Online programming platforms are popular in programming education.However,there has been no research investigating students’real opinions and expectations of the error feedback mechanisms,leaving educators without a ...Online programming platforms are popular in programming education.However,there has been no research investigating students’real opinions and expectations of the error feedback mechanisms,leaving educators without a solid data foundation when attempting to improve the error feedback mechanisms.This paper makes a survey of 834 students across various programming courses and investigates student perceptions of error feedback mechanisms on online programming platforms.It explores the effectiveness of existing feedback,student satisfaction,and preferences for potential improvements,focusing on automatic error localization and program repair mechanisms.Results reveal a significant portion of students are dissatisfied with current feedback due to its limited informativeness.Students also express a clear demand for stronger feedback mechanisms,such as error localization and repair hints.Nevertheless,they prefer feedback that subtly guides them toward solutions,rather than providing direct and explicit answers,valuing the opportunity to enhance their debugging skills.The findings suggest a need for balanced,educational-focused feedback mechanisms that aid learning while promoting independent problem-solving.展开更多
Every year, around the world, between 250,000 and 500,000 people suffer a spinal cord injury(SCI). SCI is a devastating medical condition that arises from trauma or disease-induced damage to the spinal cord, disruptin...Every year, around the world, between 250,000 and 500,000 people suffer a spinal cord injury(SCI). SCI is a devastating medical condition that arises from trauma or disease-induced damage to the spinal cord, disrupting the neural connections that allow communication between the brain and the rest of the body, which results in varying degrees of motor and sensory impairment. Disconnection in the spinal tracts is an irreversible condition owing to the poor capacity for spontaneous axonal regeneration in the affected neurons.展开更多
The performance of data restore is one of the key indicators of user experience for backup storage systems.Compared to the traditional offline restore process,online restore reduces downtime during backup restoration,...The performance of data restore is one of the key indicators of user experience for backup storage systems.Compared to the traditional offline restore process,online restore reduces downtime during backup restoration,allowing users to operate on already restored files while other files are still being restored.This approach improves availability during restoration tasks but suffers from a critical limitation:inconsistencies between the access sequence and the restore sequence.In many cases,the file a user needs to access at a given moment may not yet be restored,resulting in significant delays and poor user experience.To this end,we present Histore,which builds on the user’s historical access sequence to schedule the restore sequence,in order to reduce users’access delayed time.Histore includes three restore approaches:(i)the frequency-based approach,which restores files based on historical file access frequencies and prioritizes ensuring the availability of frequently accessed files;(ii)the graph-based approach,which preferentially restores the frequently accessed files as well as their correlated files based on historical access patterns,and(iii)the trie-based approach,which restores particular files based on both users’real-time and historical access patterns to deduce and restore the files to be accessed in the near future.We implement a prototype of Histore and evaluate its performance from multiple perspectives.Trace-driven experiments on two datasets show that Histore significantly reduces users’delay time by 4-700×with only 1.0%-14.5%additional performance overhead.展开更多
The creator economy is revolutionizing the way in which individuals can profit from their engagement with online platforms.In this paper,we initiate the formal study of online learning in a creator economy by modeling...The creator economy is revolutionizing the way in which individuals can profit from their engagement with online platforms.In this paper,we initiate the formal study of online learning in a creator economy by modeling it as a three-party game between users,a platform,and content creators.The platform interacts with creators through contracts under a principal-agent framework and with users via a recommender system.We study how the platform can jointly optimize contracts and recommendation policies in an online learning setting.We analyze return-based and feature-based contracts.Under smoothness assumptions,return-based contracts achieve regretΘ(T^(2/3)).For feature-based contracts,we introduce an intrinsic dimension d and prove a regret bound O(T^(d+1)/(d+2)),which is tight for linear families.展开更多
Existing load forecasting methods typically assume that recent load data are available for prediction.This is not in conformity with reality since there is a time gap between the flow date(when power is consumed)and w...Existing load forecasting methods typically assume that recent load data are available for prediction.This is not in conformity with reality since there is a time gap between the flow date(when power is consumed)and when measurement values are obtained.To this end,this letter proposes an online learning-based probabilistic load forecasting method considering the impact of the data gap.Specifically,an adaptive ensemble backpropagation-enabled online quantile regression algorithm is developed to optimize the parameters of the attention network recursively using the newly obtained load observations.To further improve the reliability and sharpness of prediction intervals under significant data gaps,we introduce an online interval calibration technique.The proposed online learning method allows us to adaptively capture the dynamic changes in load patterns and alleviate the information lags caused by data gaps.Comparative tests utilizing real-world datasets reveal the superiority of the proposed method.展开更多
Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed...Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed among forecast results produced by different ensemble members when applied to South China.To enhance the accuracy of sub-seasonal forecasts in this region,it is essential to develop new methods that can effectively leverage multiple predictive models.This study introduces a weighted ensemble forecasting method based on online learning to improve forecast accuracy.We utilized ensemble forecasts from three models:the Integrated Forecasting System model from the European Centre for Medium-Range Weather Forecasts,the Climate Forecast System Version 2 model from the National Centers for Environmental Prediction,and the Beijing Climate Center-Climate Prediction System version 3 model from the China Meteorological Administration.The ensemble weights are trained using an online learning approach.The results indicate that the forecasts obtained through online learning outperform those of the original dynamical models.Compared to the simple ensemble results of the three models,the weighted ensemble model showed a stronger capability to capture temperature and precipitation patterns in South China.Therefore,this method has the potential to improve the accuracy of sub-seasonal forecasts in this region.展开更多
In practical microgrids,current saturation of inverters and power interaction coupling of different forms of DERs complicate the system's transient behaviors.Existing methods of online transient stability predicti...In practical microgrids,current saturation of inverters and power interaction coupling of different forms of DERs complicate the system's transient behaviors.Existing methods of online transient stability prediction(TSP)are suitable for power systems consisting of homogeneous distributed energy resources(DERs),thus showing limited accuracy for stability prediction of microgrids.This paper develops a deep-learning-based TSP method for accurate online prediction of microgrids consisting of diverse forms of DERs under current saturation.First,a general key input feature selection method for microgrid TSP is systematically designed to ensure prediction accuracy.It is derived from a comprehensive mechanism analysis of the influence of DER's intrinsic and interaction characteristics under current saturation.Besides,impacts of load fluctuation and fault change are also considered to improve robust prediction performance.Second,to further improve prediction accuracy,an online TSP model based on deep learning is developed by effectively using the powerful nonlinear mapping capability of the deep belief network(DBN).Then,by combining feature selection method and deep-learning-based TSP model,an online TSP method is derived.Test results show the proposed method greatly improves accuracy of microgrid TSP under complex operating conditions.Furthermore,the method effectively avoids feature redundancy and the curse of dimensionality.Numbers of input features are independent of the scale of microgrids.展开更多
Topological information is very important for understanding different types of online web services,in particular,for online social networks(OSNs).People leverage such information for various applications,such as socia...Topological information is very important for understanding different types of online web services,in particular,for online social networks(OSNs).People leverage such information for various applications,such as social relationship modeling,community detection,user profiling,and user behavior prediction.However,the leak of such information will also pose severe challenges for user privacy preserving due to its usefulness in characterizing users.Large-scale web crawling-based information probing is a representative way for obtaining topological information of online web services.In this paper,we explore how to defend against topological information probing for online web services,with a particular focus on online decentralized web services such as Mastodon.Different from traditional centralized web services,the federated nature of decentralized web services makes the identification of distributed crawlers even more difficult.We analyze the behavioral differences between legitimate users and crawlers in decentralized web services and highlight two key behavioral attributes that distinguish crawlers from legitimate users:instance interaction preferences and hop count in profile viewing patterns.Based on these insights:we propose a supervised machine learning-based framework for crawler detection,which is able to learn the federation-aware feature representations for users.To validate the framework’s effectiveness,we construct a labeled dataset that integrates real users with real-trace driven simulated crawlers in Mastodon.We use this dataset to train various supervised classifiers for crawler detection.Experimental results demonstrate that our framework can achieve an excellent classification performance.Moreover,it is observed that federation-aware features are effective in improving detection performance.展开更多
Background:Music has proven to be vital in enhancing resilience and promotingwell-being.Previously,the impact of music in sports environments was solely investigated,while this paper applies it to study environments,s...Background:Music has proven to be vital in enhancing resilience and promotingwell-being.Previously,the impact of music in sports environments was solely investigated,while this paper applies it to study environments,standing out as pioneering research.The study consists of a systematic development of a conceptual framework based on theories of Uses and Gratification Expectancy(UGE)and perceived motivation based on music elements.Their components are observed variables influencing students’psychological well-being(as the dependent variable).Resilience is examined as a mediator,influencing the relationships of both observed and dependent variables.The main purpose of this study is to highlight the positive effects of online music consumption on the psychological well-being of students.Methods:Semi-structured qualitative interviews were conducted with eighteen final year creative multimedia undergraduate students belonging to five central region Malaysian universities,especially on their UGE needs,and a similar concept survey instrument with two hundred participants.The interview data were analysed through thematic analysis,while the survey data through descriptive and Partial Least Squares Structural Equation Modeling(PLS-SEM).Results:The results highlight that students gain motivation from online music,which positively affects their psychological well-being(β=0.190,p=0.003,f^(2)=0.037),while resilience significantly affects this relationship(β=0.562,p<0.001,f^(2)=0.461).However,the results also predict a partial relationship between constructs based on UGE with psychological well-being,mediated by resilience,i.e.,AT-UGE(β=0.021,p=0.783,f^(2)=0.000),SIPI-UGE(β=0.228,p=0.004,f^(2)=0.044).Conclusion:The outcome of the study reflected practical,meaningful,and statistically significant results.The majority of the predictors,with the exception of one,i.e.,AT-UGE,displayed a clear positive relation of online music consumption on the Psychological Well-being of students.Future research will explore varying contextual factors impacting online music-related gratifications,motivations,and resilience,along with additional potential mediators and moderators.展开更多
To explore effective paths for improving college students’ mental health, this study integrates narrative therapy and painting therapy to design a 7-week online group psychological counseling program. A total of 121 ...To explore effective paths for improving college students’ mental health, this study integrates narrative therapy and painting therapy to design a 7-week online group psychological counseling program. A total of 121 volunteer college students participated as subjects, and themed painting counseling was conducted via Tencent Meeting. Five scales, including the General Self-Efficacy Scale, Self-Esteem Scale, and Self-Rating Depression Scale, were used for pre-test and post-test comparisons. The results show that after the intervention, students’ self-efficacy (t = -5.528, p = 0.000) and self-esteem level (t = -2.153, p = 0.033) significantly improved statistically, and depression and anxiety showed a positive improvement trend. The research indicates that online narrative painting therapy can effectively release students’ psychological pressure, promote in-depth self-cognition and interpersonal connection construction, providing an operable innovative paradigm for college mental health education. Its interactivity and effectiveness are compatible with the psychological needs and internet usage habits of contemporary college students.展开更多
Background:Emerging adulthood is a critical period for ego identity exploration and consolidation,and self-presentation on social media constitutes a salient online context for this developmental process.However,limit...Background:Emerging adulthood is a critical period for ego identity exploration and consolidation,and self-presentation on social media constitutes a salient online context for this developmental process.However,limited research has explored the associations between self-presentation on WeChat Moments and ego identity.This study aims to examine these associations,focusing on the mediating role of online positive feedback and the moderating role of gender.Methods:Using a three-wave longitudinal design,this study followed 767 Chinese college students(Mean age=18.96 years)through cluster sampling.Participants completed self-report questionnaires assessing self-presentation on WeChat Moments,online positive feedback,and ego identity status.Data analyses were conducted using mediation modeling and multi-group structural equation modeling.Results:Authentic self-presentation was positively associated with identity achievement and negatively associated with identity diffusion,whereas positive self-presentation was linked to higher levels of identity foreclosure.Online positive feedback played a significant mediating role in the associations between self-presentation strategies and identity statuses,and gender differences were observed in this mediating pathway.For both males and females,authentic self-presentation was associated with higher identity achievement through online positive feedback.However,indirect associations with identity foreclosure and diffusion were observed only among females:authentic self-presentation was linked to lower levels,whereas positive self-presentation was linked to higher levels of foreclosure and diffusion through online positive feedback.No comparable indirect associations were detected among males.Conclusions:Online positive feedback is closely linked to self-presentation strategies and ego identity statuses,with these associations varying by gender.展开更多
Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lack...Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.展开更多
In this paper,we study a class of Linear Fractional Programming on a nonempty bounded set,called the Problem(LFP),and design a branch and bound algorithm to find the global optimal solution of the problem(LFP).First,w...In this paper,we study a class of Linear Fractional Programming on a nonempty bounded set,called the Problem(LFP),and design a branch and bound algorithm to find the global optimal solution of the problem(LFP).First,we convert the problem(LFP)to the equivalent problem(EP2).Secondly,by applying the linear relaxation technique to the problem(EP2),the linear relaxation programming problem(LRP2Y)was obtained.Then,the overall framework of the algorithm is given,and the convergence and complexity of the algorithm are analyzed.Finally,experimental results are listed to illustrate the effectiveness of the algorithm.展开更多
The operational demands of a wide range significantly exacerbate combustion instability issues within ramjet combustor.To suppress combustion oscillations,an open-loop control system utilizing Linear Genetic Programmi...The operational demands of a wide range significantly exacerbate combustion instability issues within ramjet combustor.To suppress combustion oscillations,an open-loop control system utilizing Linear Genetic Programming(LGP)has been developed for a full-scale annular ramjet combustor.The LGP is used to generate control laws that include multi-frequency forcing.These laws are then transformed into square waves to actuate the solenoid valve,which modulates the kerosene supply for open-loop control.The results show that the duty cycle has little effect on instability amplitude,whereas an increase in frequency leads to a remarked reduction in combustion amplitude.After five generations evolvements,the pressure amplitude is reduced by 40.6% under the optimal control law generated by LGP.Furthermore,the machine learning process is depicted using a proximity map of control law similarity,with the search pathway visualized by the steepest descent.All individuals go forward to the upper left corner of the map with the evolution process,terminating at the optimal individual of the fifth generation.展开更多
During the use of robotics in applications such as antiterrorism or combat,a motion-constrained pursuer vehicle,such as a Dubins unmanned surface vehicle(USV),must get close enough(within a prescribed zero or positive...During the use of robotics in applications such as antiterrorism or combat,a motion-constrained pursuer vehicle,such as a Dubins unmanned surface vehicle(USV),must get close enough(within a prescribed zero or positive distance)to a moving target as quickly as possible,resulting in the extended minimum-time intercept problem(EMTIP).Existing research has primarily focused on the zero-distance intercept problem,MTIP,establishing the necessary or sufficient conditions for MTIP optimality,and utilizing analytic algorithms,such as root-finding algorithms,to calculate the optimal solutions.However,these approaches depend heavily on the properties of the analytic algorithm,making them inapplicable when problem settings change,such as in the case of a positive effective range or complicated target motions outside uniform rectilinear motion.In this study,an approach employing a high-accuracy and quality-guaranteed mixed-integer piecewise-linear program(QG-PWL)is proposed for the EMTIP.This program can accommodate different effective interception ranges and complicated target motions(variable velocity or complicated trajectories).The high accuracy and quality guarantees of QG-PWL originate from elegant strategies such as piecewise linearization and other developed operation strategies.The approximate error in the intercept path length is proved to be bounded to h^(2)/(4√2),where h is the piecewise length.展开更多
Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning appr...Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.展开更多
Programmable/reprogrammable magneto-responsive composites(MRCs)are highly desirable for applications in soft robotics,morphable actuators,and biomedical devices due to their capabilities of undergoing reversible,compl...Programmable/reprogrammable magneto-responsive composites(MRCs)are highly desirable for applications in soft robotics,morphable actuators,and biomedical devices due to their capabilities of undergoing reversible,complex,untethered,and rapid deformations.However,current MRC-based devices primarily rely on soft matrices,which revert to their original shapes and cease functioning when external magnetic fields are removed.Moreover,their magnetization programming,deformations,and functioning need to alternate between encoding and actuation platforms,limiting the adaptability and efficiency.Here,we present a reprogrammable magnetic shape-memory composite(RM-SMC)integrating a shape-memory polymer(SMP)skeleton with phase-transition magnetic microcapsules.High-intensity laser melts microcapsules for magnetic realignment under programmed fields,while low-intensity laser softens SMP for structural reconfiguration without compromising integrity.This dual-laser strategy facilitates in situ magnetization programming,shape morphing,and function execution within a single material system.Our innovative approach enables unique applications,including omnidirectional multi-degree-of-freedom actuators that can activate light switches,solar trackers that optimize energy capture,and adaptive impellers that modulate fluid pumping.By eliminating platform alternation and enabling shape/function retention post-actuation,the RM-SMC platform overcomes critical limitations in conventional MRCs,establishing a paradigm for multifunctional devices requiring persistent configuration control and field-independent operation.展开更多
In the present work, two new, （multi-）parametric programming （mp-P）-inspired algorithms for the solutionof mixed-integer nonlinear programming （MINLP） problems are developed, with their main focus being onproces...In the present work, two new, （multi-）parametric programming （mp-P）-inspired algorithms for the solutionof mixed-integer nonlinear programming （MINLP） problems are developed, with their main focus being onprocess synthesis problems. The algorithms are developed for the special case in which the nonlinearitiesarise because of logarithmic terms, with the first one being developed for the deterministic case, and thesecond for the parametric case （p-MINLP）. The key idea is to formulate and solve the square system of thefirst-order Karush-Kuhn-Tucker （KKT） conditions in an analytical way, by treating the binary variables and/or uncertain parameters as symbolic parameters. To this effect, symbolic manipulation and solution tech-niques are employed. In order to demonstrate the applicability and validity of the proposed algorithms, twoprocess synthesis case studies are examined. The corresponding solutions are then validated using state-of-the-art numerical MINLP solvers. For p-MINLP, the solution is given by an optimal solution as an explicitfunction of the uncertain parameters.展开更多
The penalty function method, presented many years ago, is an important nu- merical method for the mathematical programming problems. In this article, we propose a dual-relax penalty function approach, which is signifi...The penalty function method, presented many years ago, is an important nu- merical method for the mathematical programming problems. In this article, we propose a dual-relax penalty function approach, which is significantly different from penalty func- tion approach existing for solving the bilevel programming, to solve the nonlinear bilevel programming with linear lower level problem. Our algorithm will redound to the error analysis for computing an approximate solution to the bilevel programming. The error estimate is obtained among the optimal objective function value of the dual-relax penalty problem and of the original bilevel programming problem. An example is illustrated to show the feasibility of the proposed approach.展开更多
基金supported by the National Natural Science Foundation of China under Grant No.92582204,No.62577007,and No.62177003the Fundamental Research Funds for the Central Universities under Grant No.JKF-2025011975129.
文摘Online programming platforms are popular in programming education.However,there has been no research investigating students’real opinions and expectations of the error feedback mechanisms,leaving educators without a solid data foundation when attempting to improve the error feedback mechanisms.This paper makes a survey of 834 students across various programming courses and investigates student perceptions of error feedback mechanisms on online programming platforms.It explores the effectiveness of existing feedback,student satisfaction,and preferences for potential improvements,focusing on automatic error localization and program repair mechanisms.Results reveal a significant portion of students are dissatisfied with current feedback due to its limited informativeness.Students also express a clear demand for stronger feedback mechanisms,such as error localization and repair hints.Nevertheless,they prefer feedback that subtly guides them toward solutions,rather than providing direct and explicit answers,valuing the opportunity to enhance their debugging skills.The findings suggest a need for balanced,educational-focused feedback mechanisms that aid learning while promoting independent problem-solving.
基金financially supported by Ministerio de Ciencia e Innovación projects SAF2017-82736-C2-1-R to MTMFin Universidad Autónoma de Madrid and by Fundación Universidad Francisco de Vitoria to JS+2 种基金a predoctoral scholarship from Fundación Universidad Francisco de Vitoriafinancial support from a 6-month contract from Universidad Autónoma de Madrida 3-month contract from the School of Medicine of Universidad Francisco de Vitoria。
文摘Every year, around the world, between 250,000 and 500,000 people suffer a spinal cord injury(SCI). SCI is a devastating medical condition that arises from trauma or disease-induced damage to the spinal cord, disrupting the neural connections that allow communication between the brain and the rest of the body, which results in varying degrees of motor and sensory impairment. Disconnection in the spinal tracts is an irreversible condition owing to the poor capacity for spontaneous axonal regeneration in the affected neurons.
基金supported in part by National Key R&D Program of China(2022YFB4501200),National Natural Science Foundation of China(62332018)Science and Technology Program(2024NSFTD0031,2024YFHZ0339 and 2025ZNSFSC0497).
文摘The performance of data restore is one of the key indicators of user experience for backup storage systems.Compared to the traditional offline restore process,online restore reduces downtime during backup restoration,allowing users to operate on already restored files while other files are still being restored.This approach improves availability during restoration tasks but suffers from a critical limitation:inconsistencies between the access sequence and the restore sequence.In many cases,the file a user needs to access at a given moment may not yet be restored,resulting in significant delays and poor user experience.To this end,we present Histore,which builds on the user’s historical access sequence to schedule the restore sequence,in order to reduce users’access delayed time.Histore includes three restore approaches:(i)the frequency-based approach,which restores files based on historical file access frequencies and prioritizes ensuring the availability of frequently accessed files;(ii)the graph-based approach,which preferentially restores the frequently accessed files as well as their correlated files based on historical access patterns,and(iii)the trie-based approach,which restores particular files based on both users’real-time and historical access patterns to deduce and restore the files to be accessed in the near future.We implement a prototype of Histore and evaluate its performance from multiple perspectives.Trace-driven experiments on two datasets show that Histore significantly reduces users’delay time by 4-700×with only 1.0%-14.5%additional performance overhead.
文摘The creator economy is revolutionizing the way in which individuals can profit from their engagement with online platforms.In this paper,we initiate the formal study of online learning in a creator economy by modeling it as a three-party game between users,a platform,and content creators.The platform interacts with creators through contracts under a principal-agent framework and with users via a recommender system.We study how the platform can jointly optimize contracts and recommendation policies in an online learning setting.We analyze return-based and feature-based contracts.Under smoothness assumptions,return-based contracts achieve regretΘ(T^(2/3)).For feature-based contracts,we introduce an intrinsic dimension d and prove a regret bound O(T^(d+1)/(d+2)),which is tight for linear families.
基金supported in part by National Natural Science Foundation of China under Grant 72401055in part by National Natural Science Foundation of China under Grant 52277083in part by the joint founding of Guangdong,and Dongguan under Grant 2023A1515110939.
文摘Existing load forecasting methods typically assume that recent load data are available for prediction.This is not in conformity with reality since there is a time gap between the flow date(when power is consumed)and when measurement values are obtained.To this end,this letter proposes an online learning-based probabilistic load forecasting method considering the impact of the data gap.Specifically,an adaptive ensemble backpropagation-enabled online quantile regression algorithm is developed to optimize the parameters of the attention network recursively using the newly obtained load observations.To further improve the reliability and sharpness of prediction intervals under significant data gaps,we introduce an online interval calibration technique.The proposed online learning method allows us to adaptively capture the dynamic changes in load patterns and alleviate the information lags caused by data gaps.Comparative tests utilizing real-world datasets reveal the superiority of the proposed method.
基金Science and Technology Development Program of the“Taihu Light”(K20231023)CMA Numerical Weather Prediction R&D Project(TCYF2024QH007)+1 种基金“Qing Lan”Project of Jiangsu Province for C.H.LUWuxi University Research Start-up Fund for Introduced Talents(2023r037)。
文摘Since the initiation of the subseasonal-to-seasonal prediction project by the World Meteorological Organization,the accuracy of model forecasts has improved notably.However,substantial discrepancies have been observed among forecast results produced by different ensemble members when applied to South China.To enhance the accuracy of sub-seasonal forecasts in this region,it is essential to develop new methods that can effectively leverage multiple predictive models.This study introduces a weighted ensemble forecasting method based on online learning to improve forecast accuracy.We utilized ensemble forecasts from three models:the Integrated Forecasting System model from the European Centre for Medium-Range Weather Forecasts,the Climate Forecast System Version 2 model from the National Centers for Environmental Prediction,and the Beijing Climate Center-Climate Prediction System version 3 model from the China Meteorological Administration.The ensemble weights are trained using an online learning approach.The results indicate that the forecasts obtained through online learning outperform those of the original dynamical models.Compared to the simple ensemble results of the three models,the weighted ensemble model showed a stronger capability to capture temperature and precipitation patterns in South China.Therefore,this method has the potential to improve the accuracy of sub-seasonal forecasts in this region.
基金supported in part by the National Key RD Program of China under Grant 2023YFB4204400,and in part by the National Natural Science Foundation of China under Grant 52125705.
文摘In practical microgrids,current saturation of inverters and power interaction coupling of different forms of DERs complicate the system's transient behaviors.Existing methods of online transient stability prediction(TSP)are suitable for power systems consisting of homogeneous distributed energy resources(DERs),thus showing limited accuracy for stability prediction of microgrids.This paper develops a deep-learning-based TSP method for accurate online prediction of microgrids consisting of diverse forms of DERs under current saturation.First,a general key input feature selection method for microgrid TSP is systematically designed to ensure prediction accuracy.It is derived from a comprehensive mechanism analysis of the influence of DER's intrinsic and interaction characteristics under current saturation.Besides,impacts of load fluctuation and fault change are also considered to improve robust prediction performance.Second,to further improve prediction accuracy,an online TSP model based on deep learning is developed by effectively using the powerful nonlinear mapping capability of the deep belief network(DBN).Then,by combining feature selection method and deep-learning-based TSP model,an online TSP method is derived.Test results show the proposed method greatly improves accuracy of microgrid TSP under complex operating conditions.Furthermore,the method effectively avoids feature redundancy and the curse of dimensionality.Numbers of input features are independent of the scale of microgrids.
基金funded by the National Key R&D Program of China under Grant(No.2022YFB3102901)National Natural Science Foundation of China(No.62072115,No.62102094)Shanghai Science and Technology Innovation Action Plan Project(No.22510713600).
文摘Topological information is very important for understanding different types of online web services,in particular,for online social networks(OSNs).People leverage such information for various applications,such as social relationship modeling,community detection,user profiling,and user behavior prediction.However,the leak of such information will also pose severe challenges for user privacy preserving due to its usefulness in characterizing users.Large-scale web crawling-based information probing is a representative way for obtaining topological information of online web services.In this paper,we explore how to defend against topological information probing for online web services,with a particular focus on online decentralized web services such as Mastodon.Different from traditional centralized web services,the federated nature of decentralized web services makes the identification of distributed crawlers even more difficult.We analyze the behavioral differences between legitimate users and crawlers in decentralized web services and highlight two key behavioral attributes that distinguish crawlers from legitimate users:instance interaction preferences and hop count in profile viewing patterns.Based on these insights:we propose a supervised machine learning-based framework for crawler detection,which is able to learn the federation-aware feature representations for users.To validate the framework’s effectiveness,we construct a labeled dataset that integrates real users with real-trace driven simulated crawlers in Mastodon.We use this dataset to train various supervised classifiers for crawler detection.Experimental results demonstrate that our framework can achieve an excellent classification performance.Moreover,it is observed that federation-aware features are effective in improving detection performance.
基金funded by Malaysian Ministry of Higher Education(MOHE)under the Fundamental Research Grant Scheme(FRGS/1/2023/SSI07/MMU/02/3)which is awarded to the Multimedia University.The project is led by the second author.
文摘Background:Music has proven to be vital in enhancing resilience and promotingwell-being.Previously,the impact of music in sports environments was solely investigated,while this paper applies it to study environments,standing out as pioneering research.The study consists of a systematic development of a conceptual framework based on theories of Uses and Gratification Expectancy(UGE)and perceived motivation based on music elements.Their components are observed variables influencing students’psychological well-being(as the dependent variable).Resilience is examined as a mediator,influencing the relationships of both observed and dependent variables.The main purpose of this study is to highlight the positive effects of online music consumption on the psychological well-being of students.Methods:Semi-structured qualitative interviews were conducted with eighteen final year creative multimedia undergraduate students belonging to five central region Malaysian universities,especially on their UGE needs,and a similar concept survey instrument with two hundred participants.The interview data were analysed through thematic analysis,while the survey data through descriptive and Partial Least Squares Structural Equation Modeling(PLS-SEM).Results:The results highlight that students gain motivation from online music,which positively affects their psychological well-being(β=0.190,p=0.003,f^(2)=0.037),while resilience significantly affects this relationship(β=0.562,p<0.001,f^(2)=0.461).However,the results also predict a partial relationship between constructs based on UGE with psychological well-being,mediated by resilience,i.e.,AT-UGE(β=0.021,p=0.783,f^(2)=0.000),SIPI-UGE(β=0.228,p=0.004,f^(2)=0.044).Conclusion:The outcome of the study reflected practical,meaningful,and statistically significant results.The majority of the predictors,with the exception of one,i.e.,AT-UGE,displayed a clear positive relation of online music consumption on the Psychological Well-being of students.Future research will explore varying contextual factors impacting online music-related gratifications,motivations,and resilience,along with additional potential mediators and moderators.
基金General Project of the 14th Five-Year Plan for Educational Science in Liaoning Province(2025):“Teaching Research on Group Narrative Painting Training to Improve College Students’Self-Efficacy and Psychological Resilience”(Project No.:JG25DB118)。
文摘To explore effective paths for improving college students’ mental health, this study integrates narrative therapy and painting therapy to design a 7-week online group psychological counseling program. A total of 121 volunteer college students participated as subjects, and themed painting counseling was conducted via Tencent Meeting. Five scales, including the General Self-Efficacy Scale, Self-Esteem Scale, and Self-Rating Depression Scale, were used for pre-test and post-test comparisons. The results show that after the intervention, students’ self-efficacy (t = -5.528, p = 0.000) and self-esteem level (t = -2.153, p = 0.033) significantly improved statistically, and depression and anxiety showed a positive improvement trend. The research indicates that online narrative painting therapy can effectively release students’ psychological pressure, promote in-depth self-cognition and interpersonal connection construction, providing an operable innovative paradigm for college mental health education. Its interactivity and effectiveness are compatible with the psychological needs and internet usage habits of contemporary college students.
基金supported by the National Social Science Fund of China(No.23BSH123).
文摘Background:Emerging adulthood is a critical period for ego identity exploration and consolidation,and self-presentation on social media constitutes a salient online context for this developmental process.However,limited research has explored the associations between self-presentation on WeChat Moments and ego identity.This study aims to examine these associations,focusing on the mediating role of online positive feedback and the moderating role of gender.Methods:Using a three-wave longitudinal design,this study followed 767 Chinese college students(Mean age=18.96 years)through cluster sampling.Participants completed self-report questionnaires assessing self-presentation on WeChat Moments,online positive feedback,and ego identity status.Data analyses were conducted using mediation modeling and multi-group structural equation modeling.Results:Authentic self-presentation was positively associated with identity achievement and negatively associated with identity diffusion,whereas positive self-presentation was linked to higher levels of identity foreclosure.Online positive feedback played a significant mediating role in the associations between self-presentation strategies and identity statuses,and gender differences were observed in this mediating pathway.For both males and females,authentic self-presentation was associated with higher identity achievement through online positive feedback.However,indirect associations with identity foreclosure and diffusion were observed only among females:authentic self-presentation was linked to lower levels,whereas positive self-presentation was linked to higher levels of foreclosure and diffusion through online positive feedback.No comparable indirect associations were detected among males.Conclusions:Online positive feedback is closely linked to self-presentation strategies and ego identity statuses,with these associations varying by gender.
基金supported by the Fundamental Research Funds for the Central Universities(No.CUC25SG013)the Foundation of Key Laboratory of Education Informatization for Nationalities(Yunnan Normal University),Ministry of Education(No.EIN2024C006).
文摘Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.
基金Supported by the National Natural Science Foundation of China(Grant Nos.12571317 and 12071133).
文摘In this paper,we study a class of Linear Fractional Programming on a nonempty bounded set,called the Problem(LFP),and design a branch and bound algorithm to find the global optimal solution of the problem(LFP).First,we convert the problem(LFP)to the equivalent problem(EP2).Secondly,by applying the linear relaxation technique to the problem(EP2),the linear relaxation programming problem(LRP2Y)was obtained.Then,the overall framework of the algorithm is given,and the convergence and complexity of the algorithm are analyzed.Finally,experimental results are listed to illustrate the effectiveness of the algorithm.
基金support from the National Natural Science Foundation of China(No.12002372)the Young Elite Scientists Sponsorship Program by China Association for Science and Technology(No.2022QNRC001)the Natural Science Foundation of Hunan Province,China(No.2021JJ40674)。
文摘The operational demands of a wide range significantly exacerbate combustion instability issues within ramjet combustor.To suppress combustion oscillations,an open-loop control system utilizing Linear Genetic Programming(LGP)has been developed for a full-scale annular ramjet combustor.The LGP is used to generate control laws that include multi-frequency forcing.These laws are then transformed into square waves to actuate the solenoid valve,which modulates the kerosene supply for open-loop control.The results show that the duty cycle has little effect on instability amplitude,whereas an increase in frequency leads to a remarked reduction in combustion amplitude.After five generations evolvements,the pressure amplitude is reduced by 40.6% under the optimal control law generated by LGP.Furthermore,the machine learning process is depicted using a proximity map of control law similarity,with the search pathway visualized by the steepest descent.All individuals go forward to the upper left corner of the map with the evolution process,terminating at the optimal individual of the fifth generation.
基金supported by the National Natural Sci‐ence Foundation of China(Grant No.62306325)。
文摘During the use of robotics in applications such as antiterrorism or combat,a motion-constrained pursuer vehicle,such as a Dubins unmanned surface vehicle(USV),must get close enough(within a prescribed zero or positive distance)to a moving target as quickly as possible,resulting in the extended minimum-time intercept problem(EMTIP).Existing research has primarily focused on the zero-distance intercept problem,MTIP,establishing the necessary or sufficient conditions for MTIP optimality,and utilizing analytic algorithms,such as root-finding algorithms,to calculate the optimal solutions.However,these approaches depend heavily on the properties of the analytic algorithm,making them inapplicable when problem settings change,such as in the case of a positive effective range or complicated target motions outside uniform rectilinear motion.In this study,an approach employing a high-accuracy and quality-guaranteed mixed-integer piecewise-linear program(QG-PWL)is proposed for the EMTIP.This program can accommodate different effective interception ranges and complicated target motions(variable velocity or complicated trajectories).The high accuracy and quality guarantees of QG-PWL originate from elegant strategies such as piecewise linearization and other developed operation strategies.The approximate error in the intercept path length is proved to be bounded to h^(2)/(4√2),where h is the piecewise length.
文摘Online examinations have become a dominant assessment mode,increasing concerns over academic integrity.To address the critical challenge of detecting cheating behaviours,this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification.The methodology utilises object detection models—You Only Look Once(YOLOv12),Faster Region-based Convolutional Neural Network(RCNN),and Single Shot Detector(SSD)MobileNet—integrated with classification models such as Convolutional Neural Networks(CNN),Bidirectional Gated Recurrent Unit(Bi-GRU),and CNN-LSTM(Long Short-Term Memory).Two distinct datasets were used:the Online Exam Proctoring(EOP)dataset from Michigan State University and the School of Computer Science,Duy Tan Unievrsity(SCS-DTU)dataset collected in a controlled classroom setting.A diverse set of cheating behaviours,including book usage,unauthorised interaction,internet access,and mobile phone use,was categorised.Comprehensive experiments evaluated the models based on accuracy,precision,recall,training time,inference speed,and memory usage.We evaluate nine detector-classifier pairings under a unified budget and score them via a calibrated harmonic mean of detection and classification accuracies,enabling deployment-oriented selection under latency and memory constraints.Macro-Precision/Recall/F1 and Receiver Operating Characteristic-Area Under the Curve(ROC-AUC)are reported for the top configurations,revealing consistent advantages of object-centric pipelines for fine-grained cheating cues.The highest overall score is achieved by YOLOv12+CNN(97.15%accuracy),while SSD-MobileNet+CNN provides the best speed-efficiency trade-off for edge devices.This research provides valuable insights into selecting and deploying appropriate deep learning models for maintaining exam integrity under varying resource constraints.
基金supported by the National Natural Science Foundation of China(Nos.52075516,61927814,62325507,and 52122511)the National Key Research and Development Program of China(No.2021YFF0502700)+2 种基金the Major Scientific and Technological Projects in Anhui Province(202103a05020005,202203a05020014)the Students’Innovation and Entrepreneurship Foundation of USTC(CY2022G09)the Hefei Municipal Natural Science Foundation(No.HZR2450)。
文摘Programmable/reprogrammable magneto-responsive composites(MRCs)are highly desirable for applications in soft robotics,morphable actuators,and biomedical devices due to their capabilities of undergoing reversible,complex,untethered,and rapid deformations.However,current MRC-based devices primarily rely on soft matrices,which revert to their original shapes and cease functioning when external magnetic fields are removed.Moreover,their magnetization programming,deformations,and functioning need to alternate between encoding and actuation platforms,limiting the adaptability and efficiency.Here,we present a reprogrammable magnetic shape-memory composite(RM-SMC)integrating a shape-memory polymer(SMP)skeleton with phase-transition magnetic microcapsules.High-intensity laser melts microcapsules for magnetic realignment under programmed fields,while low-intensity laser softens SMP for structural reconfiguration without compromising integrity.This dual-laser strategy facilitates in situ magnetization programming,shape morphing,and function execution within a single material system.Our innovative approach enables unique applications,including omnidirectional multi-degree-of-freedom actuators that can activate light switches,solar trackers that optimize energy capture,and adaptive impellers that modulate fluid pumping.By eliminating platform alternation and enabling shape/function retention post-actuation,the RM-SMC platform overcomes critical limitations in conventional MRCs,establishing a paradigm for multifunctional devices requiring persistent configuration control and field-independent operation.
基金financial support from EPSRC grants (EP/M027856/1 EP/M028240/1)
文摘In the present work, two new, （multi-）parametric programming （mp-P）-inspired algorithms for the solutionof mixed-integer nonlinear programming （MINLP） problems are developed, with their main focus being onprocess synthesis problems. The algorithms are developed for the special case in which the nonlinearitiesarise because of logarithmic terms, with the first one being developed for the deterministic case, and thesecond for the parametric case （p-MINLP）. The key idea is to formulate and solve the square system of thefirst-order Karush-Kuhn-Tucker （KKT） conditions in an analytical way, by treating the binary variables and/or uncertain parameters as symbolic parameters. To this effect, symbolic manipulation and solution tech-niques are employed. In order to demonstrate the applicability and validity of the proposed algorithms, twoprocess synthesis case studies are examined. The corresponding solutions are then validated using state-of-the-art numerical MINLP solvers. For p-MINLP, the solution is given by an optimal solution as an explicitfunction of the uncertain parameters.
基金supported by the National Science Foundation of China (70771080)Social Science Foundation of Ministry of Education (10YJC630233)
文摘The penalty function method, presented many years ago, is an important nu- merical method for the mathematical programming problems. In this article, we propose a dual-relax penalty function approach, which is significantly different from penalty func- tion approach existing for solving the bilevel programming, to solve the nonlinear bilevel programming with linear lower level problem. Our algorithm will redound to the error analysis for computing an approximate solution to the bilevel programming. The error estimate is obtained among the optimal objective function value of the dual-relax penalty problem and of the original bilevel programming problem. An example is illustrated to show the feasibility of the proposed approach.
