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 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
Abs As a crucial vehicle for young children’s artistic enlightenment,music appreciation holds an irreplaceable value in cognitive development,emotional edification,and the cultivation of aesthetic abilities.Currently...Abs As a crucial vehicle for young children’s artistic enlightenment,music appreciation holds an irreplaceable value in cognitive development,emotional edification,and the cultivation of aesthetic abilities.Currently,in music appreciation activities for senior kindergarten classes,there is a widespread phenomenon of homogenized teaching content and mechanized teaching methods,which results in insufficient enthusiasm for participation among young children and a superficial understanding of music.The situational teaching method,by constructing concrete and immersive learning scenarios,can effectively activate young children’s multi-dimensional sensory experiences.Its characteristics of intuitiveness and interactivity are highly consistent with the traits of young children’s concrete thinking,thus providing a new approach to resolving the current predicament.The research focuses on the practical pain points in music appreciation activities for senior kindergarten classes and proposes targeted solutions from four dimensions:content design,method innovation,resource integration,and teacher training,aiming to reconstruct a child-centered,in-depth music learning model.Practice has shown that the situational teaching method can not only enhance young children’s perceptual sensitivity to musical elements but also guide them to achieve emotional resonance through role-playing and life-related associations,laying a foundation for the sustainable development of young children’s musical literacy.展开更多
Dialogue and fusion of horizons are two important concepts of Gadamer’s philosophical hermeneutics,which falls into the pedagogical category of teaching English News Listening Classes.The course of English News Liste...Dialogue and fusion of horizons are two important concepts of Gadamer’s philosophical hermeneutics,which falls into the pedagogical category of teaching English News Listening Classes.The course of English News Listening is one of the most fundamental and difficult courses in the curriculum for college students who are English majors.The simultaneous interpreting training method of shadowing is used in English News Listening Classes in helping students improve their language skill of listening and speaking.In fulfilling a teacher’s pedagogical performance of dialoguing and fusion of horizons,still one thing is important,i.e.,solidarity triggered between students and teacher,which is the good or the ethical choice between students and teacher.In English News Listening Classes,“道”or“the way(Dao)”is shadowing.In teaching English News Listening,a“dialogue”of shadowing could be achieved between students and teacher is even more significant than that of other courses.This paper intends to present the dialogic ethical triggering of fusion of horizons in class.In another word,students’knowing could be guided by teacher’s dialogic ethical triggering in English News classes.In voicing out the language,knowing in listening and speaking could help students have confidence in not only their language skills but in conquering their difficulties in their life.Teaching English News Listening at Northeastern University(NEU)in this way since 2013 has turned out to be good for students’growth and maturation in life.展开更多
Letϕbe a smooth radial weight that decays faster than the class Gaussian ones.We obtain certain estimates for the reproducing kernels and the Lp-estimates for solutions of theδ-equation on the weighted Fock spaces F_...Letϕbe a smooth radial weight that decays faster than the class Gaussian ones.We obtain certain estimates for the reproducing kernels and the Lp-estimates for solutions of theδ-equation on the weighted Fock spaces F_(ϕ)^(p)(1≤p≤∞),which extends the classical Hörmander Theorem.Furthermore,for a suitable f,we completely characterize the boundedness and compactness of the Hankel operator H_(f):F_(ϕ)^(p)→L^(q)(C,e^(qϕ(·))dm)for all possible 1≤p,q<∞and also characterize the Schatten-p class Hankel operator Hf from F_(ϕ)^(2)to L^(2)(C,E^(-2ϕ)dm) for all 0<p<∞. As an application, we give a complete characterization of the simultaneously bounded, compact and Schatten-p classes Hankel operators H_(f) and h_(f)^(-) on F_(ϕ)^(2).展开更多
In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) i...In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) in C^(n).Let g be a convex function in U. We mainly establish the sharp bounds of all terms of homogeneous polynomial expansions for a subclass of g-parametric starlike mappings of complex order γ on B (resp.U^(n))when the mappings f are k-fold symmetric, k ∈ N. Our results partly solve the Bieberbach conjecture in several complex variables and generalize some prior works.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
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
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
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
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
Teaching large,heterogeneous English class is now a teaching fact in China.It brings a lot of practical problems to English teachers who teach that kind of class because of the existence of differences among learners....Teaching large,heterogeneous English class is now a teaching fact in China.It brings a lot of practical problems to English teachers who teach that kind of class because of the existence of differences among learners.This paper aims to provide practical principles illustrated by some scholars to address problems appeared in those classes and achieve the aim of better learning for all members of the class.展开更多
Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates...Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates of the n K width d n(W M(A),L 2[0,1]) .展开更多
Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates...Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates of the n K width d n(W M(A),L 2[0,1]) .展开更多
With more and more people who are jumping into the line of learning the second language (especially English),and also due to the limited resources in language teaching,many foreign language teachers are nowadays confr...With more and more people who are jumping into the line of learning the second language (especially English),and also due to the limited resources in language teaching,many foreign language teachers are nowadays confronting the large classes when teaching.So how to teach foreign language effectively in large classes has become an issue as well as a special field to make researches in.展开更多
In recent years, the scale of enrollment of college students has been expanded. As a result, in colleges teachers are badly needed for the basic course of college English. To solve this problem, big classes are adopte...In recent years, the scale of enrollment of college students has been expanded. As a result, in colleges teachers are badly needed for the basic course of college English. To solve this problem, big classes are adopted for college English teaching in some universities. And scientific management can guarantee the quality of college English teaching of big classes. Finally, this article introduces four tactics to manage college English teaching of big classes.展开更多
Translation teaching in college English classes is highly teacher-centered, so students are not fully motivated and therefore lack basic interests to fulfill these tasks. In order for students to be more involved and ...Translation teaching in college English classes is highly teacher-centered, so students are not fully motivated and therefore lack basic interests to fulfill these tasks. In order for students to be more involved and more learning independent, translation teaching needs to become student-centered and task-based. This paper discusses the theoretical basis of this teaching method and suggests possible ways to use the method.展开更多
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.
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.
文摘Abs As a crucial vehicle for young children’s artistic enlightenment,music appreciation holds an irreplaceable value in cognitive development,emotional edification,and the cultivation of aesthetic abilities.Currently,in music appreciation activities for senior kindergarten classes,there is a widespread phenomenon of homogenized teaching content and mechanized teaching methods,which results in insufficient enthusiasm for participation among young children and a superficial understanding of music.The situational teaching method,by constructing concrete and immersive learning scenarios,can effectively activate young children’s multi-dimensional sensory experiences.Its characteristics of intuitiveness and interactivity are highly consistent with the traits of young children’s concrete thinking,thus providing a new approach to resolving the current predicament.The research focuses on the practical pain points in music appreciation activities for senior kindergarten classes and proposes targeted solutions from four dimensions:content design,method innovation,resource integration,and teacher training,aiming to reconstruct a child-centered,in-depth music learning model.Practice has shown that the situational teaching method can not only enhance young children’s perceptual sensitivity to musical elements but also guide them to achieve emotional resonance through role-playing and life-related associations,laying a foundation for the sustainable development of young children’s musical literacy.
基金Liaoning Province Education and Scientific Research Young and Middle-Aged Teachers Special Project:Innovative Research and Practice of Chunk-Based Interpreting Teaching for IP’s Curriculum(Fund No.:JG24QGA06).
文摘Dialogue and fusion of horizons are two important concepts of Gadamer’s philosophical hermeneutics,which falls into the pedagogical category of teaching English News Listening Classes.The course of English News Listening is one of the most fundamental and difficult courses in the curriculum for college students who are English majors.The simultaneous interpreting training method of shadowing is used in English News Listening Classes in helping students improve their language skill of listening and speaking.In fulfilling a teacher’s pedagogical performance of dialoguing and fusion of horizons,still one thing is important,i.e.,solidarity triggered between students and teacher,which is the good or the ethical choice between students and teacher.In English News Listening Classes,“道”or“the way(Dao)”is shadowing.In teaching English News Listening,a“dialogue”of shadowing could be achieved between students and teacher is even more significant than that of other courses.This paper intends to present the dialogic ethical triggering of fusion of horizons in class.In another word,students’knowing could be guided by teacher’s dialogic ethical triggering in English News classes.In voicing out the language,knowing in listening and speaking could help students have confidence in not only their language skills but in conquering their difficulties in their life.Teaching English News Listening at Northeastern University(NEU)in this way since 2013 has turned out to be good for students’growth and maturation in life.
文摘Letϕbe a smooth radial weight that decays faster than the class Gaussian ones.We obtain certain estimates for the reproducing kernels and the Lp-estimates for solutions of theδ-equation on the weighted Fock spaces F_(ϕ)^(p)(1≤p≤∞),which extends the classical Hörmander Theorem.Furthermore,for a suitable f,we completely characterize the boundedness and compactness of the Hankel operator H_(f):F_(ϕ)^(p)→L^(q)(C,e^(qϕ(·))dm)for all possible 1≤p,q<∞and also characterize the Schatten-p class Hankel operator Hf from F_(ϕ)^(2)to L^(2)(C,E^(-2ϕ)dm) for all 0<p<∞. As an application, we give a complete characterization of the simultaneously bounded, compact and Schatten-p classes Hankel operators H_(f) and h_(f)^(-) on F_(ϕ)^(2).
基金supported by the National Natural Science Foundation of China(12061035)the Research Foundation of Jiangxi Science and Technology Normal University of China(2021QNBJRC003)supported by the Graduate Innovation Fund of Jiangxi Science and Technology Normal University(YC2024-X10).
文摘In this paper,the class of starlike functions of complex order γ(γ∈ℂ−{0})is extended from the case on unit disk U=(z∈C:|z|<1)to the case on the unit ball B in a complex Banach space or the unit polydisk U^(n) in C^(n).Let g be a convex function in U. We mainly establish the sharp bounds of all terms of homogeneous polynomial expansions for a subclass of g-parametric starlike mappings of complex order γ on B (resp.U^(n))when the mappings f are k-fold symmetric, k ∈ N. Our results partly solve the Bieberbach conjecture in several complex variables and generalize some prior works.
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 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.
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.
文摘Teaching large,heterogeneous English class is now a teaching fact in China.It brings a lot of practical problems to English teachers who teach that kind of class because of the existence of differences among learners.This paper aims to provide practical principles illustrated by some scholars to address problems appeared in those classes and achieve the aim of better learning for all members of the class.
文摘Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates of the n K width d n(W M(A),L 2[0,1]) .
文摘Let M(u) be an N function, A=D r+∑r-1k=0a k(x)D k a linear differential operator and W M(A) the Sobolev Orlicz class defined by M(u) and A. In this paper we give the asymptotic estimates of the n K width d n(W M(A),L 2[0,1]) .
文摘With more and more people who are jumping into the line of learning the second language (especially English),and also due to the limited resources in language teaching,many foreign language teachers are nowadays confronting the large classes when teaching.So how to teach foreign language effectively in large classes has become an issue as well as a special field to make researches in.
文摘In recent years, the scale of enrollment of college students has been expanded. As a result, in colleges teachers are badly needed for the basic course of college English. To solve this problem, big classes are adopted for college English teaching in some universities. And scientific management can guarantee the quality of college English teaching of big classes. Finally, this article introduces four tactics to manage college English teaching of big classes.
文摘Translation teaching in college English classes is highly teacher-centered, so students are not fully motivated and therefore lack basic interests to fulfill these tasks. In order for students to be more involved and more learning independent, translation teaching needs to become student-centered and task-based. This paper discusses the theoretical basis of this teaching method and suggests possible ways to use the method.
