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
Tinnitus:the hearing of a sound that has not been produced by any external or internal source,is a rather heterogeneous hearing disorder.Background/Objectives:Hearing loss has been shown to be the main risk factor for...Tinnitus:the hearing of a sound that has not been produced by any external or internal source,is a rather heterogeneous hearing disorder.Background/Objectives:Hearing loss has been shown to be the main risk factor for tinnitus while emotional disorders are risk factors for developing intrusive or bothersome tinnitus.Moreover,aging has also been identified as another risk factor.The aim of this paper was to analyse the correlation between hearing loss,age and tinnitus severity in a cohort of 610 tinnitus sufferers.Methods:Age,audiometric(hearing condition)and tinnitus(time duration and severity)data were assessed and analysed for all subjects just after recruiting(baseline).Furthermore,the average hearing loss(HL)curves of the participants for age groups were compared to these with the corresponding Age Related HL(ARHL).Results:For most of the age groups,the measured HL curves exceeded in 10-20 dB those of the ARHL.The average age of tinnitus onset(age minus tinnitus duration)was found to be 44-46 years in both men and women.Weak correlation between audiometric feature and tinnitus distress was observed.Conclusions:Hearing loss has been shown to be a clear risk factor for triggering tinnitus(86%of participants were hearing impaired).In this cohort,average measures of hearing loss showed,at most,weak associations with tinnitus-related distress,suggesting that non-audiological factors may play a predominant role.展开更多
Background:Brucellosis is a zoonotic infection common in Mediterranean countries and the Middle East.Neurological involvement,although rare,can lead to severe complications,including sensorineural hearing loss(SNHL).T...Background:Brucellosis is a zoonotic infection common in Mediterranean countries and the Middle East.Neurological involvement,although rare,can lead to severe complications,including sensorineural hearing loss(SNHL).This case is particularly noteworthy as it highlights irreversible auditory nerve damage in brucellosis,emphasizing the importance of early diagnosis and treatment to prevent permanent neurological consequences.The novelty of this case lies in the severity of auditory involvement despite timely treatment.Case Presentation:A 43-year-old male farmer of Maghrebi origin presented with neurobrucellosis complicated by severe,irreversible bilateral sensorineural hearing loss.The patient initially reported symptoms of hearing loss and dizziness,which were confirmed to be associated with auditory nerve involvement.Wright's serology and polymerase chain reaction(PCR)testing confirmed brucellosis.Despite appropriate and prolonged antibiotic therapy,including drugs that penetrate the meningeal barrier and act intracellularly,the patient's auditory impairment remained permanent.The patient is currently a candidate for cochlear implantation to manage his severe hearing loss.Neurological symptoms did not improve with treatment,but cochlear implantation may offer a potential solution to his hearing deficit.Conclusions:This case highlights the importance of early recognition and intervention in brucellosis cases,particularly those with neurological involvement.Delayed diagnosis and treatment can result in irreversible neurological damage.It also underscores the potential for cochlear implantation in patients with severe,irreversible sensorineural hearing loss caused by neurobrucellosis.Cochlear implantation offers an important solution for patients with brucellosis-related hearing deficits,improving their quality of life despite the neurological damage caused by the infection.展开更多
Objective:To investigate the potential link between chromosomal polymorphisms in couples who had a medical history of idiopathic recurrent pregnancy loss.Methods:Cytogenetic investigation was conducted with mitogen(Ph...Objective:To investigate the potential link between chromosomal polymorphisms in couples who had a medical history of idiopathic recurrent pregnancy loss.Methods:Cytogenetic investigation was conducted with mitogen(Phytohemagglutinin-M,Gibco)stimulated blood T lymphocytes by Giemsa trypsin Giemsa banding and Ag-NOR banding on 580 couples with a history of idiopathic recurrent pregnancy loss and 240 couples from the general population.Thirty good chromosomal spreads were captured,karyotyped,and analyzed.The karyotypes were designated using the International System for Human Cytogenomic Nomenclature 2024.Pearson Chi-square test was used to compare the frequency of chromosomal polymorphism variations in the idiopathic recurrent pregnancy loss group with the general population group.Results:A conventional cytogenetic investigation revealed that 45.43%of couples experiencing idiopathic recurrent pregnancy loss presented with various types of chromosomal polymorphic variants,compared to 11.88%in the general population.The overall frequency of these chromosomal polymorphic variants was significantly higher in the idiopathic recurrent pregnancy loss group compared to the general population group(OR 9.97,95%CI 6.99-14.21;P<0.05).Additionally,the prevalence of polymorphic variants was higher among males(49.14%)than females(41.72%)(P=0.01).Conclusions:Chromosomal polymorphic analysis may play a crucial role in the assessment and careful clinical management of cases with idiopathic recurrent pregnancy loss,especially when no other conclusive reasons are identified during the initial evaluation.Therefore,heteromorphism should not be overlooked while investigating the causes of idiopathic recurrent pregnancy loss.展开更多
The micro-riblet structures have been demonstrated effective in controlling the Total Pressure Loss(TPL)of aero-engine blades.However,due to the considerable scale gap between micro-texture and an actual aero-engine b...The micro-riblet structures have been demonstrated effective in controlling the Total Pressure Loss(TPL)of aero-engine blades.However,due to the considerable scale gap between micro-texture and an actual aero-engine blade,wind tunnel tests and numerical simulations with massive grids directly describing the global flow field are costly for aerodynamic evaluation.Furthermore,the fine micro surface structure brings unavoidable manufacturing errors,and the probability prediction contributes to gaining the confidence interval of the results.Therefore,a novel relay-based probabilistic model for multi-fidelity scenarios in the TPL prediction of a compressor cascade with micro-riblet surfaces is proposed to trade off accuracy and efficiency.Combined with the low-fidelity flow data generated by an aerodynamic solution strategy using the boundary surrogate model and the high-fidelity flow data from the experiment,the relay-based modeling has been achieved through knowledge transferring,and the confidence interval can be provided by the Gaussian Process Regression(GPR)model.The TPL of compressor cascades with micro-riblet surfaces under different surface structures at March number Ma=0.64,0.74,0.84 have been evaluated using the Relay-Based Probabilistic(RBP)model.The results illustrate that the RBP model could provide higher accuracy than the Single-Fidelity-Data-Driven(SFDD)prediction model,which show the promising potential of multi-fidelity scenarios data fusion in the aerodynamic evaluation of multi-scale configurations.展开更多
The lateral transport of labile organic carbon represents a critical pathway for soil organic carbon(SOC) loss,reducing organic carbon sequestration and increasing the risk of waterbody pollution.Livestock manure appl...The lateral transport of labile organic carbon represents a critical pathway for soil organic carbon(SOC) loss,reducing organic carbon sequestration and increasing the risk of waterbody pollution.Livestock manure application on croplands serves as a common fertilizer reduction practice to sustain crop yields,enhance SOC sequestration,and reduce water erosion.However,limited quantitative assessments have examined the effects of livestock manure substitution on labile organic carbon lateral loss and fluxes in long-term experiments.This study conducted a three-year field investigation on subtropical sloping croplands to assess the impact of livestock manure substitution on dissolved organic carbon(DOC) and particulate organic carbon(POC) loss via surface runoff,interflow and eroded sediments.There are four treatments:no fertilization(CK);chemical nitrogen fertilizer(SF),40% nitrogen substitution with pig manure(PMF),and 100% nitrogen substitution from pig manure(PM).Compared to SF treatment,long-term livestock manure substitution in PMF and PM treatments significantly(P<0.05) reduced annual cumulative surface runoff fluxes by 13.5 and 21.6%,respectively.Manure applications decreased annual sediment fluxes by 12.9 and 19.1%,respectively.Soil water stable aggregates for mean weight diameter(MWD) increased significantly by 37.7 and 73.6%.Annual cumulative POC loss flux via eroded sediment under PMF and PM treatments increased significantly(P<0.05) by 61.1 and 47.9%,respectively.The labile organic carbon loss fluxes,including DOC and POC losses,under PMF and PM treatments increased significantly(P<0.05) by 11.9 and 31.4%,respectively.These results demonstrate that while water erosion intensity decreases due to enhanced soil aggregate stability,the risk of labile organic carbon loss increases after long-term livestock manure substitution in subtropical sloping croplands.Future research should examine labile organic carbon lateral migration under various soil types and slope gradients for livestock manure application in subtropical agricultural ecosystem croplands to better understand extreme rainfall effects.展开更多
Highlights OsCAX2 is localized to tonoplast,and cadmium induces its expression.OsCAX2 overexpression reduces cadmium concentration in indica rice grains by 49.1%.Cadmium(Cd)exposure poses significant health risks to h...Highlights OsCAX2 is localized to tonoplast,and cadmium induces its expression.OsCAX2 overexpression reduces cadmium concentration in indica rice grains by 49.1%.Cadmium(Cd)exposure poses significant health risks to humans,and the International Agency for Research on Cancer has classified it as a Group I carcinogen.Cadmium undergoes minimal metabolism in the human body;consequently,prolonged Cd^(2+)exposure can cause severe damage to multiple organs including the liver,kidneys,lungs,bones,and immune system(Shao et al.2024).Rice,one of the three global staple crops,and Cd exposure in humans primarily occurs the consumption of contaminated rice grains.The contribution of rice to the total dietary Cd intake is over 50% for non-smoking Asian populations(Chen et al.2018;Shi et al.2020).展开更多
Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instabili...Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.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
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
Accurate aging diagnosis is crucial for the health and safety management of lithium-ion batteries in electric vehicles.Despite significant advancements achieved by data-driven methods,diagnosis accuracy remains constr...Accurate aging diagnosis is crucial for the health and safety management of lithium-ion batteries in electric vehicles.Despite significant advancements achieved by data-driven methods,diagnosis accuracy remains constrained by the high costs of check-up tests and the scarcity of labeled data.This paper presents a framework utilizing self-supervised machine learning to harness the potential of unlabeled data for diagnosing battery aging in electric vehicles during field operations.We validate our method using battery degradation datasets collected over more than two years from twenty real-world electric vehicles.Our analysis comprehensively addresses cell inconsistencies,physical interpretations,and charging uncertainties in real-world applications.This is achieved through self-supervised feature extraction using random short charging sequences in the main peak of incremental capacity curves.By leveraging inexpensive unlabeled data in a self-supervised approach,our method demonstrates improvements in average root mean square errors of 74.54%and 60.50%in the best and worst cases,respectively,compared to the supervised benchmark.This work underscores the potential of employing low-cost unlabeled data with self-supervised machine learning for effective battery health and safety management in realworld scenarios.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.
文摘Tinnitus:the hearing of a sound that has not been produced by any external or internal source,is a rather heterogeneous hearing disorder.Background/Objectives:Hearing loss has been shown to be the main risk factor for tinnitus while emotional disorders are risk factors for developing intrusive or bothersome tinnitus.Moreover,aging has also been identified as another risk factor.The aim of this paper was to analyse the correlation between hearing loss,age and tinnitus severity in a cohort of 610 tinnitus sufferers.Methods:Age,audiometric(hearing condition)and tinnitus(time duration and severity)data were assessed and analysed for all subjects just after recruiting(baseline).Furthermore,the average hearing loss(HL)curves of the participants for age groups were compared to these with the corresponding Age Related HL(ARHL).Results:For most of the age groups,the measured HL curves exceeded in 10-20 dB those of the ARHL.The average age of tinnitus onset(age minus tinnitus duration)was found to be 44-46 years in both men and women.Weak correlation between audiometric feature and tinnitus distress was observed.Conclusions:Hearing loss has been shown to be a clear risk factor for triggering tinnitus(86%of participants were hearing impaired).In this cohort,average measures of hearing loss showed,at most,weak associations with tinnitus-related distress,suggesting that non-audiological factors may play a predominant role.
文摘Background:Brucellosis is a zoonotic infection common in Mediterranean countries and the Middle East.Neurological involvement,although rare,can lead to severe complications,including sensorineural hearing loss(SNHL).This case is particularly noteworthy as it highlights irreversible auditory nerve damage in brucellosis,emphasizing the importance of early diagnosis and treatment to prevent permanent neurological consequences.The novelty of this case lies in the severity of auditory involvement despite timely treatment.Case Presentation:A 43-year-old male farmer of Maghrebi origin presented with neurobrucellosis complicated by severe,irreversible bilateral sensorineural hearing loss.The patient initially reported symptoms of hearing loss and dizziness,which were confirmed to be associated with auditory nerve involvement.Wright's serology and polymerase chain reaction(PCR)testing confirmed brucellosis.Despite appropriate and prolonged antibiotic therapy,including drugs that penetrate the meningeal barrier and act intracellularly,the patient's auditory impairment remained permanent.The patient is currently a candidate for cochlear implantation to manage his severe hearing loss.Neurological symptoms did not improve with treatment,but cochlear implantation may offer a potential solution to his hearing deficit.Conclusions:This case highlights the importance of early recognition and intervention in brucellosis cases,particularly those with neurological involvement.Delayed diagnosis and treatment can result in irreversible neurological damage.It also underscores the potential for cochlear implantation in patients with severe,irreversible sensorineural hearing loss caused by neurobrucellosis.Cochlear implantation offers an important solution for patients with brucellosis-related hearing deficits,improving their quality of life despite the neurological damage caused by the infection.
基金funded by the Technology Development Board(TDB)of India's Ministry of Science and Technology(TDB/M-25/2018-19).
文摘Objective:To investigate the potential link between chromosomal polymorphisms in couples who had a medical history of idiopathic recurrent pregnancy loss.Methods:Cytogenetic investigation was conducted with mitogen(Phytohemagglutinin-M,Gibco)stimulated blood T lymphocytes by Giemsa trypsin Giemsa banding and Ag-NOR banding on 580 couples with a history of idiopathic recurrent pregnancy loss and 240 couples from the general population.Thirty good chromosomal spreads were captured,karyotyped,and analyzed.The karyotypes were designated using the International System for Human Cytogenomic Nomenclature 2024.Pearson Chi-square test was used to compare the frequency of chromosomal polymorphism variations in the idiopathic recurrent pregnancy loss group with the general population group.Results:A conventional cytogenetic investigation revealed that 45.43%of couples experiencing idiopathic recurrent pregnancy loss presented with various types of chromosomal polymorphic variants,compared to 11.88%in the general population.The overall frequency of these chromosomal polymorphic variants was significantly higher in the idiopathic recurrent pregnancy loss group compared to the general population group(OR 9.97,95%CI 6.99-14.21;P<0.05).Additionally,the prevalence of polymorphic variants was higher among males(49.14%)than females(41.72%)(P=0.01).Conclusions:Chromosomal polymorphic analysis may play a crucial role in the assessment and careful clinical management of cases with idiopathic recurrent pregnancy loss,especially when no other conclusive reasons are identified during the initial evaluation.Therefore,heteromorphism should not be overlooked while investigating the causes of idiopathic recurrent pregnancy loss.
基金supported by the National Natural Science Foundation of China(No.12301672)the Shanghai Science and Technology Innovation Action Plan(Yangfan Special Project),China(No.23YF1401300)。
文摘The micro-riblet structures have been demonstrated effective in controlling the Total Pressure Loss(TPL)of aero-engine blades.However,due to the considerable scale gap between micro-texture and an actual aero-engine blade,wind tunnel tests and numerical simulations with massive grids directly describing the global flow field are costly for aerodynamic evaluation.Furthermore,the fine micro surface structure brings unavoidable manufacturing errors,and the probability prediction contributes to gaining the confidence interval of the results.Therefore,a novel relay-based probabilistic model for multi-fidelity scenarios in the TPL prediction of a compressor cascade with micro-riblet surfaces is proposed to trade off accuracy and efficiency.Combined with the low-fidelity flow data generated by an aerodynamic solution strategy using the boundary surrogate model and the high-fidelity flow data from the experiment,the relay-based modeling has been achieved through knowledge transferring,and the confidence interval can be provided by the Gaussian Process Regression(GPR)model.The TPL of compressor cascades with micro-riblet surfaces under different surface structures at March number Ma=0.64,0.74,0.84 have been evaluated using the Relay-Based Probabilistic(RBP)model.The results illustrate that the RBP model could provide higher accuracy than the Single-Fidelity-Data-Driven(SFDD)prediction model,which show the promising potential of multi-fidelity scenarios data fusion in the aerodynamic evaluation of multi-scale configurations.
基金funded by the Joint Funds of the National Natural Science Foundation of China (U20A20107 and U22A20562)the National Key Research and Development Program of China (2023YFD1900201-3)the International Cooperation Project,Ministry of Science and Technology of China (G2023019005L)。
文摘The lateral transport of labile organic carbon represents a critical pathway for soil organic carbon(SOC) loss,reducing organic carbon sequestration and increasing the risk of waterbody pollution.Livestock manure application on croplands serves as a common fertilizer reduction practice to sustain crop yields,enhance SOC sequestration,and reduce water erosion.However,limited quantitative assessments have examined the effects of livestock manure substitution on labile organic carbon lateral loss and fluxes in long-term experiments.This study conducted a three-year field investigation on subtropical sloping croplands to assess the impact of livestock manure substitution on dissolved organic carbon(DOC) and particulate organic carbon(POC) loss via surface runoff,interflow and eroded sediments.There are four treatments:no fertilization(CK);chemical nitrogen fertilizer(SF),40% nitrogen substitution with pig manure(PMF),and 100% nitrogen substitution from pig manure(PM).Compared to SF treatment,long-term livestock manure substitution in PMF and PM treatments significantly(P<0.05) reduced annual cumulative surface runoff fluxes by 13.5 and 21.6%,respectively.Manure applications decreased annual sediment fluxes by 12.9 and 19.1%,respectively.Soil water stable aggregates for mean weight diameter(MWD) increased significantly by 37.7 and 73.6%.Annual cumulative POC loss flux via eroded sediment under PMF and PM treatments increased significantly(P<0.05) by 61.1 and 47.9%,respectively.The labile organic carbon loss fluxes,including DOC and POC losses,under PMF and PM treatments increased significantly(P<0.05) by 11.9 and 31.4%,respectively.These results demonstrate that while water erosion intensity decreases due to enhanced soil aggregate stability,the risk of labile organic carbon loss increases after long-term livestock manure substitution in subtropical sloping croplands.Future research should examine labile organic carbon lateral migration under various soil types and slope gradients for livestock manure application in subtropical agricultural ecosystem croplands to better understand extreme rainfall effects.
基金financially supported by the National Key R&D Program of China(2024YFD1200800)the Guangdong Basic and Applied Basic Research Foundation,China(2024A1515030094)。
文摘Highlights OsCAX2 is localized to tonoplast,and cadmium induces its expression.OsCAX2 overexpression reduces cadmium concentration in indica rice grains by 49.1%.Cadmium(Cd)exposure poses significant health risks to humans,and the International Agency for Research on Cancer has classified it as a Group I carcinogen.Cadmium undergoes minimal metabolism in the human body;consequently,prolonged Cd^(2+)exposure can cause severe damage to multiple organs including the liver,kidneys,lungs,bones,and immune system(Shao et al.2024).Rice,one of the three global staple crops,and Cd exposure in humans primarily occurs the consumption of contaminated rice grains.The contribution of rice to the total dietary Cd intake is over 50% for non-smoking Asian populations(Chen et al.2018;Shi et al.2020).
基金Supported by the National Defense Basic Scientific Research Program of China.
文摘Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.
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.
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.
基金supported by the research project‘‘SafeDaBatt”(03EMF0409A)funded by the German Federal Ministry for Digital and Transport(BMDV)+2 种基金the National Key Research and Development Program of China(2022YFE0102700)the Key Research and Development Program of Shaanxi Province(2023-GHYB-05,2023-YBSF-104)the financial support from the China Scholarship Council(CSC)(202206567008)。
文摘Accurate aging diagnosis is crucial for the health and safety management of lithium-ion batteries in electric vehicles.Despite significant advancements achieved by data-driven methods,diagnosis accuracy remains constrained by the high costs of check-up tests and the scarcity of labeled data.This paper presents a framework utilizing self-supervised machine learning to harness the potential of unlabeled data for diagnosing battery aging in electric vehicles during field operations.We validate our method using battery degradation datasets collected over more than two years from twenty real-world electric vehicles.Our analysis comprehensively addresses cell inconsistencies,physical interpretations,and charging uncertainties in real-world applications.This is achieved through self-supervised feature extraction using random short charging sequences in the main peak of incremental capacity curves.By leveraging inexpensive unlabeled data in a self-supervised approach,our method demonstrates improvements in average root mean square errors of 74.54%and 60.50%in the best and worst cases,respectively,compared to the supervised benchmark.This work underscores the potential of employing low-cost unlabeled data with self-supervised machine learning for effective battery health and safety management in realworld scenarios.
