Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely id...Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.展开更多
In this paper,we propose a novel graph signal processing convolution recurrent network(GSP CRN)for signal enhancement against high suppressive interference(HSI)in wireless communications.GSPCRN consists of the short-t...In this paper,we propose a novel graph signal processing convolution recurrent network(GSP CRN)for signal enhancement against high suppressive interference(HSI)in wireless communications.GSPCRN consists of the short-time graph signal processing(SGSP)approach and a modified convolution recurrent network.Similar to the traditional shorttime time-frequency transformation,SGSP frames the complex-valued communication signal and transforms it to the graph-domain representations,where the connection and weight flexibility of each vertex are fully taken into account.In the presence of HSI,SGSP can extract signal features from new graph-domain dimensions and empower neural networks for weak signal enhancement.Two SGSP methods,adjacency singular value decomposition and implicit graph transformation,are designed to capture relationships among the sampling points in the segmented signals.Simulation results demonstrate that our proposed GSPCRN outperforms existing classic methods in extracting weak signals from the HSI environment.When the interference-to-signal ratio exceeds 27dB,only our proposed GSPCRN can achieve the interference mitigation.展开更多
Low-voltage direct current(DC)microgrids have recently emerged as a promising and viable alternative to traditional alternating cur-rent(AC)microgrids,offering numerous advantages.Consequently,researchers are explorin...Low-voltage direct current(DC)microgrids have recently emerged as a promising and viable alternative to traditional alternating cur-rent(AC)microgrids,offering numerous advantages.Consequently,researchers are exploring the potential of DC microgrids across var-ious configurations.However,despite the sustainability and accuracy offered by DC microgrids,they pose various challenges when integrated into modern power distribution systems.Among these challenges,fault diagnosis holds significant importance.Rapid fault detection in DC microgrids is essential to maintain stability and ensure an uninterrupted power supply to critical loads.A primary chal-lenge is the lack of standards and guidelines for the protection and safety of DC microgrids,including fault detection,location,and clear-ing procedures for both grid-connected and islanded modes.In response,this study presents a brief overview of various approaches for protecting DC microgrids.展开更多
Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert p...Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert performance.This survey reviews the principal model families as convolutional,recurrent,generative,reinforcement,autoencoder,and transfer-learning approaches as emphasising how their architectural choices map to tasks such as segmentation,classification,reconstruction,and anomaly detection.A dedicated treatment of multimodal fusion networks shows how imaging features can be integrated with genomic profiles and clinical records to yield more robust,context-aware predictions.To support clinical adoption,we outline post-hoc explainability techniques(Grad-CAM,SHAP,LIME)and describe emerging intrinsically interpretable designs that expose decision logic to end users.Regulatory guidance from the U.S.FDA,the European Medicines Agency,and the EU AI Act is summarised,linking transparency and lifecycle-monitoring requirements to concrete development practices.Remaining challenges as data imbalance,computational cost,privacy constraints,and cross-domain generalization are discussed alongside promising solutions such as federated learning,uncertainty quantification,and lightweight 3-D architectures.The article therefore offers researchers,clinicians,and policymakers a concise,practice-oriented roadmap for deploying trustworthy deep-learning systems in healthcare.展开更多
Power converters are essential components in modern life,being widely used in industry,automation,transportation,and household appliances.In many critical applications,their failure can lead not only to financial loss...Power converters are essential components in modern life,being widely used in industry,automation,transportation,and household appliances.In many critical applications,their failure can lead not only to financial losses due to operational downtime but also to serious risks to human safety.The capacitors forming the output filter,typically aluminumelectrolytic capacitors(AECs),are among the most critical and susceptible components in power converters.The electrolyte in AECs often evaporates over time,causing the internal resistance to rise and the capacitance to drop,ultimately leading to component failure.Detecting this fault requires measuring the current in the capacitor,rendering the method invasive and frequently impractical due to spatial constraints or operational limitations imposed by the integration of a current sensor in the capacitor branch.This article proposes the implementation of an online noninvasive fault diagnosis technique for estimating the Equivalent Series Resistance(ESR)and Capacitance(C)values of the capacitor,employing a combination of signal processing techniques(SPT)and machine learning(ML)algorithms.This solution relies solely on the converter’s input and output signals,therefore making it a non-invasive approach.The ML algorithm used was linear regression,applied to 27 attributes,21 of which were generated through feature engineering to enhance the model’s performance.The proposed solution demonstrates an R^(2) score greater than 0.99 in the estimation of both ESR and C.展开更多
This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-preci...This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-precision laser interferometric displacement measurement.A stable power supply module is designed to provide low-noise voltage to the entire circuit.An analog circuit system is constructed,including key circuits such as photoelectric sensors,I-V amplification,zero adjustment,fully differential amplification,and amplitude modulation filtering.To acquire and process signals,the PMAC Acc24E3 data acquisition card is selected,which realizes phase demodulation through reversible square wave counting,inverts displacement information,and a visual interface for the host computer is designed.Experimental verification shows that the designed system achieves micrometer-level measurement accuracy within a range of 0-10mm,with a maximum measurement error of less than 1.2μm,a maximum measurement speed of 6m/s,and a resolution better than 0.158μm.展开更多
This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal fea...This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal features with the Transformer encoder that captures long-range dependencies in time-series data through multi-head attention.Model performance was evaluated on two widely used tactile biosignal datasets,HAART and CoST,which contain diverse affective touch gestures recorded from pressure sensor arrays.TheCNN-Transformer model achieved recognition rates of 93.33%on HAART and 80.89%on CoST,outperforming existing methods on both benchmarks.By incorporating temporal windowing,the model enables instantaneous prediction,improving generalization across gestures of varying duration.These results highlight the effectiveness of deep learning for tactile biosignal processing and demonstrate the potential of theCNN-Transformer approach for future applications in wearable sensors,affective computing,and biomedical monitoring.展开更多
Decomposition and reconstruction of Mallat fast wavelet transformation （WT） is described. A fast algorithm, which can greatly decrease the processing burden and can be very easy for hardware implementation in real-t...Decomposition and reconstruction of Mallat fast wavelet transformation （WT） is described. A fast algorithm, which can greatly decrease the processing burden and can be very easy for hardware implementation in real-time, is analyzed. The algorithm will no longer have the processing of decimation and interpolation of usual WT. The formulae of the decomposition and the reconstruction are given. Simulation results of the MEMS （micro-electro mechanical systems） gyroscope drift signal show that the algorithm spends much less processing time to finish the de-noising process than the usual WT. And the de-noising effect is the same. The fast algorithm has been implemented in a TMS320C6713 digital signal processor. The standard variance of the gyroscope static drift signal decreases from 78. 435 5 （°）/h to 36. 763 5 （°）/h. It takes 0. 014 ms to process all input data and can meet the real-time analysis of signal.展开更多
Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods dif...Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.展开更多
The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-dom...The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-domain methods have been partly successful in identifying small cracks, but not so successful in estimating crack size, especially in strong backscattering noise. Sparse signal representation can provide sparse information that represents the signal time-frequency signature, which can also be used in processing ultrasonic nondestructive signals. A novel ultrasonic nondestructive signal processing algorithm based on signal sparse representation is proposed. In order to suppress noise, matching pursuit algorithm with Gabor dictionary is selected as the signal decomposition method. Precise echoes information, such as crack location and size, can be estimated by quantitative analysis with Gabor atom. To verify the performance, the proposed algorithm is applied to computer simulation signal and experimental ultrasonic signals which represent multiple backscattered echoes from a thin metal plate with artificial holes. The results show that this algorithm not only has an excellent performance even when dealing with signals in the presence of strong noise, but also is successful in estimating crack location and size. Moreover, the algorithm can be applied to data compression of ultrasonic nondestructive signal.展开更多
Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can ex...Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can extract the potent time-frequency-domain characteristics of signals;however,the performance of conventional characteristics-based classification needs to be improved.Widely used deep learning algorithms(e.g.,convolutional neural networks(CNNs))can conduct classification by extracting high-dimensional data features,with outstanding performance.Hence,combining the advantages of signal processing and deep-learning algorithms can significantly enhance vibration recognition performance.A novel vibration recognition method based on signal processing and deep neural networks is proposed herein.First,environmental vibration signals are collected;then,signal processing is conducted to obtain the coefficient matrices of the time-frequency-domain characteristics using three typical algorithms:the wavelet transform,Hilbert-Huang transform,and Mel frequency cepstral coefficient extraction method.Subsequently,CNNs,long short-term memory(LSTM)networks,and combined deep CNN-LSTM networks are trained for vibration recognition,according to the time-frequencydomain characteristics.Finally,the performance of the trained deep neural networks is evaluated and validated.The results confirm the effectiveness of the proposed vibration recognition method combining signal preprocessing and deep learning.展开更多
Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communicati...Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communications systems.Meanwhile,it has been recently admitted that implementing artificial intelligence(AI)into RIS communications will extensively benefit the reconfiguration capacity and enhance the robustness to complicated transmission environments.Besides the conventional model-driven approaches,AI can also deal with the existing signal processing problems in a data-driven manner via digging the inherent characteristic from the real data.Hence,AI is particularly suitable for the signal processing problems over RIS networks under unideal scenarios like modeling mismatching,insufficient resource,hardware impairment,as well as dynamical transmissions.As one of the earliest survey papers,we will introduce the merging of AI and RIS,called AIRIS,over various signal processing topics,including environmental sensing,channel acquisition,beamforming design,and resource scheduling,etc.We will also discuss the challenges of AIRIS and present some interesting future directions.展开更多
The construction of basic wavelet was discussed and many basic analyzing wavelets was compared. Acomplex analyzing wavelet which is continuous, smoothing, orthogonal and exponential decreasing was presented, andit was...The construction of basic wavelet was discussed and many basic analyzing wavelets was compared. Acomplex analyzing wavelet which is continuous, smoothing, orthogonal and exponential decreasing was presented, andit was used to decompose two blasting seismic signals with the continuous wavelet transforms (CWT). The resultshows that wavelet analysis is the better method to help us determine the essential factors which create damage effectsthan Fourier analysis.展开更多
Traffic monitoring is of major importance for enforcing traffic management policies.To accomplish this task,the detection of vehicle can be achieved by exploiting image analysis techniques.In this paper,a solution is ...Traffic monitoring is of major importance for enforcing traffic management policies.To accomplish this task,the detection of vehicle can be achieved by exploiting image analysis techniques.In this paper,a solution is presented to obtain various traffic parameters through vehicular video detection system(VVDS).VVDS exploits the algorithm based on virtual loops to detect moving vehicle in real time.This algorithm uses the background differencing method,and vehicles can be detected through luminance difference of pixels between background image and current image.Furthermore a novel technology named as spatio-temporal image sequences analysis is applied to background differencing to improve detection accuracy.Then a hardware implementation of a digital signal processing (DSP) based board is described in detail and the board can simultaneously process four-channel video from different cameras. The benefit of usage of DSP is that images of a roadway can be processed at frame rate due to DSP′s high performance.In the end,VVDS is tested on real-world scenes and experiment results show that the system is both fast and robust to the surveillance of transportation.展开更多
DQPSK modem has been chosen as the modem scheme in many mobile communication systems. A new signal processing technique of π/4-DQPSK modem based on software radio is discussed in this paper. Unlike many other softwar...DQPSK modem has been chosen as the modem scheme in many mobile communication systems. A new signal processing technique of π/4-DQPSK modem based on software radio is discussed in this paper. Unlike many other software radio solutions to the subject, we choose a universal digital radio baseband processor operating as the co-processor of DSP. Only the core algorithms for signal processing are implemented with DSP. Thus the computation burden on DSP is reduced significantly. Compared with the traditional ones, the technique mentioned in this paper is more promising and attractive. It is extremely compact and power-efficient, which is often required by a mobile communication system. The implementation of baseband signal processing for π/4-DQPSK modem on this platform is illustrated in detail. Special emphases are laid on the architecture of the system and the algorithms used in the baseband signal processing. Finally, some experimental results are presented and the performances of the signal processing and compensation algorithms are evaluated through computer simulations.展开更多
Radar is an electronic device that uses radio waves to determine the range, angle, or velocity of objects. Real-time signal and information processor is an important module for real-time positioning, imaging, detectio...Radar is an electronic device that uses radio waves to determine the range, angle, or velocity of objects. Real-time signal and information processor is an important module for real-time positioning, imaging, detection and recognition of targets. With the development of ultra-wideband technology, synthetic aperture technology, signal and information processing technology, the radar coverage, detection accuracy and resolution have been greatly improved, especially in terms of one-dimensional(1D) high-resolution radar detection, tracking, recognition, and two-dimensional(2D) synthetic aperture radar imaging technology. Meanwhile, for the application of radar detection and remote sensing with high resolution and wide swath, the amount of data has been greatly increased. Therefore, the radar is required to have low-latency and real-time processing capability under the constraints of size, weight and power consumption. This paper systematically introduces the new technology of high resolution radar and real-time signal and information processing. The key problems and solutions are discussed, including the detection and tracking of 1D high-resolution radar, the accurate signal modeling and wide-swath imaging for geosynchronous orbit synthetic aperture radar, and real-time signal and information processing architecture and efficient algorithms. Finally, the latest research progress and representative results are presented, and the development trends are prospected.展开更多
Due to the heavy congestion in HF bands, HF radars are restricted to operating within narrow frequency bands. To improve the system bandwidth and avoid heavy interference bands, a quasi-random step frequency signal wi...Due to the heavy congestion in HF bands, HF radars are restricted to operating within narrow frequency bands. To improve the system bandwidth and avoid heavy interference bands, a quasi-random step frequency signal with discontinuous bands is presented. A novel two-dimensional signal processing scheme for this signal is proposed on the basis of delicate signal analysis. Simulation results demonstrate that the scheme could successfully realize the resolutions by decoupling the range-Doppler ambiguity, and effectively suppress the maximal sidelobe. Moreover, the scheme is simple and has good numerical stability.展开更多
The neutron count rate fluctuation reaches six orders of magnitude between the ohmic plasma scenario and high power of auxiliary heating on an experimental advanced superconducting tokamak(EAST).The measurement result...The neutron count rate fluctuation reaches six orders of magnitude between the ohmic plasma scenario and high power of auxiliary heating on an experimental advanced superconducting tokamak(EAST).The measurement result of neutron flux monitoring(NFM)is a significant feedback parameter related to the acquisition of radiation protection-related information and rapid fluctuations in neutron emission induced by plasma magnetohydrodynamic activity.Therefore,a wide range and high time resolution are required for the NFM system on EAST.To satisfy these requirements,a digital pulse signal acquisition and processing system with a wide dynamic range and fast response time was developed.The present study was conducted using a field-programmable gate array(FPGA)and peripheral component interconnect extension for instrument express(PXIe)platform.The digital dual measurement modes,which are composed of the pulse-counting mode and AC coupled square integral's Campbelling mode,were designed to expand the measurement range of the signal acquisition and processing system.The time resolution of the signal acquisition and processing system was improved from 10 to 1 ms owing to utilizing highspeed analog-to-digital converters(ADCs),a high-speed PXIe communication with a direct memory access(DMA)mode,and online data preprocessing technology of FPGA.The signal acquisition and processing system was tested experimentally in the EAST radiation field.The test results showed that the time resolution of NFM was improved to 1 ms,and the dynamic range of the neutron counts rate was expanded to more than 10^(6) counts per second.The Campbelling mode was calibrated using a multipoint average linear fitting method;subsequently,the fitting coefficient reached 0.9911.Therefore,the newly developed pulse signal acquisition and processing system ensures that the NFM system meets the requirements of high-parameter experiments conducted on EAST more effectively.展开更多
The investigation of novel signal processing tools is one of the hottest research topics in modern signal processing community. Among them, the algebraic and geometric signal processing methods are the most powerful t...The investigation of novel signal processing tools is one of the hottest research topics in modern signal processing community. Among them, the algebraic and geometric signal processing methods are the most powerful tools for the representation of the classical signal processing method. In this paper, we provide an overview of recent contributions to the algebraic and geometric signal processing. Specifically, the paper focuses on the mathematical structures behind the signal processing by emphasizing the algebraic and geometric structure of signal processing. The two major topics are discussed. First, the classical signal processing concepts are related to the algebraic structures, and the recent results associated with the algebraic signal processing theory are introduced. Second, the recent progress of the geometric signal and information processing representations associated with the geometric structure are discussed. From these discussions, it is concluded that the research on the algebraic and geometric structure of signal processing can help the researchers to understand the signal processing tools deeply, and also help us to find novel signal processing methods in signal processing community. Its practical applications are expected to grow significantly in years to come, given that the algebraic and geometric structure of signal processing offer many advantages over the traditional signal processing.展开更多
The grain production prediction is one of the most important links in precision agriculture. In the process of grain production prediction, mechanical noise caused by the factors of difference in field topography and ...The grain production prediction is one of the most important links in precision agriculture. In the process of grain production prediction, mechanical noise caused by the factors of difference in field topography and mechanical vibration will be mixed in the original signal, which undoubtedly will affect the prediction accuracy. Therefore, in order to reduce the influence of vibration noise on the prediction accuracy, an adaptive Ensemble Empirical Mode Decomposition(EEMD) threshold filtering algorithm was applied to the original signal in this paper: the output signal was decomposed into a finite number of Intrinsic Mode Functions(IMF) from high frequency to low frequency by using the Empirical Mode Decomposition(EMD) algorithm which could effectively restrain the mode mixing phenomenon; then the demarcation point of high and low frequency IMF components were determined by Continuous Mean Square Error criterion(CMSE), the high frequency IMF components were denoised by wavelet threshold algorithm, and finally the signal was reconstructed. The algorithm was an improved algorithm based on the commonly used wavelet threshold. The two algorithms were used to denoise the original production signal respectively, the adaptive EEMD threshold filtering algorithm had significant advantages in three denoising performance indexes of signal denoising ratio, root mean square error and smoothness. The five field verification tests showed that the average error of field experiment was 1.994% and the maximum relative error was less than 3%. According to the test results, the relative error of the predicted yield per hectare was 2.97%, which was relative to the actual yield. The test results showed that the algorithm could effectively resist noise and improve the accuracy of prediction.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.42130719 and 42177173)the Doctoral Direct Train Project of Chongqing Natural Science Foundation(Grant No.CSTB2023NSCQ-BSX0029).
文摘Underground engineering projects such as deep tunnel excavation often encounter rockburst disasters accompanied by numerous microseismic events.Rapid interpretation of microseismic signals is crucial for the timely identification of rockbursts.However,conventional processing encompasses multi-step workflows,including classification,denoising,picking,locating,and computational analysis,coupled with manual intervention,which collectively compromise the reliability of early warnings.To address these challenges,this study innovatively proposes the“microseismic stethoscope"-a multi-task machine learning and deep learning model designed for the automated processing of massive microseismic signals.This model efficiently extracts three key parameters that are necessary for recognizing rockburst disasters:rupture location,microseismic energy,and moment magnitude.Specifically,the model extracts raw waveform features from three dedicated sub-networks:a classifier for source zone classification,and two regressors for microseismic energy and moment magnitude estimation.This model demonstrates superior efficiency compared to traditional processing and semi-automated processing,reducing per-event processing time from 0.71 s to 0.49 s to merely 0.036 s.It concurrently achieves 98%accuracy in source zone classification,with microseismic energy and moment magnitude estimation errors of 0.13 and 0.05,respectively.This model has been well applied and validated in the Daxiagu Tunnel case in Sichuan,China.The application results indicate that the model is as accurate as traditional methods in determining source parameters,and thus can be used to identify potential geomechanical processes of rockburst disasters.By enhancing the signal processing reliability of microseismic events,the proposed model in this study presents a significant advancement in the identification of rockburst disasters.
基金supported by he National Social Science Found of China(2022-SKJJ-B-112).
文摘In this paper,we propose a novel graph signal processing convolution recurrent network(GSP CRN)for signal enhancement against high suppressive interference(HSI)in wireless communications.GSPCRN consists of the short-time graph signal processing(SGSP)approach and a modified convolution recurrent network.Similar to the traditional shorttime time-frequency transformation,SGSP frames the complex-valued communication signal and transforms it to the graph-domain representations,where the connection and weight flexibility of each vertex are fully taken into account.In the presence of HSI,SGSP can extract signal features from new graph-domain dimensions and empower neural networks for weak signal enhancement.Two SGSP methods,adjacency singular value decomposition and implicit graph transformation,are designed to capture relationships among the sampling points in the segmented signals.Simulation results demonstrate that our proposed GSPCRN outperforms existing classic methods in extracting weak signals from the HSI environment.When the interference-to-signal ratio exceeds 27dB,only our proposed GSPCRN can achieve the interference mitigation.
文摘Low-voltage direct current(DC)microgrids have recently emerged as a promising and viable alternative to traditional alternating cur-rent(AC)microgrids,offering numerous advantages.Consequently,researchers are exploring the potential of DC microgrids across var-ious configurations.However,despite the sustainability and accuracy offered by DC microgrids,they pose various challenges when integrated into modern power distribution systems.Among these challenges,fault diagnosis holds significant importance.Rapid fault detection in DC microgrids is essential to maintain stability and ensure an uninterrupted power supply to critical loads.A primary chal-lenge is the lack of standards and guidelines for the protection and safety of DC microgrids,including fault detection,location,and clear-ing procedures for both grid-connected and islanded modes.In response,this study presents a brief overview of various approaches for protecting DC microgrids.
基金supported by the Science Committee of the Ministry of Higher Education and Science of the Republic of Kazakhstan within the framework of grant AP23489899“Applying Deep Learning and Neuroimaging Methods for Brain Stroke Diagnosis”.
文摘Deep learning now underpins many state-of-the-art systems for biomedical image and signal processing,enabling automated lesion detection,physiological monitoring,and therapy planning with accuracy that rivals expert performance.This survey reviews the principal model families as convolutional,recurrent,generative,reinforcement,autoencoder,and transfer-learning approaches as emphasising how their architectural choices map to tasks such as segmentation,classification,reconstruction,and anomaly detection.A dedicated treatment of multimodal fusion networks shows how imaging features can be integrated with genomic profiles and clinical records to yield more robust,context-aware predictions.To support clinical adoption,we outline post-hoc explainability techniques(Grad-CAM,SHAP,LIME)and describe emerging intrinsically interpretable designs that expose decision logic to end users.Regulatory guidance from the U.S.FDA,the European Medicines Agency,and the EU AI Act is summarised,linking transparency and lifecycle-monitoring requirements to concrete development practices.Remaining challenges as data imbalance,computational cost,privacy constraints,and cross-domain generalization are discussed alongside promising solutions such as federated learning,uncertainty quantification,and lightweight 3-D architectures.The article therefore offers researchers,clinicians,and policymakers a concise,practice-oriented roadmap for deploying trustworthy deep-learning systems in healthcare.
文摘Power converters are essential components in modern life,being widely used in industry,automation,transportation,and household appliances.In many critical applications,their failure can lead not only to financial losses due to operational downtime but also to serious risks to human safety.The capacitors forming the output filter,typically aluminumelectrolytic capacitors(AECs),are among the most critical and susceptible components in power converters.The electrolyte in AECs often evaporates over time,causing the internal resistance to rise and the capacitance to drop,ultimately leading to component failure.Detecting this fault requires measuring the current in the capacitor,rendering the method invasive and frequently impractical due to spatial constraints or operational limitations imposed by the integration of a current sensor in the capacitor branch.This article proposes the implementation of an online noninvasive fault diagnosis technique for estimating the Equivalent Series Resistance(ESR)and Capacitance(C)values of the capacitor,employing a combination of signal processing techniques(SPT)and machine learning(ML)algorithms.This solution relies solely on the converter’s input and output signals,therefore making it a non-invasive approach.The ML algorithm used was linear regression,applied to 27 attributes,21 of which were generated through feature engineering to enhance the model’s performance.The proposed solution demonstrates an R^(2) score greater than 0.99 in the estimation of both ESR and C.
文摘This thesis addresses the issues existing in traditional laser tracking displacement measurement technology in the field of ultraprecision metrology by designing a differential signal processing circuit for high-precision laser interferometric displacement measurement.A stable power supply module is designed to provide low-noise voltage to the entire circuit.An analog circuit system is constructed,including key circuits such as photoelectric sensors,I-V amplification,zero adjustment,fully differential amplification,and amplitude modulation filtering.To acquire and process signals,the PMAC Acc24E3 data acquisition card is selected,which realizes phase demodulation through reversible square wave counting,inverts displacement information,and a visual interface for the host computer is designed.Experimental verification shows that the designed system achieves micrometer-level measurement accuracy within a range of 0-10mm,with a maximum measurement error of less than 1.2μm,a maximum measurement speed of 6m/s,and a resolution better than 0.158μm.
文摘This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal features with the Transformer encoder that captures long-range dependencies in time-series data through multi-head attention.Model performance was evaluated on two widely used tactile biosignal datasets,HAART and CoST,which contain diverse affective touch gestures recorded from pressure sensor arrays.TheCNN-Transformer model achieved recognition rates of 93.33%on HAART and 80.89%on CoST,outperforming existing methods on both benchmarks.By incorporating temporal windowing,the model enables instantaneous prediction,improving generalization across gestures of varying duration.These results highlight the effectiveness of deep learning for tactile biosignal processing and demonstrate the potential of theCNN-Transformer approach for future applications in wearable sensors,affective computing,and biomedical monitoring.
基金The National High Technology Research and Devel-opment Program of China (863Program) (No2002AA812038)
文摘Decomposition and reconstruction of Mallat fast wavelet transformation （WT） is described. A fast algorithm, which can greatly decrease the processing burden and can be very easy for hardware implementation in real-time, is analyzed. The algorithm will no longer have the processing of decimation and interpolation of usual WT. The formulae of the decomposition and the reconstruction are given. Simulation results of the MEMS （micro-electro mechanical systems） gyroscope drift signal show that the algorithm spends much less processing time to finish the de-noising process than the usual WT. And the de-noising effect is the same. The fast algorithm has been implemented in a TMS320C6713 digital signal processor. The standard variance of the gyroscope static drift signal decreases from 78. 435 5 （°）/h to 36. 763 5 （°）/h. It takes 0. 014 ms to process all input data and can meet the real-time analysis of signal.
基金National Natural Science Foundation of China (Grant Nos. 51835009, 52105116)China Postdoctoral Science Foundation (Grant Nos. 2021M692557, 2021TQ0263)。
文摘Deep learning(DL) is progressively popular as a viable alternative to traditional signal processing(SP) based methods for fault diagnosis. However, the lack of explainability makes DL-based fault diagnosis methods difficult to be trusted and understood by industrial users. In addition, the extraction of weak fault features from signals with heavy noise is imperative in industrial applications. To address these limitations, inspired by the Filterbank-Feature-Decision methodology, we propose a new Signal Processing Informed Neural Network(SPINN) framework by embedding SP knowledge into the DL model. As one of the practical implementations for SPINN, a denoising fault-aware wavelet network(DFAWNet) is developed, which consists of fused wavelet convolution(FWConv), dynamic hard thresholding(DHT),index-based soft filtering(ISF), and a classifier. Taking advantage of wavelet transform, FWConv extracts multiscale features while learning wavelet scales and selecting important wavelet bases automatically;DHT dynamically eliminates noise-related components via point-wise hard thresholding;inspired by index-based filtering, ISF optimizes and selects optimal filters for diagnostic feature extraction. It’s worth noting that SPINN may be readily applied to different deep learning networks by simply adding filterbank and feature modules in front. Experiments results demonstrate a significant diagnostic performance improvement over other explainable or denoising deep learning networks. The corresponding code is available at https://github. com/alber tszg/DFAWn et.
基金supported by National Natural Science Foundation of China (Grant No. 60672108, Grant No. 60372020)
文摘The success of ultrasonic nondestructive testing technology depends not only on the generation and measurement of the desired waveform, but also on the signal processing of the measured waves. The traditional time-domain methods have been partly successful in identifying small cracks, but not so successful in estimating crack size, especially in strong backscattering noise. Sparse signal representation can provide sparse information that represents the signal time-frequency signature, which can also be used in processing ultrasonic nondestructive signals. A novel ultrasonic nondestructive signal processing algorithm based on signal sparse representation is proposed. In order to suppress noise, matching pursuit algorithm with Gabor dictionary is selected as the signal decomposition method. Precise echoes information, such as crack location and size, can be estimated by quantitative analysis with Gabor atom. To verify the performance, the proposed algorithm is applied to computer simulation signal and experimental ultrasonic signals which represent multiple backscattered echoes from a thin metal plate with artificial holes. The results show that this algorithm not only has an excellent performance even when dealing with signals in the presence of strong noise, but also is successful in estimating crack location and size. Moreover, the algorithm can be applied to data compression of ultrasonic nondestructive signal.
文摘Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification.Signal-processing methods can extract the potent time-frequency-domain characteristics of signals;however,the performance of conventional characteristics-based classification needs to be improved.Widely used deep learning algorithms(e.g.,convolutional neural networks(CNNs))can conduct classification by extracting high-dimensional data features,with outstanding performance.Hence,combining the advantages of signal processing and deep-learning algorithms can significantly enhance vibration recognition performance.A novel vibration recognition method based on signal processing and deep neural networks is proposed herein.First,environmental vibration signals are collected;then,signal processing is conducted to obtain the coefficient matrices of the time-frequency-domain characteristics using three typical algorithms:the wavelet transform,Hilbert-Huang transform,and Mel frequency cepstral coefficient extraction method.Subsequently,CNNs,long short-term memory(LSTM)networks,and combined deep CNN-LSTM networks are trained for vibration recognition,according to the time-frequencydomain characteristics.Finally,the performance of the trained deep neural networks is evaluated and validated.The results confirm the effectiveness of the proposed vibration recognition method combining signal preprocessing and deep learning.
基金This work was supported in part by National Key Research and Development Program of China under Grant 2017YFB1010002in part by National Natural Science Foundation of China under Grant 61871455,61831013.
文摘Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communications systems.Meanwhile,it has been recently admitted that implementing artificial intelligence(AI)into RIS communications will extensively benefit the reconfiguration capacity and enhance the robustness to complicated transmission environments.Besides the conventional model-driven approaches,AI can also deal with the existing signal processing problems in a data-driven manner via digging the inherent characteristic from the real data.Hence,AI is particularly suitable for the signal processing problems over RIS networks under unideal scenarios like modeling mismatching,insufficient resource,hardware impairment,as well as dynamical transmissions.As one of the earliest survey papers,we will introduce the merging of AI and RIS,called AIRIS,over various signal processing topics,including environmental sensing,channel acquisition,beamforming design,and resource scheduling,etc.We will also discuss the challenges of AIRIS and present some interesting future directions.
文摘The construction of basic wavelet was discussed and many basic analyzing wavelets was compared. Acomplex analyzing wavelet which is continuous, smoothing, orthogonal and exponential decreasing was presented, andit was used to decompose two blasting seismic signals with the continuous wavelet transforms (CWT). The resultshows that wavelet analysis is the better method to help us determine the essential factors which create damage effectsthan Fourier analysis.
文摘Traffic monitoring is of major importance for enforcing traffic management policies.To accomplish this task,the detection of vehicle can be achieved by exploiting image analysis techniques.In this paper,a solution is presented to obtain various traffic parameters through vehicular video detection system(VVDS).VVDS exploits the algorithm based on virtual loops to detect moving vehicle in real time.This algorithm uses the background differencing method,and vehicles can be detected through luminance difference of pixels between background image and current image.Furthermore a novel technology named as spatio-temporal image sequences analysis is applied to background differencing to improve detection accuracy.Then a hardware implementation of a digital signal processing (DSP) based board is described in detail and the board can simultaneously process four-channel video from different cameras. The benefit of usage of DSP is that images of a roadway can be processed at frame rate due to DSP′s high performance.In the end,VVDS is tested on real-world scenes and experiment results show that the system is both fast and robust to the surveillance of transportation.
文摘DQPSK modem has been chosen as the modem scheme in many mobile communication systems. A new signal processing technique of π/4-DQPSK modem based on software radio is discussed in this paper. Unlike many other software radio solutions to the subject, we choose a universal digital radio baseband processor operating as the co-processor of DSP. Only the core algorithms for signal processing are implemented with DSP. Thus the computation burden on DSP is reduced significantly. Compared with the traditional ones, the technique mentioned in this paper is more promising and attractive. It is extremely compact and power-efficient, which is often required by a mobile communication system. The implementation of baseband signal processing for π/4-DQPSK modem on this platform is illustrated in detail. Special emphases are laid on the architecture of the system and the algorithms used in the baseband signal processing. Finally, some experimental results are presented and the performances of the signal processing and compensation algorithms are evaluated through computer simulations.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.61427802,31727901,61625103,61501032,61471038the Chang Jiang Scholars Program(T2012122)+1 种基金part by the 111 project of China under Grant B14010supported by the Program for Changjiang Scholars and Innovative Research Team in University of Ministry of Education of China
文摘Radar is an electronic device that uses radio waves to determine the range, angle, or velocity of objects. Real-time signal and information processor is an important module for real-time positioning, imaging, detection and recognition of targets. With the development of ultra-wideband technology, synthetic aperture technology, signal and information processing technology, the radar coverage, detection accuracy and resolution have been greatly improved, especially in terms of one-dimensional(1D) high-resolution radar detection, tracking, recognition, and two-dimensional(2D) synthetic aperture radar imaging technology. Meanwhile, for the application of radar detection and remote sensing with high resolution and wide swath, the amount of data has been greatly increased. Therefore, the radar is required to have low-latency and real-time processing capability under the constraints of size, weight and power consumption. This paper systematically introduces the new technology of high resolution radar and real-time signal and information processing. The key problems and solutions are discussed, including the detection and tracking of 1D high-resolution radar, the accurate signal modeling and wide-swath imaging for geosynchronous orbit synthetic aperture radar, and real-time signal and information processing architecture and efficient algorithms. Finally, the latest research progress and representative results are presented, and the development trends are prospected.
文摘Due to the heavy congestion in HF bands, HF radars are restricted to operating within narrow frequency bands. To improve the system bandwidth and avoid heavy interference bands, a quasi-random step frequency signal with discontinuous bands is presented. A novel two-dimensional signal processing scheme for this signal is proposed on the basis of delicate signal analysis. Simulation results demonstrate that the scheme could successfully realize the resolutions by decoupling the range-Doppler ambiguity, and effectively suppress the maximal sidelobe. Moreover, the scheme is simple and has good numerical stability.
基金supported by the Users with Excellence Program of the Hefei Science Center CAS (No. 2020HSC-UE012)
文摘The neutron count rate fluctuation reaches six orders of magnitude between the ohmic plasma scenario and high power of auxiliary heating on an experimental advanced superconducting tokamak(EAST).The measurement result of neutron flux monitoring(NFM)is a significant feedback parameter related to the acquisition of radiation protection-related information and rapid fluctuations in neutron emission induced by plasma magnetohydrodynamic activity.Therefore,a wide range and high time resolution are required for the NFM system on EAST.To satisfy these requirements,a digital pulse signal acquisition and processing system with a wide dynamic range and fast response time was developed.The present study was conducted using a field-programmable gate array(FPGA)and peripheral component interconnect extension for instrument express(PXIe)platform.The digital dual measurement modes,which are composed of the pulse-counting mode and AC coupled square integral's Campbelling mode,were designed to expand the measurement range of the signal acquisition and processing system.The time resolution of the signal acquisition and processing system was improved from 10 to 1 ms owing to utilizing highspeed analog-to-digital converters(ADCs),a high-speed PXIe communication with a direct memory access(DMA)mode,and online data preprocessing technology of FPGA.The signal acquisition and processing system was tested experimentally in the EAST radiation field.The test results showed that the time resolution of NFM was improved to 1 ms,and the dynamic range of the neutron counts rate was expanded to more than 10^(6) counts per second.The Campbelling mode was calibrated using a multipoint average linear fitting method;subsequently,the fitting coefficient reached 0.9911.Therefore,the newly developed pulse signal acquisition and processing system ensures that the NFM system meets the requirements of high-parameter experiments conducted on EAST more effectively.
基金Sponsored by Program for Changjiang Scholars and Innovative Research Team in University ( IRT1005 )the National Natural Science Founda-tions of China ( 61171195 and 61179031)Program for New Century Excellent Talents in University ( NCET-12-0042)
文摘The investigation of novel signal processing tools is one of the hottest research topics in modern signal processing community. Among them, the algebraic and geometric signal processing methods are the most powerful tools for the representation of the classical signal processing method. In this paper, we provide an overview of recent contributions to the algebraic and geometric signal processing. Specifically, the paper focuses on the mathematical structures behind the signal processing by emphasizing the algebraic and geometric structure of signal processing. The two major topics are discussed. First, the classical signal processing concepts are related to the algebraic structures, and the recent results associated with the algebraic signal processing theory are introduced. Second, the recent progress of the geometric signal and information processing representations associated with the geometric structure are discussed. From these discussions, it is concluded that the research on the algebraic and geometric structure of signal processing can help the researchers to understand the signal processing tools deeply, and also help us to find novel signal processing methods in signal processing community. Its practical applications are expected to grow significantly in years to come, given that the algebraic and geometric structure of signal processing offer many advantages over the traditional signal processing.
基金Supported by National Science and Technology Support Program(2014BAD06B04-1-09)China Postdoctoral Fund(2016M601406)Heilongjiang Postdoctoral Fund(LBHZ15024)
文摘The grain production prediction is one of the most important links in precision agriculture. In the process of grain production prediction, mechanical noise caused by the factors of difference in field topography and mechanical vibration will be mixed in the original signal, which undoubtedly will affect the prediction accuracy. Therefore, in order to reduce the influence of vibration noise on the prediction accuracy, an adaptive Ensemble Empirical Mode Decomposition(EEMD) threshold filtering algorithm was applied to the original signal in this paper: the output signal was decomposed into a finite number of Intrinsic Mode Functions(IMF) from high frequency to low frequency by using the Empirical Mode Decomposition(EMD) algorithm which could effectively restrain the mode mixing phenomenon; then the demarcation point of high and low frequency IMF components were determined by Continuous Mean Square Error criterion(CMSE), the high frequency IMF components were denoised by wavelet threshold algorithm, and finally the signal was reconstructed. The algorithm was an improved algorithm based on the commonly used wavelet threshold. The two algorithms were used to denoise the original production signal respectively, the adaptive EEMD threshold filtering algorithm had significant advantages in three denoising performance indexes of signal denoising ratio, root mean square error and smoothness. The five field verification tests showed that the average error of field experiment was 1.994% and the maximum relative error was less than 3%. According to the test results, the relative error of the predicted yield per hectare was 2.97%, which was relative to the actual yield. The test results showed that the algorithm could effectively resist noise and improve the accuracy of prediction.
