无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到...无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。展开更多
Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each l...Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.展开更多
Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are st...Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaini...In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaining energy levels and battery replacement is both inadequate and costly.This paper introduces an energy management system for indoor IoT,which includes a mobile energy station(ES)for enabling on-demand wireless energy transfer(WET)in radio frequency(RF),some energy receivers(ERs),and a cloud server.By implementing a two-stage positioning system and embedding energy receivers into traditional IoT devices,we robustly manage their energy storage.The experimental results demonstrate that the energy receiver can harvest a minimum power of 58 mW.展开更多
Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for...Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.展开更多
Repetitive traumatic brain injury impacts adult neurogenesis in the hippocampal dentate gyrus,leading to long-term cognitive impairment.However,the mechanism underlying this neurogenesis impairment remains unknown.In ...Repetitive traumatic brain injury impacts adult neurogenesis in the hippocampal dentate gyrus,leading to long-term cognitive impairment.However,the mechanism underlying this neurogenesis impairment remains unknown.In this study,we established a male mouse model of repetitive traumatic brain injury and performed long-term evaluation of neurogenesis of the hippocampal dentate gyrus after repetitive traumatic brain injury.Our results showed that repetitive traumatic brain injury inhibited neural stem cell proliferation and development,delayed neuronal maturation,and reduced the complexity of neuronal dendrites and spines.Mice with repetitive traumatic brain injuryalso showed deficits in spatial memory retrieval.Moreover,following repetitive traumatic brain injury,neuroinflammation was enhanced in the neurogenesis microenvironment where C1q levels were increased,C1q binding protein levels were decreased,and canonical Wnt/β-catenin signaling was downregulated.An inhibitor of C1 reversed the long-term impairment of neurogenesis induced by repetitive traumatic brain injury and improved neurological function.These findings suggest that repetitive traumatic brain injury–induced C1-related inflammation impairs long-term neurogenesis in the dentate gyrus and contributes to spatial memory retrieval dysfunction.展开更多
Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dyna...Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dynamic modeling.Firstly,the dynamic equations of shield thrust system were established to clarify the relationship between force and movement of shield machine.Secondly,an analytical model was proposed to predict future multistep pose of the shield machine.Finally,a virtual prototype model was developed to simulate the dynamic behavior of the shield machine and validate the accuracy of the proposed pose prediction method.Results reveal that the model proposed can predict the shield pose with high accuracy,which can provide a decision basis whether for manual or automatic control of shield pose.展开更多
Genetic Programming (GP) is an important approach to deal with complex problem analysis and modeling, and has been applied in a wide range of areas. The development of GP involves various aspects, including design of ...Genetic Programming (GP) is an important approach to deal with complex problem analysis and modeling, and has been applied in a wide range of areas. The development of GP involves various aspects, including design of genetic operators, evolutionary controls and implementations of heuristic strategy, evaluations and other mechanisms. When designing genetic operators, it is necessary to consider the possible limitations of encoding methods of individuals. And when selecting evolutionary control strategies, it is also necessary to balance search efficiency and diversity based on representation characteristics as well as the problem itself. More importantly, all of these matters, among others, have to be implemented through tedious coding work. Therefore, GP development is both complex and time-consuming. To overcome some of these difficulties that hinder the enhancement of GP development efficiency, we explore the feasibility of mutual assistance among GP variants, and then propose a rapid GP prototyping development method based on πGrammatical Evolution (πGE). It is demonstrated through regression analysis experiments that not only is this method beneficial for the GP developers to get rid of some tedious implementations, but also enables them to concentrate on the essence of the referred problem, such as individual representation, decoding means and evaluation. Additionally, it provides new insights into the roles of individual delineations in phenotypes and semantic research of individuals.展开更多
Based on the Prototype Theory,the prototypical feature of advertisement is found to be the combination of three language functions:the informative function,the expressive function,and the vocative function.The adverti...Based on the Prototype Theory,the prototypical feature of advertisement is found to be the combination of three language functions:the informative function,the expressive function,and the vocative function.The advertisement translation means the adjustment of the informative function and the expressive function according to the differences between languages or cultures in order to maximize the vocative function.The faithful translation is the closest to the prototype of the source text but not necessarily the best translation.展开更多
Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take ca...Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.展开更多
Spinal cord injury remains a major cause of disability in young adults,and beyond acute decompression and rehabilitation,there are no pharmacological treatments to limit the progression of injury and optimize recovery...Spinal cord injury remains a major cause of disability in young adults,and beyond acute decompression and rehabilitation,there are no pharmacological treatments to limit the progression of injury and optimize recovery in this population.Following the thorough investigation of the complement system in triggering and propagating cerebral neuroinflammation,a similar role for complement in spinal neuroinflammation is a focus of ongoing research.In this work,we survey the current literature investigating the role of complement in spinal cord injury including the sources of complement proteins,triggers of complement activation,and role of effector functions in the pathology.We study relevant data demonstrating the different triggers of complement activation after spinal cord injury including direct binding to cellular debris,and or activation via antibody binding to damage-associated molecular patterns.Several effector functions of complement have been implicated in spinal cord injury,and we critically evaluate recent studies on the dual role of complement anaphylatoxins in spinal cord injury while emphasizing the lack of pathophysiological understanding of the role of opsonins in spinal cord injury.Following this pathophysiological review,we systematically review the different translational approaches used in preclinical models of spinal cord injury and discuss the challenges for future translation into human subjects.This review emphasizes the need for future studies to dissect the roles of different complement pathways in the pathology of spinal cord injury,to evaluate the phases of involvement of opsonins and anaphylatoxins,and to study the role of complement in white matter degeneration and regeneration using translational strategies to supplement genetic models.展开更多
Since its inception,the Internet has been rapidly evolving.With the advancement of science and technology and the explosive growth of the population,the demand for the Internet has been on the rise.Many applications i...Since its inception,the Internet has been rapidly evolving.With the advancement of science and technology and the explosive growth of the population,the demand for the Internet has been on the rise.Many applications in education,healthcare,entertainment,science,and more are being increasingly deployed based on the internet.Concurrently,malicious threats on the internet are on the rise as well.Distributed Denial of Service(DDoS)attacks are among the most common and dangerous threats on the internet today.The scale and complexity of DDoS attacks are constantly growing.Intrusion Detection Systems(IDS)have been deployed and have demonstrated their effectiveness in defense against those threats.In addition,the research of Machine Learning(ML)and Deep Learning(DL)in IDS has gained effective results and significant attention.However,one of the challenges when applying ML and DL techniques in intrusion detection is the identification of unknown attacks.These attacks,which are not encountered during the system’s training,can lead to misclassification with significant errors.In this research,we focused on addressing the issue of Unknown Attack Detection,combining two methods:Spatial Location Constraint Prototype Loss(SLCPL)and Fuzzy C-Means(FCM).With the proposed method,we achieved promising results compared to traditional methods.The proposed method demonstrates a very high accuracy of up to 99.8%with a low false positive rate for known attacks on the Intrusion Detection Evaluation Dataset(CICIDS2017)dataset.Particularly,the accuracy is also very high,reaching 99.7%,and the precision goes up to 99.9%for unknown DDoS attacks on the DDoS Evaluation Dataset(CICDDoS2019)dataset.The success of the proposed method is due to the combination of SLCPL,an advanced Open-Set Recognition(OSR)technique,and FCM,a traditional yet highly applicable clustering technique.This has yielded a novel method in the field of unknown attack detection.This further expands the trend of applying DL and ML techniques in the development of intrusion detection systems and cybersecurity.Finally,implementing the proposed method in real-world systems can enhance the security capabilities against increasingly complex threats on computer networks.展开更多
The complement system is crucial for maintaining immunological homeostasis in the liver,playing a significant role in both innate and adaptive immune responses.Dysregulation of this system is closely linked to the pat...The complement system is crucial for maintaining immunological homeostasis in the liver,playing a significant role in both innate and adaptive immune responses.Dysregulation of this system is closely linked to the pathogenesis of various liver diseases.Modulating the complement system can affect the progression of these conditions.To provide insights into treating liver injury by targeting the regu-lation of the complement system,we conducted a comprehensive search of major biomedical databases,including MEDLINE,PubMed,EMBASE,and Web of Science,to identify articles on complement and liver injury and reviewed the functions and mechanisms of the complement system in liver injury.展开更多
BACKGROUND Hepatocellular carcinoma(HCC)surveillance is crucial for patients with compensated cirrhosis(CC)and decompensated cirrhosis(DC).Increasing evidence has revealed a connection between thyroid hormone(TH)and H...BACKGROUND Hepatocellular carcinoma(HCC)surveillance is crucial for patients with compensated cirrhosis(CC)and decompensated cirrhosis(DC).Increasing evidence has revealed a connection between thyroid hormone(TH)and HCC,although this relationship remains contentious.Complements and immunoglobulin(Ig),which serve as surrogates of cirrhosis-associated immune dysfunc-tion,are associated with the severity and outcomes of liver cirrhosis(LC).To date,there is a lack of evidence supporting the recommendation of TH,Ig,and com-plement tests in patients at high risk of HCC.AIM To assess the predictive value of TH,Ig,and complements for HCC development.METHODS Data from 142 patients,comprising 72 patients with CC and 70 patients with DC,were analysed as a training set.Among them,100 patients who underwent complement and Ig tests were considered for internal validation.Logistic regression was employed to identify independent risk factors for HCC development.RESULTS The median follow-up duration was 32(24-37 months)months.The incidence of HCC was significantly higher in the DC group(16/70,22.9%)compared to the CC group(3/72,4.2%)(χ^(2)=10.698,P<0.01).Patients with DC exhibited lower total tetraiodothyronine(TT4),total triiodothyronine(TT3),free triiodothyronine,complement C3,and C4(all P<0.01),and higher IgA and IgG(both P<0.01).In both CC and DC patients,TT3 and TT4 positively correlated with alanine transaminase(ALT),aspartate transaminase(AST),and gamma-glutamyl transpeptidase(GGT).IgG positively correlated with IgM,IgA,ALT,and AST,while it negatively correlated with C3 and C4.Multivariable analysis indicated that age,DC status,and GGT were independent risk factors for HCC development.CONCLUSION The predictive value of TH,Ig,and complements for HCC development is suboptimal.Age,DC,and GGT emerge as more significant factors during HCC surveillance in hepatitis B virus-related LC.展开更多
Antibody-mediated rejection(AMR)represents a major challenge in kidney transplantation,significantly contributing to tissue injury and graft failure.AMR is primarily driven by donor-specific alloantibodies(DSAs),which...Antibody-mediated rejection(AMR)represents a major challenge in kidney transplantation,significantly contributing to tissue injury and graft failure.AMR is primarily driven by donor-specific alloantibodies(DSAs),which recognize and bind to specific target antigens present within the transplanted kidney tissue.Upon binding,these DSAs commonly initiate activation of the complement system within the graft.The activation of the complement cascade sets off a powerful inflammatory response characterized by the recruitment and activation of immune cells,endothelial damage,and subsequent tissue injury.This inflammation underlies many clinical and histological manifestations of AMR,making complement activation a critical player in the disease process.Advancements in our understanding of how complement pathways contribute to kidney graft injury have opened new avenues for therapeutic intervention.Recent research has facilitated the development and application of novel therapies specifically designed to inhibit complement activation.Such targeted complement-inhibitory strategies have shown promise in improving graft outcomes by inhibiting complement-mediated damage and extending graft survival.This review comprehensively discusses the critical role of complement activation in inducing kidney graft injury with a focus on its role in AMR.By elucidating the detailed mechanisms and contributions of complement pathways,the review seeks to enhance the understanding necessary for developing targeted therapeutic interventions to prevent or treat AMR effectively.展开更多
Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships amo...Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.展开更多
文摘无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。
基金supported in part by the Gansu Haizhi Characteristic Demonstration Project(No.GSHZTS2022-2).
文摘Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.
基金supported by the National Natural Science Foundation of China under Grant No.62162009the Key Technologies R&D Program of He’nan Province under Grant No.242102211065+1 种基金the Scientific Research Innovation Team of Xuchang University under GrantNo.2022CXTD003Postgraduate Education Reform and Quality Improvement Project of Henan Province under Grant No.YJS2024JD38.
文摘Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
基金supported in part by the Natural Science Foundation of China(NSFC)under Grant 61971102in part by the Key Research and Development Program of Zhejiang Province under Grant 2022C01093.
文摘In indoor environments,various batterypowered Internet of Things(IoT)devices,such as remote controllers and electronic tags on high-level shelves,require efficient energy management.However,manually monitoring remaining energy levels and battery replacement is both inadequate and costly.This paper introduces an energy management system for indoor IoT,which includes a mobile energy station(ES)for enabling on-demand wireless energy transfer(WET)in radio frequency(RF),some energy receivers(ERs),and a cloud server.By implementing a two-stage positioning system and embedding energy receivers into traditional IoT devices,we robustly manage their energy storage.The experimental results demonstrate that the energy receiver can harvest a minimum power of 58 mW.
基金supported in part by the National Natural Science Foundation of China(No.12302252)。
文摘Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.
基金supported by the Fundamental Research Program of Shanxi Province of China,No.20210302124277the Science Foundation of Shanxi Bethune Hospital,No.2021YJ13(both to JW)。
文摘Repetitive traumatic brain injury impacts adult neurogenesis in the hippocampal dentate gyrus,leading to long-term cognitive impairment.However,the mechanism underlying this neurogenesis impairment remains unknown.In this study,we established a male mouse model of repetitive traumatic brain injury and performed long-term evaluation of neurogenesis of the hippocampal dentate gyrus after repetitive traumatic brain injury.Our results showed that repetitive traumatic brain injury inhibited neural stem cell proliferation and development,delayed neuronal maturation,and reduced the complexity of neuronal dendrites and spines.Mice with repetitive traumatic brain injuryalso showed deficits in spatial memory retrieval.Moreover,following repetitive traumatic brain injury,neuroinflammation was enhanced in the neurogenesis microenvironment where C1q levels were increased,C1q binding protein levels were decreased,and canonical Wnt/β-catenin signaling was downregulated.An inhibitor of C1 reversed the long-term impairment of neurogenesis induced by repetitive traumatic brain injury and improved neurological function.These findings suggest that repetitive traumatic brain injury–induced C1-related inflammation impairs long-term neurogenesis in the dentate gyrus and contributes to spatial memory retrieval dysfunction.
基金Project(2023JBZY030)supported by the Fundamental Research Funds for the Central Universities,ChinaProject(U1834208)supported by the National Natural Science Foundation of China。
文摘Compared with traditional feedback control,predictive control can eliminate the lag of pose control and avoid the snakelike motion of shield machines.Therefore,a shield pose prediction model was proposed based on dynamic modeling.Firstly,the dynamic equations of shield thrust system were established to clarify the relationship between force and movement of shield machine.Secondly,an analytical model was proposed to predict future multistep pose of the shield machine.Finally,a virtual prototype model was developed to simulate the dynamic behavior of the shield machine and validate the accuracy of the proposed pose prediction method.Results reveal that the model proposed can predict the shield pose with high accuracy,which can provide a decision basis whether for manual or automatic control of shield pose.
文摘Genetic Programming (GP) is an important approach to deal with complex problem analysis and modeling, and has been applied in a wide range of areas. The development of GP involves various aspects, including design of genetic operators, evolutionary controls and implementations of heuristic strategy, evaluations and other mechanisms. When designing genetic operators, it is necessary to consider the possible limitations of encoding methods of individuals. And when selecting evolutionary control strategies, it is also necessary to balance search efficiency and diversity based on representation characteristics as well as the problem itself. More importantly, all of these matters, among others, have to be implemented through tedious coding work. Therefore, GP development is both complex and time-consuming. To overcome some of these difficulties that hinder the enhancement of GP development efficiency, we explore the feasibility of mutual assistance among GP variants, and then propose a rapid GP prototyping development method based on πGrammatical Evolution (πGE). It is demonstrated through regression analysis experiments that not only is this method beneficial for the GP developers to get rid of some tedious implementations, but also enables them to concentrate on the essence of the referred problem, such as individual representation, decoding means and evaluation. Additionally, it provides new insights into the roles of individual delineations in phenotypes and semantic research of individuals.
文摘Based on the Prototype Theory,the prototypical feature of advertisement is found to be the combination of three language functions:the informative function,the expressive function,and the vocative function.The advertisement translation means the adjustment of the informative function and the expressive function according to the differences between languages or cultures in order to maximize the vocative function.The faithful translation is the closest to the prototype of the source text but not necessarily the best translation.
文摘Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.
基金supported by the Department of Veterans Affairs(VA Merit Award BX004256)(to AMA)Emory Department of Neurosurgery Catalyst GrantEmory Medical Care Foundation Grant(to AMA and JG)。
文摘Spinal cord injury remains a major cause of disability in young adults,and beyond acute decompression and rehabilitation,there are no pharmacological treatments to limit the progression of injury and optimize recovery in this population.Following the thorough investigation of the complement system in triggering and propagating cerebral neuroinflammation,a similar role for complement in spinal neuroinflammation is a focus of ongoing research.In this work,we survey the current literature investigating the role of complement in spinal cord injury including the sources of complement proteins,triggers of complement activation,and role of effector functions in the pathology.We study relevant data demonstrating the different triggers of complement activation after spinal cord injury including direct binding to cellular debris,and or activation via antibody binding to damage-associated molecular patterns.Several effector functions of complement have been implicated in spinal cord injury,and we critically evaluate recent studies on the dual role of complement anaphylatoxins in spinal cord injury while emphasizing the lack of pathophysiological understanding of the role of opsonins in spinal cord injury.Following this pathophysiological review,we systematically review the different translational approaches used in preclinical models of spinal cord injury and discuss the challenges for future translation into human subjects.This review emphasizes the need for future studies to dissect the roles of different complement pathways in the pathology of spinal cord injury,to evaluate the phases of involvement of opsonins and anaphylatoxins,and to study the role of complement in white matter degeneration and regeneration using translational strategies to supplement genetic models.
基金This research was partly supported by the National Science and Technology Council,Taiwan with Grant Numbers 112-2221-E-992-045,112-2221-E-992-057-MY3 and 112-2622-8-992-009-TD1.
文摘Since its inception,the Internet has been rapidly evolving.With the advancement of science and technology and the explosive growth of the population,the demand for the Internet has been on the rise.Many applications in education,healthcare,entertainment,science,and more are being increasingly deployed based on the internet.Concurrently,malicious threats on the internet are on the rise as well.Distributed Denial of Service(DDoS)attacks are among the most common and dangerous threats on the internet today.The scale and complexity of DDoS attacks are constantly growing.Intrusion Detection Systems(IDS)have been deployed and have demonstrated their effectiveness in defense against those threats.In addition,the research of Machine Learning(ML)and Deep Learning(DL)in IDS has gained effective results and significant attention.However,one of the challenges when applying ML and DL techniques in intrusion detection is the identification of unknown attacks.These attacks,which are not encountered during the system’s training,can lead to misclassification with significant errors.In this research,we focused on addressing the issue of Unknown Attack Detection,combining two methods:Spatial Location Constraint Prototype Loss(SLCPL)and Fuzzy C-Means(FCM).With the proposed method,we achieved promising results compared to traditional methods.The proposed method demonstrates a very high accuracy of up to 99.8%with a low false positive rate for known attacks on the Intrusion Detection Evaluation Dataset(CICIDS2017)dataset.Particularly,the accuracy is also very high,reaching 99.7%,and the precision goes up to 99.9%for unknown DDoS attacks on the DDoS Evaluation Dataset(CICDDoS2019)dataset.The success of the proposed method is due to the combination of SLCPL,an advanced Open-Set Recognition(OSR)technique,and FCM,a traditional yet highly applicable clustering technique.This has yielded a novel method in the field of unknown attack detection.This further expands the trend of applying DL and ML techniques in the development of intrusion detection systems and cybersecurity.Finally,implementing the proposed method in real-world systems can enhance the security capabilities against increasingly complex threats on computer networks.
基金Supported by the Science and Technology Planning Projects of Guizhou Province,No.QKHJC-ZK[2022]YB642the Science and Technology Planning Projects of Zunyi City,No.ZSKHHZ(2022)344+4 种基金the WBE Liver Fibrosis Foundation,No.CFHPC2025028the Chinese Foundation for Hepatitis Prevention and Control Muxin Research Fund of CHB,No.MX202404Beijing Liver and Gallbladder Mutual Aid Public Welfare Foundation Artificial Liver Special Fund,No.iGandanF-1082024-Rgg018the Graduate Research Fund Project of Zunyi Medical University,No.ZYK246the Student Innovation and Entrepreneurship Training Program of Zunyi Medical University,No.2024106610923 and No.S202310661028.
文摘The complement system is crucial for maintaining immunological homeostasis in the liver,playing a significant role in both innate and adaptive immune responses.Dysregulation of this system is closely linked to the pathogenesis of various liver diseases.Modulating the complement system can affect the progression of these conditions.To provide insights into treating liver injury by targeting the regu-lation of the complement system,we conducted a comprehensive search of major biomedical databases,including MEDLINE,PubMed,EMBASE,and Web of Science,to identify articles on complement and liver injury and reviewed the functions and mechanisms of the complement system in liver injury.
基金Supported by The Research Foundation of Jiangsu Province Administration of Traditional Chinese Medicine,No.MS2023088The Science and Technology Project of Changzhou,No.CE20225040+1 种基金The Research Foundation of Nanjing Medical University Changzhou Medical Center,No.CMCC202311Leading Talent of Changzhou“The 14th Five-Year Plan”High-Level Health Talents Training Project,No.2022CZLJ021.
文摘BACKGROUND Hepatocellular carcinoma(HCC)surveillance is crucial for patients with compensated cirrhosis(CC)and decompensated cirrhosis(DC).Increasing evidence has revealed a connection between thyroid hormone(TH)and HCC,although this relationship remains contentious.Complements and immunoglobulin(Ig),which serve as surrogates of cirrhosis-associated immune dysfunc-tion,are associated with the severity and outcomes of liver cirrhosis(LC).To date,there is a lack of evidence supporting the recommendation of TH,Ig,and com-plement tests in patients at high risk of HCC.AIM To assess the predictive value of TH,Ig,and complements for HCC development.METHODS Data from 142 patients,comprising 72 patients with CC and 70 patients with DC,were analysed as a training set.Among them,100 patients who underwent complement and Ig tests were considered for internal validation.Logistic regression was employed to identify independent risk factors for HCC development.RESULTS The median follow-up duration was 32(24-37 months)months.The incidence of HCC was significantly higher in the DC group(16/70,22.9%)compared to the CC group(3/72,4.2%)(χ^(2)=10.698,P<0.01).Patients with DC exhibited lower total tetraiodothyronine(TT4),total triiodothyronine(TT3),free triiodothyronine,complement C3,and C4(all P<0.01),and higher IgA and IgG(both P<0.01).In both CC and DC patients,TT3 and TT4 positively correlated with alanine transaminase(ALT),aspartate transaminase(AST),and gamma-glutamyl transpeptidase(GGT).IgG positively correlated with IgM,IgA,ALT,and AST,while it negatively correlated with C3 and C4.Multivariable analysis indicated that age,DC status,and GGT were independent risk factors for HCC development.CONCLUSION The predictive value of TH,Ig,and complements for HCC development is suboptimal.Age,DC,and GGT emerge as more significant factors during HCC surveillance in hepatitis B virus-related LC.
文摘Antibody-mediated rejection(AMR)represents a major challenge in kidney transplantation,significantly contributing to tissue injury and graft failure.AMR is primarily driven by donor-specific alloantibodies(DSAs),which recognize and bind to specific target antigens present within the transplanted kidney tissue.Upon binding,these DSAs commonly initiate activation of the complement system within the graft.The activation of the complement cascade sets off a powerful inflammatory response characterized by the recruitment and activation of immune cells,endothelial damage,and subsequent tissue injury.This inflammation underlies many clinical and histological manifestations of AMR,making complement activation a critical player in the disease process.Advancements in our understanding of how complement pathways contribute to kidney graft injury have opened new avenues for therapeutic intervention.Recent research has facilitated the development and application of novel therapies specifically designed to inhibit complement activation.Such targeted complement-inhibitory strategies have shown promise in improving graft outcomes by inhibiting complement-mediated damage and extending graft survival.This review comprehensively discusses the critical role of complement activation in inducing kidney graft injury with a focus on its role in AMR.By elucidating the detailed mechanisms and contributions of complement pathways,the review seeks to enhance the understanding necessary for developing targeted therapeutic interventions to prevent or treat AMR effectively.
基金supported by the Glocal University 30 Project Fund of Gyeongsang National University in 2025.
文摘Scene graph prediction has emerged as a critical task in computer vision,focusing on transforming complex visual scenes into structured representations by identifying objects,their attributes,and the relationships among them.Extending this to 3D semantic scene graph(3DSSG)prediction introduces an additional layer of complexity because it requires the processing of point-cloud data to accurately capture the spatial and volumetric characteristics of a scene.A significant challenge in 3DSSG is the long-tailed distribution of object and relationship labels,causing certain classes to be severely underrepresented and suboptimal performance in these rare categories.To address this,we proposed a fusion prototypical network(FPN),which combines the strengths of conventional neural networks for 3DSSG with a Prototypical Network.The former are known for their ability to handle complex scene graph predictions while the latter excels in few-shot learning scenarios.By leveraging this fusion,our approach enhances the overall prediction accuracy and substantially improves the handling of underrepresented labels.Through extensive experiments using the 3DSSG dataset,we demonstrated that the FPN achieves state-of-the-art performance in 3D scene graph prediction as a single model and effectively mitigates the impact of the long-tailed distribution,providing a more balanced and comprehensive understanding of complex 3D environments.
