclusions can provide theoretical basis for vibration signals identification of residual pressure utilization hydraulic unit. When the vibration signal of each unit cannot be clearly distinguished, the vibration signals of the units are identified by the method proposed in this paper. According to the obtained results, a feasible classification method can be provided for the vibration signals belonging to different units.

A robust zero-watermarking scheme based on non-negative matrix factorization for audio protection

The copyright problem of digital products is becoming more and more prominent. In this case, digital watermarking technology has attracted the attention of many experts and scholars in the field of information security. Among the proposed technologies, zero-watermarking technology has been favored greatly with its excellent imperceptibility. In this paper, a novel robust audio zero-watermarking scheme is designed by applying non-negative matrix decomposition algorithm to zero-watermarking technology. Firstly, the proposed scheme divides the input audio signal into fixed frames, then applies fast Fourier transform(FFT) and non-negative matrix factorization(NMF) algorithm to extract the feature vector of the original audio signal. Finally, XOR the feature vector and the digital watermark sequence to achieve the embedding of zero-watermarking. The experimental results show that the proposed scheme performs more effectively in resisting common and frame-desynchronization attacks than the existing zero-watermarking schemes.

Research on rotor system fault diagnosis method based on vibration signal feature vector transfer learning

Aiming at the common fault diagnosis problems of rotors in industrial applications. A rotor system fault diagnosis method based on vibration signal feature vector transfer learning is proposed. First, Statistical methods and wavelet packet decomposition are used for vibration signal feature extraction. Then, the ReliefF algorithm is used to evaluate the fault features and screen out the sensitive fault features set. Next, the training data and real time test data are mapped to the kernel Hilbert space using the transfer component analysis method. Finally, the weighted k-nearest neighbor method is used as the fault feature classifier for fault pattern recognition. Model training and validation using typical failure datasets of different equipment and different operating conditions. Compared with other related methods, the results indicate that the proposed method has better generalization and diagnostic accuracy. This research will promote the engineering application of intelligent fault diagnosis of rotor system.

An automatic modulation classification network for IoT terminal spectrum monitoring under zero-sample situations

Rely on powerful computing resources, a large number of internet of things (IoT) sensors are placed in various locations to sense the environment we live. However, the proliferation of IoT devices has led to the misuse of spectrum resources, and many IoT devices occupy the frequency band without permission. As a consequence, the spectrum regulation has become an essential part of the development of IoT. Automatic modulation classification (AMC) is a task in spectrum monitoring, which senses the electromagnetic space and is carried out under non-cooperative communication. Generally, deep learning (DL)-based methods are data-driven and require large amounts of training data. In fact, under some non-cooperative communication scenarios, it is challenging to collect the wireless signal data directly. How can the DL-based algorithm complete the inference task under zero-sample conditions? In this paper, a signal zero-shot learning network (SigZSLNet) is proposed for AMC under the zero-sample situations. The semantic descriptions and the corresponding semantic vectors are designed to generate the feature vectors of the modulated signals. The generated feature vectors act as the training data of zero-sample classes. The experimental results demonstrate the effectiveness of the proposed SigZSLNet. The accuracy of one unseen class and two unseen classes exceeds 90% and 76%, respectively. Simultaneously, we show the generated feature vectors and the intermediate layer output of the model.

Time Series Segmentation Clustering: A New Method for S-Phase Picking in Microseismic Data

Phase picking is a critical step in the analysis of microseismic data. However, there is a lack of relevant methods for S-phase picking. In this letter, we pick the P-phase and extract the data around the S-phase arrival firstly based on previous studies. Then, we propose a method called time series segmentation clustering (TSSC) which is based on the K-means algorithm to pick the S-phase. In the TSSC method, we construct a feature vector of the microseismic signal and standardize the feature vector first. Then, we modify the K-means objective function into a function of time. We subsequently obtain the S-phase arrival corresponding to the minimum value of the objective function. We tested the objective function of the TSSC method on synthetic signals and microseismic signals, and the results show that the method is reliable. This automatic picking algorithm has been used to pick 1763 S-phase arrivals from microseismic signals. In comparison with manual picking results, a statistical analysis shows that this method is feasible.

EEG authentication based on deep learning of triplet loss

As a novel biometric characteristic, the electroencephalogram (EEG) is used for biometric authentication. To solve the challenge of efficiently growing the number of classifications in traditional classification networks and to increase the practicality of engineering, this paper proposes an authentication approach for EEG data based on an attention mechanism and a triplet loss function. The method begins by feeding EEG signals into a deep convolutional network, maps them to 512-dimensional Euclidean space using a long short-term memory network combined with an attention mechanism, and obtains feature vectors for EEG signals with identity information; it then adjusts the network parameters using a triplet loss function, such that the Euclidean distance between feature vectors of similar signals decreases while the distance between signals of a different type increases. Finally, the recognition method is evaluated using publicly available EEG data sets. The experimental results suggest that the method maintains the recognition rate while effectively expanding the classifications of the model, hence thus boosting the practicability of EEG authentication.

Fault diagnosis of gearbox based on ant colony algorithm optimized support vector machine

The kernel function parameter g and penalty factor c in Support Vector Machine (SVM) will have an important impact on the fault classification and performance of the support vector machine. Based on this, a fault analysis and diagnosis model using ant colony algorithm to optimize support vector machine is proposed to improve the accuracy of gearbox fault diagnosis. First, the collected original vibration signal is decomposed by EEMD to obtain the modal function component IMF, and then the energy entropy of the IMF component is calculated as the feature vector of the original vibration signal. Finally, the feature vector is input to the support vector optimized by the ant colony algorithm identify and classify in the machine, and finally get the diagnosis result. Comparing ACO-SVM with SVM, the experimental results prove that the ACO-SVM model has a higher fault diagnosis rate, stronger optimization ability, and faster convergence speed.

A One-Dimensional Siamese Few-Shot Learning Approach for ECG Classification under Limited Data.

Electrocardiogram (ECG) is mainly used by medical domain to diagnose arrhythmia. With the development of deep learning algorithms in the ECG classification field, related algorithms have achieved very high accuracy. However, the training of deep learning algorithms always requires large amounts of samples, while the labeled samples are often lacked in the field of medical signals. Therefore, the performance of deep learning algorithms will be greatly restricted. To overcome the sample scarcity problem, we propose a few-shot ECG classification approach based on the Siamese network. This network architecture first uses two one-dimensional convolutional neural network (CNN) that share weights to extract feature vectors of the paired input signals. Then, L1-distance between the two feature vectors is calculated and inputted into the fully connected layer with an activation function sigmoid to determine whether the input pairs belong to same category. We validated our method on the MIT-BIH arrhythmia database. By experiments, our method performs better than existing networks under the circumstance of extremely few amounts of data.

Parameterisation of human speech after total laryngectomy surgery

The aim of the rehabilitation in laryngectomised patients is to produce phonatory communication. It is important to choose the optimal method of speech rehabilitation. Most of the patients use esophageal or pharyngeal speech as an effect of natural rehabilitation with the vocalistic method. The aim of the study was to compare the quality of esophageal speech in laryngectomised people during speech rehabilitation with the speech of healthy people — without speech disorders. The purpose was to compare the values of the physical features of the speech signal (feature vector) read from the time and spectral domains. Voice samples were taken from 12 people aged 30–70 after total laryngectomy. They were recorded at the Bydgoszcz Laryngectomy Association (Bydgoszcz, Poland). In line with the rehabilitation process, words (spoken in Polish) such as “barrel”, “roll”, “egg”, “package”, and “snow” were analysed (each as a separate pattern). In addition, the slow counting from 1 to 10 was analysed, each word separately. In order to compare the values of the obtained descriptors of the speech signals of the laryngectomised people, voice samples (the same words) were also recorded by healthy people (3 men and 3 women aged 25–60). The obtained research results may help to improve the quality of the rehabilitation process of larygectomised patients by increasing the quality of esophageal speech.

Surface Electromyogram Feature Set Optimization for Lower Limb Activity Classification

Surface electromyogram (SEMG) shows the vital information of human motor activity. This information can identify the motor activity and controlling assistive and rehabilitative devices. However, its efficient extraction and interpretation plays a very critical role. The present study is focused on lower limb activity classification by selecting the efficient feature vector of the lower limb SEMG signal. Here, the SEMG signal-dependent continuous locomotion mode classification method has been proposed along with a dual-stage Feature Selection Algorithm (FSA). To evaluate the proposed method, SEMG signals of fifteen subjects were recorded from two lower limb muscles (Fibularis longus and Biceps Femoris) for five lower limb activities. The performance of six different classifiers was compared for intuitive feature vectors and FSA. The study analysed the performance of the proposed model for a single muscle approach and a dual muscle approach of activity classification. The time domain features were found more effective over other features, whereas Biceps Femoris muscle came out as a dominant muscle. The FSA enhanced the performance of classification model with fewer features as compared to intuitive feature subsets. Moreover, the dual muscle approach outperformed (p-value<0.05) over the single muscle approach. The best performance, for the dual muscle approach, was achieved 97.73 ± 2.47%, 98.99 ± 1.26% and 96.33 ± 2.70% for Neural Network, Linear Discriminant Analysis and Support Vector Machine classifiers, respectively (p-value > 0.05).

Research on Pipeline Defect Classification Based on SVM

The defect identification and evaluation of buried steel pipeline is a long-term challenge in the field of pipeline detection, and the prerequisite for efficient identification of defects is the accurate extraction of pipeline damage signals. Aiming at the characteristics of buried pipeline defect signals, a method of pipeline defect signal extraction and recognition is proposed, which is based on support vector machine (SVM). A dictionary is obtained by learning from the original signal, the dictionary is used to construct a sparse model of the defect signal using a regularized orthogonal matching pursuit algorithm, and the feature vector of the signal is obtained according to the compressed sensing theory. Furthermore, multi-classification SVM is used to establish a mapping relationship between the feature vector of the defect signal and the actual defect type of the pipeline, and Genetic Algorithm-Particle Swarm Optimization is used to guide the selection of SVM parameters. The results showed that the proposed classification method can realize the accurate division of the damage degree of pipeline defects.

RETRACTED ARTICLE: Big Data Mining and Analysis Based on Convolutional Fuzzy Neural Network

The purpose of this paper is to solve the shortcomings of traditional big data mining and analysis (BDMA); this paper compares and analyzes the denoise effect of wavelet transform and wavelet packet analysis and chooses to use wavelet packet analysis method to denoise the signal and extract fault feature vector. Finally, the extracted feature vectors are divided into two libraries, including training and testing. The fuzzy convolutional neural network (FCNN) is trained by using the training sample database data, the network weights are constantly modified, and the projection of nonlinear is computed between the input features and output features. After the expected recognition accuracy is achieved, the performance of FCNN is evaluated by using the detection samples. The performance comparison and analysis are conducted with the traditional BDMA algorithm, mainly including the comparison of recognition accuracy and learning convergence speed. Two stages of feature extraction and data mining (DM) are constructed on the big data set. The experimental results prove the effectiveness of wavelet transform feature and FCNN in analyzing and mining in big data. Finally, through the example of BDMA, this paper verifies that the organic combination of wavelet transform feature extraction and FCNN algorithm obviously improves the efficiency, meets the requirements of big data analysis, and provides potential application value for BDMA.

Centralized spectrum sensing based on covariance matrix decomposition and particle swarm clustering

As the essential technology of cognitive radio networks, numerous spectrum sensing approaches have been established to date. However, some spectrum sensing methods seem to fail in providing an effective signal feature and an accurate decision threshold, which affects the detection accuracy of the spectrum holes. In this article, to further ameliorate the recognition rate of the spectrum holes, a novel centralized spectrum sensing method based on covariance matrix decomposition and particle swarm clustering is presented. A novel signal feature vector is extracted by the IQ decomposition method and the Cholesky decomposition technique. Moreover, particle swarm clustering algorithm is trained to obtain a decision classifier, which can be used to identify whether the licensed spectrum is available or not. Additionally, two different application scenarios are considered here. Indeed, simulations examples are provided to demonstrate that the proposed algorithm can considerably ameliorate the sensing performance for centralized spectrum sensing.

Phantom motion intent decoding for transhumeral prosthesis control with fused neuromuscular and brain wave signals

In recent years, the electroencephalography (EEG) brain–computer interface (BCI) has been researched in the area of upper-limb prosthesis control due to the promise of being able to record neurological signals which follow activation patterns in the cortex directly from the brain with non-invasive electrodes. This is seen as a way of bypassing the limitation posed by acquiring neuromuscular signals predominantly with electromyography (EMG) directly from the stump, which possesses residual limb anatomy post-amputation. In this study, the sequential forward selection algorithm to form a 10-optimal-channel representation, alongside an extended signal feature vector was applied, to investigate the motion intent decoding performance of EMG-only, EEG-only, and a fused EMG–EEG sensing configuration for four transhumeral amputees with varying stump lengths. The results showed a considerable improvement for the EMG-only configuration with the advanced feature vector, but only a small increase for the EEG-only, and thus a marginal improvement when information from both signals was fused together. This is likely due to the EEG requiring a greater number of channels spread across the skull to provide a reliable intent decoding. Further work will now involve optimisation studies to find a greater representation of electrode representation and parsimony, to minimise the number of channels while boosting motion intent decoding accuracy.

A Method to Obtain Parameters of One-Column Jansen–Rit Model Using Genetic Algorithm and Spectral Characteristics

In this paper, a method of obtaining parameters of one-column Jansen–Rit model was proposed. Methods present in literature are focused on obtaining parameters in an on-line manner, producing a set of parameters for every point in time. The method described in this paper can provide one set of parameters for a whole, arbitrarily long signal. The procedure consists of obtaining specific frequency features, then minimizing mean square error of those features between the measured signal and the modeled signal, using genetic algorithm. This method produces an 8-element vector, which can be treated as an EEG signal feature vector specific for a person. The parameters which were being obtained are maximum postsynaptic potential amplitude, maximum inhibitory potential amplitude, ratio of the number of connections between particular neuron populations, the shape of a nonlinear function transforming the average membrane potential into the firing rate and the input noise range. The method shows high reproducibility (intraclass correlation coefficient for particular parameters ranging from 0.676 to 0.978) and accuracy (ranging from 0.662 to 0.863). It was additionally verified using EEG signal obtained for a single participant. This signal was measured using Emotiv EPOC+ NeuroHeadset.