《嵌入式系统导论》课程师生互动系统的研究

对《嵌入式系统导论》课程师生互动系统进行了分析和研究,提出了一种基于．NET的《嵌入式系统导论》课程师生互动系统的详细设计方案,实现了电子作业、在线测试、学生成绩管理和上传下载资源等功能。     

学生在线学习网络安全系统设计

随着网络技术在教育领域的日益普及,新的学习方式正在改变着教育和学习系统.本文针对校园学生,设计了一套在线学习系统,主要从开发此系统的背景及系统特点出发,分别对其教育环境、应用技术、开发环境进行了阐述,重点对该系统的模块分析,数据库设计以及使用后的评价进行了总体论述.     

Blended Learning to Increase Student Satisfaction: An Exploratory Study

Undergraduate nursing research courses are often difficult to teach due to the challenging content and lack of student satisfaction. To address this issue, two nursing instructors and a librarian embedded online discussions into an accelerated format, introductory nursing research course. The study was conducted over two semesters with two different instructors. The researchers investigated if using the blended learning strategy of discussion boards enhanced the learning experience and tested their theory with two measures: a weekly qualitative questionnaire and a post-study survey. Results suggested that asynchronous online discussions increased student satisfaction in introductory nursing research course work.     

大规模在线协作学习分组方法及应用研究

学习孤独感问题是造成MOOC课程学习完成率低的原因之一,构建与学习者学习特征相适应的协作学习小组,可以有效解决学习孤独感问题。利用自编码神经网络提取在线学习者的关键特征,根据同质分组原则,利用模糊C均值算法对在线学习者进行迭代分组,使在线学习者从独自学习转变为以团队的形式进行协作学习,从而改善在线学习者的学习体验,降低学习孤独感。以edX平台上选择计算机科学与编程入门课程的19?846名在线学习者为实验对象,进行在线协作学习分组。实验结果表明,基于该分组方法,每个小组内学习者都有较高的同质性,可以很好地解决学习孤独感问题。     

Written Interaction: A Key Component in Online Learning

This study investigated the relationship of traditional social behavior to social communication via the Internet in a completely wired campus where every professor uses computers in classroom teaching, each residence is wired to the Internet, and every student is issued a laptop computer. It has been suggested that shy and socially isolated individuals communicate more on the Internet because it provides some protection from social anxiety. However, little research has empirically tested this assumption. In line with social network theory, we proposed, instead, that online social communication would complement or supplement the uses of face-to-face social contact resulting in a positive association between the two forms of social behaviors. We assessed the frequency and intimacy of traditional social behaviors, sociability, and shyness in 115 undergraduates (52 male, 63 female). These variables were then used to predict the frequency and intimacy of Internet social communication. Sociability and the frequency of traditional social behaviors were positively associated with the frequency of Internet social communication. The intimacy of traditional social behaviors was positively associated with the intimacy of Internet social communication. Overall, the findings supported the implications of social network theory in that online social communication appeared to complement or be an extension of traditional social behavior rather than being a compensatory medium for shy and socially anxious individuals. With relation to uses and gratifications theory, however, shyness was associated with increased intimate socializing over the Internet, indicating that traditional and Internet communication are not functionally equivalent.     

Clustering and Sequential Pattern Mining of Online Collaborative Learning Data

Group work is widespread in education. The growing use of online tools supporting group work generates huge amounts of data. We aim to exploit this data to support mirroring: presenting useful high-level views of information about the group, together with desired patterns characterizing the behavior of strong groups. The goal is to enable the groups and their facilitators to see relevant aspects of the group's operation and provide feedback if these are more likely to be associated with positive or negative outcomes and indicate where the problems are. We explore how useful mirror information can be extracted via a theory-driven approach and a range of clustering and sequential pattern mining. The context is a senior software development project where students use the collaboration tool TRAC. We extract patterns distinguishing the better from the weaker groups and get insights in the success factors. The results point to the importance of leadership and group interaction, and give promising indications if they are occurring. Patterns indicating good individual practices were also identified. We found that some key measures can be mined from early data. The results are promising for advising groups at the start and early identification of effective and poor practices, in time for remediation.     

基于MOSS 2007的网络协作学习研究与实现

网络课程作为网络教育的核心资源,已日益受到教育部门和教育专家、学者的广泛关注。同时,协作学习是目前教育界比较提倡的一种教育模式。该文以分析利用Microsoft Office SharePoint Server2007(MOSS2007)网络教学平台开展协作学习的可行性为起点,阐述MOSS2007知识共享和协同工作的功能,继而描述MOSS2007网络教学平台的基本结构,最后讨论该平台可实现的协作学习功能。     

Learning Online Brand Personality and Satisfaction: The Moderating Effects of Gaming Engagement

This research assesses the association between the perceived brand personality of interactive IT and users' satisfaction. In the model of this study, satisfaction is affected by the perceived brand personality that contains four dimensions: perceived imaginative personality, perceived cheerful personality, perceived successful personality, and perceived interactive personality. Gaming engagement moderates each model path. The statistical results indicate that the influences of imaginative personality, cheerful personality, and successful personality on satisfaction are significant, whereas the influence of interactive personality on satisfaction is insignificant. Meanwhile, the influence of imaginative personality, cheerful personality, and successful personality on satisfaction is moderated by engagement, whereas the remaining model path between interactive personality and satisfaction is not moderated. Last, the discussion and managerial implications based on the empirical results are provided.     

基于表示学习的在线学习交互质量评价方法

当今的教育模式发生着非常重大的变革,教育正在向泛在化、智能化、个性化的方向发展。以Massive Open Online Courses(MOOCs)为代表的在线教育逐渐进入大众视野,在线教育中的交互性成为了决定在线学习质量的关键。研究表明,学习过程中的交互为学习者提供了有效且高效的帮助和支持,对学习过程的评价反馈可以有效地提高学习效果。在教育领域,对学习者和学习资源之间的交互进行建模至关重要,表示学习技术为学习者和学习资源之间的顺序交互建模提供了具体方案。文中首先建立在线学习的交互网络模型,然后使用两个循环神经网络将网络中的学习者和学习资源节点嵌入到一个欧氏空间中,并提出交互质量评价指标,以判断学习者的学习效果是否达到预期。在实际数据集上的实验证明了所提方法的有效性。     

在线学习算法综述

随着信息技术的迅猛发展,尤其是互联网行业的广泛应用,越来越多的领域出现了对海量、高速到达的数据实时处理需求。如何从浩瀚的“数据海洋”中挖掘有用的知识变得尤为重要。传统批处理模式的机器学习算法在面临 大数据时变得力不从心,而在线学习通过流式计算框架,在内存中直接对数据实时运算,为大数据的学习提供了有力的工具,这类在线学习框架有望应对大数据背景下机器学习任务面临的困境与挑战。本文总结了经典和目前主流的在线学习算法,主要包括：(1）在线线性学习算法;(2）基于核的在线学习算法;(3）其他经典的在线学习算法;(4）在线学习算法的优化理论。本文介绍在线学习与深度学习结合方法的研究现状,探讨在线学习算法研究中的关键问题与应用场景,最后展望了在线学习下一步的研究方向。     

基于多代理的网络协作学习模型研究

多Agent技术在远程教育中的应用成为目前人工智能领域的研究热点。CSCL系统普遍存在智能化不足,交互性差的问题,据此结合Web技术和多Agent技术提出了一个新的基于多Agent的网络协作学习模型,给出了模型的体系结构,并对模型中几个主要的Agent的内部功能结构和同步协作过程进行了描述。     

基于校园上网行为感知的学生成绩预测方法

学生成绩预测旨在利用学生的相关信息预测其在未来的学业表现.随着校园信息化建设的持续推进,校园网络认证系统越来越完善,各高校逐步积累了丰富的学生校园上网行为数据.考虑到人的行为表现和学习能力密切相关,以校园上网行为感知为切入点,通过挖掘学生的上网行为日志来预测他们的成绩.为此,收集构建了一个同时包含学生校园上网行为和成绩数据的真实数据集,并通过数据分析证明两者之间确实存在一定的关联性.在此基础上,提出了一个端到端的双层自注意力网络(dual-level self-attention network, DEAN),引入级联式的自注意力机制来分别提取学生每一天的局部上网行为特征和长时间的全局上网行为特征,更好地解决了长行为序列建模问题.此外,通过多任务学习策略在统一的框架下同时解决面向不同专业的学生成绩预测问题,并设计了基于学生排名差的代价敏感损失来进一步提升方法的性能.实验结果表明：相比于传统的序列建模方法,所提出的方法具有更好的预测精度.     

Local Groups Online: Political Learning and Participation

Voluntary associations serve crucial roles in local communities and within our larger democratic society. They aggregate shared interests, collective will, and cultivate civic competencies that nurture democratic participation. People active in multiple local groups frequently act as opinion leaders and create “weak” social ties across groups. In Blacksburg and surrounding Montgomery County, Virginia, the Blacksburg Electronic Village (BEV) community computer network has helped to foster nearly universal Internet penetration. Set in this dense Internet context, the present study investigated if and how personal affiliation with local groups enhanced political participation in this high information and communication technology environment. This paper presents findings from longitudinal survey data that indicate as individuals’ uses of information technology within local formal groups increases over time, so do their levels and types of involvement in the group. Furthermore, these increases most often appear among people who serve as opinion leaders and maintain weak social ties in their communities. Individuals’ changes in community participation, interests and activities, and Internet use suggest ways in which group members act upon political motivations and interests across various group types.      

基于资源的计算机支持的协作式学习

本文首次提出了基于资源的计算机支持的协作式学习模式,所谓CSCLBR是指在网络环境下,通过学习角色的协作活动,实行以学习资源为主要表现形式的知识交互,和进行以知识获取为最终目的的资源重组,使学习者达到完成学习任务、获取知识的目的的学习模式。文中还进一步讨论了CSCLBR的结构、构建思路等,对设计和应用CSCLBR有重要的参考价值。     

MICSL: Multiple Iterative Constraint Satisfaction based Learning

A novel concept learning algorithm named, MICSL: Multiple Iterative Constraint Satisfaction based Learning, is presented. The algorithm utilizes mathematical programming and constraint satisfaction techniques towards uniform representation and management of both data and background knowledge. It offers a flexible enough learning framework and respective services. The representation flexibility of MICSL rests on a method that transforms propositional cases, represented as propositional clauses, into constraint equivalents. The theoretical background as well as the validity of the transformation process are analyzed and studied. Following a ‘general-to-specific’ generalization strategy the algorithm iterates on multiple calls of a constraint satisfaction process. The outcome is a consistent set of rules. Each rule composes a minimal model of the given set of cases. Theoretical results relating the solutions of a constraint satisfaction process and the minimal models of a set of cases are stated and proved. The performance of the algorithm on some real-world benchmark domains is assessed and compared with widely used machine learning systems, such as C4.5 and CN2. Issues related to the algorithm’s complexity are also raised and discussed.     

基于协同过滤的在线拍卖商品推荐

随着电子商务的发展，基于C2C环境的在线拍卖也迅速发展起来，用户数和拍卖商品数的急剧增加，使得信息过载和如何提高客户忠诚度这一问题凸现出来。而推荐系统则成了解决这一问题的手段之一。但是C2C和B2C环境存在很大的不同，对推荐系统的应用提出了一定的挑战。该文对用户在拍卖网站的行为进行了分析，在此基础上建立了用户的偏好模型，利用协同过滤技术进行拍卖商品的推荐。     

基于在线聚类的协同作弊团体识别方法

针对大规模服务计算环境中聚集反馈、协同作弊和虚假评价等问题,通过融合在线聚类与共谋欺骗检测技术,提出了一种支持大规模服务可信度分析的在线协同作弊用户发现方法.首先,根据大规模服务系统日志中用户反馈评分信息,综合考虑大规模服务计算的大数据特性问题,设计了一种新颖的基于改进更新规则的在线KMeans聚类算法：在基于随机梯度法的在线聚类算法的基础上,采用了一种改进的基于小批量学习的在线聚类方法;并且,通过自动修正权重的聚类分组方差计算,进行递减增量优化,提高了在线KMeans算法的聚类质量,同时保证了聚类算法的时间效率;然后,充分考虑了协同作弊团体的同谋行为特征和协同攻击现象,利用聚类分组的性质和同谋团体异常性的特征,检测出协同作弊团体.仿真实验结果表明：提出的基于在线聚类的协同作弊团体识别方法具有良好时间性能,有效地解决了大规模服务计算中虚假反馈的问题.     

基于在线学习行为分析的个性化学习推荐

随着在线课程和线上学习的普及,大量的在线学习行为数据被积累。如何利用数据挖掘技术分析积累的大数据,从而为教学决策和学习优化提供服务,已经成为新的研究重点。文中分析了在线学习的行为特征,挖掘学习者的性格特征与学习效率的关系,实现个性化学习方法推荐。首先,提取在线学习行为特征,并提出了一种基于BP神经网络的学习成绩预测方法,通过分析在线学习行为特征,预测其相应的线下学习成绩;其次,为了进一步分析学习者的在线学习行为与成绩的关系,提出了基于实际熵的在线学习行为规律性分析,通过分析学习者的在线学习行为,定义并计算相应的实际熵值来评估个体的学习行为规律性,从而分析规律性与最终成绩的关系;再次,基于Felder-Silverman性格分类法获得学习者的性格特征,对学习者实现基于K-means的聚类分析获得相似学习者的类别,将学习成绩较优的学习者的在线学习习惯推荐给同一类别的其他学习者,从而提高学习者的在线学习效率;最终,以某在线课程平台的实际数据为实验对象,分别实现在线学习行为特征提取、线下成绩预测、学习规律性分析和个性化学习推荐,从而验证了所提方法的有效性和应用价值。     

基于MAS的协作学习机制研究

基于多Agent技术构建了一个网上协作学习系统模型MACL,给出了系统的结构框架,就其中的学生模型的构建、协作学习小组的创建以及协作学习和评价机制进行了探讨,结合KQML通信机制设计了Agent的交互模型,并进一步研究了协作小组的创建策略和算法.     

协同深度学习推荐算法研究

针对当用户评分较少时,推荐系统由于数据稀疏推荐性能显著降低这一问题,介绍了协同深度学习算法（Collaborative In Deep Learning,CIDL）.本算法首先对大量数据进行深度学习,然后对数据文本进行挖掘提取词汇表,最后对评级（反馈）矩阵进行协同过滤,从而得出对用户的推荐项目.本文使用真实的电影数据进行实验,与另外四种优秀算法进行对比,证明该算法可以真实有效得解决由于数据稀疏使得性能降低的问题,并提高推荐的准确度.