The accurate segmentation of deep gray matter nuclei is critical for neuropathological research,disease diagnosis and treatment.Existing methods employ the supervised learning training approach,which requires large la...The accurate segmentation of deep gray matter nuclei is critical for neuropathological research,disease diagnosis and treatment.Existing methods employ the supervised learning training approach,which requires large labeled datasets.It is challenging and time-consuming to obtain such datasets for medical image analysis.In addition,these methods based on convolutional neural networks(CNNs)only achieve suboptimal performance due to the locality of convolutional operations.Vision Transformers(ViTs)efficiently model long-range dependencies and thus have the potentiality to outperform these methods in segmentation tasks.To address these issues,we propose a novel hybrid network based on self-supervised pre-training for deep gray matter nuclei segmentation.Specifically,we present a CNN-Transformer hybrid network(CTNet),whose encoder consists of 3D CNN and ViT to learn local spatial-detailed features and global semantic information.A self-supervised learning(SSL)approach that integrates rotation prediction and masked feature reconstruction is proposed to pre-train the CTNet,enabling the model to learn valuable visual representations from unlabeled data.We evaluate the effectiveness of our method on 3T and 7T human brain MRI datasets.The results demonstrate that our CTNet achieves better performance than other comparison models and our pre-training strategy outperforms other advanced self-supervised methods.When the training set has only one sample,our pre-trained CTNet enhances segmentation performance,showing an 8.4%improvement in Dice similarity coefficient(DSC)compared to the randomly initialized CTNet.展开更多
Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This st...Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.展开更多
Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur ...Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur combines factors such as larger ray sources,scattering and imaging system vibration.To address the problem,we propose DeblurTomo,a novel self-supervised learning-based deblurring and reconstruction algorithm that efficiently reconstructs sharp CT images from blurry input without needing external data and blur measurement.Specifically,we constructed a coordinate-based implicit neural representation reconstruction network,which can map the coordinates to the attenuation coefficient in the reconstructed space formore convenient ray representation.Then,wemodel the blur as aweighted sumof offset rays and design the RayCorrectionNetwork(RCN)andWeight ProposalNetwork(WPN)to fit these rays and their weights bymulti-view consistency and geometric information,thereby extending 2D deblurring to 3D space.In the training phase,we use the blurry input as the supervision signal to optimize the reconstruction network,the RCN,and the WPN simultaneously.Extensive experiments on the widely used synthetic dataset show that DeblurTomo performs superiorly on the limited-angle and sparse-view in the simulated blurred scenarios.Further experiments on real datasets demonstrate the superiority of our method in practical scenarios.展开更多
Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caus...Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caused by artificial or natural effects during blended acquisition. Therefore, blending noise attenuation and missing shots reconstruction are essential for providing high-quality seismic data for further seismic processing and interpretation. The iterative shrinkage thresholding algorithm can help obtain deblended data based on sparsity assumptions of complete unblended data, and it characterizes seismic data linearly. Supervised learning algorithms can effectively capture the nonlinear relationship between incomplete pseudo-deblended data and complete unblended data. However, the dependence on complete unblended labels limits their practicality in field applications. Consequently, a self-supervised algorithm is presented for simultaneous deblending and interpolation of incomplete blended data, which minimizes the difference between simulated and observed incomplete pseudo-deblended data. The used blind-trace U-Net (BTU-Net) prevents identity mapping during complete unblended data estimation. Furthermore, a multistep process with blending noise simulation-subtraction and missing traces reconstruction-insertion is used in each step to improve the deblending and interpolation performance. Experiments with synthetic and field incomplete blended data demonstrate the effectiveness of the multistep self-supervised BTU-Net algorithm.展开更多
Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely us...Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.展开更多
Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain su...Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.展开更多
Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning mo...Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.展开更多
Intelligent Transportation Systems(ITS)leverage Integrated Sensing and Communications(ISAC)to enhance data exchange between vehicles and infrastructure in the Internet of Vehicles(IoV).This integration inevitably incr...Intelligent Transportation Systems(ITS)leverage Integrated Sensing and Communications(ISAC)to enhance data exchange between vehicles and infrastructure in the Internet of Vehicles(IoV).This integration inevitably increases computing demands,risking real-time system stability.Vehicle Edge Computing(VEC)addresses this by offloading tasks to Road Side Units(RSUs),ensuring timely services.Our previous work,the FLSimCo algorithm,which uses local resources for federated Self-Supervised Learning(SSL),has a limitation:vehicles often can’t complete all iteration tasks.Our improved algorithm offloads partial tasks to RSUs and optimizes energy consumption by adjusting transmission power,CPU frequency,and task assignment ratios,balancing local and RSU-based training.Meanwhile,setting an offloading threshold further prevents inefficiencies.Simulation results show that the enhanced algorithm reduces energy consumption and improves offloading efficiency and accuracy of federated SSL.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
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
Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning th...Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability.Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.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
State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to ac...State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.展开更多
Time series data has attached extensive attention as multi-domain data, but it is difficult to analyze due to its high dimension and few labels. Self-supervised representation learning provides an effective way for pr...Time series data has attached extensive attention as multi-domain data, but it is difficult to analyze due to its high dimension and few labels. Self-supervised representation learning provides an effective way for processing such data. Considering the frequency domain features of the time series data itself and the contextual feature in the classification task, this paper proposes an unsupervised Long Short-Term Memory(LSTM) and contrastive transformer-based time series representation model using contrastive learning. Firstly, transforming data with frequency domainbased augmentation increases the ability to represent features in the frequency domain. Secondly, the encoder module with three layers of LSTM and convolution maps the augmented data to the latent space and calculates the temporal loss with a contrastive transformer module and contextual loss. Finally, after selfsupervised training, the representation vector of the original data can be got from the pre-trained encoder. Our model achieves satisfied performances on Human Activity Recognition(HAR) and sleepEDF real-life datasets.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
基金supported in part by the National Natural Science Foundation of China under Grant 62071405the National Natural Science Foundation of China under Grant 12175189.
文摘The accurate segmentation of deep gray matter nuclei is critical for neuropathological research,disease diagnosis and treatment.Existing methods employ the supervised learning training approach,which requires large labeled datasets.It is challenging and time-consuming to obtain such datasets for medical image analysis.In addition,these methods based on convolutional neural networks(CNNs)only achieve suboptimal performance due to the locality of convolutional operations.Vision Transformers(ViTs)efficiently model long-range dependencies and thus have the potentiality to outperform these methods in segmentation tasks.To address these issues,we propose a novel hybrid network based on self-supervised pre-training for deep gray matter nuclei segmentation.Specifically,we present a CNN-Transformer hybrid network(CTNet),whose encoder consists of 3D CNN and ViT to learn local spatial-detailed features and global semantic information.A self-supervised learning(SSL)approach that integrates rotation prediction and masked feature reconstruction is proposed to pre-train the CTNet,enabling the model to learn valuable visual representations from unlabeled data.We evaluate the effectiveness of our method on 3T and 7T human brain MRI datasets.The results demonstrate that our CTNet achieves better performance than other comparison models and our pre-training strategy outperforms other advanced self-supervised methods.When the training set has only one sample,our pre-trained CTNet enhances segmentation performance,showing an 8.4%improvement in Dice similarity coefficient(DSC)compared to the randomly initialized CTNet.
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004)Supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korean government(MSIT)(No.RS-2022-00155885,Artificial Intelligence Convergence Innovation Human Resources Development(Hanyang University ERICA)).
文摘Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.
基金supported in part by the National Natural Science Foundation of China under Grants 62472434 and 62402171in part by the National Key Research and Development Program of China under Grant 2022YFF1203001+1 种基金in part by the Science and Technology Innovation Program of Hunan Province under Grant 2022RC3061in part by the Sci-Tech Innovation 2030 Agenda under Grant 2023ZD0508600.
文摘Computed Tomography(CT)reconstruction is essential inmedical imaging and other engineering fields.However,blurring of the projection during CT imaging can lead to artifacts in the reconstructed images.Projection blur combines factors such as larger ray sources,scattering and imaging system vibration.To address the problem,we propose DeblurTomo,a novel self-supervised learning-based deblurring and reconstruction algorithm that efficiently reconstructs sharp CT images from blurry input without needing external data and blur measurement.Specifically,we constructed a coordinate-based implicit neural representation reconstruction network,which can map the coordinates to the attenuation coefficient in the reconstructed space formore convenient ray representation.Then,wemodel the blur as aweighted sumof offset rays and design the RayCorrectionNetwork(RCN)andWeight ProposalNetwork(WPN)to fit these rays and their weights bymulti-view consistency and geometric information,thereby extending 2D deblurring to 3D space.In the training phase,we use the blurry input as the supervision signal to optimize the reconstruction network,the RCN,and the WPN simultaneously.Extensive experiments on the widely used synthetic dataset show that DeblurTomo performs superiorly on the limited-angle and sparse-view in the simulated blurred scenarios.Further experiments on real datasets demonstrate the superiority of our method in practical scenarios.
基金supported by the National Natural Science Foundation of China(42374134,42304125,U20B6005)the Science and Technology Commission of Shanghai Municipality(23JC1400502)the Fundamental Research Funds for the Central Universities.
文摘Blended acquisition offers efficiency improvements over conventional seismic data acquisition, at the cost of introducing blending noise effects. Besides, seismic data often suffers from irregularly missing shots caused by artificial or natural effects during blended acquisition. Therefore, blending noise attenuation and missing shots reconstruction are essential for providing high-quality seismic data for further seismic processing and interpretation. The iterative shrinkage thresholding algorithm can help obtain deblended data based on sparsity assumptions of complete unblended data, and it characterizes seismic data linearly. Supervised learning algorithms can effectively capture the nonlinear relationship between incomplete pseudo-deblended data and complete unblended data. However, the dependence on complete unblended labels limits their practicality in field applications. Consequently, a self-supervised algorithm is presented for simultaneous deblending and interpolation of incomplete blended data, which minimizes the difference between simulated and observed incomplete pseudo-deblended data. The used blind-trace U-Net (BTU-Net) prevents identity mapping during complete unblended data estimation. Furthermore, a multistep process with blending noise simulation-subtraction and missing traces reconstruction-insertion is used in each step to improve the deblending and interpolation performance. Experiments with synthetic and field incomplete blended data demonstrate the effectiveness of the multistep self-supervised BTU-Net algorithm.
基金supported by the National Natural Science Foundation of China(62276092,62303167)the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation(GZC20230707)+3 种基金the Key Science and Technology Program of Henan Province,China(242102211051,242102211042,212102310084)Key Scientiffc Research Projects of Colleges and Universities in Henan Province,China(25A520009)the China Postdoctoral Science Foundation(2024M760808)the Henan Province medical science and technology research plan joint construction project(LHGJ2024069).
文摘Feature fusion is an important technique in medical image classification that can improve diagnostic accuracy by integrating complementary information from multiple sources.Recently,Deep Learning(DL)has been widely used in pulmonary disease diagnosis,such as pneumonia and tuberculosis.However,traditional feature fusion methods often suffer from feature disparity,information loss,redundancy,and increased complexity,hindering the further extension of DL algorithms.To solve this problem,we propose a Graph-Convolution Fusion Network with Self-Supervised Feature Alignment(Self-FAGCFN)to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis.The network integrates Convolutional Neural Networks(CNNs)for robust feature extraction from two-dimensional grid structures and Graph Convolutional Networks(GCNs)within a Graph Neural Network branch to capture features based on graph structure,focusing on significant node representations.Additionally,an Attention-Embedding Ensemble Block is included to capture critical features from GCN outputs.To ensure effective feature alignment between pre-and post-fusion stages,we introduce a feature alignment loss that minimizes disparities.Moreover,to address the limitations of proposed methods,such as inappropriate centroid discrepancies during feature alignment and class imbalance in the dataset,we develop a Feature-Centroid Fusion(FCF)strategy and a Multi-Level Feature-Centroid Update(MLFCU)algorithm,respectively.Extensive experiments on public datasets LungVision and Chest-Xray demonstrate that the Self-FAGCFN model significantly outperforms existing methods in diagnosing pneumonia and tuberculosis,highlighting its potential for practical medical applications.
基金supported in part by the National Natural Science Foundation of China under Grants 62071345。
文摘Self-supervised monocular depth estimation has emerged as a major research focus in recent years,primarily due to the elimination of ground-truth depth dependence.However,the prevailing architectures in this domain suffer from inherent limitations:existing pose network branches infer camera ego-motion exclusively under static-scene and Lambertian-surface assumptions.These assumptions are often violated in real-world scenarios due to dynamic objects,non-Lambertian reflectance,and unstructured background elements,leading to pervasive artifacts such as depth discontinuities(“holes”),structural collapse,and ambiguous reconstruction.To address these challenges,we propose a novel framework that integrates scene dynamic pose estimation into the conventional self-supervised depth network,enhancing its ability to model complex scene dynamics.Our contributions are threefold:(1)a pixel-wise dynamic pose estimation module that jointly resolves the pose transformations of moving objects and localized scene perturbations;(2)a physically-informed loss function that couples dynamic pose and depth predictions,designed to mitigate depth errors arising from high-speed distant objects and geometrically inconsistent motion profiles;(3)an efficient SE(3)transformation parameterization that streamlines network complexity and temporal pre-processing.Extensive experiments on the KITTI and NYU-V2 benchmarks show that our framework achieves state-of-the-art performance in both quantitative metrics and qualitative visual fidelity,significantly improving the robustness and generalization of monocular depth estimation under dynamic conditions.
基金funded by theNational Science and TechnologyCouncil(NSTC),Taiwan,under grant numbers NSTC 112-2634-F-019-001 and NSTC 113-2634-F-A49-007.
文摘Few-shot learning has emerged as a crucial technique for coral species classification,addressing the challenge of limited labeled data in underwater environments.This study introduces an optimized few-shot learning model that enhances classification accuracy while minimizing reliance on extensive data collection.The proposed model integrates a hybrid similarity measure combining Euclidean distance and cosine similarity,effectively capturing both feature magnitude and directional relationships.This approach achieves a notable accuracy of 71.8%under a 5-way 5-shot evaluation,outperforming state-of-the-art models such as Prototypical Networks,FEAT,and ESPT by up to 10%.Notably,the model demonstrates high precision in classifying Siderastreidae(87.52%)and Fungiidae(88.95%),underscoring its effectiveness in distinguishing subtle morphological differences.To further enhance performance,we incorporate a self-supervised learning mechanism based on contrastive learning,enabling the model to extract robust representations by leveraging local structural patterns in corals.This enhancement significantly improves classification accuracy,particularly for species with high intra-class variation,leading to an overall accuracy of 76.52%under a 5-way 10-shot evaluation.Additionally,the model exploits the repetitive structures inherent in corals,introducing a local feature aggregation strategy that refines classification through spatial information integration.Beyond its technical contributions,this study presents a scalable and efficient approach for automated coral reef monitoring,reducing annotation costs while maintaining high classification accuracy.By improving few-shot learning performance in underwater environments,our model enhances monitoring accuracy by up to 15%compared to traditional methods,offering a practical solution for large-scale coral conservation efforts.
文摘Intelligent Transportation Systems(ITS)leverage Integrated Sensing and Communications(ISAC)to enhance data exchange between vehicles and infrastructure in the Internet of Vehicles(IoV).This integration inevitably increases computing demands,risking real-time system stability.Vehicle Edge Computing(VEC)addresses this by offloading tasks to Road Side Units(RSUs),ensuring timely services.Our previous work,the FLSimCo algorithm,which uses local resources for federated Self-Supervised Learning(SSL),has a limitation:vehicles often can’t complete all iteration tasks.Our improved algorithm offloads partial tasks to RSUs and optimizes energy consumption by adjusting transmission power,CPU frequency,and task assignment ratios,balancing local and RSU-based training.Meanwhile,setting an offloading threshold further prevents inefficiencies.Simulation results show that the enhanced algorithm reduces energy consumption and improves offloading efficiency and accuracy of federated SSL.
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.
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.
基金by National Natural Science Foundation of China(Nos.61822204 and 61521002).
文摘Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability.Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.
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funded by the “SMART BATTERY” project, granted by Villum Foundation in 2021 (project number 222860)。
文摘State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.
基金Supported by the National Key Research and Development Program of China(2019YFB1706401)。
文摘Time series data has attached extensive attention as multi-domain data, but it is difficult to analyze due to its high dimension and few labels. Self-supervised representation learning provides an effective way for processing such data. Considering the frequency domain features of the time series data itself and the contextual feature in the classification task, this paper proposes an unsupervised Long Short-Term Memory(LSTM) and contrastive transformer-based time series representation model using contrastive learning. Firstly, transforming data with frequency domainbased augmentation increases the ability to represent features in the frequency domain. Secondly, the encoder module with three layers of LSTM and convolution maps the augmented data to the latent space and calculates the temporal loss with a contrastive transformer module and contextual loss. Finally, after selfsupervised training, the representation vector of the original data can be got from the pre-trained encoder. Our model achieves satisfied performances on Human Activity Recognition(HAR) and sleepEDF real-life datasets.
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.
