Signal Feature Recognition Research Articles

Electromagnetic signal denoising model based on stacked ET layers structure

Electromagnetic signal denoising is crucial for safeguarding sensitive data from electromagnetic leakage. We introduce the Adaptive Stacked Temporal Pyramid Network (ASTPNet) for serial cable electromagnetic signals. ASTPNet combines dynamic convolution, pyramid channel convolution, and stacked ET layers structure to tackle non-linear and non-smooth noise. Dynamic convolution adjusts kernel parameters dynamically based on input signal variations, addressing signal non-smoothness. Pyramid channel convolution enhances the model’s capability to process non-linear features by analyzing key features across multiple scales. Stacked ET layers structure improve signal feature recognition by stacking multiple temporal network structures. Experimental results show that ASTPNet surpasses existing deep learning models in SNR, PSNR, and SI-SDR. The denoised signals can decode restored transmitted information, enhancing methodologies for the processing of electromagnetic signals.

Research on Surface Processing Method of Pulse Transmission Signal of Amplitude-Modulated Drilling Fluid in 10,000-m Deep Wells

Conventional Measurement-While-Drilling (MWD) technology is unable to function statically at the predicted temperatures of deep formations exceeding 200 °C in wells reaching depths of 10,000 m. It is limited to measuring downhole engineering parameters through purely mechanical means, such as inclination. However, the accurate long-distance transmission of drilling fluid pulse signals poses a significant bottleneck, restricting the application of these mechanical measurement methods. To address these issues, this paper develops and designs an algorithm to identify and analyze the amplitude characteristics of deep well mud signals. By employing a signal coding algorithm, a signal processing analysis method, and a signal feature recognition algorithm based on grey correlation degree, we construct a signal recognition method capable of decoding mud amplitude encoded signals. Key techniques such as filtering, smoothing, and feature extraction are utilized in the signal processing, and the proposed method’s effectiveness is verified through the analysis of collected signals. Furthermore, long-distance simulation analysis software is developed to evaluate waveform distortion during extended transmission, confirming the feasibility of the recognition algorithm. Laboratory experiments demonstrate that this algorithm can accurately recognize and demodulate signals generated by mechanical inclinometer structures, providing a novel decoding method for signal transmission in deep and ultra-deep wells.

Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network

Abstract In this paper, a multi-layer feed-forward neural network is used to construct a Meier spectrogram recognition system. By analyzing the algorithmic role of recurrent neural, the backpropagation algorithm is applied to update the weights in the neural network to obtain the mapping relationship between audio input and output. Combined with the algorithmic formula of the spectrum, the short-time Fourier transform is used to analyze the audio information. By architecting a multilayer feedforward recurrent neural network, the music signals are fused and classified. The cross-entropy loss function is applied to calculate the accuracy of micro and macro averages to improve the accuracy of music signal feature recognition. The results show that the feedforward recurrent neural network has the lowest error rate in different note recognition, and the error rate for “do” is 4%.

Nondestructive characterization and artificial intelligence recognition of acoustic identifiers of ancient ceramics

Cultural heritage identity management is the most basic and important work in the process of cultural heritage protection. It is of great significance to provide a unique and identifiable digital identity for ancient ceramics. At present, the identification information of ancient ceramics is mainly composed of external visual characteristics, and there is no report on feature identification method that can reflect the properties of ancient ceramics. Audible sound signals not only have advantages in non-destructive testing, but also can be used as voiceprint information to identify, monitor and analyze ancient ceramics. In this paper, seven ancient ceramics and 12 similar modern ceramic cups are taken as research objects, and an acoustic identifier (AID) is constructed. We put forward a reliable acoustic identification method for ancient ceramics, and established a digital code of acoustic characteristics of ancient ceramics. The results show that audible sound waves can reflect the attribute information of ancient ceramics. Sufficient acoustic data combined with deep learning can not only accurately match the identity of ancient ceramics, but also detect the real-time identity information of ancient ceramics, and make a comparative analysis of its cracks and whether it has caused damage. This method can provide a variety of practical applications for audible signal feature recognition technology in the exhibition, protection, trading, recognition and safety management of ancient ceramics and other cultural relics.

Multi-source perceptual blind compensation inspection method for substation based on equipment’s visual blind area identification and saliency detection

Abstract In order to expand the detection range and ensure the operation stability, the substation multi-source perception blind compensation detection method based on equipment visual blind area recognition and significance detection is studied. Acoustic sensors are used to collect acoustic signals from visual blind areas of equipment. The characteristics of noise signal are identified by wavelet analysis and noise reduction. The supercomplex Fourier transform model was used to extract the important region in the device image, and the texture features of the region were detected by Gabor filter. The blind compensation detection feature vector is formed by integrating two multi-source sensing features. The detection model of support vector machine is input to complete the blind compensation detection of the substation. The experimental results show that the proposed method is effective for the sound signal feature recognition in the visual blind area and the texture feature detection in the significant area of the device image. The different operating states of each equipment detected by the multi-source sensing feature vector are more accurate, which can realize the purpose of the multi-source sensing blind compensation check of the substation and ensure the safe and stable operation of the substation.

Multi-Morphological Pulse Signal Feature Point Recognition Based on One-Dimensional Deep Convolutional Neural Network

Radial pulse signals are produced by the periodic ejection of blood from the heart, and physiological and pathological information of the human body can be analyzed by extracting the time-domain characteristics of pulse waves. However, since pulse signals are weak physiological signals on the body surface and complex, the acquisition of pulse characteristics using the traditional curvature method will produce a large error, which cannot meet the needs of pulse wave analysis in current clinical practice. To solve this problem, a multi-morphological pulse signal feature recognition algorithm based on the one-dimensional deep convolutional neural network (1D-DCNN) model is proposed. We used the multi-channel pulse diagnosis instrument independently developed by the team to collect radial pulse signals under continuous pressure of the test subjects and collected 115 subjects and extracted a total of 1300 single-cycle pulse signals and then divided these pulse signals into 6 different forms. Five types of pulse signal time-domain feature points were labeled, and five independent feature point datasets were labeled and formed five customized neural network models that were generated to train and identify the pulse feature point datasets independently. The results show that the correction coefficient (Radjusted2) of the multi-class pulse signal processing algorithm proposed in this paper for each type of feature point recognition reaches more than 0.92. The performance is significantly better than that of the traditional curvature method, which shows the accuracy and superiority of the proposed method. Therefore, the multi-class pulse signal characteristic parameter recognition model based on the 1D-DCNN model proposed in this paper can efficiently and accurately identify pulse time-domain characteristic parameters, which can be applied to discriminate time-domain pulse information in clinical practice and assist doctors in diagnosis.

Research on multi-modal autonomous diagnosis algorithm of COVID-19 based on whale optimized support vector machine and improved D-S evidence fusion

Aiming at the problem that the single CT image signal feature recognition method in the self-diagnosis of diseases cannot accurately and reliably classify COVID-19, and it is easily confused with suspected cases. The collected CT signals and experimental indexes are extracted to construct different feature vectors. The support vector machine is optimized by the improved whale algorithm for the preliminary diagnosis of COVID-19, and the basic probability distribution function of each evidence is calculated by the posterior probability modeling method. Then the similarity measure is introduced to optimize the basic probability distribution function. Finally, the multi-domain feature fusion prediction model is established by using the weighted D-S evidence theory. The experimental results show that the fusion of multi-domain feature information by whale optimized support vector machine and improved D-S evidence theory can effectively improve the accuracy and the precision of COVID-19 autonomous diagnosis. The method of replacing a single feature parameter with multi-modal indicators (CT, routine laboratory indexes, serum cytokines and chemokines) provides a more reliable signal source for the diagnosis model, which can effectively distinguish COVID-19 from the suspected cases.

Low-Power Communication Signal Enhancement Method of Internet of Things Based on Nonlocal Mean Denoising

In order to improve the transmission effect of low-power communication signal of Internet of Things and compress the enhancement time of low-power communication signal, this paper designs a low-power communication signal enhancement method of Internet of Things based on nonlocal mean denoising. Firstly, the residual of one-dimensional communication layer is preprocessed by convolution core to obtain the residual of one-dimensional communication layer. Then, according to the two classification recognition methods, the noise reduction signal feature recognition of the low-power communication signal of the Internet of Things is realized, the nonlocal mean noise reduction algorithm is used to remove the low-power communication signal of the Internet of Things, and the weight value between similar blocks is calculated according to the European distance method. Finally, the low-power communication signal enhancement of the Internet of Things is realized by the nonlocal mean value denoising method. The experimental results show that the communication signal enhancement time overhead of this method is low, which is always less than 2.6 s. The lowest bit error rate after signal enhancement is about 1%, and the signal-to-noise ratio is up to 18 dB, which shows that this method can achieve signal enhancement.

Music Feature Extraction Method Based on Internet of Things Technology and Its Application.

Due to the influence of factors such as strong music specialization, complex music theory knowledge, and various variations, it is difficult to identify music features. We have developed a music characteristic identification system using the Internet-based method. The physical sensing layer of our designed system deploys audio sensors on various coordinates to capture the raw audio signal and performs audio signal processing and analysis using the TMS320VC5402 digital signal processor; the Internet transport layer places audio sensors at various locations to capture the raw audio signal. The TMS320VC5402 digital signal processor is used for audio signal diagnosis and treatment. The network transport layer transmits the finished audio signal to the data base of song signal in the application layer of the system; the song characteristic analysis block in the application layer adopts dynamics. The music characteristic analysis block in the applied layer adopts dynamic time warping algorithm to acquire the maximal resemblance between the test template and the reference template to achieve music signal characteristic identification and identify music tunes and music modes based on the identification results. The application layer music feature analysis block adopts dynamic time regularization algorithm and mel-frequency cepstrum coefficient to achieve music signal feature recognition and identify music tunes and music patterns based on the recognition results. We have verified through experiments, and the results show that the system operates consistently, can obtain high-quality music samples, and can extract good music characteristics.

Music Signal Recognition Based on the Mathematical and Physical Equation Inversion Method

Digitization and analysis processing technology of music signals is the core of digital music technology. The paper studies the music signal feature recognition technology based on the mathematical equation inversion method, which is aimed at designing a method that can help music learners in music learning and music composition. The paper firstly studies the modeling of music signal and its analysis and processing algorithm, combining the four elements of music sound, analyzing and extracting the characteristic parameters of notes, and establishing the mathematical model of single note signal and music score signal. The single note recognition algorithm is studied to extract the Mel frequency cepstrum coefficient of the signal and improve the DTW algorithm to achieve single note recognition. Based on the implementation of the single note algorithm, we combine the note temporal segmentation method based on the energy-entropy ratio to segment the music score into single note sequences to realize the music score recognition. The paper then goes on to study the music synthesis algorithm and perform simulations. The benchmark model demonstrates the positive correlation of pitch features on recognition through comparative experiments and explores the number of harmonics that should be attended to when recognizing different instruments. The attention network-based classification model draws on the properties of human auditory attention to improve the recognition scores of the main playing instruments and the overall recognition accuracy of all instruments. The two-stage classification model is divided into a first-stage classification model and a second-stage classification model, and the second-stage classification model consists of three residual networks, which are trained separately to specifically identify strings, winds, and percussions. This method has the highest recognition score and overall accuracy.

基于时域微分周期比的脉搏波信号特征识别

基于时域微分周期比的脉搏波信号特征识别

基于时域微分周期比的脉搏波信号特征识别

基于时域微分周期比的脉搏波信号特征识别

A hybrid BCI system based on motor imagery and transient visual evoked potential

Motion imaging (MI) refers to the psychological realization of motions without movement or muscle activity; the basis of neural rehabilitation as a brain-computer interface (BCI) technique has been extensively studied. The combination of motor imaging and brain-computer interface technology can take advantage of patients’ willingness to take the initiative to assist them in rehabilitation. Studies have shown that MI combined with BCI rehabilitation training is better than traditional rehabilitation training. Transient visual evoked potentials and motor imaging constructed a hybrid BCI system. Three healthy subjects were tested. EEG signals were superimposed preprocessing according to visual stimulus superimposed frequency and motor guidance frequency respectively. Transient visual evoked EEG segmentation is used as a control signal of choice, the use of wavelet decomposition helps to extract features, and then use BP neural network recognition for classification and identification. Visual guidance, motion-oriented event-related synchronization, or desynchronization feature signals as rehabilitation exercise control signals, are using time-domain sliding energy analysis to extract features, and then using BP neural network recognition for classification and identification. EEG signals collected in the experiment were superimposed signals of transient visual evoked and motorized EEG. There were 300 transient electroencephalogram (EEG) and 100 segments Imagine EEG segmentation. According to the results of the test, the average recognition rate of visual evoked EEG reached 95.42%; the average recognition rate of motor imaginary EEG was 73.08%, but there was a large individual difference in motor imaging EEG signals except 1 Name of the test rate of 85%, the remaining two subjects were less than 70% recognition rate. There is a large individual difference between motion imaging and signal feature recognition, and it takes a long time to train. Therefore, it is necessary to study further the selection of control signals for rehabilitation training. As the threshold feedback signal, controlling the amplitude feedback of rehabilitation training can promote the motivation of participants’ motivation to stimulate and enhance the rehabilitation treatment effect.

A New Methodology for Identifying Arc Fault by Sparse Representation and Neural Network

This paper proposes a sparse representation and fully connected neural network (SRFCNN) methodology for residential ac series arc fault identification. The SRFCNN method captures the features of idiographic signal using sparse coding and conducts intelligent feature learning and classification through neural network (NN). The methodology is elaborately structured by a pretreatment layer, a sparse representation layer, and a decision layer. The processing procedure includes the following main steps. A set of customized bases are first designed via dictionary learning to behave as precise feature descriptors rather than choosing a fixed dictionary. The pretreated input samples are accordingly transformed into a series of sparse coefficients and then fed into the NN for recognition. Experimental results indicate that the method works well in distinguishing the signature of the arcing state from that of normal state within a certain single load type, as well as recognizing the two states of various load types (resistive, inductive, capacitive, switching, etc.) all together. The general classification accuracy of every half-cycle signal in the 10 tested classes could reach 94.3% and be probably higher. The methodology’s good generality and reliability for arc fault identification show its potential in other unsupervised signal feature recognition and fault detection.

Feature Extraction Method for DC Charging Signal of Electric Vehicle

The high-power DC charging of electric vehicle charging stations leads to a large amount of ripple and unsteady waves in the power grid, which seriously affects power quality. The existing algorithms cannot accurately identify the signal characteristics of the fundamental wave, ripple, and the unsteady wave, and it is urgent to develop a comprehensive signal feature extraction method. Aiming at the time-varying characteristics of fundamental and non-steady-state waves in DC charging signals, the layered parameters of wavelet transform are modified, a multi-resolution method is established, and the fundamental and unsteady wave signals are identified and separated. Based on the amplitude-frequency and phase-frequency characteristics of DC charging signal, Fourier transform (FFT) is used to identify the amplitude and frequency of each sub-ripple, and a signal feature recognition method based on Fourier/wavelet transform is proposed to extract the signal characteristics of the DC charging process. The experimental results show that the signal feature recognition method based on Fourier/wavelet transform can identify the DC charging signal characteristics of electric vehicle with high accuracy, and can separate the unsteady state signal from the steady state signal.

Joint Rapid Spectrum Scanning and Signal Feature Recognition Scheme Using Compressed Sensing and Cyclostationary Technologies

This paper proposes a joint rapid spectrum scanning and signal feature recognition scheme by using both compressed sensing (CS) and cyclostationary technologies to solve the paradox of rapid spectrum scanning and accurate signal feature recognition. First, a new system architecture for signal feature recognition is designed based on rapid spectrum scanning results to decrease the times of proposed signal feature recognition scheme. Moreover, an improved CS technology is brought forward to accelerate the sensing speed without reconstructing received signals for a rapid spectrum scanning. And a tunable compression gain is proposed to reduce both computation complexity and sampling rate based on the difference of modulation mode and symbol rate for various signals. To further reduce the effect of noise on the modulation classification performance, a novel noise reduction scheme is proposed using the cyclostationary technology. Results prove that proposed scheme can achieve both rapid spectrum scanning and accurate signal feature recognition simultaneously. Furthermore, it can reduce the sampling rate for CS over 30% and achieves a signal detection gain of 2–3 dB with signal to noise ratio constraints.

Aero-engine Vibration Signal Blind Separation Based on BP Neural Network Algorithm

The normal running of the aero-engine is an important guarantee to the aviation aircraft flying in safe. As a result, the analysis and processing of the aero-engine vibration signal is an important task, which can realize the running state monitoring and fault diagnosis to the aviation aircraft. Due to the complexity of the aero-engine’s structure, the vibration signals of aero-engine from the sensors fixed upon the aero-engine’s brake often consist of several signals in aliasing, and also contain noise and other disturbance signal among them. The traditional vibration signal processing methods aiming at the anti-interference and de-noising have no significant effect. In addition, due to the non-linearity of the mixed signal, signal feature recognition and extraction is difficulties. This paper presented an application of the BP neural network to the aero-engine vibration signal separation, through the simulation of the aero-engine vibration signal induced by the high pressure rotor and low pressure rotor rotational imbalance; we proved the accuracy of the algorithm, which can separate the aero-engine vibration signal effectively. Through comparing with the fault spectrum characteristics of the aero-engine, the method can predict and diagnosis the aero-engine fault, which has a very important practical value.

Analysis of the Interference Signal of the Distributed Optical Fiber Sensing Based on DSP

In this paper, the author analyzes characteristics and extracting method of interference signal of the distributed optical fiber sensing. In the distributed optical fiber sensing, realizing alarm and positioning function only through the cross-correlation operation will increase the load of the system, can make misinformation rate of the system be improved greatly. Therefore, before the localization algorithm, adding a interference signal feature recognition is very necessary, can reduce unnecessary operation loss and reduce the load of the system, also reducing the number of the false positives.

Signal feature recognition based on lightwave neuromorphic signal processing

We developed a hybrid analog/digital lightwave neuromorphic processing device that effectively performs signal feature recognition. The approach, which mimics the neurons in a crayfish responsible for the escape response mechanism, provides a fast and accurate reaction to its inputs. The analog processing portion of the device uses the integration characteristic of an electro-absorption modulator, while the digital processing portion employ optical thresholding in a highly Ge-doped nonlinear loop mirror. The device can be configured to respond to different sets of input patterns by simply varying the weights and delays of the inputs. We experimentally demonstrated the use of the proposed lightwave neuromorphic signal processing device for recognizing specific input patterns.