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
In today's connected world,the generation of massive streaming data across diverse domains has become commonplace.In the presence of concept drift,class imbalance,label scarcity,and new class emergence,these chall...In today's connected world,the generation of massive streaming data across diverse domains has become commonplace.In the presence of concept drift,class imbalance,label scarcity,and new class emergence,these challenges jointly degrade representation stability,bias learning toward outdated distributions,and reduce the resilience and reliability of detection in dynamic environments.This paper proposes a streaming classincremental learning(SCIL)framework to address these issues.The SCIL framework integrates an autoencoder(AE)with a multi-layer perceptron for multi-class prediction,employs a dual-loss strategy(classification and reconstruction)for prediction and new class detection,uses corrected pseudo-labels for online training,manages classes with queues,and applies oversampling to handle imbalance.The rationale behind the method's structure is elucidated through ablation studies,and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance,incremental classes,and concept drifts.Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods.In line with our commitment to Open Science,we make our code and datasets available to the community.展开更多
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
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
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
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
Natural gas hydrate in Class Ⅰ reservoirs holds significant commercial potential,as demonstrated by production trials in the South China Sea.However,experimental studies have focused largely on Class Ⅲ systems,with ...Natural gas hydrate in Class Ⅰ reservoirs holds significant commercial potential,as demonstrated by production trials in the South China Sea.However,experimental studies have focused largely on Class Ⅲ systems,with Class Ⅰ/Ⅱ reservoirs remaining underrepresented due to the difficulties in simulating the geothermal gradient and interlayer interactions.This study investigates depressurization performance across all three classes using a novel 360°rotatable reactor with segmented temperature control,enabling precise simulation of reservoir conditions.Results reveal:(i)Class Ⅰ shows two-stage gas production,with 50%from early free gas enabling rapid depressurization,followed by dissociated gas dominance.They achieve 38.4%-78.3%higher cumulative production and superior gas-to-water ratios due to efficient energy use.(ii)The free gas layer in Class Ⅰ accelerates pressure and heat transfer.Class Ⅱ’s water layer provides sensible heat but causes water blocking,impairing heat flow.Class Ⅲ exhibits rapid initial dissociation but a quick decline without fluid support.(iii)Low temperature,low hydrate saturation,and high production pressure collectively reduce efficiency by increasing flow resistance,limiting gas supply,and reducing dissociation drive.Over-depressurization risks hydrate reformation and ice blockage.This work bridges experimental gaps for Class Ⅰ/Ⅱ reservoirs,offering key insights for optimizing recovery.展开更多
Given the growing number of vehicle accidents caused by unintended acceleration and braking failure,verifying Sudden Unintended Acceleration(SUA)incidents has become a persistent challenge.A central issue of debate is...Given the growing number of vehicle accidents caused by unintended acceleration and braking failure,verifying Sudden Unintended Acceleration(SUA)incidents has become a persistent challenge.A central issue of debate is whether such events stem frommechanical malfunctions or driver pedalmisapplications.However,existing verification procedures implemented by vehiclemanufacturers often involve closed tests after vehicle recalls;thus raising ongoing concerns about reliability and transparency.Consequently,there is a growing need for a user-driven framework that enables independent data acquisition and verification.Although previous studies have addressed SUA detection using deep learning,few have explored howclass granularity optimization affects power efficiency and inference performance in real-time Edge AI systems.To address this problem,this work presents a cloud-assisted artificial intelligence(AI)solution for the reliable verification of SUA occurrences.The proposed system integrates multimodal sensor streams including camera-based foot images,On-Board Diagnostics II(OBD-II)signals,and six-axismeasurements to determine whether the brake pedal was actually engaged at themoment of a suspected SUA.Beyond image acquisition,convolutional neural network(CNN)models perform real-time inference to classify the driver’s pedal operation states with the resulting outputs transmitted and archived in the cloud.A dedicated dataset of brake and accelerator pedal images was collected from 15 vehicles produced by 6 domestic and international manufacturers.Using this dataset,transfer learning techniques were applied to compare and analyze model performance and generalization as the CNN class granularity varied from coarse to fine levels.Furthermore,classification performance was evaluated in terms of latency and power efficiency under different class configurations.The experimental results demonstrated that the proposed solution identified the driver’s pedal behavior accurately and promptly,with the two-class model achieving the highest F1-score and accuracy among all granularity settings.展开更多
This paper addresses a fundamental question in rock mechanics:Are there Class Ⅱ rocks?The historical development of servo-controlled rock testing machines is reviewed,followed by a brief review of some stiff testing ...This paper addresses a fundamental question in rock mechanics:Are there Class Ⅱ rocks?The historical development of servo-controlled rock testing machines is reviewed,followed by a brief review of some stiff testing machines.The pioneering work of some researchers is reviewed,and the misconception of classifying rocks into Class Ⅰ and Class Ⅱ is discussed.The mechanism of post-peak Class Ⅱ behavior is discussed based on some recent test results.When a brittle hard rock is tested using a soft testing machine under axial-strain-controlled loading,violent failure can occur when the peak strength is reached,and the post-peak stress-strain curve cannot be obtained.However,a Class Ⅱ post-peak stress-strain curve can be obtained when the rock is tested under lateral-strain-controlled loading.If a stiff testing machine is used,Class Ⅰ and Class Ⅱ post-peak stress-strain curves will be obtained under axial-and lateral-strain-controlled loadings,respectively.It is therefore not appropriate to classify rocks into Class Ⅰ or Class Ⅱ rocks.The influences of other conditions,such as rock type,confinement,and specimen height-to-diameter ratio,on the type(Class Ⅰ or Class Ⅱ)of post-peak stress-strain curves are also discussed.Finally,some misconceptions in the rock mechanics community,stemming from the concept of“Class Ⅱ rock”,are discussed.By clarifying these concepts related to Class Ⅰ and Class Ⅱ behaviors,this paper seeks to clarify misunderstandings and misapplications related to post-peak strength and deformation properties in the field.展开更多
Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional...Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.展开更多
This study demonstrates the complexity and importance of water quality as a measure of the health and sustainability of ecosystems that directly influence biodiversity,human health,and the world economy.The predictabi...This study demonstrates the complexity and importance of water quality as a measure of the health and sustainability of ecosystems that directly influence biodiversity,human health,and the world economy.The predictability of water quality thus plays a crucial role in managing our ecosystems to make informed decisions and,hence,proper environmental management.This study addresses these challenges by proposing an effective machine learning methodology applied to the“Water Quality”public dataset.The methodology has modeled the dataset suitable for providing prediction classification analysis with high values of the evaluating parameters such as accuracy,sensitivity,and specificity.The proposed methodology is based on two novel approaches:(a)the SMOTE method to deal with unbalanced data and(b)the skillfully involved classical machine learning models.This paper uses Random Forests,Decision Trees,XGBoost,and Support Vector Machines because they can handle large datasets,train models for handling skewed datasets,and provide high accuracy in water quality classification.A key contribution of this work is the use of custom sampling strategies within the SMOTE approach,which significantly enhanced performance metrics and improved class imbalance handling.The results demonstrate significant improvements in predictive performance,achieving the highest reported metrics:accuracy(98.92%vs.96.06%),sensitivity(98.3%vs.71.26%),and F1 score(98.37%vs.79.74%)using the XGBoost model.These improvements underscore the effectiveness of our custom SMOTE sampling strategies in addressing class imbalance.The findings contribute to environmental management by enabling ecology specialists to develop more accurate strategies for monitoring,assessing,and managing drinking water quality,ensuring better ecosystem and public health outcomes.展开更多
Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,l...Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.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
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
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
In this study we review the occurrence of different types (A, B, C, M, and X classes) of solar flares during different solar cycle phases from 1996 to 2019 covering the solar cycles 23 and 24. During this period, a to...In this study we review the occurrence of different types (A, B, C, M, and X classes) of solar flares during different solar cycle phases from 1996 to 2019 covering the solar cycles 23 and 24. During this period, a total of 19,126 solar flares were observed regardless the class: 3548 flares in solar cycle 23 (SC23) and 15,668 flares in solar cycle 24 (SC24). Our findings show that the cycle 23 has observed the highest occurrences of M-class and X-class flares, whereas cycle 24 has pointed out a predominance of B-class and C-class flares throughout its different phases. The results indicate that the cycle 23 was magnetically more intense than cycle 24, leading to more powerful solar flares and more frequent geomagnetic storms, capable of generating significant electromagnetic emissions that can affect satellites and GPS signals. The decrease in intense solar flares during cycle 24 compared to cycle 23 reflects an evolution in solar activity patterns over time.展开更多
Natural gas hydrate widely exists in the South China Sea as clean energy.A three-phase transition layer widely exists in low permeability Class I hydrates in the Shenhu offshore area.Therefore,taking into account the ...Natural gas hydrate widely exists in the South China Sea as clean energy.A three-phase transition layer widely exists in low permeability Class I hydrates in the Shenhu offshore area.Therefore,taking into account the low-permeability characteristics with an average permeability of 5.5 mD and moderate heterogeneity,a 3-D geological model of heterogeneous Class I hydrate reservoirs with three-phase transition layers is established by Kriging interpolation and stochastic modeling method,and a numerical simulation model is used to describe the depressurization production performance of the reservoir.With the development of depressurization,a specific range of complete decomposition zones appear both in the hydrate and transition layers.The entire decomposition zone of the whole reservoir tends to outward and upward diffusion.There is apparent methane escape in the three-phase transition layer.Due to the improvement of local permeability caused by the phase transition of hydrate dissociation,some methane accumulation occurs at the bottom of the hydrate layer,forming a local methane enrichment zone.The methane migration trends in reservoirs are mainly characterized by movement toward production wells and hydrate layers under the influence of gravity.However,due to the permeability limitation of hydrate reservoirs,many fluids have not been effectively produced and remain in the reservoir.Therefore,to improve the effective pressure drop of the reservoir,the perforation method and pressure reduction method were optimized by analyzing the influencing factors based on the gas production rate.The comparative study demonstrates that perforating through the free gas layer combined with one-time depressurization can enhance the effective depressurization and improve production performance.The gas production rate from perforating through the free gas layer can be twice as high as that from perforating through the transition layer.This study can provide theoretical support for the utilization of marine energy.展开更多
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supported by the European Research Council(ERC)under Grant Agreement No.951424(Water-Futures)by the Republic of Cyprus through the Deputy Ministry of Research,Innovation and Digital Policy.
文摘In today's connected world,the generation of massive streaming data across diverse domains has become commonplace.In the presence of concept drift,class imbalance,label scarcity,and new class emergence,these challenges jointly degrade representation stability,bias learning toward outdated distributions,and reduce the resilience and reliability of detection in dynamic environments.This paper proposes a streaming classincremental learning(SCIL)framework to address these issues.The SCIL framework integrates an autoencoder(AE)with a multi-layer perceptron for multi-class prediction,employs a dual-loss strategy(classification and reconstruction)for prediction and new class detection,uses corrected pseudo-labels for online training,manages classes with queues,and applies oversampling to handle imbalance.The rationale behind the method's structure is elucidated through ablation studies,and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance,incremental classes,and concept drifts.Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods.In line with our commitment to Open Science,we make our code and datasets available to the community.
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 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 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partially funded by Shenzhen Science and Technology Program(No.JCYJ20240813112038050)the National Natural Science Foundation of China(No.52404059)+1 种基金the Economy Trade and Information Commission of Shenzhen Municipality,China(No.HYCYPT20140507010002)the Key Program of Marine Economy Development(Six Marine Industries)Special Foundation of the Department of Natural Resources of Guangdong Province,China(No.GDOE[2021]55).
文摘Natural gas hydrate in Class Ⅰ reservoirs holds significant commercial potential,as demonstrated by production trials in the South China Sea.However,experimental studies have focused largely on Class Ⅲ systems,with Class Ⅰ/Ⅱ reservoirs remaining underrepresented due to the difficulties in simulating the geothermal gradient and interlayer interactions.This study investigates depressurization performance across all three classes using a novel 360°rotatable reactor with segmented temperature control,enabling precise simulation of reservoir conditions.Results reveal:(i)Class Ⅰ shows two-stage gas production,with 50%from early free gas enabling rapid depressurization,followed by dissociated gas dominance.They achieve 38.4%-78.3%higher cumulative production and superior gas-to-water ratios due to efficient energy use.(ii)The free gas layer in Class Ⅰ accelerates pressure and heat transfer.Class Ⅱ’s water layer provides sensible heat but causes water blocking,impairing heat flow.Class Ⅲ exhibits rapid initial dissociation but a quick decline without fluid support.(iii)Low temperature,low hydrate saturation,and high production pressure collectively reduce efficiency by increasing flow resistance,limiting gas supply,and reducing dissociation drive.Over-depressurization risks hydrate reformation and ice blockage.This work bridges experimental gaps for Class Ⅰ/Ⅱ reservoirs,offering key insights for optimizing recovery.
基金supported by Basic Science Research Program to Research Institute for Basic Sciences(RIBS)of Jeju National University through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2019-NR040080)This research was also carried out with the support of the Jeju RISE Center,funded by the Ministry of Education and Jeju Special Self-Governing Province in 2025,as part of the“Regional Innovation System&Education(RISE):Glocal University 30”initiative.
文摘Given the growing number of vehicle accidents caused by unintended acceleration and braking failure,verifying Sudden Unintended Acceleration(SUA)incidents has become a persistent challenge.A central issue of debate is whether such events stem frommechanical malfunctions or driver pedalmisapplications.However,existing verification procedures implemented by vehiclemanufacturers often involve closed tests after vehicle recalls;thus raising ongoing concerns about reliability and transparency.Consequently,there is a growing need for a user-driven framework that enables independent data acquisition and verification.Although previous studies have addressed SUA detection using deep learning,few have explored howclass granularity optimization affects power efficiency and inference performance in real-time Edge AI systems.To address this problem,this work presents a cloud-assisted artificial intelligence(AI)solution for the reliable verification of SUA occurrences.The proposed system integrates multimodal sensor streams including camera-based foot images,On-Board Diagnostics II(OBD-II)signals,and six-axismeasurements to determine whether the brake pedal was actually engaged at themoment of a suspected SUA.Beyond image acquisition,convolutional neural network(CNN)models perform real-time inference to classify the driver’s pedal operation states with the resulting outputs transmitted and archived in the cloud.A dedicated dataset of brake and accelerator pedal images was collected from 15 vehicles produced by 6 domestic and international manufacturers.Using this dataset,transfer learning techniques were applied to compare and analyze model performance and generalization as the CNN class granularity varied from coarse to fine levels.Furthermore,classification performance was evaluated in terms of latency and power efficiency under different class configurations.The experimental results demonstrated that the proposed solution identified the driver’s pedal behavior accurately and promptly,with the two-class model achieving the highest F1-score and accuracy among all granularity settings.
基金the Natural Science and Engineering Research Council of Canada(RGPIN/4052-16,ALLRP 560390-20).
文摘This paper addresses a fundamental question in rock mechanics:Are there Class Ⅱ rocks?The historical development of servo-controlled rock testing machines is reviewed,followed by a brief review of some stiff testing machines.The pioneering work of some researchers is reviewed,and the misconception of classifying rocks into Class Ⅰ and Class Ⅱ is discussed.The mechanism of post-peak Class Ⅱ behavior is discussed based on some recent test results.When a brittle hard rock is tested using a soft testing machine under axial-strain-controlled loading,violent failure can occur when the peak strength is reached,and the post-peak stress-strain curve cannot be obtained.However,a Class Ⅱ post-peak stress-strain curve can be obtained when the rock is tested under lateral-strain-controlled loading.If a stiff testing machine is used,Class Ⅰ and Class Ⅱ post-peak stress-strain curves will be obtained under axial-and lateral-strain-controlled loadings,respectively.It is therefore not appropriate to classify rocks into Class Ⅰ or Class Ⅱ rocks.The influences of other conditions,such as rock type,confinement,and specimen height-to-diameter ratio,on the type(Class Ⅰ or Class Ⅱ)of post-peak stress-strain curves are also discussed.Finally,some misconceptions in the rock mechanics community,stemming from the concept of“Class Ⅱ rock”,are discussed.By clarifying these concepts related to Class Ⅰ and Class Ⅱ behaviors,this paper seeks to clarify misunderstandings and misapplications related to post-peak strength and deformation properties in the field.
基金supported by Ongoing Research Funding Program(ORF-2025-488)King Saud University,Riyadh,Saudi Arabia.
文摘Effectively handling imbalanced datasets remains a fundamental challenge in computational modeling and machine learning,particularly when class overlap significantly deteriorates classification performance.Traditional oversampling methods often generate synthetic samples without considering density variations,leading to redundant or misleading instances that exacerbate class overlap in high-density regions.To address these limitations,we propose Wasserstein Generative Adversarial Network Variational Density Estimation WGAN-VDE,a computationally efficient density-aware adversarial resampling framework that enhances minority class representation while strategically reducing class overlap.The originality of WGAN-VDE lies in its density-aware sample refinement,ensuring that synthetic samples are positioned in underrepresented regions,thereby improving class distinctiveness.By applying structured feature representation,targeted sample generation,and density-based selection mechanisms strategies,the proposed framework ensures the generation of well-separated and diverse synthetic samples,improving class separability and reducing redundancy.The experimental evaluation on 20 benchmark datasets demonstrates that this approach outperforms 11 state-of-the-art rebalancing techniques,achieving superior results in F1-score,Accuracy,G-Mean,and AUC metrics.These results establish the proposed method as an effective and robust computational approach,suitable for diverse engineering and scientific applications involving imbalanced data classification and computational modeling.
文摘This study demonstrates the complexity and importance of water quality as a measure of the health and sustainability of ecosystems that directly influence biodiversity,human health,and the world economy.The predictability of water quality thus plays a crucial role in managing our ecosystems to make informed decisions and,hence,proper environmental management.This study addresses these challenges by proposing an effective machine learning methodology applied to the“Water Quality”public dataset.The methodology has modeled the dataset suitable for providing prediction classification analysis with high values of the evaluating parameters such as accuracy,sensitivity,and specificity.The proposed methodology is based on two novel approaches:(a)the SMOTE method to deal with unbalanced data and(b)the skillfully involved classical machine learning models.This paper uses Random Forests,Decision Trees,XGBoost,and Support Vector Machines because they can handle large datasets,train models for handling skewed datasets,and provide high accuracy in water quality classification.A key contribution of this work is the use of custom sampling strategies within the SMOTE approach,which significantly enhanced performance metrics and improved class imbalance handling.The results demonstrate significant improvements in predictive performance,achieving the highest reported metrics:accuracy(98.92%vs.96.06%),sensitivity(98.3%vs.71.26%),and F1 score(98.37%vs.79.74%)using the XGBoost model.These improvements underscore the effectiveness of our custom SMOTE sampling strategies in addressing class imbalance.The findings contribute to environmental management by enabling ecology specialists to develop more accurate strategies for monitoring,assessing,and managing drinking water quality,ensuring better ecosystem and public health outcomes.
基金sponsored by the National Natural Science Foundation of China Grant No.62271302the Shanghai Municipal Natural Science Foundation Grant 20ZR1423500.
文摘Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.
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.
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 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In this study we review the occurrence of different types (A, B, C, M, and X classes) of solar flares during different solar cycle phases from 1996 to 2019 covering the solar cycles 23 and 24. During this period, a total of 19,126 solar flares were observed regardless the class: 3548 flares in solar cycle 23 (SC23) and 15,668 flares in solar cycle 24 (SC24). Our findings show that the cycle 23 has observed the highest occurrences of M-class and X-class flares, whereas cycle 24 has pointed out a predominance of B-class and C-class flares throughout its different phases. The results indicate that the cycle 23 was magnetically more intense than cycle 24, leading to more powerful solar flares and more frequent geomagnetic storms, capable of generating significant electromagnetic emissions that can affect satellites and GPS signals. The decrease in intense solar flares during cycle 24 compared to cycle 23 reflects an evolution in solar activity patterns over time.
基金supported by the Sinopec Technology Research and Development Project(No.30000000-22-ZC0607-0235,No.33550000-22-ZC0607-0009)the National Natural Science Foundation of China(No.52334002).
文摘Natural gas hydrate widely exists in the South China Sea as clean energy.A three-phase transition layer widely exists in low permeability Class I hydrates in the Shenhu offshore area.Therefore,taking into account the low-permeability characteristics with an average permeability of 5.5 mD and moderate heterogeneity,a 3-D geological model of heterogeneous Class I hydrate reservoirs with three-phase transition layers is established by Kriging interpolation and stochastic modeling method,and a numerical simulation model is used to describe the depressurization production performance of the reservoir.With the development of depressurization,a specific range of complete decomposition zones appear both in the hydrate and transition layers.The entire decomposition zone of the whole reservoir tends to outward and upward diffusion.There is apparent methane escape in the three-phase transition layer.Due to the improvement of local permeability caused by the phase transition of hydrate dissociation,some methane accumulation occurs at the bottom of the hydrate layer,forming a local methane enrichment zone.The methane migration trends in reservoirs are mainly characterized by movement toward production wells and hydrate layers under the influence of gravity.However,due to the permeability limitation of hydrate reservoirs,many fluids have not been effectively produced and remain in the reservoir.Therefore,to improve the effective pressure drop of the reservoir,the perforation method and pressure reduction method were optimized by analyzing the influencing factors based on the gas production rate.The comparative study demonstrates that perforating through the free gas layer combined with one-time depressurization can enhance the effective depressurization and improve production performance.The gas production rate from perforating through the free gas layer can be twice as high as that from perforating through the transition layer.This study can provide theoretical support for the utilization of marine energy.
