采用贝叶斯网络建立一种智能学习环境学生代理模型的研究

贝叶斯（Bayesian）网络近年成为智能代理引人注目的研究方向，本文在介绍Bayesian网络及其构建方法、学习方法的基础上，构建了一个通用的可扩展的智能学习环境中的学生模型。     

高职学生学习行为影响因素分类模型设计与实现

高职学生个性化学习行为是目前高等教育比较重要的研究方向,本文以心理学、教育学理论为基础、结合计算机数据挖掘技术,选择合适的分类算法构建了一个通用的、可扩展的、智能学习环境中的高职学生学习模型。     

基于Web和数据挖掘的ITS系统的设计与实现

网络化和智能化是计算机辅助教学发展的两大趋势,基于网络环境的智能教学系统(ITS)的研究已经成为当前和今后相当长时期的一个重要课题。本文结合“首都师范大学智能教学系统”的开发过程,主要讨论了系统模型的构建、数据挖掘技术的应用以及知识库、教师模型、认知型学生模型的建构、基于模糊理论的知识表示和推理等关键技术和实现方法。目的在于借助通用的、一般的技术手段,为学习者提供一个自主的、智能化、个性化的、有利于学生意义建构的学习环境。     

Agent技术在智能教学系统中的应用与研究

在传统的学习平台的基础上,以人本主义学习理论和建构主义学习理论为指导,将Agent技术应用于智能教学系统的构建和研究,为越来越多的学习者提供更加智能化和人性化的协同学习环境和协同学习方法,也为现代教育模式的研究和素质教育的大发展提供了一个新的思路.以多Agent技术为基础,提出了一种新的基于Agent的智能教学系统框架,并讨论了其主要功能及实现该系统的部分关键技术.     

改进的ID3算法在学习模型中的研究与应用

ID3算法是决策树中的核心算法,文章针对ID3算法倾向于取值较多的属性的缺点,引进用户兴趣度对ID3算法作了改进,并在此基础上构建了一个通用的可扩展的智能学习环境中的学生学习模型.     

智能试郑生成和自适应考试系统

介绍了一种基于项目反应理论的智能组卷及自适应考试系统的实现方法。它提供了一个通用的平台，挂接不同的题库可以适应不同科目的学习、组卷及考试。     

基于HLA的潜艇CGF研究与实现

论文首先介绍了HLA先进仿真技术的概念并构建出了潜艇CGF的物理模型、环境模型和行为模型结构。此后，提出了一套在HLA技术框架下实现潜艇CGF的思想和方法。在工程实践方面上，论文又具体应用HLA这一新技术初步构建起了实现潜艇CGF主要物理模型、环境模型的通用程序框架MMS。在潜艇CGF行为决策实现方面，论文研究了潜艇CGF行为决策的特点，提出了基于过程的潜艇CGF智能决策实现方法并初步研究了决策机CDM的技术实现问题。论文初步研究和解决了在HLA先进仿真技术框架下实现潜艇CGF的主要理论问题和实践问题。     

基于生态演化的通用智能系统结构模型研究

从系统论、认知神经科学和生态演化的角度看, 智能是指生物体根据环境、条件、目标, 自适应地调整自身或调度各种资源实现目标的能力, 智能起源于生命, 智能是生物的基本特征.借助于脑神经系统演化的历史, 展示了自然智能的演化过程, 并由此构建了一个基于生态演化的通用智能系统结构模型, 系统地分析了一般智能系统的普遍性、开放性、动态演化性、相对稳定性、功能性、结构性、依附性、相对独立性、可延续性等基本特征.论文根据智能演化进程将智能系统分为7级, 利用智能系统结构模型分类探索专用人工智能和通用人工智能的发展方向以及有关智能系统的学习方法.这些工作对人工智能和智能科学基础理论研究与应用具有一定的启发意义.     

智能试卷生成和自适应考试系统

介绍了一种基于项目反应理论的智能组卷及自适应考试系统的实现方法.它提供了一个通用的平台,挂接不同的题库可以适应不同科目的学习、组卷及考试.     

基于虚拟学习社区的智能学习算法研究

随着信息技术和互联网技术的发展,虚拟学习社区为学习者提供一个开放的学习环境,是满足时代教育要求的强有力的平台,成为学习者网络交流、网络学习的重要手段。如何利用虚拟学习社区来提高学习者的学习效率成为当前研究的热点和重点。本文基于虚拟学习社区,提出一种智能的个性化推荐学习算法,使学习者能够方便、有效、智能、反思性学习,为构建虚拟学习社区提供理论技术支撑,以便更好地指导虚拟学习社区的学习实践。     

基于Multi-agent的智能学习环境的设计与实现

传统的智能学习环境由于只有一个学习者模型难以满足用户个性化学习的需要。为此本文提出了一个基于Multi-Agent的智能学习环境,并对该学习环境的体系结构、客户端学习者模型与服务器端学习者模型及其之间的交互作了具体的阐述。     

Recommender System to Analyze Student’s Academic Performance

A sufficient amount of studies worldwide prove an interrelation linking student learning productivity and interest in learning to physiological parameters. An interest in learning affects learning productivity, while physiological parameters demonstrate such changes. Since the research by the authors of the present article confirmed these interdependencies, a Recommender System to Analyze Student’s Academic Performance (Recommender System hereafter) has been developed. The Recommender System determines the level of learning productivity integrally by employing three main techniques (physiological, psychological and behavioral). This Recommender System, developed by these authors, uses motivational, educational persistence and social learning theories and the database of best global practices based on above theories to come up with recommendations for students on how to improve their learning efficiency. The Recommender System can pick learning materials taking into account a student’s learning productivity and the degree to which learning is interesting. Worldwide research includes various scientists who conducted in-depth studies on the different and very important areas of physiological measurements and intelligent systems. We did not manage to find any physiological measurements or any intelligent or integrated system that would take physiological parameters of students, analyze their learning efficiency and, in turn, provide recommendations.     

一种面向个性化协同学习的任务生成方法

现有协同学习应用无法很好地支持学习任务的生成以及学习者的个性化学习.针对此问题,提出了一种面向个性化协同学习的学习任务生成方法.该方法在学习任务形式化描述的基础上,通过学习者分组、确定学习资源、分解学习单元、分配学习模式以及生成事件序列等步骤,生成既符合学习者群体认知水平,又符合个体学习者个性特征的协同学习任务.根据此任务,可以较好地实现网络环境下群体学习者的个性化协同学习.目前,该方法已在Smart-Realcalss网络教学系统中得到应用.     

The foundations of a theory-aware authoring tool for CSCL design

One of the most useful ways to enhance collaboration is to create scenarios where learners are able to interact more effectively. Nevertheless, the design of pedagogically sound and well-thought-out collaborative learning scenarios is a complex issue. This is due to the context of group learning where the synergy among learners’ interactions affects learning processes and, hence, the learning outcome. Although many advances have been made to support the designing of collaborative learning scenarios through technology, a more systematic approach is lacking. With the limitations of the current designing methods and tools, it is difficult to develop intelligent authoring systems that can guide users in order to produce more effective collaboration. One of the main difficulties with creating a more consistent (computer-understandable) approach to designing collaboration is the necessity of proposing better ways to formalize the group learning processes. In this paper, we present an innovative approach that uses ontologies and concepts from learning theories to create a framework that represents collaborative learning and its processes. Ontologies provide the necessary formalization to represent collaboration, while learning theories provide the concepts to justify and support the development of effective learning scenarios. Such an approach contributes to establish the foundations for the development of the next generation of intelligent authoring systems referred to as theory-aware systems. To verify the viability and usefulness of our proposed ontological framework in the context of systematic design, the development and use of an intelligent authoring tool for CSCL design is presented. This system is able to reason on ontologies to give suggestions that help users to create theory-compliant collaborative learning scenarios. We carried out several experiments with teachers in a geometry drawing course and the results indicate that the system helps teachers to create and interchange their scenarios more easily and facilitates the selection of important pedagogical strategies that influence positively the designing and effectiveness of group activities.     

RETRACTED ARTICLE: Community guidance model based on interactive multimedia system

The rapid development of current wisdom education has become the mainstream that leads the development of education informatization. The development of wisdom education relies on big data network resources to adapt to online teaching resources and online learning environment. Wisdom education can meet the needs of teachers, students, researchers, and the public areas under the support of the Internet of Things, cloud computing, big data, and ubiquitous networks. As a very important part of wisdom education, the wisdom education environment plays a fundamental role in wisdom education. In an intelligent learning environment, personalized learners need to build an efficient community intelligence education model, which acquires and stores the data produced by the learners touching the related physical elements in the intelligent situation through the sensing device. An intelligent learning environment is able to analyze and infer the data and adapt the present educational research according to the individual needs of learners’ program providing “intelligent” learning services. In addition, guided by the system model and design principles of the wisdom education environment, this paper put forward the initial design ideas of the wisdom education inquiry base in order to provide some guidance to the construction of the wisdom education environment. This paper introduces XML language to standardize the representation of learning situation model and illustrates it with a concrete example.

     

融合两级注意力的多机器人强化学习导航

针对多智能体强化学习中因智能体之间的复杂关系所导致的学习效率低及收敛速度慢的问题, 提出基于两级注意力机制的方法MADDPG-Attention, 在MADDPG算法的Critic网络中增加了软硬两级注意力机制, 通过注意力机制学习智能体之间的可借鉴经验, 提升智能体之间的相互学习效率. 由于单层的软注意力机制会给完全不相关的智能体也赋予学习权重, 因此采用硬注意力判断两个智能体之间学习的必要性, 裁减无关信息的智能体, 再用软注意力判断两个智能体间学习的重要性, 按重要性分布来分配学习权重, 据此向有可用经验的智能体学习. 在多智能体粒子的合作导航环境上进行测试, 实验结果表明, MADDPG-Attention算法对复杂关系的理解更为清晰, 在3种环境的导航成功率都达到了90%以上, 有效提高了学习效率, 加快了收敛速度.     

TEx-Sys model for building intelligent tutoring systems

Special classes of asynchronous e-learning systems are the intelligent tutoring systems which represent an advanced learning and teaching environment adaptable to individual student’s characteristics. Authoring shells have an environment that enables development of the intelligent tutoring systems. In this paper we present, in entirety, for the first time, our approach to research, development and implementation related to intelligent tutoring systems and ITS authoring shells. Our research relies on the traditional intelligent tutoring system, the consideration that teaching is control of learning and principles of good human tutoring in order to develop the Tutor–Expert System model for building intelligent tutoring systems in freely chosen domain knowledge. In this way we can wrap up an ongoing process that has lasted for the previous fifteen years. Prototype tests with the implemented systems have been carried out with students from a primary education to an academic level. Results of those tests are advantageous, according to surveys, and the implemented and deployed software satisfies functionalities and actors’ demands.     

智能代理和学习对象的集成—— 一种应用于在线教学的设计思想

讨论了一种很有发展前景的E教学开发设计思想,集智能代理和学习对象为一体来开发更智能化,更高交互性和高扩展性的在线教学系统。在该系统中,每个对象都被附加上一个智能代理,从而在在线学习中像一个代理程序一样,从学习环境中获得各项实时参数,然后根据这些参数采取相应的操作。此外,与内置智能代理的对象一样,用户模块被设计用来记录和保存一切与用户有关的信息,包括习惯的学习方式以及所有在线学习课程当中的活动事件。由于用户模块可以更好地了解每个用户,系统就会以一种更具有针对性的方式工作,就像老师在课堂上可以对不同的学生采取     

强化学习研究综述

摘要强化学习通过试错与环境交互获得策略的改进,其自学习和在线学习的特点使其成为 机器学习研究的一个重要分支.该文首先介绍强化学习的原理和结构;其次构造一个二维分类 图,分别在马尔可夫环境和非马尔可夫环境下讨论最优搜索型和经验强化型两类算法;然后结 合近年来的研究综述了强化学习技术的核心问题,包括部分感知、函数估计、多agent强化学 习,以及偏差技术;最后还简要介绍强化学习的应用情况和未来的发展方向.     

有效智慧学习环境的设计框架

随着信息技术的深入发展，使学习系统智能化是计算机科学和教育领域许多研究人员的共同目标。近年来， 智慧教室、智慧学习环境、下一代学习空间成为研究热点。文章系统梳理了智慧学习环境的定义、功能要素，站在认知学习视 角，提出了有效智慧学习环境的设计理念与技术模块设计框架。