Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinct...Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.展开更多
As blockchain technology rapidly evolves,smart contracts have seen widespread adoption in financial transactions and beyond.However,the growing prevalence of malicious Ponzi scheme contracts presents serious security ...As blockchain technology rapidly evolves,smart contracts have seen widespread adoption in financial transactions and beyond.However,the growing prevalence of malicious Ponzi scheme contracts presents serious security threats to blockchain ecosystems.Although numerous detection techniques have been proposed,existing methods suffer from significant limitations,such as class imbalance and insufficient modeling of transaction-related semantic features.To address these challenges,this paper proposes an oversampling-based detection framework for Ponzi smart contracts.We enhance the Adaptive Synthetic Sampling(ADASYN)algorithm by incorporating sample proximity to decision boundaries and ensuring realistic sample distributions.This enhancement facilitates the generation of high-quality minority class samples and effectively mitigates class imbalance.In addition,we design a Contract Transaction Graph(CTG)construction algorithm to preserve key transactional semantics through feature extraction from contract code.A graph neural network(GNN)is then applied for classification.This study employs a publicly available dataset from the XBlock platform,consisting of 318 verified Ponzi contracts and 6498 benign contracts.Sourced from real Ethereum deployments,the dataset reflects diverse application scenarios and captures the varied characteristics of Ponzi schemes.Experimental results demonstrate that our approach achieves an accuracy of 96%,a recall of 92%,and an F1-score of 94%in detecting Ponzi contracts,outperforming state-of-the-art methods.展开更多
Objective:Sepsis exhibits remarkable heterogeneity in disease progression trajectories,and accurate identificationof distinct trajectory-based phenotypes is critical for implementing personalized therapeutic strategie...Objective:Sepsis exhibits remarkable heterogeneity in disease progression trajectories,and accurate identificationof distinct trajectory-based phenotypes is critical for implementing personalized therapeutic strategies and prognostic assessment.However,trajectory clustering analysis of time-series clinical data poses substantial methodological challenges for researchers.This study provides a comprehensive tutorial framework demonstrating six trajectory modeling approaches integrated with proteomic analysis to guide researchers in identifying sepsis subtypes after laparoscopic surgery.Methods:This study employs simulated longitudinal data from 300 septic patients after laparoscopic surgery to demonstrate six trajectory modeling methods(group-based trajectory modeling,latent growth mixture modeling,latent transition analysis,time-varying effect modeling,K-means for longitudinal data,agglomerative hierarchical clustering)for identifying associations between predefinedsequential organ failure assessment trajectories and 25 proteomic biomarkers.Clustering performance was evaluated via multiple metrics,and a biomarker discovery pipeline integrating principal component analysis,random forests,feature selection,and receiver operating characteristic analysis was developed.Results:The six methods demonstrated varying performance in identifying trajectory structures,with each approach exhibiting distinct analytical characteristics.The performance metrics revealed differences across methods,which may inform context-specificmethod selection and interpretation strategies.Conclusion:This study illustrates practical implementations of trajectory modeling approaches under controlled conditions,facilitating informed method selection for clinical researchers.The inclusion of complete R code and integrated proteomics workflows offers a reproducible analytical framework connecting temporal pattern recognition to biomarker discovery.Beyond sepsis,this pipeline-oriented approach may be adapted to diverse clinical scenarios requiring longitudinal disease characterization and precision medicine applications.The comparative analysis reveals that each method has distinct strengths,providing a practical guide for clinical researchers in selecting appropriate methods based on their specificstudy goals and data characteristics.展开更多
Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that ...Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that can predict when turbofan engines will fail.It uses the NASA CMAPSS dataset,which has over 200,000 engine cycles from260 engines.The process begins with systematic preprocessing,which includes imputation,outlier removal,scaling,and labelling of the remaining useful life.Dimensionality is reduced using a hybrid selection method that combines variance filtering,recursive elimination,and gradient-boosted importance scores,yielding a stable set of 10 informative sensors.To mitigate class imbalance,minority cases are oversampled,and class-weighted losses are applied during training.Benchmarking is carried out with logistic regression,gradient boosting,and a recurrent design that integrates gated recurrent units with long short-term memory networks.The Long Short-Term Memory–Gated Recurrent Unit(LSTM–GRU)hybrid achieved the strongest performance with an F1 score of 0.92,precision of 0.93,recall of 0.91,ReceiverOperating Characteristic–AreaUnder the Curve(ROC-AUC)of 0.97,andminority recall of 0.75.Interpretability testing using permutation importance and Shapley values indicates that sensors 13,15,and 11 are the most important indicators of engine wear.The proposed system combines imbalance handling,feature reduction,and Interpretability into a practical design suitable for real industrial settings.展开更多
Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classificati...Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.展开更多
Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from...Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.展开更多
Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting...Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.展开更多
In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic per...In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.展开更多
With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion det...With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion detection models,this paper proposes a Dual-Attention model for NID,which combines Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM)to design two modules:the FocusConV and the TempoNet module.The FocusConV module,which automatically adjusts and weights CNN extracted local features,focuses on local features that are more important for intrusion detection.The TempoNet module focuses on global information,identifies more important features in time steps or sequences,and filters and weights the information globally to further improve the accuracy and robustness of NID.Meanwhile,in order to solve the class imbalance problem in the dataset,the EQL v2 method is used to compute the class weights of each class and to use them in the loss computation,which optimizes the performance of the model on the class imbalance problem.Extensive experiments were conducted on the NSL-KDD,UNSW-NB15,and CIC-DDos2019 datasets,achieving average accuracy rates of 99.66%,87.47%,and 99.39%,respectively,demonstrating excellent detection accuracy and robustness.The model also improves the detection performance of minority classes in the datasets.On the UNSW-NB15 dataset,the detection rates for Analysis,Exploits,and Shellcode attacks increased by 7%,7%,and 10%,respectively,demonstrating the Dual-Attention CNN-BiLSTM model’s excellent performance in NID.展开更多
The high polymorphism of histocompatibility complex class Ⅱ(MHC-Ⅱ)alleles and limited immunopeptidomic data hinder pan-species epitope prediction.In this study,leveraging the predictive power of AlphaFold(AF)and the...The high polymorphism of histocompatibility complex class Ⅱ(MHC-Ⅱ)alleles and limited immunopeptidomic data hinder pan-species epitope prediction.In this study,leveraging the predictive power of AlphaFold(AF)and the conserved structural features of the core region of MHC-Ⅱ-binding peptides,derived from a comprehensive analysis of MHC-Ⅱ structure data in the PDB database,we developed a new tool,AF-prediction(AF-pred),with explicit quantitative criteria for MHC-Ⅱ-restricted epitope prediction.We validated AF-pred across human,porcine,bovine,and bat MHC-Ⅱ molecules through large-scale in silico analyses using known immunopeptidome datasets(1000 positive and 1000 negative antigenic peptides),together with in vitro binding assays and crystallographic characterization of newly predicted epitopes.Using uncharacterized bat MHC-Ⅱ structures,we demonstrated that AF-pred’s amino-acid interaction prediction underpins its pan-prediction capability and the underlying rationale of the method.Conversely,this characteristic limits the prediction of atypical MHC-Ⅱ peptide-binding modes.Compared with sequence-based tools,AF-pred demonstrates enhanced cross-species MHC-Ⅱ binding prediction,with higher accuracy and interpretability,and further reveals that iterative AF updates improve AF-pred performance.AF-pred has the potential to facilitate the development of novel T-cell epitope vaccines and advance the“One Health”initiative.展开更多
师幼互动质量不仅是幼儿园教育质量的关键要素,还是我国学前教育内涵式发展的重要方面。运用文献资料、逻辑分析等方法,从CLASS理论视域下探析师幼互动的关联逻辑、困境与创新路径。研究发现:CLASS理论与师幼互动的关联逻辑在于理论同...师幼互动质量不仅是幼儿园教育质量的关键要素,还是我国学前教育内涵式发展的重要方面。运用文献资料、逻辑分析等方法,从CLASS理论视域下探析师幼互动的关联逻辑、困境与创新路径。研究发现:CLASS理论与师幼互动的关联逻辑在于理论同源性与实践契合性。CLASS视域下师幼互动面临情感支持的缺乏、课堂组织的失衡、教学支持的脱节的现实困境。基于此,提出情感交融,以情育情;协调秩序,灵活组织;回应需求,弥合引导的创新路径。The quality of teacher-child interaction is not only a key element of the quality of kindergarten education, but also an important aspect of the connotative development of pre-school education in China. Using literature, logical analysis and other methods, we analyze the associated logic, dilemma and innovative path of teacher-child interaction from the perspective of CLASS theory. The study found that the logic of CLASS theory and teacher-child interaction lies in the homology of the theory and the fit of practice, and that teacher-child interaction in the CLASS perspective faces the dilemmas of lack of emotional support, imbalance of classroom organization, and disconnection of pedagogical support. Based on this, we propose innovative paths of emotional integration, nurturing emotions with emotions, coordinating order, flexible organization, responding to needs, and bridging guidance.展开更多
Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accu...Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.展开更多
The prevalence of Class Ⅲ malocclusion varies among different countries and regions. The populations from Southeast Asian countries (Chinese and Malaysian) showed the highest prevalence rate of 15.8%, which can serio...The prevalence of Class Ⅲ malocclusion varies among different countries and regions. The populations from Southeast Asian countries (Chinese and Malaysian) showed the highest prevalence rate of 15.8%, which can seriously affect oral function, facial appearance, and mental health. As anterior crossbite tends to worsen with growth, early orthodontic treatment can harness growth potential to normalize maxillofacial development or reduce skeletal malformation severity, thereby reducing the difficulty and shortening the treatment cycle of later-stage treatment. This is beneficial for the physical and mental growth of children. Therefore,early orthodontic treatment for Class Ⅲ malocclusion is particularly important. Determining the optimal timing for early orthodontic treatment requires a comprehensive assessment of clinical manifestations, dental age, and skeletal age, and can lead to better results with less effort. Currently, standardized treatment guidelines for early orthodontic treatment of Class Ⅲ malocclusion are lacking. This review provides a comprehensive summary of the etiology, clinical manifestations, classification, and early orthodontic techniques for Class Ⅲ malocclusion, along with systematic discussions on selecting early treatment plans. The purpose of this expert consensus is to standardize clinical practices and improve the treatment outcomes of Class Ⅲ malocclusion through early orthodontic treatment.展开更多
Olfactory ensheathing glia promote axonal regeneration in the mammalian central nervous system,including retinal ganglion cell axonal growth through the injured optic nerve.Still,it is unknown whether olfactory enshea...Olfactory ensheathing glia promote axonal regeneration in the mammalian central nervous system,including retinal ganglion cell axonal growth through the injured optic nerve.Still,it is unknown whether olfactory ensheathing glia also have neuroprotective properties.Olfactory ensheathing glia express brain-derived neurotrophic factor,one of the best neuroprotectants for axotomized retinal ganglion cells.Therefore,we aimed to investigate the neuroprotective capacity of olfactory ensheating glia after optic nerve crush.Olfactory ensheathing glia cells from an established rat immortalized clonal cell line,TEG3,were intravitreally injected in intact and axotomized retinas in syngeneic and allogeneic mode with or without microglial inhibition or immunosuppressive treatments.Anatomical and gene expression analyses were performed.Olfactory bulb-derived primary olfactory ensheathing glia and TEG3 express major histocompatibility complex classⅡmolecules.Allogeneically and syngenically transplanted TEG3 cells survived in the vitreous for up to 21 days,forming an epimembrane.In axotomized retinas,only the allogeneic TEG3 transplant rescued retinal ganglion cells at 7 days but not at 21 days.In these retinas,microglial anatomical activation was higher than after optic nerve crush alone.In intact retinas,both transplants activated microglial cells and caused retinal ganglion cell death at 21 days,a loss that was higher after allotransplantation,triggered by pyroptosis and partially rescued by microglial inhibition or immunosuppression.However,neuroprotection of axotomized retinal ganglion cells did not improve with these treatments.The different neuroprotective properties,different toxic effects,and different responses to microglial inhibitory treatments of olfactory ensheathing glia in the retina depending on the type of transplant highlight the importance of thorough preclinical studies to explore these variables.展开更多
Credit risk assessment is a crucial task in bank risk management.By making lending decisions based on credit risk assessment results,banks can reduce the probability of non-performing loans.However,class imbalance in ...Credit risk assessment is a crucial task in bank risk management.By making lending decisions based on credit risk assessment results,banks can reduce the probability of non-performing loans.However,class imbalance in bank credit default datasets limits the predictive performance of traditional machine learning and deep learning models.To address this issue,this study employs the conditional variational autoencoder-Wasserstein generative adversarial network with gradient penalty(CVAE-WGAN-gp)model for oversampling,generating samples similar to the original default customer data to enhance model prediction performance.To evaluate the quality of the data generated by the CVAE-WGAN-gp model,we selected several bank loan datasets for experimentation.The experimental results demonstrate that using the CVAE-WGAN-gp model for oversampling can significantly improve the predictive performance in credit risk assessment problems.展开更多
China’s growing number of co#ee consumers helps to boost Uganda’s coffee production In recent years,China has witnessed a significant surge in co!ee consumption,driven by a growing middle class and increasing demand...China’s growing number of co#ee consumers helps to boost Uganda’s coffee production In recent years,China has witnessed a significant surge in co!ee consumption,driven by a growing middle class and increasing demand for specialty brews.This trend has had a profound impact on co!ee-producing countries around the world,including Uganda.展开更多
文摘Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.
基金supported by the Key Project of Joint Fund of the National Natural Science Foundation of China“Research on Key Technologies and Demonstration Applications for Trusted and Secure Data Circulation and Trading”(U24A20241)the National Natural Science Foundation of China“Research on Trusted Theories and Key Technologies of Data Security Trading Based on Blockchain”(62202118)+4 种基金the Major Scientific and Technological Special Project of Guizhou Province([2024]014)Scientific and Technological Research Projects from the Guizhou Education Department(Qian jiao ji[2023]003)the Hundred-Level Innovative Talent Project of the Guizhou Provincial Science and Technology Department(Qiankehe Platform Talent-GCC[2023]018)the Major Project of Guizhou Province“Research and Application of Key Technologies for Trusted Large Models Oriented to Public Big Data”(Qiankehe Major Project[2024]003)the Guizhou Province Computational Power Network Security Protection Science and Technology Innovation Talent Team(Qiankehe Talent CXTD[2025]029).
文摘As blockchain technology rapidly evolves,smart contracts have seen widespread adoption in financial transactions and beyond.However,the growing prevalence of malicious Ponzi scheme contracts presents serious security threats to blockchain ecosystems.Although numerous detection techniques have been proposed,existing methods suffer from significant limitations,such as class imbalance and insufficient modeling of transaction-related semantic features.To address these challenges,this paper proposes an oversampling-based detection framework for Ponzi smart contracts.We enhance the Adaptive Synthetic Sampling(ADASYN)algorithm by incorporating sample proximity to decision boundaries and ensuring realistic sample distributions.This enhancement facilitates the generation of high-quality minority class samples and effectively mitigates class imbalance.In addition,we design a Contract Transaction Graph(CTG)construction algorithm to preserve key transactional semantics through feature extraction from contract code.A graph neural network(GNN)is then applied for classification.This study employs a publicly available dataset from the XBlock platform,consisting of 318 verified Ponzi contracts and 6498 benign contracts.Sourced from real Ethereum deployments,the dataset reflects diverse application scenarios and captures the varied characteristics of Ponzi schemes.Experimental results demonstrate that our approach achieves an accuracy of 96%,a recall of 92%,and an F1-score of 94%in detecting Ponzi contracts,outperforming state-of-the-art methods.
基金funding from the China National Key Research and Development Program(No.2023YFC3603104)the National Natural Science Foundation of China(Nos.82472243 and 82272180)+6 种基金the Fundamental Research Funds for the Central Universities(No.226-2025-00024)the Huadong Medicine Joint Funds of the Zhejiang Provincial Natural Science Foundation of China(No.LHDMD24H150001)the Key Research&Development Project of Zhejiang Province(No.2024C03240)a collaborative scientific project co-established by the Science and Technology Department of the National Administration of Traditional Chinese Medicine and the Zhejiang Provincial Administration of Traditional Chinese Medicine(No.GZY-ZJ-KJ-24082)he General Health Science and Technology Program of Zhejiang Province(No.2024KY1099)the Project of Zhejiang University Longquan Innovation Center(No.ZJDXLQCXZCJBGS2024016)Wu Jieping Medical Foundation Special Research Grant(No.320.6750.2024-23-07).
文摘Objective:Sepsis exhibits remarkable heterogeneity in disease progression trajectories,and accurate identificationof distinct trajectory-based phenotypes is critical for implementing personalized therapeutic strategies and prognostic assessment.However,trajectory clustering analysis of time-series clinical data poses substantial methodological challenges for researchers.This study provides a comprehensive tutorial framework demonstrating six trajectory modeling approaches integrated with proteomic analysis to guide researchers in identifying sepsis subtypes after laparoscopic surgery.Methods:This study employs simulated longitudinal data from 300 septic patients after laparoscopic surgery to demonstrate six trajectory modeling methods(group-based trajectory modeling,latent growth mixture modeling,latent transition analysis,time-varying effect modeling,K-means for longitudinal data,agglomerative hierarchical clustering)for identifying associations between predefinedsequential organ failure assessment trajectories and 25 proteomic biomarkers.Clustering performance was evaluated via multiple metrics,and a biomarker discovery pipeline integrating principal component analysis,random forests,feature selection,and receiver operating characteristic analysis was developed.Results:The six methods demonstrated varying performance in identifying trajectory structures,with each approach exhibiting distinct analytical characteristics.The performance metrics revealed differences across methods,which may inform context-specificmethod selection and interpretation strategies.Conclusion:This study illustrates practical implementations of trajectory modeling approaches under controlled conditions,facilitating informed method selection for clinical researchers.The inclusion of complete R code and integrated proteomics workflows offers a reproducible analytical framework connecting temporal pattern recognition to biomarker discovery.Beyond sepsis,this pipeline-oriented approach may be adapted to diverse clinical scenarios requiring longitudinal disease characterization and precision medicine applications.The comparative analysis reveals that each method has distinct strengths,providing a practical guide for clinical researchers in selecting appropriate methods based on their specificstudy goals and data characteristics.
基金supported by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia Grant No.KFU253765.
文摘Most predictive maintenance studies have emphasized accuracy but provide very little focus on Interpretability or deployment readiness.This study improves on prior methods by developing a small yet robust system that can predict when turbofan engines will fail.It uses the NASA CMAPSS dataset,which has over 200,000 engine cycles from260 engines.The process begins with systematic preprocessing,which includes imputation,outlier removal,scaling,and labelling of the remaining useful life.Dimensionality is reduced using a hybrid selection method that combines variance filtering,recursive elimination,and gradient-boosted importance scores,yielding a stable set of 10 informative sensors.To mitigate class imbalance,minority cases are oversampled,and class-weighted losses are applied during training.Benchmarking is carried out with logistic regression,gradient boosting,and a recurrent design that integrates gated recurrent units with long short-term memory networks.The Long Short-Term Memory–Gated Recurrent Unit(LSTM–GRU)hybrid achieved the strongest performance with an F1 score of 0.92,precision of 0.93,recall of 0.91,ReceiverOperating Characteristic–AreaUnder the Curve(ROC-AUC)of 0.97,andminority recall of 0.75.Interpretability testing using permutation importance and Shapley values indicates that sensors 13,15,and 11 are the most important indicators of engine wear.The proposed system combines imbalance handling,feature reduction,and Interpretability into a practical design suitable for real industrial settings.
基金supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF),funded by the Ministry of Education(RS-2023-00249743).
文摘Most Convolutional Neural Network(CNN)interpretation techniques visualize only the dominant cues that the model relies on,but there is no guarantee that these represent all the evidence the model uses for classification.This limitation becomes critical when hidden secondary cues—potentially more meaningful than the visualized ones—remain undiscovered.This study introduces CasCAM(Cascaded Class Activation Mapping)to address this fundamental limitation through counterfactual reasoning.By asking“if this dominant cue were absent,what other evidence would the model use?”,CasCAM progressively masks the most salient features and systematically uncovers the hierarchy of classification evidence hidden beneath them.Experimental results demonstrate that CasCAM effectively discovers the full spectrum of reasoning evidence and can be universally applied with nine existing interpretation methods.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)[RS-2021-II211341,Artificial Intelligence Graduate School Program(Chung-Ang University)],and by the Chung-Ang University Graduate Research Scholarship in 2024.
文摘Legal case classification involves the categorization of legal documents into predefined categories,which facilitates legal information retrieval and case management.However,real-world legal datasets often suffer from class imbalances due to the uneven distribution of case types across legal domains.This leads to biased model performance,in the form of high accuracy for overrepresented categories and underperformance for minority classes.To address this issue,in this study,we propose a data augmentation method that masks unimportant terms within a document selectively while preserving key terms fromthe perspective of the legal domain.This approach enhances data diversity and improves the generalization capability of conventional models.Our experiments demonstrate consistent improvements achieved by the proposed augmentation strategy in terms of accuracy and F1 score across all models,validating the effectiveness of the proposed method in legal case classification.
基金National Key Research and Development Program of China,No.2023YFC3006704National Natural Science Foundation of China,No.42171047CAS-CSIRO Partnership Joint Project of 2024,No.177GJHZ2023097MI。
文摘Accurate prediction of flood events is important for flood control and risk management.Machine learning techniques contributed greatly to advances in flood predictions,and existing studies mainly focused on predicting flood resource variables using single or hybrid machine learning techniques.However,class-based flood predictions have rarely been investigated,which can aid in quickly diagnosing comprehensive flood characteristics and proposing targeted management strategies.This study proposed a prediction approach of flood regime metrics and event classes coupling machine learning algorithms with clustering-deduced membership degrees.Five algorithms were adopted for this exploration.Results showed that the class membership degrees accurately determined event classes with class hit rates up to 100%,compared with the four classes clustered from nine regime metrics.The nonlinear algorithms(Multiple Linear Regression,Random Forest,and least squares-Support Vector Machine)outperformed the linear techniques(Multiple Linear Regression and Stepwise Regression)in predicting flood regime metrics.The proposed approach well predicted flood event classes with average class hit rates of 66.0%-85.4%and 47.2%-76.0%in calibration and validation periods,respectively,particularly for the slow and late flood events.The predictive capability of the proposed prediction approach for flood regime metrics and classes was considerably stronger than that of hydrological modeling approach.
基金supported by the Funds for Central-Guided Local Science and Technology Development(Grant No.202407AC110005)Key Technologies for the Construction of a Whole-Process Intelligent Service System for Neuroendocrine Neoplasm.Supported by 2023 Opening Research Fund of Yunnan Key Laboratory of Digital Communications(YNJTKFB-20230686,YNKLDC-KFKT-202304).
文摘In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.
基金supported by the High-Level Talent Foundation of Jinling Institute of Technology(grant number.JIT-B-202413).
文摘With the increasing severity of network security threats,Network Intrusion Detection(NID)has become a key technology to ensure network security.To address the problem of low detection rate of traditional intrusion detection models,this paper proposes a Dual-Attention model for NID,which combines Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM)to design two modules:the FocusConV and the TempoNet module.The FocusConV module,which automatically adjusts and weights CNN extracted local features,focuses on local features that are more important for intrusion detection.The TempoNet module focuses on global information,identifies more important features in time steps or sequences,and filters and weights the information globally to further improve the accuracy and robustness of NID.Meanwhile,in order to solve the class imbalance problem in the dataset,the EQL v2 method is used to compute the class weights of each class and to use them in the loss computation,which optimizes the performance of the model on the class imbalance problem.Extensive experiments were conducted on the NSL-KDD,UNSW-NB15,and CIC-DDos2019 datasets,achieving average accuracy rates of 99.66%,87.47%,and 99.39%,respectively,demonstrating excellent detection accuracy and robustness.The model also improves the detection performance of minority classes in the datasets.On the UNSW-NB15 dataset,the detection rates for Analysis,Exploits,and Shellcode attacks increased by 7%,7%,and 10%,respectively,demonstrating the Dual-Attention CNN-BiLSTM model’s excellent performance in NID.
基金supported by the National Key Research and Development Program of China(grant number 2021YFD1800100 to N.Z.)the National Natural Science Foundation of China(grant number 32172871 to N.Z.)the 2115 Talent Development Program of China Agricultural University to N.Z.This study was supported by High-performance Computing Platform of China Agricultural University.
文摘The high polymorphism of histocompatibility complex class Ⅱ(MHC-Ⅱ)alleles and limited immunopeptidomic data hinder pan-species epitope prediction.In this study,leveraging the predictive power of AlphaFold(AF)and the conserved structural features of the core region of MHC-Ⅱ-binding peptides,derived from a comprehensive analysis of MHC-Ⅱ structure data in the PDB database,we developed a new tool,AF-prediction(AF-pred),with explicit quantitative criteria for MHC-Ⅱ-restricted epitope prediction.We validated AF-pred across human,porcine,bovine,and bat MHC-Ⅱ molecules through large-scale in silico analyses using known immunopeptidome datasets(1000 positive and 1000 negative antigenic peptides),together with in vitro binding assays and crystallographic characterization of newly predicted epitopes.Using uncharacterized bat MHC-Ⅱ structures,we demonstrated that AF-pred’s amino-acid interaction prediction underpins its pan-prediction capability and the underlying rationale of the method.Conversely,this characteristic limits the prediction of atypical MHC-Ⅱ peptide-binding modes.Compared with sequence-based tools,AF-pred demonstrates enhanced cross-species MHC-Ⅱ binding prediction,with higher accuracy and interpretability,and further reveals that iterative AF updates improve AF-pred performance.AF-pred has the potential to facilitate the development of novel T-cell epitope vaccines and advance the“One Health”initiative.
文摘师幼互动质量不仅是幼儿园教育质量的关键要素,还是我国学前教育内涵式发展的重要方面。运用文献资料、逻辑分析等方法,从CLASS理论视域下探析师幼互动的关联逻辑、困境与创新路径。研究发现:CLASS理论与师幼互动的关联逻辑在于理论同源性与实践契合性。CLASS视域下师幼互动面临情感支持的缺乏、课堂组织的失衡、教学支持的脱节的现实困境。基于此,提出情感交融,以情育情;协调秩序,灵活组织;回应需求,弥合引导的创新路径。The quality of teacher-child interaction is not only a key element of the quality of kindergarten education, but also an important aspect of the connotative development of pre-school education in China. Using literature, logical analysis and other methods, we analyze the associated logic, dilemma and innovative path of teacher-child interaction from the perspective of CLASS theory. The study found that the logic of CLASS theory and teacher-child interaction lies in the homology of the theory and the fit of practice, and that teacher-child interaction in the CLASS perspective faces the dilemmas of lack of emotional support, imbalance of classroom organization, and disconnection of pedagogical support. Based on this, we propose innovative paths of emotional integration, nurturing emotions with emotions, coordinating order, flexible organization, responding to needs, and bridging guidance.
基金funded by the Youth Fund of the National Natural Science Foundation of China(Grant No.42261070).
文摘Spectrum-based fault localization (SBFL) generates a ranked list of suspicious elements by using the program execution spectrum, but the excessive number of elements ranked in parallel results in low localization accuracy. Most researchers consider intra-class dependencies to improve localization accuracy. However, some studies show that inter-class method call type faults account for more than 20%, which means such methods still have certain limitations. To solve the above problems, this paper proposes a two-phase software fault localization based on relational graph convolutional neural networks (Two-RGCNFL). Firstly, in Phase 1, the method call dependence graph (MCDG) of the program is constructed, the intra-class and inter-class dependencies in MCDG are extracted by using the relational graph convolutional neural network, and the classifier is used to identify the faulty methods. Then, the GraphSMOTE algorithm is improved to alleviate the impact of class imbalance on classification accuracy. Aiming at the problem of parallel ranking of element suspicious values in traditional SBFL technology, in Phase 2, Doc2Vec is used to learn static features, while spectrum information serves as dynamic features. A RankNet model based on siamese multi-layer perceptron is constructed to score and rank statements in the faulty method. This work conducts experiments on 5 real projects of Defects4J benchmark. Experimental results show that, compared with the traditional SBFL technique and two baseline methods, our approach improves the Top-1 accuracy by 262.86%, 29.59% and 53.01%, respectively, which verifies the effectiveness of Two-RGCNFL. Furthermore, this work verifies the importance of inter-class dependencies through ablation experiments.
文摘The prevalence of Class Ⅲ malocclusion varies among different countries and regions. The populations from Southeast Asian countries (Chinese and Malaysian) showed the highest prevalence rate of 15.8%, which can seriously affect oral function, facial appearance, and mental health. As anterior crossbite tends to worsen with growth, early orthodontic treatment can harness growth potential to normalize maxillofacial development or reduce skeletal malformation severity, thereby reducing the difficulty and shortening the treatment cycle of later-stage treatment. This is beneficial for the physical and mental growth of children. Therefore,early orthodontic treatment for Class Ⅲ malocclusion is particularly important. Determining the optimal timing for early orthodontic treatment requires a comprehensive assessment of clinical manifestations, dental age, and skeletal age, and can lead to better results with less effort. Currently, standardized treatment guidelines for early orthodontic treatment of Class Ⅲ malocclusion are lacking. This review provides a comprehensive summary of the etiology, clinical manifestations, classification, and early orthodontic techniques for Class Ⅲ malocclusion, along with systematic discussions on selecting early treatment plans. The purpose of this expert consensus is to standardize clinical practices and improve the treatment outcomes of Class Ⅲ malocclusion through early orthodontic treatment.
基金supported by the Spanish Ministry of Economy and Competitiveness,No.PID2019-106498GB-I00(to MVS)the Instituto de Salud CarlosⅢ,Fondo Europeo de Desarrollo Regional“Una manera de hacer Europa”,No.PI19/00071(to MAB)+1 种基金Ministerio de Ciencia e Innovación Project,No.SAF2017-82736-C2-1-R(to MTMF)in Universidad Autónoma de MadridFundación Universidad Francisco de Vitoria(to JS)。
文摘Olfactory ensheathing glia promote axonal regeneration in the mammalian central nervous system,including retinal ganglion cell axonal growth through the injured optic nerve.Still,it is unknown whether olfactory ensheathing glia also have neuroprotective properties.Olfactory ensheathing glia express brain-derived neurotrophic factor,one of the best neuroprotectants for axotomized retinal ganglion cells.Therefore,we aimed to investigate the neuroprotective capacity of olfactory ensheating glia after optic nerve crush.Olfactory ensheathing glia cells from an established rat immortalized clonal cell line,TEG3,were intravitreally injected in intact and axotomized retinas in syngeneic and allogeneic mode with or without microglial inhibition or immunosuppressive treatments.Anatomical and gene expression analyses were performed.Olfactory bulb-derived primary olfactory ensheathing glia and TEG3 express major histocompatibility complex classⅡmolecules.Allogeneically and syngenically transplanted TEG3 cells survived in the vitreous for up to 21 days,forming an epimembrane.In axotomized retinas,only the allogeneic TEG3 transplant rescued retinal ganglion cells at 7 days but not at 21 days.In these retinas,microglial anatomical activation was higher than after optic nerve crush alone.In intact retinas,both transplants activated microglial cells and caused retinal ganglion cell death at 21 days,a loss that was higher after allotransplantation,triggered by pyroptosis and partially rescued by microglial inhibition or immunosuppression.However,neuroprotection of axotomized retinal ganglion cells did not improve with these treatments.The different neuroprotective properties,different toxic effects,and different responses to microglial inhibitory treatments of olfactory ensheathing glia in the retina depending on the type of transplant highlight the importance of thorough preclinical studies to explore these variables.
基金supported by National Key R&D Program of China(2022YFA1008000)the National Natural Science Foundation of China(12571297,12101585)+1 种基金the CAS Talent Introduction Program(Category B)the Young Elite Scientist Sponsorship Program by CAST(YESS20220125).
文摘Credit risk assessment is a crucial task in bank risk management.By making lending decisions based on credit risk assessment results,banks can reduce the probability of non-performing loans.However,class imbalance in bank credit default datasets limits the predictive performance of traditional machine learning and deep learning models.To address this issue,this study employs the conditional variational autoencoder-Wasserstein generative adversarial network with gradient penalty(CVAE-WGAN-gp)model for oversampling,generating samples similar to the original default customer data to enhance model prediction performance.To evaluate the quality of the data generated by the CVAE-WGAN-gp model,we selected several bank loan datasets for experimentation.The experimental results demonstrate that using the CVAE-WGAN-gp model for oversampling can significantly improve the predictive performance in credit risk assessment problems.
文摘China’s growing number of co#ee consumers helps to boost Uganda’s coffee production In recent years,China has witnessed a significant surge in co!ee consumption,driven by a growing middle class and increasing demand for specialty brews.This trend has had a profound impact on co!ee-producing countries around the world,including Uganda.
