The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spa...The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spatial-temporal structures,and the deep learning model can fully describe the potential semantic structure of human motion.To improve the authenticity of the generated human motion sequences,we propose a multi-task motion generation model that consists of a discriminator and a generator.The discriminator classifies motion sequences into different styles according to their similarity to the mean spatial-temporal templates from motion sequences of 17 crucial human joints in three-freedom degrees.And target motion sequences are created with these styles by the generator.Unlike traditional related works,our model can handle multiple tasks,such as identifying styles and generating data.In addition,by extracting 17 crucial joints from 29 human joints,our model avoids data redundancy and improves the accuracy of model recognition.The experimental results show that the discriminator of the model can effectively recognize diversified movements,and the generated data can correctly fit the actual data.The combination of discriminator and generator solves the problem of low reuse rate of motion data,and the generated motion sequences are more suitable for actual movement.展开更多
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
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
At high count rates,pile-up events involving neutron and gamma signals result in inaccurate neutron counting and distortions in the energy spectrum.Additionally,a bipolar cusp-like pulse shaping algorithm based on an ...At high count rates,pile-up events involving neutron and gamma signals result in inaccurate neutron counting and distortions in the energy spectrum.Additionally,a bipolar cusp-like pulse shaping algorithm based on an unfolding synthesis technique was proposed.This algorithm exhibits a narrow pulse shape,and the parallel design of the dual algorithms enables the recovery of pile-up signal amplitudes while preserving the distinct characteristics of neutron and gamma signals.The simplicity of the algorithm facilitates real-time neutron/gamma discrimination on an FPGA,allowing the energy spectra to be updated with each incoming signal.Furthermore,the algorithm can be readily tailored to various experimental conditions by adjusting the decay time constants.Multi-objective optimization reduces the need for manual parameter tuning by rapidly identifying the optimal parameters.Testing with a^(241)Am-Be neutron source and a NaIL scintillator yielded a figure of merit(FoM)value of 2.11 and produced a clear energy spectrum even at high count rates.展开更多
Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in comp...Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in complex backgrounds,small target objects,and limited training data,leading to poor recognition.Fine-grained images exhibit“small inter-class differences,”and while second-order feature encoding enhances discrimination,it often requires dual Convolutional Neural Networks(CNN),increasing training time and complexity.This study proposes a model integrating discriminative region localization and efficient second-order feature encoding.By ranking feature map channels via a fully connected layer,it selects high-importance channels to generate an enhanced map,accurately locating discriminative regions.Cropping and erasing augmentations further refine recognition.To improve efficiency,a novel second-order feature encoding module generates an attention map from the fourth convolutional group of Residual Network 50 layers(ResNet-50)and multiplies it with features from the fifth group,producing second-order features while reducing dimensionality and training time.Experiments on Caltech-University of California,San Diego Birds-200-2011(CUB-200-2011),Stanford Car,and Fine-Grained Visual Classification of Aircraft(FGVC Aircraft)datasets show state-of-the-art accuracy of 88.9%,94.7%,and 93.3%,respectively.展开更多
Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements...Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements at transceivers and RIS,the codebook based beamforming can be utilized in a computationally efficient manner.However,the codeword selection for analog beamforming is an intractable combinatorial optimization(CO)problem.To this end,by taking the CO problem as a classification problem,a multi-task learning based analog beam selection(MTL-ABS)framework is developed to implement cooperative beam selection concurrently at transceivers and RIS.In addition,residual network and self-attention mechanism are used to combat the network degradation and mine intrinsic THz channel features.Finally,the network convergence is analyzed from a blockwise perspective,and numerical results demonstrate that the MTL-ABS framework greatly decreases the beam selection overhead and achieves near optimal sum-rate compared with heuristic search based counterparts.展开更多
Objectives:Psychological resilience is a critical resource for vocational high school students navigating social biases and fostering mental well-being.This six-month longitudinal study investigated the developmental ...Objectives:Psychological resilience is a critical resource for vocational high school students navigating social biases and fostering mental well-being.This six-month longitudinal study investigated the developmental trajectories of discrimination perception,vocational identity,and psychological resilience in this population.It further examined the longitudinal mediating role of vocational identity in the relationship between discrimination perception and psychological resilience.Methods:A total of 526 students from five vocational high schools in Guangdong,China,were assessed via convenience sampling at two time points:baseline(T1,September 2023)and six-month follow-up(T2,March 2024).Measures of discrimination perception,psychological resilience,and vocational identity were administered.Data were analyzed using a cross-lagged panel model to test for bidirectional relationships.Results:Over the six-month period,students showed significant decreases in discrimination perception and vocational identity,but a significant increase in psychological resilience.The cross-lagged model revealed significant bidirectional relationships:discrimination perception and psychological resilience negatively predicted each other over time(β=−0.124,p<0.01;β=−0.200,p<0.001),while psychological resilience and vocational identity positively predicted each other(β=0.084,p<0.05;β=0.076,p<0.05).The mediation analysis revealed a dual-pathway mechanism.T1 discrimination perception exerted both a significant direct negative effect on T2 psychological resilience(β=−0.332,p<0.001)and a significant indirect positive effect via T1 vocational identity(indirect effect=0.020,95%CI[0.001,0.046]).This confirms a partial mediating role,indicating that vocational identity functions as a compensatory mechanism,transforming the experience of discrimination perception into a potential source of psychological resilience.Conclusions:For vocational high school students,perception of discrimination directly undermines psychological resilience,but also indirectly fosters it through the positive development of vocational identity.These findings highlight vocational identity as a pivotal mechanism in the complex relationship between social adversity and mental resilience.展开更多
A new neutron-gamma discriminator based on the support vector machine(SVM) method is proposed to improve the performance of the time-of-flight neutron spectrometer. The neutron detector is an EJ-299-33 plastic scintil...A new neutron-gamma discriminator based on the support vector machine(SVM) method is proposed to improve the performance of the time-of-flight neutron spectrometer. The neutron detector is an EJ-299-33 plastic scintillator with pulse-shape discrimination(PSD) property. The SVM algorithm is implemented in field programmable gate array(FPGA) to carry out the real-time sifting of neutrons in neutron-gamma mixed radiation fields. This study compares the ability of the pulse gradient analysis method and the SVM method. The results show that this SVM discriminator can provide a better discrimination accuracy of 99.1%. The accuracy and performance of the SVM discriminator based on FPGA have been evaluated in the experiments. It can get a figure of merit of 1.30.展开更多
Frequency lock loops （FLL） discriminating algorithms for direct-sequence spread-spectrum are discussed. The existing algorithms can＇t solve the problem of data bit reversal during one pre-detection integral period....Frequency lock loops （FLL） discriminating algorithms for direct-sequence spread-spectrum are discussed. The existing algorithms can＇t solve the problem of data bit reversal during one pre-detection integral period. And when the initial frequency offset is large, the frequency discriminator can＇ t work normally. To solve these problems, a new FLL discriminating algorithm is introduced. The least-squares discriminator is used in this new algorithm. As the least-squares discriminator has a short process unit period, the correspond- ing frequency discriminating range is large. And the data bit reversal just influence one process unit period, so the least-squares discriminated result will not be affected. Compared with traditional frequency discriminator, the least-squares algorithm can effectively solve the problem of data bit reversal and can endure larger initial frequency offset.展开更多
Multipath and continuous wave (CW) interference may cause severe performance degradation of global navigation satellite system (GNSS) receivers. This paper analyzes the code tracking performance of early-minus-late po...Multipath and continuous wave (CW) interference may cause severe performance degradation of global navigation satellite system (GNSS) receivers. This paper analyzes the code tracking performance of early-minus-late power (EMLP) discriminator of GNSS receivers in the presence of multipath and CW interference. An analytical expression of the code tracking error is suggested for EMLP discriminator, and it can be used to assess the effect of multipath and CW interference. The derived expression shows that the combined effects include three components: multipath component;CW interference component and the combined component of multipath and CW interference. The effect of these components depends on some factors which can be classified into two categories: the receiving environment and the receiver parameters. Numerical results show how these factors affect the tracking performances. It is shown that the proper receiver parameters can suppress the combined effects of multipath and CW interference.展开更多
Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs ...Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.展开更多
Orthogonal Time Frequency and Space(OTFS) modulation is expected to provide high-speed and ultra-reliable communications for emerging mobile applications, including low-orbit satellite communications. Using the Dopple...Orthogonal Time Frequency and Space(OTFS) modulation is expected to provide high-speed and ultra-reliable communications for emerging mobile applications, including low-orbit satellite communications. Using the Doppler frequency for positioning is a promising research direction on communication and navigation integration. To tackle the high Doppler frequency and low signal-to-noise ratio(SNR) in satellite communication, this paper proposes a Red and Blue Frequency Shift Discriminator(RBFSD) based on the pseudo-noise(PN) sequence.The paper derives that the cross-correlation function on the Doppler domain exhibits the characteristic of a Sinc function. Therefore, it applies modulation onto the Delay-Doppler domain using PN sequence and adjusts Doppler frequency estimation by red-shifting or blue-shifting. Simulation results show that the performance of Doppler frequency estimation is close to the Cramér-Rao Lower Bound when the SNR is greater than -15dB. The proposed algorithm is about 1/D times less complex than the existing PN pilot sequence algorithm, where D is the resolution of the fractional Doppler.展开更多
In this paper we propose the derivation of the expressions for the non-coherent Delay Locked Loop (DLL) Discriminator Curve (DC) in the absence and presence of Multipath (MP). Also derived, are the expressions of MP t...In this paper we propose the derivation of the expressions for the non-coherent Delay Locked Loop (DLL) Discriminator Curve (DC) in the absence and presence of Multipath (MP). Also derived, are the expressions of MP tracking errors in non-coherent configuration. The proposed models are valid for all Binary Offset Carrier (BOC) modulated signals in Global Navigation Satellite Systems (GNSS) such as Global Positioning System (GPS) and Future Galileo. The non-coherent configuration is used whenever the phase of the received signal cannot be estimated and thus cannot be demodulated. Therefore, the signal must be treated in a transposed band by the non-coherent DLL. The computer implementations show that the proposed models coincide with the numerical ones.展开更多
The counter-meshing gears （CMG） discriminator is a mechanically coded lock, which is used to prevent the occurrence of High Consequence Events. This paper advanced a new kind of self-assembly metal CMG discriminator...The counter-meshing gears （CMG） discriminator is a mechanically coded lock, which is used to prevent the occurrence of High Consequence Events. This paper advanced a new kind of self-assembly metal CMG discriminator based on multi-exposure LiGA like process and sacrificial layer process. The new CMG discriminator has the following characters except low cost： 1） it has only discrimination teeth sections; 2） the thickness of each gear layer exceeds one hundred micrometers; 3） it is axially driven by a separate dectronic magnetic micromotor directly; 4） its CMG is made of metal and is batch fabricated in the assembled state; 5） it is prevented from rotating in the opposite direction by pawl/ratchet wheel mechanism; 6） it has simpler structure. This device has better strength and reliability in abnormal environment compared to the existing surface micro machining （SMM） discriminator.展开更多
Due to variable time for charge collection,energy resolution of nuclear detectors declines,especially compound semiconductor detectors like cadmium zinc telluride(CdZnTe) detector.To solve this problem,an analog rise-...Due to variable time for charge collection,energy resolution of nuclear detectors declines,especially compound semiconductor detectors like cadmium zinc telluride(CdZnTe) detector.To solve this problem,an analog rise-time discriminator based on charge comparison principle is designed.The reference charge signal after attenuation is compared with the deconvoluted and delayed current signal.It is found that the amplitude of delayed current signal is higher than that of the reference charge signal when rise time of the input signal is shorter than the discrimination time,thus generating gating signal and triggering DMCA(digital multi-channel analyzer) to receive the total integral charge signal.When rise time of the input signal is longer than discrimination time,DMCA remains inactivated and the corresponding total integral charge signal is abandoned.Test results show that combination of the designed rise-time discriminator and DMCA can reduce hole tailing of CdZnTe detector significantly.Energy resolution of the system is 0.98%@662 keV,and it is still excellent under high counting rates.展开更多
In recent years,self-supervised learning has achieved great success in areas such as computer vision and natural language processing because it can mine supervised signals from unlabeled data and reduce the reliance o...In recent years,self-supervised learning has achieved great success in areas such as computer vision and natural language processing because it can mine supervised signals from unlabeled data and reduce the reliance on manual labels.However,the currently generated self-supervised signals are either neighbor discrimination or self-discrimination,and there is no model to integrate neighbor discrimination and self-discrimination.Based on this,this paper proposes Fu-Rec that integrates neighbor-discrimination contrastive learning and self-discrimination contrastive learning,which consists of three modules:(1)neighbor-discrimination contrastive learning,(2)selfdiscrimination contrastive learning,and(3)recommendation module.The neighbor-discrimination contrastive learning and selfdiscrimination contrastive learning tasks are used as auxiliary tasks to assist the recommendation task.The Fu-Rec model effectively utilizes the respective advantages of neighbor-discrimination and self-discrimination to consider the information of the user’s neighbors as well as the user and the item itself for the recommendation,which results in better performance of the recommendation module.Experimental results on several public datasets demonstrate the effectiveness of the Fu-Rec proposed in this paper.展开更多
Recently,the technology of digital image forgery based on a generative adversarial network(GAN)has considerably improved to the extent that it is difficult to distinguish it from the original image with the naked eye ...Recently,the technology of digital image forgery based on a generative adversarial network(GAN)has considerably improved to the extent that it is difficult to distinguish it from the original image with the naked eye by compositing and editing a person’s face or a specific part with the original image.Thus,much attention has been paid to digital image forgery as a social issue.Further,document forgery through GANs can completely change the meaning and context in a document,and it is difficult to identify whether the document is forged or not,which is dangerous.Nonetheless,few studies have been conducted on document forgery and new forgery-related attacks have emerged daily.Therefore,in this study,we propose a novel convolutional neural network(CNN)forensic discriminator that can detect forged text or numeric images by GANs using CNNs,which have been widely used in image classification for many years.To strengthen the detection performance of the proposed CNN forensic discriminator,CNN was trained after image preprocessing,including salt and pepper as well asGaussian noises.Moreover,we performed CNN optimization to make existing CNN more suitable for forged text or numeric image detection,which have mainly focused on the discrimination of forged faces to date.The test evaluation results using Hangul texts and numbers showed that the accuracy of forgery discrimination of the proposed method was significantly improved by 20%in Hangul texts and 5%in numbers compared with that of existing state-of-the-art methods,which proved the proposed model performance superiority and verified that it could be a useful tool in reducing crime potential.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research issue.Different fromnatural images,character images pay more attention to stroke information.Howev...Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research issue.Different fromnatural images,character images pay more attention to stroke information.However,existingmodelsmainly consider pixel-level informationwhile ignoring structural information of the character,such as its edge and glyph,resulting in reconstructed images with mottled local structure and character damage.To solve these problems,we propose a novel generative adversarial network(GAN)framework based on an edge-guided generator and a discriminator constructed by a dual-domain U-Net framework,i.e.,EDU-GAN.Unlike existing frameworks,the generator introduces the edge extractionmodule,guiding it into the denoising process through the attention mechanism,which maintains the edge detail of the restored inscription image.Moreover,a dual-domain U-Net-based discriminator is proposed to learn the global and local discrepancy between the denoised and the label images in both image and morphological domains,which is helpful to blind denoising tasks.The proposed dual-domain discriminator and generator for adversarial training can reduce local artifacts and keep the denoised character structure intact.Due to the lack of a real-inscription image,we built the real-inscription dataset to provide an effective benchmark for studying inscription image denoising.The experimental results show the superiority of our method both in the synthetic and real-inscription datasets.展开更多
Recently,deep learning-based image outpainting has made greatly notable improvements in computer vision field.However,due to the lack of fully extracting image information,the existing methods often generate unnatural...Recently,deep learning-based image outpainting has made greatly notable improvements in computer vision field.However,due to the lack of fully extracting image information,the existing methods often generate unnatural and blurry outpainting results in most cases.To solve this issue,we propose a perceptual image outpainting method,which effectively takes the advantage of low-level feature fusion and multi-patch discriminator.Specifically,we first fuse the texture information in the low-level feature map of encoder,and simultaneously incorporate these aggregated features reusability with semantic(or structural)information of deep feature map such that we could utilizemore sophisticated texture information to generate more authentic outpainting images.Then we also introduce a multi-patch discriminator to enhance the generated texture,which effectively judges the generated image from the different level features and concurrently impels our network to produce more natural and clearer outpainting results.Moreover,we further introduce perceptual loss and style loss to effectively improve the texture and style of outpainting images.Compared with the existing methods,our method could produce finer outpainting results.Experimental results on Places2 and Paris StreetView datasets illustrated the effectiveness of our method for image outpainting.展开更多
文摘The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spatial-temporal structures,and the deep learning model can fully describe the potential semantic structure of human motion.To improve the authenticity of the generated human motion sequences,we propose a multi-task motion generation model that consists of a discriminator and a generator.The discriminator classifies motion sequences into different styles according to their similarity to the mean spatial-temporal templates from motion sequences of 17 crucial human joints in three-freedom degrees.And target motion sequences are created with these styles by the generator.Unlike traditional related works,our model can handle multiple tasks,such as identifying styles and generating data.In addition,by extracting 17 crucial joints from 29 human joints,our model avoids data redundancy and improves the accuracy of model recognition.The experimental results show that the discriminator of the model can effectively recognize diversified movements,and the generated data can correctly fit the actual data.The combination of discriminator and generator solves the problem of low reuse rate of motion data,and the generated motion sequences are more suitable for actual movement.
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.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
基金supported by the National Natural Science Foundation of China(NSFC)(No.12075308)。
文摘At high count rates,pile-up events involving neutron and gamma signals result in inaccurate neutron counting and distortions in the energy spectrum.Additionally,a bipolar cusp-like pulse shaping algorithm based on an unfolding synthesis technique was proposed.This algorithm exhibits a narrow pulse shape,and the parallel design of the dual algorithms enables the recovery of pile-up signal amplitudes while preserving the distinct characteristics of neutron and gamma signals.The simplicity of the algorithm facilitates real-time neutron/gamma discrimination on an FPGA,allowing the energy spectra to be updated with each incoming signal.Furthermore,the algorithm can be readily tailored to various experimental conditions by adjusting the decay time constants.Multi-objective optimization reduces the need for manual parameter tuning by rapidly identifying the optimal parameters.Testing with a^(241)Am-Be neutron source and a NaIL scintillator yielded a figure of merit(FoM)value of 2.11 and produced a clear energy spectrum even at high count rates.
基金supported,in part,by the National Nature Science Foundation of China under Grant 62272236,62376128 and 62306139the Natural Science Foundation of Jiangsu Province under Grant BK20201136,BK20191401.
文摘Discriminative region localization and efficient feature encoding are crucial for fine-grained object recognition.However,existing data augmentation methods struggle to accurately locate discriminative regions in complex backgrounds,small target objects,and limited training data,leading to poor recognition.Fine-grained images exhibit“small inter-class differences,”and while second-order feature encoding enhances discrimination,it often requires dual Convolutional Neural Networks(CNN),increasing training time and complexity.This study proposes a model integrating discriminative region localization and efficient second-order feature encoding.By ranking feature map channels via a fully connected layer,it selects high-importance channels to generate an enhanced map,accurately locating discriminative regions.Cropping and erasing augmentations further refine recognition.To improve efficiency,a novel second-order feature encoding module generates an attention map from the fourth convolutional group of Residual Network 50 layers(ResNet-50)and multiplies it with features from the fifth group,producing second-order features while reducing dimensionality and training time.Experiments on Caltech-University of California,San Diego Birds-200-2011(CUB-200-2011),Stanford Car,and Fine-Grained Visual Classification of Aircraft(FGVC Aircraft)datasets show state-of-the-art accuracy of 88.9%,94.7%,and 93.3%,respectively.
文摘Reconfigurable intelligent surface(RIS)have been cast as a promising alternative to alleviate blockage vulnerability and enhance coverage capability for terahertz(THz)communications.Owing to large-scale array elements at transceivers and RIS,the codebook based beamforming can be utilized in a computationally efficient manner.However,the codeword selection for analog beamforming is an intractable combinatorial optimization(CO)problem.To this end,by taking the CO problem as a classification problem,a multi-task learning based analog beam selection(MTL-ABS)framework is developed to implement cooperative beam selection concurrently at transceivers and RIS.In addition,residual network and self-attention mechanism are used to combat the network degradation and mine intrinsic THz channel features.Finally,the network convergence is analyzed from a blockwise perspective,and numerical results demonstrate that the MTL-ABS framework greatly decreases the beam selection overhead and achieves near optimal sum-rate compared with heuristic search based counterparts.
基金supported by the Guangdong Provincial Philosophy and Social Science“14th Five-Year Plan”Discipline Co-Construction Project(Grant No.GD22XJY14)the 2022 Guangdong Provincial Higher Education Teaching Reform Project(Grant No.Yue Jiao Gao[2023]4)Guangdong Polytechnic Normal University’s Project for Enhancing the Research Capacity of Doctoral Application Institution(Grant No.22GPNUZDJS48).
文摘Objectives:Psychological resilience is a critical resource for vocational high school students navigating social biases and fostering mental well-being.This six-month longitudinal study investigated the developmental trajectories of discrimination perception,vocational identity,and psychological resilience in this population.It further examined the longitudinal mediating role of vocational identity in the relationship between discrimination perception and psychological resilience.Methods:A total of 526 students from five vocational high schools in Guangdong,China,were assessed via convenience sampling at two time points:baseline(T1,September 2023)and six-month follow-up(T2,March 2024).Measures of discrimination perception,psychological resilience,and vocational identity were administered.Data were analyzed using a cross-lagged panel model to test for bidirectional relationships.Results:Over the six-month period,students showed significant decreases in discrimination perception and vocational identity,but a significant increase in psychological resilience.The cross-lagged model revealed significant bidirectional relationships:discrimination perception and psychological resilience negatively predicted each other over time(β=−0.124,p<0.01;β=−0.200,p<0.001),while psychological resilience and vocational identity positively predicted each other(β=0.084,p<0.05;β=0.076,p<0.05).The mediation analysis revealed a dual-pathway mechanism.T1 discrimination perception exerted both a significant direct negative effect on T2 psychological resilience(β=−0.332,p<0.001)and a significant indirect positive effect via T1 vocational identity(indirect effect=0.020,95%CI[0.001,0.046]).This confirms a partial mediating role,indicating that vocational identity functions as a compensatory mechanism,transforming the experience of discrimination perception into a potential source of psychological resilience.Conclusions:For vocational high school students,perception of discrimination directly undermines psychological resilience,but also indirectly fosters it through the positive development of vocational identity.These findings highlight vocational identity as a pivotal mechanism in the complex relationship between social adversity and mental resilience.
基金partially supported by the National Science and Technology Major Project of Ministry of Science and Technology of China (Grant Nos. 2014GB109003 and 2015GB111002)National Natural Science Foundation of China (Grant Nos. 11375195, 11575184, 11375004 and 11775068)
文摘A new neutron-gamma discriminator based on the support vector machine(SVM) method is proposed to improve the performance of the time-of-flight neutron spectrometer. The neutron detector is an EJ-299-33 plastic scintillator with pulse-shape discrimination(PSD) property. The SVM algorithm is implemented in field programmable gate array(FPGA) to carry out the real-time sifting of neutrons in neutron-gamma mixed radiation fields. This study compares the ability of the pulse gradient analysis method and the SVM method. The results show that this SVM discriminator can provide a better discrimination accuracy of 99.1%. The accuracy and performance of the SVM discriminator based on FPGA have been evaluated in the experiments. It can get a figure of merit of 1.30.
文摘Frequency lock loops （FLL） discriminating algorithms for direct-sequence spread-spectrum are discussed. The existing algorithms can＇t solve the problem of data bit reversal during one pre-detection integral period. And when the initial frequency offset is large, the frequency discriminator can＇ t work normally. To solve these problems, a new FLL discriminating algorithm is introduced. The least-squares discriminator is used in this new algorithm. As the least-squares discriminator has a short process unit period, the correspond- ing frequency discriminating range is large. And the data bit reversal just influence one process unit period, so the least-squares discriminated result will not be affected. Compared with traditional frequency discriminator, the least-squares algorithm can effectively solve the problem of data bit reversal and can endure larger initial frequency offset.
文摘Multipath and continuous wave (CW) interference may cause severe performance degradation of global navigation satellite system (GNSS) receivers. This paper analyzes the code tracking performance of early-minus-late power (EMLP) discriminator of GNSS receivers in the presence of multipath and CW interference. An analytical expression of the code tracking error is suggested for EMLP discriminator, and it can be used to assess the effect of multipath and CW interference. The derived expression shows that the combined effects include three components: multipath component;CW interference component and the combined component of multipath and CW interference. The effect of these components depends on some factors which can be classified into two categories: the receiving environment and the receiver parameters. Numerical results show how these factors affect the tracking performances. It is shown that the proper receiver parameters can suppress the combined effects of multipath and CW interference.
基金This work was supported by National Natural Science Foundation of China(NSFC)under Grant No.61771299,No.61771322,No.61375015,No.61301027.
文摘Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.
文摘Orthogonal Time Frequency and Space(OTFS) modulation is expected to provide high-speed and ultra-reliable communications for emerging mobile applications, including low-orbit satellite communications. Using the Doppler frequency for positioning is a promising research direction on communication and navigation integration. To tackle the high Doppler frequency and low signal-to-noise ratio(SNR) in satellite communication, this paper proposes a Red and Blue Frequency Shift Discriminator(RBFSD) based on the pseudo-noise(PN) sequence.The paper derives that the cross-correlation function on the Doppler domain exhibits the characteristic of a Sinc function. Therefore, it applies modulation onto the Delay-Doppler domain using PN sequence and adjusts Doppler frequency estimation by red-shifting or blue-shifting. Simulation results show that the performance of Doppler frequency estimation is close to the Cramér-Rao Lower Bound when the SNR is greater than -15dB. The proposed algorithm is about 1/D times less complex than the existing PN pilot sequence algorithm, where D is the resolution of the fractional Doppler.
文摘In this paper we propose the derivation of the expressions for the non-coherent Delay Locked Loop (DLL) Discriminator Curve (DC) in the absence and presence of Multipath (MP). Also derived, are the expressions of MP tracking errors in non-coherent configuration. The proposed models are valid for all Binary Offset Carrier (BOC) modulated signals in Global Navigation Satellite Systems (GNSS) such as Global Positioning System (GPS) and Future Galileo. The non-coherent configuration is used whenever the phase of the received signal cannot be estimated and thus cannot be demodulated. Therefore, the signal must be treated in a transposed band by the non-coherent DLL. The computer implementations show that the proposed models coincide with the numerical ones.
文摘The counter-meshing gears （CMG） discriminator is a mechanically coded lock, which is used to prevent the occurrence of High Consequence Events. This paper advanced a new kind of self-assembly metal CMG discriminator based on multi-exposure LiGA like process and sacrificial layer process. The new CMG discriminator has the following characters except low cost： 1） it has only discrimination teeth sections; 2） the thickness of each gear layer exceeds one hundred micrometers; 3） it is axially driven by a separate dectronic magnetic micromotor directly; 4） its CMG is made of metal and is batch fabricated in the assembled state; 5） it is prevented from rotating in the opposite direction by pawl/ratchet wheel mechanism; 6） it has simpler structure. This device has better strength and reliability in abnormal environment compared to the existing surface micro machining （SMM） discriminator.
基金supported by the Natural Science Foundation of China(NSFC)(No.41474159)National High-tech R&D Program of China(863 Program)(Nos.2012AA061803 and 2014AA093403)Open Foundation of Applied Nuclear Techniques in Geosciences Key Laboratory of Sichuan Province(No.gnzds2014006)
文摘Due to variable time for charge collection,energy resolution of nuclear detectors declines,especially compound semiconductor detectors like cadmium zinc telluride(CdZnTe) detector.To solve this problem,an analog rise-time discriminator based on charge comparison principle is designed.The reference charge signal after attenuation is compared with the deconvoluted and delayed current signal.It is found that the amplitude of delayed current signal is higher than that of the reference charge signal when rise time of the input signal is shorter than the discrimination time,thus generating gating signal and triggering DMCA(digital multi-channel analyzer) to receive the total integral charge signal.When rise time of the input signal is longer than discrimination time,DMCA remains inactivated and the corresponding total integral charge signal is abandoned.Test results show that combination of the designed rise-time discriminator and DMCA can reduce hole tailing of CdZnTe detector significantly.Energy resolution of the system is 0.98%@662 keV,and it is still excellent under high counting rates.
基金Supported by the Scientific and Technological Innovation 2030-Major Project of New Generation Artificial Intelligence(2020AAA0109300)Science and Technology Commission of Shanghai Municipality(21DZ2203100)2023 Anhui Province Key Research and Development Plan Project-Special Project of Science and Technology Cooperation(2023i11020002)。
文摘In recent years,self-supervised learning has achieved great success in areas such as computer vision and natural language processing because it can mine supervised signals from unlabeled data and reduce the reliance on manual labels.However,the currently generated self-supervised signals are either neighbor discrimination or self-discrimination,and there is no model to integrate neighbor discrimination and self-discrimination.Based on this,this paper proposes Fu-Rec that integrates neighbor-discrimination contrastive learning and self-discrimination contrastive learning,which consists of three modules:(1)neighbor-discrimination contrastive learning,(2)selfdiscrimination contrastive learning,and(3)recommendation module.The neighbor-discrimination contrastive learning and selfdiscrimination contrastive learning tasks are used as auxiliary tasks to assist the recommendation task.The Fu-Rec model effectively utilizes the respective advantages of neighbor-discrimination and self-discrimination to consider the information of the user’s neighbors as well as the user and the item itself for the recommendation,which results in better performance of the recommendation module.Experimental results on several public datasets demonstrate the effectiveness of the Fu-Rec proposed in this paper.
基金This research was funded by a National Research Foundation of Korea(NRF)grant funded by the Korean government(MOE)(No.2021R1I1A3055973)the Soonchunhyang University Research Fund。
文摘Recently,the technology of digital image forgery based on a generative adversarial network(GAN)has considerably improved to the extent that it is difficult to distinguish it from the original image with the naked eye by compositing and editing a person’s face or a specific part with the original image.Thus,much attention has been paid to digital image forgery as a social issue.Further,document forgery through GANs can completely change the meaning and context in a document,and it is difficult to identify whether the document is forged or not,which is dangerous.Nonetheless,few studies have been conducted on document forgery and new forgery-related attacks have emerged daily.Therefore,in this study,we propose a novel convolutional neural network(CNN)forensic discriminator that can detect forged text or numeric images by GANs using CNNs,which have been widely used in image classification for many years.To strengthen the detection performance of the proposed CNN forensic discriminator,CNN was trained after image preprocessing,including salt and pepper as well asGaussian noises.Moreover,we performed CNN optimization to make existing CNN more suitable for forged text or numeric image detection,which have mainly focused on the discrimination of forged faces to date.The test evaluation results using Hangul texts and numbers showed that the accuracy of forgery discrimination of the proposed method was significantly improved by 20%in Hangul texts and 5%in numbers compared with that of existing state-of-the-art methods,which proved the proposed model performance superiority and verified that it could be a useful tool in reducing crime potential.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the Key R&D Program of Shaanxi Province,China(Grant Nos.2022GY-274,2023-YBSF-505)the National Natural Science Foundation of China(Grant No.62273273).
文摘Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research issue.Different fromnatural images,character images pay more attention to stroke information.However,existingmodelsmainly consider pixel-level informationwhile ignoring structural information of the character,such as its edge and glyph,resulting in reconstructed images with mottled local structure and character damage.To solve these problems,we propose a novel generative adversarial network(GAN)framework based on an edge-guided generator and a discriminator constructed by a dual-domain U-Net framework,i.e.,EDU-GAN.Unlike existing frameworks,the generator introduces the edge extractionmodule,guiding it into the denoising process through the attention mechanism,which maintains the edge detail of the restored inscription image.Moreover,a dual-domain U-Net-based discriminator is proposed to learn the global and local discrepancy between the denoised and the label images in both image and morphological domains,which is helpful to blind denoising tasks.The proposed dual-domain discriminator and generator for adversarial training can reduce local artifacts and keep the denoised character structure intact.Due to the lack of a real-inscription image,we built the real-inscription dataset to provide an effective benchmark for studying inscription image denoising.The experimental results show the superiority of our method both in the synthetic and real-inscription datasets.
基金This work was supported by the Sichuan Science and Technology program(2019JDJQ0002,2019YFG0496,2021016,2020JDTD0020)partially supported by National Science Foundation of China 42075142.
文摘Recently,deep learning-based image outpainting has made greatly notable improvements in computer vision field.However,due to the lack of fully extracting image information,the existing methods often generate unnatural and blurry outpainting results in most cases.To solve this issue,we propose a perceptual image outpainting method,which effectively takes the advantage of low-level feature fusion and multi-patch discriminator.Specifically,we first fuse the texture information in the low-level feature map of encoder,and simultaneously incorporate these aggregated features reusability with semantic(or structural)information of deep feature map such that we could utilizemore sophisticated texture information to generate more authentic outpainting images.Then we also introduce a multi-patch discriminator to enhance the generated texture,which effectively judges the generated image from the different level features and concurrently impels our network to produce more natural and clearer outpainting results.Moreover,we further introduce perceptual loss and style loss to effectively improve the texture and style of outpainting images.Compared with the existing methods,our method could produce finer outpainting results.Experimental results on Places2 and Paris StreetView datasets illustrated the effectiveness of our method for image outpainting.
