Mining e-Learning domain concept map from academic articles

Recent researches have demonstrated the importance of concept map and its versatile applications especially in e-Learning. For example, while designing adaptive learning materials, designers need to refer to the concept map of a subject domain. Moreover, concept maps can show the whole picture and core knowledge about a subject domain. Research from literature also suggests that graphical representation of domain knowledge can reduce the problems of information overload and learning disorientation for learners. However, construction of concept maps typically relied upon domain experts in the past; it is a time consuming and high cost task. Concept maps creation for emerging new domains such as e-Learning is even more challenging due to its ongoing development nature. The aim of this paper is to construct e-Learning domain concept maps from academic articles. We adopt some relevant journal articles and conference papers in e-Learning domain as data sources, and apply text-mining techniques to automatically construct concept maps for e-Learning domain. The constructed concept maps can provide a useful reference for researchers, who are new to the e-Leaning field, to study related issues, for teachers to design adaptive learning materials, and for learners to understand the whole picture of e-Learning domain knowledge.     

Potential pedagogical benefits and drawbacks of multimedia use in the English language classroom equipped with interactive whiteboard technology

This paper analyses the process of multimedia integration in English language classrooms equipped with interactive whiteboard (IWB) technology, and offers insights into the theoretical underpinnings of multimedia use in language learning from the perspective of cognitive learning theory. The data discussed here are drawn from a study carried out as part of a PhD research programme at Lancaster University (UK). The study was conducted within an interpretative research paradigm, and data were collected and analysed according to a qualitative approach. In the first part, the paper discusses some perceived pedagogical benefits of adopting a multimedia-oriented approach in the IWB-based classroom. Secondly, it discusses a variety of potential problems related to the use of multimedia resources in the language classroom in question. Finally, the paper draws upon the literature on multimedia learning to address the potential pedagogical implications of these research findings.     

The preferences toward constructivist Internet-based learning environments among university students in Taiwan

Numerous educators have proposed the development of constructivist Internet-based learning environments for students. When creating the constructivist Internet-based learning environments, it is important for researchers to be aware of students’ preferences toward these environments. Through gathering data from 659 university students in Taiwan, this study developed a questionnaire to assess students’ preferences toward constructivist Internet-based learning environments. The questionnaire, with adequate validity and reliability, included 34 items on the following seven scales: relevance, multiple sources (and interpretations), challenge, student negotiation, cognitive apprenticeship, reflective thinking and epistemological awareness. The questionnaire responses revealed that male students tended to prefer the Internet-based learning environments where they could solve challenging problems, acquire cognitive apprenticeship and guidance from experts, and promote epistemological development than did female students. The findings also suggested that, if educators intend to develop Internet-based learning environments for more academically advanced students, such as graduate students, care should be taken to create more opportunities for them to negotiate ideas, obtain proper guidance, reflect their own thoughts, and explore epistemological issues. Finally, students with more Internet experiences tended to demand more on many features of the constructivist Internet-based learning environments than those with less Internet experiences.     

Rollout sampling approximate policy iteration

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.     

Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine

It is well recognized that the impact-acoustic emissions contain information that can indicate the presence of the adhesive defects in the bonding structures. In our previous papers, artificial neural network (ANN) was adopted to assess the bonding integrity of the tile–walls with the feature extracted from the power spectral density (PSD) of the impact-acoustic signals acting as the input of classifier. However, in addition to the inconvenience posed by the general drawbacks such as long training time and large number of training samples needed, the performance of the classic ANN classifier is deteriorated by the similar spectral characteristics between different bonding status caused by abnormal impacts. In this paper our previous works was developed by the employment of the least-squares support vector machine (LS-SVM) classifier instead of the ANN to derive a bonding integrity recognition approach with better reliability and enhanced immunity to surface roughness. With the help of the specially designed artificial sample slabs, experiments results obtained with the proposed method are provided and compared with that using the ANN classifier, demonstrating the effectiveness of the present strategy.     

一种多分类器集成的手写体汉字识别方法

多分类器集成是手写体汉字识别领域的新方向。本文提出的多分类器集成方法通过改进的欧氏距离分类器将待识别汉字分类到某个粗分结果集中,然后根据粗分结果集选择1-N(one-against-rest)的SVM分类器对待识别汉字进行细分,最后用贝叶斯集成两级分类器。实验对国标一级汉字中的1034个手写汉字进行识别,证明了方案的有效性。     

基于主次原型超平面最接近支持向量机

基于广义特征值的最接近支持向量机GEPSVM是一种新的具有与SVM性能相当的两类分类方法,通过求解广义特征值来获得两个彼此不平行的拟合两类样本的超平面,其决策规则是将测试样本归为距其最近的超平面所在的类。然而,该规则在某些情形会导致较差的分类结果。对此,本文提出了在利用GEPSVM产生一个主原型超平面的基础上,再利用主原型超平面及它类样本的信息构造一个次原型超平面,形成一个由主次原型超平面共同决策的最接近支持向量机。该方法不仅简单且易于实现,而且具有较GEPSVM更优的分类性能。在UCI数据集上的实验验证了它的有效性。     

集成学习算法在不平衡分类中的应用研究

提出一种基于训练集分解的不平衡分类算法,该算法使用能输出后验概率的支持向量机作为分类器,使用基于测度层次信息源合并规则实现分类器的集成.在4个不同领域的不平衡数据集上的仿真实验表明:该算法有效提高分类器对正类样本的正确率,同时尽量减少对负类样本的误判.实验结果验证集成学习算法处理不平衡分类问题的有效性.     

实现兼类样本增量学习的一种算法

针对兼类样本,提出一种增量学习算法.利用超球支持向量机,在特征空间对属于同一类别的样本求得一个能包围该类尽可能多样本的最小超球,使各类样本之间通过超球隔开.增量学习过程中,只对新增样本以及与新增样本具有相同兼类的旧样本集中的支持向量进行训练,且每次训练只针对一类样本,使得算法在很小的样本集、很小的空间代价下实现兼类样本增量学习,同时保留了与新增样本类别无关的历史训练结果.分类过程中,通过计算待分类样本到各超球球心的距离判定其所属类别,分类准确快捷.实验结果证明了该算法的有效性.     

基于宠物游戏的智能教学系统

通过利用游戏宠物扮演各种教育角色,扩展智能教学系统(intelligent tutoring system,ITS)中的学生模型,从而完成宠物游戏与ITS的有机结合.设计了一个基于宠物游戏的游戏化智能教学系统架构,架构中的宠物模块能记录学习者的学习活动、分析学习者的学习进程.基于该软件架构,实现了一款游戏化智能教学系统--宠物星际旅行,将宠物游戏的游戏化特性引入到了小学分数知识的学习过程中.测试结果表明,学生对该游戏越专注,就能越快地理解和运用所学知识.