In the current trend of educational digitization,online learning platforms have proliferated,making the visual design of digital learning resources increasingly critical.However,existing visual designs for online lear...In the current trend of educational digitization,online learning platforms have proliferated,making the visual design of digital learning resources increasingly critical.However,existing visual designs for online learning resources face numerous challenges.The emergence of AIGC(Artificial Intelligence-Generated Content)technology offers innovative solutions to these issues.This paper explores the application of AIGC technology in enhancing the“new quality productive forces”of visual design for online learning resources.It emphasizes the need to balance technological innovation with humanistic care and highlights the importance of human intervention in the design process.展开更多
Recent progress in topology optimization(TO)has seen a growing integration of machine learning to accelerate computation.Among these,online learning stands out as a promising strategy for large-scale TO tasks,as it el...Recent progress in topology optimization(TO)has seen a growing integration of machine learning to accelerate computation.Among these,online learning stands out as a promising strategy for large-scale TO tasks,as it eliminates the need for pre-collected training datasets by updating surrogate models dynamically using intermediate optimization data.Stress-constrained lightweight design is an important class of problem with broad engineering relevance.Most existing frameworks use pixel or voxel-based representations and employ the finite element method(FEM)for analysis.The limited continuity across finite elements often compromises the accuracy of stress evaluation.To overcome this limitation,isogeometric analysis is employed as it enables smooth representation of structures and thus more accurate stress computation.However,the complexity of the stress-constrained design problem together with the isogeometric representation results in a large computational cost.This work proposes a multi-grid,single-mesh online learning framework for isogeometric topology optimization(ITO),leveraging the Fourier Neural Operator(FNO)as a surrogate model.Operating entirely within the isogeometric analysis setting,the framework provides smooth geometry representation and precise stress computation,without requiring traditional mesh generation.A localized training approach is employed to enhance scalability,while a multi-grid decomposition scheme incorporates global structural context into local predictions to boost FNO accuracy.By learning the mapping from spatial features to sensitivity fields,the framework enables efficient single-resolution optimization,avoiding the computational burden of two-resolution simulations.The proposed method is validated through 2D stress-constrained design examples,and the effect of key parameters is studied.展开更多
An ontology and metadata for online learning resource repository management is constructed. First, based on the analysis of the use-case diagram, the upper ontology is illustrated which includes resource library ontol...An ontology and metadata for online learning resource repository management is constructed. First, based on the analysis of the use-case diagram, the upper ontology is illustrated which includes resource library ontology and user ontology, and evaluated from its function and implementation; then the corresponding class diagram, resource description framework （RDF） schema and extensible markup language （XML） schema are given. Secondly, the metadata for online learning resource repository management is proposed based on the Dublin Core Metadata Initiative and the IEEE Learning Technologies Standards Committee Learning Object Metadata Working Group. Finally, the inference instance is shown, which proves the validity of ontology and metadata in online learning resource repository management.展开更多
This article is based on research conducted for the European CommissionEducation & Training 2020 working group on digital and online learning(ET2020 WG-DOL) specifically regarding policy challenges, such as thefol...This article is based on research conducted for the European CommissionEducation & Training 2020 working group on digital and online learning(ET2020 WG-DOL) specifically regarding policy challenges, such as thefollowing: 1) Targeted policy guidance on innovative and open learningenvironments under outcome;2) Proposal for a quality assurance modelfor open and innovative learning environments, its impact on specificassessment frameworks and its implication for EU recognition and transparencyinstruments. The article aims to define quality in open, flexible,and online learning, particularly in open education, open educationalresources (OER), and massive open online courses (MOOC). Hence,quality domains, characteristics, and criteria are outlined and discussed,as well as how they contribute to quality and personal learning so thatlearners can orchestrate and take responsibility for their own learningpathways. An additional goal is to identify the major stakeholders directlyinvolved in open online education and to describe their visions, communalities,and conflicts regarding quality in open, flexible, and online learning.The article also focuses on quality in periods of crisis, such as duringthe pandemic in 2020. Finally, the article discusses the rationale and needfor a model of quality in open, flexible, and online learning based on threemajor criteria for quality: excellence, impact, and implementation fromthe learner’s perspective.展开更多
This paper examines the strategies of developing online learning in Chinese universities.Top-down strategies include policy,funding,Senior initiative and task-based management,etc,in which funding generally plays the ...This paper examines the strategies of developing online learning in Chinese universities.Top-down strategies include policy,funding,Senior initiative and task-based management,etc,in which funding generally plays the most important role followed by Senior initiative and task-based management.Bottom-up strategies,especially staff training and contest are often seen as essential to successfully improve online learning.展开更多
Purpose:Opinion mining and sentiment analysis in Online Learning Community can truly reflect the students’learning situation,which provides the necessary theoretical basis for following revision of teaching plans.To ...Purpose:Opinion mining and sentiment analysis in Online Learning Community can truly reflect the students’learning situation,which provides the necessary theoretical basis for following revision of teaching plans.To improve the accuracy of topic-sentiment analysis,a novel model for topic sentiment analysis is proposed that outperforms other state-of-art models.Methodology/approach:We aim at highlighting the identification and visualization of topic sentiment based on learning topic mining and sentiment clustering at various granularitylevels.The proposed method comprised data preprocessing,topic detection,sentiment analysis,and visualization.Findings:The proposed model can effectively perceive students’sentiment tendencies on different topics,which provides powerful practical reference for improving the quality of information services in teaching practice.Research limitations:The model obtains the topic-terminology hybrid matrix and the document-topic hybrid matrix by selecting the real user’s comment information on the basis of LDA topic detection approach,without considering the intensity of students’sentiments and their evolutionary trends.Practical implications:The implication and association rules to visualize the negative sentiment in comments or reviews enable teachers and administrators to access a certain plaint,which can be utilized as a reference for enhancing the accuracy of learning content recommendation,and evaluating the quality of their services.Originality/value:The topic-sentiment analysis model can clarify the hierarchical dependencies between different topics,which lay the foundation for improving the accuracy of teaching content recommendation and optimizing the knowledge coherence of related courses.展开更多
With the rapid global proliferation of the Internet and telecommunication networks, online education, one form of distance education is currently becoming the fastest growing trend of domestic and international educat...With the rapid global proliferation of the Internet and telecommunication networks, online education, one form of distance education is currently becoming the fastest growing trend of domestic and international education. A major challenge to designing online learning is the development of appropriate means to facilitate the social environment that is critical for higher order learning in many disciplines. In many online learning designs, the majority of resources are channeled to web interface design and technology, while little or no resources are devoted to facilitating the teaching and learning process, the negotiation of meaning and the validation of knowledge among peers and instructors that depends on a conducive socio-cultural environment and adequate learner support.展开更多
In the post-Covid-19 pandemic era,it is more difficult for some Chinese schools in Europe to provide online extra classes for overseas Chinese children after school hours,as they did previously.To meet students'mu...In the post-Covid-19 pandemic era,it is more difficult for some Chinese schools in Europe to provide online extra classes for overseas Chinese children after school hours,as they did previously.To meet students'multifaceted learning needs,online extra classes teaching,including online Chinese language classes and some online art classes,is increasingly being offered as a supplement to the diversity of teaching activities in Chinese schools in Europe,with the ultimate goal of improving the learning abilities of overseas Chinese children while relieving pressure on teaching resources in schools.Children’s learning self-efficacy in online extracurricular courses has its own uniqueness,which can be considered from three dimensions,including learning confidence,learning ability,and self-assessment ability.This study aims to examine the factors influencing the self-efficacy of overseas Chinese children and to make optimization suggestions for better teaching methods.In search of that,an online questionnaire survey with 127 participants from overseas Chinese children agedtowas collected.The findings indicate that the role of learning confidence in overseas Chinese children outweighs their learning ability and self-assessment ability.Gender and age have a negligible effect on self-efficacy but have an impact on learning confidence.Chinese schools in Europe do not need to show gender differences when conducting classroom activities in online teaching to improve the online self-efficacy of Chinese children,and efforts should also be made to keep the courage of older students to trial and error.Teachers are expected to investigate more aspects of their students'personalities in future classrooms rather than sticking to a consistent and unchanging teaching model.展开更多
The binary perceptron is the simplest artificial neural network formed by N input units and one output unit, with the neural states and the synaptic weights all restricted to ±1 values. The task in the teacher-st...The binary perceptron is the simplest artificial neural network formed by N input units and one output unit, with the neural states and the synaptic weights all restricted to ±1 values. The task in the teacher-student scenario is to infer the hidden weight vector by training on a set of labeled patterns. Previous efforts on the passive learning mode have shown that learning from independent random patterns is quite inefficient. Here we consider the active online learning mode in which the student designs every new Ising training pattern. We demonstrate that it is mathematically possible to achieve perfect(error-free) inference using only N designed training patterns, but this is computationally unfeasible for large systems. We then investigate two Bayesian statistical designing protocols, which require 2.3N and 1.9N training patterns, respectively, to achieve error-free inference. If the training patterns are instead designed through deductive reasoning, perfect inference is achieved using N + log_2N samples. The performance gap between Bayesian and deductive designing strategies may be shortened in future work by taking into account the possibility of ergodicity breaking in the version space of the binary perceptron.展开更多
Online learning algorithms are very attractive, in which iterations are applied efficiently instead of solving some optimization problems. In this paper, online learning with protecting privacy is considered. A pertur...Online learning algorithms are very attractive, in which iterations are applied efficiently instead of solving some optimization problems. In this paper, online learning with protecting privacy is considered. A perturbation term is added into the classical online algorithms to obtain the differential privacy property. Firstly the distribution for the perturbation term is deduced, and then an error analysis for the new algorithms is performed, which shows the convergence and learning rate. From the error analysis, a choice for the parameters for differential privacy can be found theoretically.展开更多
In emerging applications such as industrial control and autonomous driving,end-to-end deterministic quality of service(QoS)transmission guarantee has become an urgent problem to be solved.Internet congestion control a...In emerging applications such as industrial control and autonomous driving,end-to-end deterministic quality of service(QoS)transmission guarantee has become an urgent problem to be solved.Internet congestion control algorithms are essential to the performance of applications.However,existing congestion control schemes follow the best-effort principle of data transmission without the perception of application QoS requirements.To enable data delivery within application QoS constraints,we leverage an online learning mechanism to design Crimson,a novel congestion control algorithm in which each sender continuously observes the gap between current performance and pre-defined QoS.Crimson can change rates adaptively that satisfy application QoS requirements as a result.Across many emulation environments and real-world experiments,our proposed scheme can efficiently balance the different trade-offs between throughput,delay and loss rate.Crimson also achieves consistent performance over a wide range of QoS constraints under diverse network scenarios.展开更多
Students'demand for online learning has exploded during the post-COvID-19 pandemic era.However,due to their poor learning experience,students'dropout rate and learning performance of online learning are not al...Students'demand for online learning has exploded during the post-COvID-19 pandemic era.However,due to their poor learning experience,students'dropout rate and learning performance of online learning are not always satisfactory.The technical advantages of Beyond Fifth Generation(B5G)can guarantee a good multimedia Quality of Experience(QoE).As a special case of multimedia services,online learning takes into account both the usability of the service and the cognitive development of the users.Factors that affect the Quality of Online Learning Experience(OL-QoE)become more complicated.To get over this dilemma,we propose a systematic scheme by integrating big data,Machine Learning(ML)technologies,and educational psychology theory.Specifically,we first formulate a general definition of OL-QoE by data analysis and experimental verification.This formula considers both the subjective and objective factors(i.e.,video watching ratio and test scores)that most affect OLQoE.Then,we induce an extended layer to the classic Broad Learning System(BLS)to construct an Extended Broad Learning System(EBLS)for the students'OL-QoE prediction.Since the extended layer can increase the width of the BLS model and reduce the redundant nodes of BLS,the proposed EBLS can achieve a trade-off between the prediction accuracy and computation complexity.Finally,we provide a series of early intervention suggestions for different types of students according to their predicted OL-QoE values.Through timely interventions,their OL-QoE and learning performance can be improved.Experimental results verify the effectiveness oftheproposed scheme.展开更多
This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm f...This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.展开更多
BACKGROUND The coronavirus disease 2019(COVID-19)epidemic disrupted education systems by forcing systems to shift to emergency online leaning.Online learning satisfaction affects academic achievement.Many factors affe...BACKGROUND The coronavirus disease 2019(COVID-19)epidemic disrupted education systems by forcing systems to shift to emergency online leaning.Online learning satisfaction affects academic achievement.Many factors affect online learning satisfaction.However there is little study focused on personal characteristics,mental status,and coping style when college students participated in emergency online courses.regression analyses were performed to identify factors that affected online learning satisfaction.RESULTS Descriptive findings indicated that 62.9%(994/1580)of students were satisfied with online learning.Factors that had significant positive effects on online learning satisfaction were online learning at scheduled times,strong exercise intensity,good health,regular schedule,focusing on the epidemic less than one hour a day,and maintaining emotional stability.Positive coping styles were protective factors of online learning satisfaction.Risk factors for poor satisfaction were depression,neurasthenia,and negative coping style.CONCLUSION College students with different personal characteristics,mental status,and coping style exhibited different degrees of online learning satisfaction.Our findings provide reference for educators,psychologists,and school adminis-trators to conduct health education intervention of college students during emergency online learning.展开更多
At the beginning of 2020,the“COVID-19”came out.Affected by the outbreaks,the universities have to carry out online teaching.Online learning provides students with full freedom and personalized learning space,but at ...At the beginning of 2020,the“COVID-19”came out.Affected by the outbreaks,the universities have to carry out online teaching.Online learning provides students with full freedom and personalized learning space,but at the same time,it also brings problems such as weak feelings between teachers and students and lack of learning experience.To solve these problems,this paper adopts the methods of questionnaire survey,experimental control and behavioral modeling.This paper studies how teachers’emotional support behavior affects students’learning process and learning emotion in online learning environment,and proposes that teachers’emotional support behavior is appealed and desired by students.Positive teachers’emotional support behavior can promote students’learning process and improve students’learning emotion.展开更多
Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-l...Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-learning capabilities implementable on embedded systems with limited memory and computational power. We present a new solution called Spiral Recurrent Neural Networks (SpiralRNN) with an online learning based on an extended Kalman filter and gradients as in Real Time Recurrent Learning. We illustrate its stability and performance using artificial and real-life time series and compare its prediction performance to other approaches. SpiralRNNs perform very stable and show an ac-curacy which is superior or similar to other state-of-the-art approaches. In a memory capacity evaluation the number of simultaneously memorized and accurately retrievable trajectories of fixed length was counted. This capacity turned out to be a linear function of the size of the recurrent hidden layer, with a memory-to-size ratio of 0.64 for shorter trajectories and 0.31 for longer trajectories. Finally, we describe two potential applications in building automation and logistics and report on an implementation of online learning SpiralRNN on a wireless sensor platform under the TinyOS embedded operating system.展开更多
Background:In response to the need to mitigate the increase in Coronavirus Disease 2019(COVID-19)cases,nursing students undertake online learning in almost all nursing education institutions in Indonesia.These student...Background:In response to the need to mitigate the increase in Coronavirus Disease 2019(COVID-19)cases,nursing students undertake online learning in almost all nursing education institutions in Indonesia.These students face distinctive learning experiences,which have not yet been identified in the Indonesian context.This study aimed to explore students’experiences of online learning during the COVID-19 pandemic.Methods:We used a descriptive exploratory design.Eleven students from three nursing education institutions in Indonesia were interviewed through telephone calls or video conference applications.Results:One main theme,Gaining access in resource-limited circumstances,was developed to describe students’experience of online learning during the COVID-19 pandemic.This theme was supported by five subthemes:struggling for internet connection;becoming familiar with the applications;flexibility;supported by others;and dealing with limitations.Conclusions:This current study provides insights into what support should be provided for nursing students to manage limitations in the online learning process.展开更多
With the advent of the big data era, personalized self-adaptive learning is implemented for college students, which promotes the balanced development of all aspects of their abilities and leads to changes in their lea...With the advent of the big data era, personalized self-adaptive learning is implemented for college students, which promotes the balanced development of all aspects of their abilities and leads to changes in their learning styles. Quality assurance and personalized education of online education have become an important direction for the further development of distance education. At present, in the online education platform, learners' participation in learning activities is not high, and educational managers and teachers do not have in-depth understanding of learners' learning status. Based on this, the article explores the connotation and components of online learning based on the background of big data, and studies the online learning process control of college students from the aspects of information retrieval power, network self-control and practice transformation. The purpose is to explore the application of big data in learning process control, establish a learning process control strategy model based on big data, and verify the effectiveness of the strategy model and control strategy by designing a variety of different control experiments to provide ideas for controlling experiments.展开更多
Through a three year qualitative research study, the researcher examed how faculty in higher education are thinking about, constructing and developing interactive learning enviorments, and identified five fundeamental...Through a three year qualitative research study, the researcher examed how faculty in higher education are thinking about, constructing and developing interactive learning enviorments, and identified five fundeamental foutors to consider in developing effective online learning communities, Which may help to negotiate the new enviorment for students and faculty.展开更多
文摘In the current trend of educational digitization,online learning platforms have proliferated,making the visual design of digital learning resources increasingly critical.However,existing visual designs for online learning resources face numerous challenges.The emergence of AIGC(Artificial Intelligence-Generated Content)technology offers innovative solutions to these issues.This paper explores the application of AIGC technology in enhancing the“new quality productive forces”of visual design for online learning resources.It emphasizes the need to balance technological innovation with humanistic care and highlights the importance of human intervention in the design process.
基金supported by the Hong Kong Research Grants under Competitive Earmarked Research Grant No.16206320.
文摘Recent progress in topology optimization(TO)has seen a growing integration of machine learning to accelerate computation.Among these,online learning stands out as a promising strategy for large-scale TO tasks,as it eliminates the need for pre-collected training datasets by updating surrogate models dynamically using intermediate optimization data.Stress-constrained lightweight design is an important class of problem with broad engineering relevance.Most existing frameworks use pixel or voxel-based representations and employ the finite element method(FEM)for analysis.The limited continuity across finite elements often compromises the accuracy of stress evaluation.To overcome this limitation,isogeometric analysis is employed as it enables smooth representation of structures and thus more accurate stress computation.However,the complexity of the stress-constrained design problem together with the isogeometric representation results in a large computational cost.This work proposes a multi-grid,single-mesh online learning framework for isogeometric topology optimization(ITO),leveraging the Fourier Neural Operator(FNO)as a surrogate model.Operating entirely within the isogeometric analysis setting,the framework provides smooth geometry representation and precise stress computation,without requiring traditional mesh generation.A localized training approach is employed to enhance scalability,while a multi-grid decomposition scheme incorporates global structural context into local predictions to boost FNO accuracy.By learning the mapping from spatial features to sensitivity fields,the framework enables efficient single-resolution optimization,avoiding the computational burden of two-resolution simulations.The proposed method is validated through 2D stress-constrained design examples,and the effect of key parameters is studied.
基金The Advanced University Action Plan of the Minis-try of Education of China (2004XD-03).
文摘An ontology and metadata for online learning resource repository management is constructed. First, based on the analysis of the use-case diagram, the upper ontology is illustrated which includes resource library ontology and user ontology, and evaluated from its function and implementation; then the corresponding class diagram, resource description framework （RDF） schema and extensible markup language （XML） schema are given. Secondly, the metadata for online learning resource repository management is proposed based on the Dublin Core Metadata Initiative and the IEEE Learning Technologies Standards Committee Learning Object Metadata Working Group. Finally, the inference instance is shown, which proves the validity of ontology and metadata in online learning resource repository management.
文摘This article is based on research conducted for the European CommissionEducation & Training 2020 working group on digital and online learning(ET2020 WG-DOL) specifically regarding policy challenges, such as thefollowing: 1) Targeted policy guidance on innovative and open learningenvironments under outcome;2) Proposal for a quality assurance modelfor open and innovative learning environments, its impact on specificassessment frameworks and its implication for EU recognition and transparencyinstruments. The article aims to define quality in open, flexible,and online learning, particularly in open education, open educationalresources (OER), and massive open online courses (MOOC). Hence,quality domains, characteristics, and criteria are outlined and discussed,as well as how they contribute to quality and personal learning so thatlearners can orchestrate and take responsibility for their own learningpathways. An additional goal is to identify the major stakeholders directlyinvolved in open online education and to describe their visions, communalities,and conflicts regarding quality in open, flexible, and online learning.The article also focuses on quality in periods of crisis, such as duringthe pandemic in 2020. Finally, the article discusses the rationale and needfor a model of quality in open, flexible, and online learning based on threemajor criteria for quality: excellence, impact, and implementation fromthe learner’s perspective.
文摘This paper examines the strategies of developing online learning in Chinese universities.Top-down strategies include policy,funding,Senior initiative and task-based management,etc,in which funding generally plays the most important role followed by Senior initiative and task-based management.Bottom-up strategies,especially staff training and contest are often seen as essential to successfully improve online learning.
基金supported by the Teaching Research Major Projects of Anhui Province(2018jyxm1446)the Natural Scientific Project of Anhui Provincial Department of Education(KJ2019A0371)+1 种基金the Anhui Demonstration Experiment Training Center Project(2018sxzx58)the Demonstration Projects for Massive Open Online Course of Anhui Province(2018mooc278)。
文摘Purpose:Opinion mining and sentiment analysis in Online Learning Community can truly reflect the students’learning situation,which provides the necessary theoretical basis for following revision of teaching plans.To improve the accuracy of topic-sentiment analysis,a novel model for topic sentiment analysis is proposed that outperforms other state-of-art models.Methodology/approach:We aim at highlighting the identification and visualization of topic sentiment based on learning topic mining and sentiment clustering at various granularitylevels.The proposed method comprised data preprocessing,topic detection,sentiment analysis,and visualization.Findings:The proposed model can effectively perceive students’sentiment tendencies on different topics,which provides powerful practical reference for improving the quality of information services in teaching practice.Research limitations:The model obtains the topic-terminology hybrid matrix and the document-topic hybrid matrix by selecting the real user’s comment information on the basis of LDA topic detection approach,without considering the intensity of students’sentiments and their evolutionary trends.Practical implications:The implication and association rules to visualize the negative sentiment in comments or reviews enable teachers and administrators to access a certain plaint,which can be utilized as a reference for enhancing the accuracy of learning content recommendation,and evaluating the quality of their services.Originality/value:The topic-sentiment analysis model can clarify the hierarchical dependencies between different topics,which lay the foundation for improving the accuracy of teaching content recommendation and optimizing the knowledge coherence of related courses.
文摘With the rapid global proliferation of the Internet and telecommunication networks, online education, one form of distance education is currently becoming the fastest growing trend of domestic and international education. A major challenge to designing online learning is the development of appropriate means to facilitate the social environment that is critical for higher order learning in many disciplines. In many online learning designs, the majority of resources are channeled to web interface design and technology, while little or no resources are devoted to facilitating the teaching and learning process, the negotiation of meaning and the validation of knowledge among peers and instructors that depends on a conducive socio-cultural environment and adequate learner support.
基金This paper is funded by research project of National College Student Innovation and Entrepreneurship Project of Wenzhou University in 2022,“A Study of Teaching Practices and Validity of Online Extra Classes of Chinese Schools in Europe”under Project No.202210351019 and research project of Wenzhou University Student Scientific Research Project(“Challenge Cup”Special Project)in 2022“Qiaozhiqiao-Chinese Ethnic Identity Education of Overseas Chinese Children”under Project No.2022kx220.
文摘In the post-Covid-19 pandemic era,it is more difficult for some Chinese schools in Europe to provide online extra classes for overseas Chinese children after school hours,as they did previously.To meet students'multifaceted learning needs,online extra classes teaching,including online Chinese language classes and some online art classes,is increasingly being offered as a supplement to the diversity of teaching activities in Chinese schools in Europe,with the ultimate goal of improving the learning abilities of overseas Chinese children while relieving pressure on teaching resources in schools.Children’s learning self-efficacy in online extracurricular courses has its own uniqueness,which can be considered from three dimensions,including learning confidence,learning ability,and self-assessment ability.This study aims to examine the factors influencing the self-efficacy of overseas Chinese children and to make optimization suggestions for better teaching methods.In search of that,an online questionnaire survey with 127 participants from overseas Chinese children agedtowas collected.The findings indicate that the role of learning confidence in overseas Chinese children outweighs their learning ability and self-assessment ability.Gender and age have a negligible effect on self-efficacy but have an impact on learning confidence.Chinese schools in Europe do not need to show gender differences when conducting classroom activities in online teaching to improve the online self-efficacy of Chinese children,and efforts should also be made to keep the courage of older students to trial and error.Teachers are expected to investigate more aspects of their students'personalities in future classrooms rather than sticking to a consistent and unchanging teaching model.
基金Supported by the National Natural Science Foundation of China under Grant Nos.11421063 and 11747601the Chinese Academy of Sciences under Grant No.QYZDJ-SSW-SYS018
文摘The binary perceptron is the simplest artificial neural network formed by N input units and one output unit, with the neural states and the synaptic weights all restricted to ±1 values. The task in the teacher-student scenario is to infer the hidden weight vector by training on a set of labeled patterns. Previous efforts on the passive learning mode have shown that learning from independent random patterns is quite inefficient. Here we consider the active online learning mode in which the student designs every new Ising training pattern. We demonstrate that it is mathematically possible to achieve perfect(error-free) inference using only N designed training patterns, but this is computationally unfeasible for large systems. We then investigate two Bayesian statistical designing protocols, which require 2.3N and 1.9N training patterns, respectively, to achieve error-free inference. If the training patterns are instead designed through deductive reasoning, perfect inference is achieved using N + log_2N samples. The performance gap between Bayesian and deductive designing strategies may be shortened in future work by taking into account the possibility of ergodicity breaking in the version space of the binary perceptron.
文摘Online learning algorithms are very attractive, in which iterations are applied efficiently instead of solving some optimization problems. In this paper, online learning with protecting privacy is considered. A perturbation term is added into the classical online algorithms to obtain the differential privacy property. Firstly the distribution for the perturbation term is deduced, and then an error analysis for the new algorithms is performed, which shows the convergence and learning rate. From the error analysis, a choice for the parameters for differential privacy can be found theoretically.
基金supported by the National Natural Science Foundation of China under Grant 62132009 and 61872211。
文摘In emerging applications such as industrial control and autonomous driving,end-to-end deterministic quality of service(QoS)transmission guarantee has become an urgent problem to be solved.Internet congestion control algorithms are essential to the performance of applications.However,existing congestion control schemes follow the best-effort principle of data transmission without the perception of application QoS requirements.To enable data delivery within application QoS constraints,we leverage an online learning mechanism to design Crimson,a novel congestion control algorithm in which each sender continuously observes the gap between current performance and pre-defined QoS.Crimson can change rates adaptively that satisfy application QoS requirements as a result.Across many emulation environments and real-world experiments,our proposed scheme can efficiently balance the different trade-offs between throughput,delay and loss rate.Crimson also achieves consistent performance over a wide range of QoS constraints under diverse network scenarios.
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX20_0733)Education Reform Foundation of Jiangsu Province(Grant No.2021JSJG364)+1 种基金Key Education Reform Foundation of NJUPT(Grant No.JG00220JX02,JG00218JX03,JG00215JX01,JG00214JX52)the Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘Students'demand for online learning has exploded during the post-COvID-19 pandemic era.However,due to their poor learning experience,students'dropout rate and learning performance of online learning are not always satisfactory.The technical advantages of Beyond Fifth Generation(B5G)can guarantee a good multimedia Quality of Experience(QoE).As a special case of multimedia services,online learning takes into account both the usability of the service and the cognitive development of the users.Factors that affect the Quality of Online Learning Experience(OL-QoE)become more complicated.To get over this dilemma,we propose a systematic scheme by integrating big data,Machine Learning(ML)technologies,and educational psychology theory.Specifically,we first formulate a general definition of OL-QoE by data analysis and experimental verification.This formula considers both the subjective and objective factors(i.e.,video watching ratio and test scores)that most affect OLQoE.Then,we induce an extended layer to the classic Broad Learning System(BLS)to construct an Extended Broad Learning System(EBLS)for the students'OL-QoE prediction.Since the extended layer can increase the width of the BLS model and reduce the redundant nodes of BLS,the proposed EBLS can achieve a trade-off between the prediction accuracy and computation complexity.Finally,we provide a series of early intervention suggestions for different types of students according to their predicted OL-QoE values.Through timely interventions,their OL-QoE and learning performance can be improved.Experimental results verify the effectiveness oftheproposed scheme.
文摘This paper deals with deriving the properties of updated neural network model that is exploited to identify an unknown nonlinear system via the standard gradient learning algorithm. The convergence of this algorithm for online training the three-layer neural networks in stochastic environment is studied. A special case where an unknown nonlinearity can exactly be approximated by some neural network with a nonlinear activation function for its output layer is considered. To analyze the asymptotic behavior of the learning processes, the so-called Lyapunov-like approach is utilized. As the Lyapunov function, the expected value of the square of approximation error depending on network parameters is chosen. Within this approach, sufficient conditions guaranteeing the convergence of learning algorithm with probability 1 are derived. Simulation results are presented to support the theoretical analysis.
基金The study protocol was approved by the Ethics Committee of Hebei General University and complied strictly with ethical requirements.Ethics Review No.2020 scientific ethics No.30.
文摘BACKGROUND The coronavirus disease 2019(COVID-19)epidemic disrupted education systems by forcing systems to shift to emergency online leaning.Online learning satisfaction affects academic achievement.Many factors affect online learning satisfaction.However there is little study focused on personal characteristics,mental status,and coping style when college students participated in emergency online courses.regression analyses were performed to identify factors that affected online learning satisfaction.RESULTS Descriptive findings indicated that 62.9%(994/1580)of students were satisfied with online learning.Factors that had significant positive effects on online learning satisfaction were online learning at scheduled times,strong exercise intensity,good health,regular schedule,focusing on the epidemic less than one hour a day,and maintaining emotional stability.Positive coping styles were protective factors of online learning satisfaction.Risk factors for poor satisfaction were depression,neurasthenia,and negative coping style.CONCLUSION College students with different personal characteristics,mental status,and coping style exhibited different degrees of online learning satisfaction.Our findings provide reference for educators,psychologists,and school adminis-trators to conduct health education intervention of college students during emergency online learning.
基金Higher Education Society of Shaanxi Province 2019 Higher Education Science Research Project(XGH19120:Wisdom Teaching Scene in Cloud model evaluation system key technology research)2019 school-level Higher Education Science Research Project(GJY-2019-YB-20).
文摘At the beginning of 2020,the“COVID-19”came out.Affected by the outbreaks,the universities have to carry out online teaching.Online learning provides students with full freedom and personalized learning space,but at the same time,it also brings problems such as weak feelings between teachers and students and lack of learning experience.To solve these problems,this paper adopts the methods of questionnaire survey,experimental control and behavioral modeling.This paper studies how teachers’emotional support behavior affects students’learning process and learning emotion in online learning environment,and proposes that teachers’emotional support behavior is appealed and desired by students.Positive teachers’emotional support behavior can promote students’learning process and improve students’learning emotion.
文摘Distributed intelligent systems like self-organizing wireless sensor and actuator networks are supposed to work mostly autonomous even under changing environmental conditions. This requires robust and efficient self-learning capabilities implementable on embedded systems with limited memory and computational power. We present a new solution called Spiral Recurrent Neural Networks (SpiralRNN) with an online learning based on an extended Kalman filter and gradients as in Real Time Recurrent Learning. We illustrate its stability and performance using artificial and real-life time series and compare its prediction performance to other approaches. SpiralRNNs perform very stable and show an ac-curacy which is superior or similar to other state-of-the-art approaches. In a memory capacity evaluation the number of simultaneously memorized and accurately retrievable trajectories of fixed length was counted. This capacity turned out to be a linear function of the size of the recurrent hidden layer, with a memory-to-size ratio of 0.64 for shorter trajectories and 0.31 for longer trajectories. Finally, we describe two potential applications in building automation and logistics and report on an implementation of online learning SpiralRNN on a wireless sensor platform under the TinyOS embedded operating system.
基金supported by Universitas Tanjungpura Pontianak,Indonesia (No. 2367/UN22.9/PG/2020)
文摘Background:In response to the need to mitigate the increase in Coronavirus Disease 2019(COVID-19)cases,nursing students undertake online learning in almost all nursing education institutions in Indonesia.These students face distinctive learning experiences,which have not yet been identified in the Indonesian context.This study aimed to explore students’experiences of online learning during the COVID-19 pandemic.Methods:We used a descriptive exploratory design.Eleven students from three nursing education institutions in Indonesia were interviewed through telephone calls or video conference applications.Results:One main theme,Gaining access in resource-limited circumstances,was developed to describe students’experience of online learning during the COVID-19 pandemic.This theme was supported by five subthemes:struggling for internet connection;becoming familiar with the applications;flexibility;supported by others;and dealing with limitations.Conclusions:This current study provides insights into what support should be provided for nursing students to manage limitations in the online learning process.
文摘With the advent of the big data era, personalized self-adaptive learning is implemented for college students, which promotes the balanced development of all aspects of their abilities and leads to changes in their learning styles. Quality assurance and personalized education of online education have become an important direction for the further development of distance education. At present, in the online education platform, learners' participation in learning activities is not high, and educational managers and teachers do not have in-depth understanding of learners' learning status. Based on this, the article explores the connotation and components of online learning based on the background of big data, and studies the online learning process control of college students from the aspects of information retrieval power, network self-control and practice transformation. The purpose is to explore the application of big data in learning process control, establish a learning process control strategy model based on big data, and verify the effectiveness of the strategy model and control strategy by designing a variety of different control experiments to provide ideas for controlling experiments.
文摘Through a three year qualitative research study, the researcher examed how faculty in higher education are thinking about, constructing and developing interactive learning enviorments, and identified five fundeamental foutors to consider in developing effective online learning communities, Which may help to negotiate the new enviorment for students and faculty.
