In the paper, we propose a surface wave suppression method in time-frequency domain based on the wavelet transform, considering the characteristic difference of polarization attributes, amplitude energy and apparent v...In the paper, we propose a surface wave suppression method in time-frequency domain based on the wavelet transform, considering the characteristic difference of polarization attributes, amplitude energy and apparent velocity between the effective signals and strong surface waves. First, we use the proposed method to obtain time-frequency spectra of seismic signals by using the wavelet transform and calculate the instantaneous polarizability at each point based on instantaneous polarization analysis. Then, we separate the surface wave area from the signal area based on the surface-wave apparent velocity and the average energy of the signal. Finally, we combine the polarizability, energy, and frequency characteristic to identify and suppress the signal noise. Model and field data are used to test the proposed filtering method.展开更多
Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyze...Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyzed. Experimental results show that for a spectrum of some density, the joint time-frequency gain-modification based speech enhancement algorithm achieves significant improvement in intelligibility. Additionally, the spectrum region where the estimated spectrum is smaller than the clean spectrum, is the most important region contributing to intelligibility improvement for the enhanced whisper. The spectrum region where the estimated spectrum is larger than twice the size of the clean spectrum is detrimental to speech intelligibility perception within the whisper context.展开更多
This paper deals with the blind separation of nonstation-ary sources and direction-of-arrival （DOA） estimation in the under-determined case, when there are more sources than sensors. We assume the sources to be time...This paper deals with the blind separation of nonstation-ary sources and direction-of-arrival （DOA） estimation in the under-determined case, when there are more sources than sensors. We assume the sources to be time-frequency （TF） disjoint to a certain extent. In particular, the number of sources presented at any TF neighborhood is strictly less than that of sensors. We can identify the real number of active sources and achieve separation in any TF neighborhood by the sparse representation method. Compared with the subspace-based algorithm under the same sparseness assumption, which suffers from the extra noise effect since it can-not estimate the true number of active sources, the proposed algorithm can estimate the number of active sources and their cor-responding TF values in any TF neighborhood simultaneously. An-other contribution of this paper is a new estimation procedure for the DOA of sources in the underdetermined case, which combines the TF sparseness of sources and the clustering technique. Sim-ulation results demonstrate the validity and high performance of the proposed algorithm in both blind source separation （BSS） and DOA estimation.展开更多
The Q-factor is an important physical parameter for characterizing the absorption and attenuation of seismic waves propagating in underground media,which is of great signifi cance for improving the resolution of seism...The Q-factor is an important physical parameter for characterizing the absorption and attenuation of seismic waves propagating in underground media,which is of great signifi cance for improving the resolution of seismic data,oil and gas detection,and reservoir description.In this paper,the local centroid frequency is defi ned using shaping regularization and used to estimate the Q values of the formation.We propose a continuous time-varying Q-estimation method in the time-frequency domain according to the local centroid frequency,namely,the local centroid frequency shift(LCFS)method.This method can reasonably reduce the calculation error caused by the low accuracy of the time picking of the target formation in the traditional methods.The theoretical and real seismic data processing results show that the time-varying Q values can be accurately estimated using the LCFS method.Compared with the traditional Q-estimation methods,this method does not need to extract the top and bottom interfaces of the target formation;it can also obtain relatively reasonable Q values when there is no eff ective frequency spectrum information.Simultaneously,a reasonable inverse Q fi ltering result can be obtained using the continuous time-varying Q values.展开更多
An air gun generates acoustic signals for seismic exploration by releasing a high-pressure gas.A large error is always gradually introduced into the ideal-gas model when the pressure in the air-gun chamber exceeds 100...An air gun generates acoustic signals for seismic exploration by releasing a high-pressure gas.A large error is always gradually introduced into the ideal-gas model when the pressure in the air-gun chamber exceeds 100 atm.In the van der Waals non-ideal-gas theory,the gas in the air gun can be regarded as an actual gas,and the error is less than 2%.The van der Waals model is established in combination with the quasi-static open thermodynamic system and bubble-motion equation by considering the bubble rise,bubble interaction,and throttling eff ect.The mismatch between the van der Waals and ideal-gas models is related to the pressure.Theoretically,under high-pressure conditions,the van der Waals air-gun model yields results that are closer to the measured results.Marine vertical cables are extended to the seafl oor using steel cables that connect the cement blocks,but the corresponding hydrophones are suspended in the seawater.Thus,noise associated with ships,ocean surges,and coupling problems is avoided,and the signal-to-noise ratio and resolution of marine seismic data are improved.This acquisition method satisfies the conditions of recording air-gun far-fi eld wavelets.According to an actual vertical-cable observation system,the van der Waals air-gun model is used to model the wavelet of different azimuth and take-off angles.The characteristics of the experimental and simulated data demonstrate good agreement,which indicates that the van der Waals method is accurate and reliable.The accuracy of the model is directly related to the resolution,thus aff ecting the resolution ability of the stratum.展开更多
The time-frequency domain electromagnetic(TFEM)sounding technique can directly detect oil and gas characteristics through anomalies in resistivity and polarizability.In recent years,it has made some breakthroughs in h...The time-frequency domain electromagnetic(TFEM)sounding technique can directly detect oil and gas characteristics through anomalies in resistivity and polarizability.In recent years,it has made some breakthroughs in hydrocarbon detection.TFEM was applied to predict the petroliferous property of the Ili Basin.In accordance with the geological structure characteristics of the study area,a two-dimensional layered medium model was constructed and forward modeling was performed.We used the forward-modeling results to guide fi eld construction and ensure the quality of the fi eld data collection.We used the model inversion results to identify and distinguish the resolution of the geoelectric information and provide a reliable basis for data processing.On the basis of our results,key technologies such as 2D resistivity tomography imaging inversion and polarimetric constrained inversion were developed,and we obtained abundant geological and geophysical information.The characteristics of the TFEM anomalies of the hydrocarbon reservoirs in the Ili Basin were summarized through an analysis of the electrical logging data in the study area.Moreover,the oil-gas properties of the Permian and Triassic layers were predicted,and the next favorable exploration targets were optimized.展开更多
The received shock waves produced by explosive charges are often polluted by bubble pulses in underwater acoustic experiments.A method based on warping operators is proposed to cancel the bubble pulses in the time-fre...The received shock waves produced by explosive charges are often polluted by bubble pulses in underwater acoustic experiments.A method based on warping operators is proposed to cancel the bubble pulses in the time-frequency domain.This is applied to the explosive data collected during the Yellow Sea experiment in November 2000.The original received signal is first transformed into a warped signal by warping operators.Then,the warped signal is analyzed in the time-frequency domain.Due to the different features between the shock waves and the bubble pulses in the time-frequency domain for the warped signal,the bubble pulses can be easily filtered out.Furthermore,the shock waves in the original time domain can be retrieved by the inverse warping transformation.The autocorrelation functions and the time-frequency representation show that the bubble pulses can be canceled effectively.展开更多
The load types in low-voltage distribution systems are diverse.Some loads have current signals that are similar to series fault arcs,making it difficult to effectively detect fault arcs during their occurrence and sus...The load types in low-voltage distribution systems are diverse.Some loads have current signals that are similar to series fault arcs,making it difficult to effectively detect fault arcs during their occurrence and sustained combustion,which can easily lead to serious electrical fire accidents.To address this issue,this paper establishes a fault arc prototype experimental platform,selects multiple commonly used loads for fault arc experiments,and collects data in both normal and fault states.By analyzing waveform characteristics and selecting fault discrimination feature indicators,corresponding feature values are extracted for qualitative analysis to explore changes in timefrequency characteristics of current before and after faults.Multiple features are then selected to form a multidimensional feature vector space to effectively reduce arc misjudgments and construct a fault discrimination feature database.Based on this,a fault arc hazard prediction model is built using random forests.The model’s multiple hyperparameters are simultaneously optimized through grid search,aiming tominimize node information entropy and complete model training,thereby enhancing model robustness and generalization ability.Through experimental verification,the proposed method accurately predicts and classifies fault arcs of different load types,with an average accuracy at least 1%higher than that of the commonly used fault predictionmethods compared in the paper.展开更多
Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conductin...Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.展开更多
Fault features in mechanical systems often manifest as transient impulses,which can be effectively analyzed using time-frequency analysis(TFA)methods.Recently,a new TFA technique known as the time-reassigned multi-syn...Fault features in mechanical systems often manifest as transient impulses,which can be effectively analyzed using time-frequency analysis(TFA)methods.Recently,a new TFA technique known as the time-reassigned multi-synchrosqueezing transform(TMssT)was proposed to capture these transient impulses for fault diagnosis.However,the TMSST,which is based on the short-time Fourier transform(STFT),suffers from unclear high-frequency re-presentations owing to the fixed sliding window used in the STFT.To address this limitation,the current study combined TMSST with the S-transform and a local maximum method to enhance the time-frequency representation for improved signal analysis.Furthermore,an extractive reconstruction algorithm that binds the maximum value of the spectral envelope is proposed for spectral decomposition.To validate the proposed technique,a simulated noise-added signal and four experimental bearing defect datasets were used.The results demonstrate that the proposed technique can effectively and accurately extract fault features from bearing signals regardless of whether the bearings operate under constant or varying speed conditions.This study offers a novel and efficient approach for fault diagnosis in mechanical systems with complex dynamic behaviors.展开更多
Recent developments in deep learning techniques have provided alternative and complementary approaches to the traditional matched-filtering methods for identifying gravitational wave(GW)signals.The rapid and accurate ...Recent developments in deep learning techniques have provided alternative and complementary approaches to the traditional matched-filtering methods for identifying gravitational wave(GW)signals.The rapid and accurate identification of GW signals is crucial to the advancement of GW physics and multi-messenger astronomy,particularly considering the upcoming fourth and fifth observing runs of LIGO-Virgo-KAGRA.In this study,we used the 2D U-Net algorithm to identify time-frequency domain GW signals from stellar-mass binary black hole(BBH)mergers.We simulated BBH mergers with component masses ranging from 7 to 50 M_(⊙)and accounted for the LIGO detector noise.We found that the GW events in the first and second observation runs could all be clearly and rapidly identified.For the third observing run,approximately 80% of the GW events could be identified.In contrast to traditional convolutional neural networks,the U-Net algorithm can output time-frequency domain signal images corresponding to probabilities,providing a more intuitive analysis.In conclusion,the U-Net algorithm can rapidly identify the time-frequency domain GW signals from BBH mergers.展开更多
Seismic inversion can be divided into time-domain inversion and frequency-domain inversion based on different transform domains.Time-domain inversion has stronger stability and noise resistance compared to frequencydo...Seismic inversion can be divided into time-domain inversion and frequency-domain inversion based on different transform domains.Time-domain inversion has stronger stability and noise resistance compared to frequencydomain inversion.Frequency domain inversion has stronger ability to identify small-scale bodies and higher inversion resolution.Therefore,the research on the joint inversion method in the time-frequency domain is of great significance for improving the inversion resolution,stability,and noise resistance.The introduction of prior information constraints can effectively reduce ambiguity in the inversion process.However,the existing modeldriven time-frequency joint inversion assumes a specific prior distribution of the reservoir.These methods do not consider the original features of the data and are difficult to describe the relationship between time-domain features and frequency-domain features.Therefore,this paper proposes a high-resolution seismic inversion method based on joint data-driven in the time-frequency domain.The method is based on the impedance and reflectivity samples from logging,using joint dictionary learning to obtain adaptive feature information of the reservoir,and using sparse coefficients to capture the intrinsic relationship between impedance and reflectivity.The optimization result of the inversion is achieved through the regularization term of the joint dictionary sparse representation.We have finally achieved an inversion method that combines constraints on time-domain features and frequency features.By testing the model data and field data,the method has higher resolution in the inversion results and good noise resistance.展开更多
The aim of this paper is to present a new method for flight flutter modal parameter identification in noisy environment. This method employs a time-frequency （TF） filter to reduce the noise before identification, wh...The aim of this paper is to present a new method for flight flutter modal parameter identification in noisy environment. This method employs a time-frequency （TF） filter to reduce the noise before identification, which depends on the localization property of sweep excitation in TF domain. Then, a generalized total least square （GTLS） identification algorithm based on stochastic framework is applied to the enhanced data. System identification with noisy data is transformed into a generalized total least square problem, and the solution is carried out by the generalized singular value decomposition （GSVD） to avoid the intensive nonlinear optimization computation. A nearly maximum likelihood property can be achieved by ＇optimally＇ weighted generalized total least square. Finally, the efficiency of the method is illustrated by means of flight test data.展开更多
With the increasingly complex and changeable electromagnetic environment,wireless communication systems are facing jamming and abnormal signal injection,which significantly affects the normal operation of a communicat...With the increasingly complex and changeable electromagnetic environment,wireless communication systems are facing jamming and abnormal signal injection,which significantly affects the normal operation of a communication system.In particular,the abnormal signals may emulate the normal signals,which makes it very challenging for abnormal signal recognition.In this paper,we propose a new abnormal signal recognition scheme,which combines time-frequency analysis with deep learning to effectively identify synthetic abnormal communication signals.Firstly,we emulate synthetic abnormal communication signals including seven jamming patterns.Then,we model an abnormal communication signals recognition system based on the communication protocol between the transmitter and the receiver.To improve the performance,we convert the original signal into the time-frequency spectrogram to develop an image classification algorithm.Simulation results demonstrate that the proposed method can effectively recognize the abnormal signals under various parameter configurations,even under low signal-to-noise ratio(SNR)and low jamming-to-signal ratio(JSR)conditions.展开更多
Recently,many Sequential Recommendation methods adopt self-attention mechanisms to model user preferences.However,these methods tend to focus more on low-frequency information while neglecting highfrequency informatio...Recently,many Sequential Recommendation methods adopt self-attention mechanisms to model user preferences.However,these methods tend to focus more on low-frequency information while neglecting highfrequency information,which makes them ineffective in balancing users’long-and short-term preferences.At the same time,manymethods overlook the potential of frequency domainmethods,ignoring their efficiency in processing frequency information.To overcome this limitation,we shift the focus to the combination of time and frequency domains and propose a novel Hybrid Time-Frequency Dual-Branch Transformer for Sequential Recommendation,namely HyTiFRec.Specifically,we design two hybrid filter modules:the learnable hybrid filter(LHF)and the window hybrid filter(WHF).We combine these with the Efficient Attention(EA)module to form the dual-branch structure to replace the self-attention components in Transformers.The EAmodule is used to extract sequential and global information.The LHF andWHF modules balance the proportion of different frequency bands,with LHF globally modulating the spectrum in the frequency domain and WHF retaining frequency components within specific local frequency bands.Furthermore,we use a time domain residual information addition operation in the hybrid filter module,which reduces information loss and further facilitates the hybrid of time-frequency methods.Extensive experiments on five widely-used real-world datasets show that our proposed method surpasses state-of-the-art methods.展开更多
The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals...The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals,which may contain important characteristics related to emotional states.Aiming at the above defects,a spatiotemporal emotion recognition method based on a 3-dimensional(3 D)time-frequency domain feature matrix was proposed.Specifically,the extracted time-frequency domain EEG features are first expressed as a 3 D matrix format according to the actual position of the cerebral cortex.Then,the input 3 D matrix is processed successively by multivariate convolutional neural network(MVCNN)and long short-term memory(LSTM)to classify the emotional state.Spatiotemporal emotion recognition method is evaluated on the DEAP data set,and achieved accuracy of 87.58%and 88.50%on arousal and valence dimensions respectively in binary classification tasks,as well as obtained accuracy of 84.58%in four class classification tasks.The experimental results show that 3 D matrix representation can represent emotional information more reasonably than two-dimensional(2 D).In addition,MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.展开更多
The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on e...The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on empirical models with limited predictive capabilities.This study focuses on the influence of optical basicity on viscosity in CaO-Al_(2)O_(3)-based refining slags,leveraging machine learning to address data scarcity and improve prediction accuracy.An automated framework for algorithm integration,parameter tuning,and evaluation ranking framework(Auto-APE)is employed to develop customized data-driven models for various slag systems,including CaO-Al_(2)O_(3)-SiO_(2),CaO-Al_(2)O_(3)-CaF_(2),CaO-Al_(2)O_(3)-SiO_(2)-MgO,and CaO-Al_(2)O_(3)-SiO_(2)-MgO-CaF_(2).By incorporating optical basicity as a key feature,the models achieve an average validation error of 8.0%to 15.1%,significantly outperforming traditional empirical models.Additionally,symbolic regression is introduced to rapidly construct domain-specific features,such as optical basicity-like descriptors,offering a potential breakthrough in performance prediction for small datasets.This work highlights the critical role of domain-specific knowledge in understanding and predicting viscosity,providing a robust machine learning-based approach for optimizing refining slag properties.展开更多
Underwater images often affect the effectiveness of underwater visual tasks due to problems such as light scattering,color distortion,and detail blurring,limiting their application performance.Existing underwater imag...Underwater images often affect the effectiveness of underwater visual tasks due to problems such as light scattering,color distortion,and detail blurring,limiting their application performance.Existing underwater image enhancement methods,although they can improve the image quality to some extent,often lead to problems such as detail loss and edge blurring.To address these problems,we propose FENet,an efficient underwater image enhancement method.FENet first obtains three different scales of images by image downsampling and then transforms them into the frequency domain to extract the low-frequency and high-frequency spectra,respectively.Then,a distance mask and a mean mask are constructed based on the distance and magnitude mean for enhancing the high-frequency part,thus improving the image details and enhancing the effect by suppressing the noise in the low-frequency part.Affected by the light scattering of underwater images and the fact that some details are lost if they are directly reduced to the spatial domain after the frequency domain operation.For this reason,we propose a multi-stage residual feature aggregation module,which focuses on detail extraction and effectively avoids information loss caused by global enhancement.Finally,we combine the edge guidance strategy to further enhance the edge details of the image.Experimental results indicate that FENet outperforms current state-of-the-art underwater image enhancement methods in quantitative and qualitative evaluations on multiple publicly available datasets.展开更多
Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional ...Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.展开更多
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis...To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.展开更多
基金supported by the National Science and Technology Major Project(No.2011ZX05002-004-002)the National Natural Science Foundation of China(No.41304111 and 41704132)+3 种基金Key Project of Science&Technology Department of Sichuan Province(No.2016JY0200)Natural Science project of Education Department of Sichuan Province(Nos.17ZA0025,16ZB0101 and 18CZ0008)the Sichuan Provincial Youth Science&Technology Innovative Research Group Fund(No.2016TD0023)the Cultivating Program of Excellent Innovation Team of Chengdu University of Technology(No.KYTD201410)
文摘In the paper, we propose a surface wave suppression method in time-frequency domain based on the wavelet transform, considering the characteristic difference of polarization attributes, amplitude energy and apparent velocity between the effective signals and strong surface waves. First, we use the proposed method to obtain time-frequency spectra of seismic signals by using the wavelet transform and calculate the instantaneous polarizability at each point based on instantaneous polarization analysis. Then, we separate the surface wave area from the signal area based on the surface-wave apparent velocity and the average energy of the signal. Finally, we combine the polarizability, energy, and frequency characteristic to identify and suppress the signal noise. Model and field data are used to test the proposed filtering method.
基金The National Natural Science Foundation of China(No.61301295,61273266,61301219,61201326,61003131)the Natural Science Foundation of Anhui Province(No.1308085QF100,1408085MF113)+2 种基金the Natural Science Foundation of Jiangsu Province(No.BK20130241)the Natural Science Foundation of Higher Education Institutions of Jiangsu Province(No.12KJB510021)the Doctoral Fund of Anhui University
文摘Some factors influencing the intelligibility of the enhanced whisper in the joint time-frequency domain are evaluated. Specifically, both the spectrum density and different regions of the enhanced spectrum are analyzed. Experimental results show that for a spectrum of some density, the joint time-frequency gain-modification based speech enhancement algorithm achieves significant improvement in intelligibility. Additionally, the spectrum region where the estimated spectrum is smaller than the clean spectrum, is the most important region contributing to intelligibility improvement for the enhanced whisper. The spectrum region where the estimated spectrum is larger than twice the size of the clean spectrum is detrimental to speech intelligibility perception within the whisper context.
基金supported by the National Natural Science Foundation of China(61072120)
文摘This paper deals with the blind separation of nonstation-ary sources and direction-of-arrival （DOA） estimation in the under-determined case, when there are more sources than sensors. We assume the sources to be time-frequency （TF） disjoint to a certain extent. In particular, the number of sources presented at any TF neighborhood is strictly less than that of sensors. We can identify the real number of active sources and achieve separation in any TF neighborhood by the sparse representation method. Compared with the subspace-based algorithm under the same sparseness assumption, which suffers from the extra noise effect since it can-not estimate the true number of active sources, the proposed algorithm can estimate the number of active sources and their cor-responding TF values in any TF neighborhood simultaneously. An-other contribution of this paper is a new estimation procedure for the DOA of sources in the underdetermined case, which combines the TF sparseness of sources and the clustering technique. Sim-ulation results demonstrate the validity and high performance of the proposed algorithm in both blind source separation （BSS） and DOA estimation.
基金This work was supported by The National Key Research and Development Program(No.2016YFC0600505 and 2018YFC0603701)National Natural Science Foundation(No.41974134 and 41774127).
文摘The Q-factor is an important physical parameter for characterizing the absorption and attenuation of seismic waves propagating in underground media,which is of great signifi cance for improving the resolution of seismic data,oil and gas detection,and reservoir description.In this paper,the local centroid frequency is defi ned using shaping regularization and used to estimate the Q values of the formation.We propose a continuous time-varying Q-estimation method in the time-frequency domain according to the local centroid frequency,namely,the local centroid frequency shift(LCFS)method.This method can reasonably reduce the calculation error caused by the low accuracy of the time picking of the target formation in the traditional methods.The theoretical and real seismic data processing results show that the time-varying Q values can be accurately estimated using the LCFS method.Compared with the traditional Q-estimation methods,this method does not need to extract the top and bottom interfaces of the target formation;it can also obtain relatively reasonable Q values when there is no eff ective frequency spectrum information.Simultaneously,a reasonable inverse Q fi ltering result can be obtained using the continuous time-varying Q values.
基金This work has been supported by the following:the National Natural Science Foundation of China(No.91958206,91858215)the National Key Research and Development Program Pilot Project(No.2018YFC1405901,2017YFC0307401)+1 种基金the Fundamental Research Funds for the Central Universities(No.201964016)the Marine Geological Survey Program of China Geological Survey(No.DD20190819).
文摘An air gun generates acoustic signals for seismic exploration by releasing a high-pressure gas.A large error is always gradually introduced into the ideal-gas model when the pressure in the air-gun chamber exceeds 100 atm.In the van der Waals non-ideal-gas theory,the gas in the air gun can be regarded as an actual gas,and the error is less than 2%.The van der Waals model is established in combination with the quasi-static open thermodynamic system and bubble-motion equation by considering the bubble rise,bubble interaction,and throttling eff ect.The mismatch between the van der Waals and ideal-gas models is related to the pressure.Theoretically,under high-pressure conditions,the van der Waals air-gun model yields results that are closer to the measured results.Marine vertical cables are extended to the seafl oor using steel cables that connect the cement blocks,but the corresponding hydrophones are suspended in the seawater.Thus,noise associated with ships,ocean surges,and coupling problems is avoided,and the signal-to-noise ratio and resolution of marine seismic data are improved.This acquisition method satisfies the conditions of recording air-gun far-fi eld wavelets.According to an actual vertical-cable observation system,the van der Waals air-gun model is used to model the wavelet of different azimuth and take-off angles.The characteristics of the experimental and simulated data demonstrate good agreement,which indicates that the van der Waals method is accurate and reliable.The accuracy of the model is directly related to the resolution,thus aff ecting the resolution ability of the stratum.
基金This work was supported by the Geology and Mineral Resources Investigation and Evaluation Program(No.12120115006601 and No.DD20160181)the National key Research and Development projects(No.2016YFC060110204 and No.2016YFC060110305).
文摘The time-frequency domain electromagnetic(TFEM)sounding technique can directly detect oil and gas characteristics through anomalies in resistivity and polarizability.In recent years,it has made some breakthroughs in hydrocarbon detection.TFEM was applied to predict the petroliferous property of the Ili Basin.In accordance with the geological structure characteristics of the study area,a two-dimensional layered medium model was constructed and forward modeling was performed.We used the forward-modeling results to guide fi eld construction and ensure the quality of the fi eld data collection.We used the model inversion results to identify and distinguish the resolution of the geoelectric information and provide a reliable basis for data processing.On the basis of our results,key technologies such as 2D resistivity tomography imaging inversion and polarimetric constrained inversion were developed,and we obtained abundant geological and geophysical information.The characteristics of the TFEM anomalies of the hydrocarbon reservoirs in the Ili Basin were summarized through an analysis of the electrical logging data in the study area.Moreover,the oil-gas properties of the Permian and Triassic layers were predicted,and the next favorable exploration targets were optimized.
基金Supported by the National Natural Science Foundation of China under Grant Nos 11174312 and 11074269.
文摘The received shock waves produced by explosive charges are often polluted by bubble pulses in underwater acoustic experiments.A method based on warping operators is proposed to cancel the bubble pulses in the time-frequency domain.This is applied to the explosive data collected during the Yellow Sea experiment in November 2000.The original received signal is first transformed into a warped signal by warping operators.Then,the warped signal is analyzed in the time-frequency domain.Due to the different features between the shock waves and the bubble pulses in the time-frequency domain for the warped signal,the bubble pulses can be easily filtered out.Furthermore,the shock waves in the original time domain can be retrieved by the inverse warping transformation.The autocorrelation functions and the time-frequency representation show that the bubble pulses can be canceled effectively.
基金This work was funded by Beijing Key Laboratory of Distribution Transformer Energy-Saving Technology(China Electric Power Research Institute).
文摘The load types in low-voltage distribution systems are diverse.Some loads have current signals that are similar to series fault arcs,making it difficult to effectively detect fault arcs during their occurrence and sustained combustion,which can easily lead to serious electrical fire accidents.To address this issue,this paper establishes a fault arc prototype experimental platform,selects multiple commonly used loads for fault arc experiments,and collects data in both normal and fault states.By analyzing waveform characteristics and selecting fault discrimination feature indicators,corresponding feature values are extracted for qualitative analysis to explore changes in timefrequency characteristics of current before and after faults.Multiple features are then selected to form a multidimensional feature vector space to effectively reduce arc misjudgments and construct a fault discrimination feature database.Based on this,a fault arc hazard prediction model is built using random forests.The model’s multiple hyperparameters are simultaneously optimized through grid search,aiming tominimize node information entropy and complete model training,thereby enhancing model robustness and generalization ability.Through experimental verification,the proposed method accurately predicts and classifies fault arcs of different load types,with an average accuracy at least 1%higher than that of the commonly used fault predictionmethods compared in the paper.
基金supported by the Innovative Human Resource Development for Local Intel-lectualization program through the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.IITP-2026-2020-0-01741)the research fund of Hanyang University(HY-2025-1110).
文摘Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.
基金Supported by National Natural Science Foundation of China(Grant No.62271230)Shandong Provincial Central Guidance on Local Science and Technology Development Fund(Grant No.YDZX2022178).
文摘Fault features in mechanical systems often manifest as transient impulses,which can be effectively analyzed using time-frequency analysis(TFA)methods.Recently,a new TFA technique known as the time-reassigned multi-synchrosqueezing transform(TMssT)was proposed to capture these transient impulses for fault diagnosis.However,the TMSST,which is based on the short-time Fourier transform(STFT),suffers from unclear high-frequency re-presentations owing to the fixed sliding window used in the STFT.To address this limitation,the current study combined TMSST with the S-transform and a local maximum method to enhance the time-frequency representation for improved signal analysis.Furthermore,an extractive reconstruction algorithm that binds the maximum value of the spectral envelope is proposed for spectral decomposition.To validate the proposed technique,a simulated noise-added signal and four experimental bearing defect datasets were used.The results demonstrate that the proposed technique can effectively and accurately extract fault features from bearing signals regardless of whether the bearings operate under constant or varying speed conditions.This study offers a novel and efficient approach for fault diagnosis in mechanical systems with complex dynamic behaviors.
基金Supported by the National SKA Program of China(2022SKA0110200,2022SKA0110203)the National Natural Science Foundation of China(12473001,11975072,11875102,11835009)the National 111 Project(B16009)。
文摘Recent developments in deep learning techniques have provided alternative and complementary approaches to the traditional matched-filtering methods for identifying gravitational wave(GW)signals.The rapid and accurate identification of GW signals is crucial to the advancement of GW physics and multi-messenger astronomy,particularly considering the upcoming fourth and fifth observing runs of LIGO-Virgo-KAGRA.In this study,we used the 2D U-Net algorithm to identify time-frequency domain GW signals from stellar-mass binary black hole(BBH)mergers.We simulated BBH mergers with component masses ranging from 7 to 50 M_(⊙)and accounted for the LIGO detector noise.We found that the GW events in the first and second observation runs could all be clearly and rapidly identified.For the third observing run,approximately 80% of the GW events could be identified.In contrast to traditional convolutional neural networks,the U-Net algorithm can output time-frequency domain signal images corresponding to probabilities,providing a more intuitive analysis.In conclusion,the U-Net algorithm can rapidly identify the time-frequency domain GW signals from BBH mergers.
文摘Seismic inversion can be divided into time-domain inversion and frequency-domain inversion based on different transform domains.Time-domain inversion has stronger stability and noise resistance compared to frequencydomain inversion.Frequency domain inversion has stronger ability to identify small-scale bodies and higher inversion resolution.Therefore,the research on the joint inversion method in the time-frequency domain is of great significance for improving the inversion resolution,stability,and noise resistance.The introduction of prior information constraints can effectively reduce ambiguity in the inversion process.However,the existing modeldriven time-frequency joint inversion assumes a specific prior distribution of the reservoir.These methods do not consider the original features of the data and are difficult to describe the relationship between time-domain features and frequency-domain features.Therefore,this paper proposes a high-resolution seismic inversion method based on joint data-driven in the time-frequency domain.The method is based on the impedance and reflectivity samples from logging,using joint dictionary learning to obtain adaptive feature information of the reservoir,and using sparse coefficients to capture the intrinsic relationship between impedance and reflectivity.The optimization result of the inversion is achieved through the regularization term of the joint dictionary sparse representation.We have finally achieved an inversion method that combines constraints on time-domain features and frequency features.By testing the model data and field data,the method has higher resolution in the inversion results and good noise resistance.
文摘The aim of this paper is to present a new method for flight flutter modal parameter identification in noisy environment. This method employs a time-frequency （TF） filter to reduce the noise before identification, which depends on the localization property of sweep excitation in TF domain. Then, a generalized total least square （GTLS） identification algorithm based on stochastic framework is applied to the enhanced data. System identification with noisy data is transformed into a generalized total least square problem, and the solution is carried out by the generalized singular value decomposition （GSVD） to avoid the intensive nonlinear optimization computation. A nearly maximum likelihood property can be achieved by ＇optimally＇ weighted generalized total least square. Finally, the efficiency of the method is illustrated by means of flight test data.
基金supported by Natural Science Foundation of China(No.62371231)Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu under Grant BK20222001Jiangsu Provincial Key Research and Development Program(No.BE2023027).
文摘With the increasingly complex and changeable electromagnetic environment,wireless communication systems are facing jamming and abnormal signal injection,which significantly affects the normal operation of a communication system.In particular,the abnormal signals may emulate the normal signals,which makes it very challenging for abnormal signal recognition.In this paper,we propose a new abnormal signal recognition scheme,which combines time-frequency analysis with deep learning to effectively identify synthetic abnormal communication signals.Firstly,we emulate synthetic abnormal communication signals including seven jamming patterns.Then,we model an abnormal communication signals recognition system based on the communication protocol between the transmitter and the receiver.To improve the performance,we convert the original signal into the time-frequency spectrogram to develop an image classification algorithm.Simulation results demonstrate that the proposed method can effectively recognize the abnormal signals under various parameter configurations,even under low signal-to-noise ratio(SNR)and low jamming-to-signal ratio(JSR)conditions.
基金supported by a grant from the Natural Science Foundation of Zhejiang Province under Grant LY21F010016.
文摘Recently,many Sequential Recommendation methods adopt self-attention mechanisms to model user preferences.However,these methods tend to focus more on low-frequency information while neglecting highfrequency information,which makes them ineffective in balancing users’long-and short-term preferences.At the same time,manymethods overlook the potential of frequency domainmethods,ignoring their efficiency in processing frequency information.To overcome this limitation,we shift the focus to the combination of time and frequency domains and propose a novel Hybrid Time-Frequency Dual-Branch Transformer for Sequential Recommendation,namely HyTiFRec.Specifically,we design two hybrid filter modules:the learnable hybrid filter(LHF)and the window hybrid filter(WHF).We combine these with the Efficient Attention(EA)module to form the dual-branch structure to replace the self-attention components in Transformers.The EAmodule is used to extract sequential and global information.The LHF andWHF modules balance the proportion of different frequency bands,with LHF globally modulating the spectrum in the frequency domain and WHF retaining frequency components within specific local frequency bands.Furthermore,we use a time domain residual information addition operation in the hybrid filter module,which reduces information loss and further facilitates the hybrid of time-frequency methods.Extensive experiments on five widely-used real-world datasets show that our proposed method surpasses state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(61872126)the Key Scientific Research Project Plan of Colleges and Universities in Henan Province(19A520004)。
文摘The research of emotion recognition based on electroencephalogram(EEG)signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals,which may contain important characteristics related to emotional states.Aiming at the above defects,a spatiotemporal emotion recognition method based on a 3-dimensional(3 D)time-frequency domain feature matrix was proposed.Specifically,the extracted time-frequency domain EEG features are first expressed as a 3 D matrix format according to the actual position of the cerebral cortex.Then,the input 3 D matrix is processed successively by multivariate convolutional neural network(MVCNN)and long short-term memory(LSTM)to classify the emotional state.Spatiotemporal emotion recognition method is evaluated on the DEAP data set,and achieved accuracy of 87.58%and 88.50%on arousal and valence dimensions respectively in binary classification tasks,as well as obtained accuracy of 84.58%in four class classification tasks.The experimental results show that 3 D matrix representation can represent emotional information more reasonably than two-dimensional(2 D).In addition,MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.
基金supported by the National Key Research and Development Program of China(No.2023YFB3712401),the National Natural Science Foundation of China(No.52274301)the Aeronautical Science Foundation of China(No.2023Z0530S6005)the Ningbo Yongjiang Talent-Introduction Programme(No.2022A-023-C).
文摘The viscosity of refining slags plays a critical role in metallurgical processes.However,obtaining accurate viscosity data remains challenging due to the complexities of high-temperature experiments,often relying on empirical models with limited predictive capabilities.This study focuses on the influence of optical basicity on viscosity in CaO-Al_(2)O_(3)-based refining slags,leveraging machine learning to address data scarcity and improve prediction accuracy.An automated framework for algorithm integration,parameter tuning,and evaluation ranking framework(Auto-APE)is employed to develop customized data-driven models for various slag systems,including CaO-Al_(2)O_(3)-SiO_(2),CaO-Al_(2)O_(3)-CaF_(2),CaO-Al_(2)O_(3)-SiO_(2)-MgO,and CaO-Al_(2)O_(3)-SiO_(2)-MgO-CaF_(2).By incorporating optical basicity as a key feature,the models achieve an average validation error of 8.0%to 15.1%,significantly outperforming traditional empirical models.Additionally,symbolic regression is introduced to rapidly construct domain-specific features,such as optical basicity-like descriptors,offering a potential breakthrough in performance prediction for small datasets.This work highlights the critical role of domain-specific knowledge in understanding and predicting viscosity,providing a robust machine learning-based approach for optimizing refining slag properties.
基金supported in part by the National Natural Science Foundation of China[Grant number 62471075]the Major Science and Technology Project Grant of the Chongqing Municipal Education Commission[Grant number KJZD-M202301901].
文摘Underwater images often affect the effectiveness of underwater visual tasks due to problems such as light scattering,color distortion,and detail blurring,limiting their application performance.Existing underwater image enhancement methods,although they can improve the image quality to some extent,often lead to problems such as detail loss and edge blurring.To address these problems,we propose FENet,an efficient underwater image enhancement method.FENet first obtains three different scales of images by image downsampling and then transforms them into the frequency domain to extract the low-frequency and high-frequency spectra,respectively.Then,a distance mask and a mean mask are constructed based on the distance and magnitude mean for enhancing the high-frequency part,thus improving the image details and enhancing the effect by suppressing the noise in the low-frequency part.Affected by the light scattering of underwater images and the fact that some details are lost if they are directly reduced to the spatial domain after the frequency domain operation.For this reason,we propose a multi-stage residual feature aggregation module,which focuses on detail extraction and effectively avoids information loss caused by global enhancement.Finally,we combine the edge guidance strategy to further enhance the edge details of the image.Experimental results indicate that FENet outperforms current state-of-the-art underwater image enhancement methods in quantitative and qualitative evaluations on multiple publicly available datasets.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00406320)the Institute of Information&Communica-tions Technology Planning&Evaluation(IITP)-Innovative Human Resource Development for Local Intellectualization Program Grant funded by the Korea government(MSIT)(IITP-2026-RS-2023-00259678).
文摘Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.
基金supported by the National Natural Science Foundation of China Funded Project(Project Name:Research on Robust Adaptive Allocation Mechanism of Human Machine Co-Driving System Based on NMS Features,Project Approval Number:52172381).
文摘To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.
