Recommendation systems can play an extensive role in online learning. In such systems, learners can receive guidance in locating and ranking references, knowledge bits, test items, and so forth. In recommender systems, users’ ratings can be applied toward items, users, other users’ ratings, and, if allowed, raters of raters of items recursively. In this chapter, we describe an online learning system — QSIA — an active recommender system for Questions Sharing and Interactive Assignments, designed to enhance knowledge sharing among learners. First, we lay out some of the theoretical background for social, open-rating mechanisms in online learning systems. We discuss concepts such as social versus black-box recommendations and the advice of neighbors as opposed to that of friends. We argue that enabling subjective views and ratings of other users is an inevitable phase of social collaboration systems. We also argue that social recommendations are critical for the exploitation of the value associated with recommendation.
E-learning as a scientific field is in an era of transition. In the last decade, several scientific fields worked as reference disciplines for the promotion of the value delivery that new technologies offered to learning. In this paper, we will emphasize the role of knowledge management as a reference theory for e-learning.
Current efforts to standardize e-learning resources are centered on the notion of a learning object as a piece of content that can be reused in diverse educational contexts. Several specifications for the description of learning objects — converging in the LOM standard — have appeared in recent years, providing a common foundation for interoperability and shared semantics. At the same time, the Semantic Web vision has resulted in a number of technologies grounded in the availability of shared, consensual knowledge representations called ontologies. As proposed by several authors, ontologies can be used to provide a richer, logics-based framework for the expression of learning object metadata, resulting in the convergence of both streams of research towards a common objective. In this article, we address the practicalities of the representation of LOM metadata instances into formal ontologies, discussing the main technical and organizational issues that must be addressed for an effective integration of both technologies, and sketching some illustrative examples using modern ontology languages and a large knowledge base.
The technological pace and the advent of the knowledge society will set in the next years the new context for e-learning evolution: The convergence of learning and daily life of citizens worldwide will be evident in new services and transparent technologies. Pervasive or ubiquitous learning will be a critical cornerstone and an ultimate achievement of the e-learning research community. Additionally, worldwide efforts will define the social responsibility character of e-learning. In this short visioning paper, we try to address two critical questions: How will knowledge management and relevant technologies affect e-learning in the forthcoming six years? and What are the critical research questions for the new period of e-learning evolution? Many of these aspects could initiate interesting PhD research.
In recent years, researchers have attempted to develop more effective distance education systems. Nevertheless, students in network-based learning environments may need additional guidance and assistance when they encounter problems in learning certain concepts. Therefore, it is important to provide learning guidance in a distance learning environment. In this paper, we propose a data mining approach that is capable of assisting teachers to provide information needed for guiding students during the learning process. Several experiments on science courses have shown the effectiveness of applying the novel approach. [PUBLICATION ABSTRACT
Human interaction is one of the most important characteristics of meetings. To explore complex human interactions in meetings, we must understand them and their components in detail. In this paper, we present our efforts in capturing human interactions in meetings using omnidirectional cameras. We present algorithms for person tracking, head pose estimation, and face recognition from omnidirectional images. We also discuss an approach for the estimation of who was talking to whom, based on tracked head poses of the participants. Finally, we address the problem of activity modeling, based on moving trajectories of people in a meeting room. We report experimental results to demonstrate the feasibility of the presented technologies and discuss future work.
Information retrieval in the context of virtual universities deals with the representation, organization and access to learning objects. The representation and organization of learning objects should provide the learner with an easy access to the learning objects. In this paper, we give an overview of the ONES system and analyze the relevance of two information retrieval models for virtual universities. We argue that keywords-based search (i.e., the Boolean model), though well suited for Web searches, is overly coarse for virtual universities. Instead, the vector model, on which our implemented search engine also is based, seems to be more appropriate, as it provides similarity measure (i.e., the learning object having the best match is presented first). We also compare the performance of four algorithms for computing the similarities (matching).
In line with the popularity of computer and communication technologies, the largest country in the world — China — has joined the era of the Internet. As one of the most important activities on the Internet, distance learning is widely developed by key universities in China. The advantage of distance learning compared to traditional education is its flexibility, timely distribution, scalability, and multi-modality of learning resources. Observing the development process and activities of distance learning from the perspective of one of the largest universities in China2, we summarize a few interesting issues in this paper.
This paper describes the design and development process of adapting computer mediated learning from a residential course to a World Wide Web-based course offered in the distance master’s degree program in Instructional Systems Technology at a large Midwestern university. A description of the Web-based course, findings regarding the adaptation process, the major changes in course components, student reactions to the Web-based course features, and its implications for designing and developing Web-based courses are discussed. Through examining the instructional design and development process of this graduate course, the researcher provides useful references for instructors who need to teach a Web-based course in the future.
Videoconferencing has seen rapid growth as an economical and effective distance education technology. In this study, a research model was proposed and employed to test the success of videoconferencing-mediated instruction (VCMI) in higher education institutions. The proposed research model examined the impact of videoconference reliability, student usefulness and university usefulness on the VCMI success. A survey instrument was distributed to university business students. A total of 266 usable responses were analyzed. Exploratory and confirmatory factor analyses were implemented using structural equation modeling techniques through LISREL version 8.51. A structural equation model was used to fit and validate the proposed research model, and the results indicated a good fit to the data. Student usefulness and reliability of video conferencing technology were proven to be key determinants of a successful integration of VCMI technology as an effective and efficient distance-learning tool. One of the implications of this study is that VCMI university usefulness is not a driving factor for VCMI success. Most of the causal relationships between the constructs considered by the VCMI research model were well supported, accounting for 90.7% of the total variance in the VCMI success.
This article introduces mathematics ontology as a means of supporting teachers for authoring teaching materials. The purpose of this study is to conduct teachers to author a teaching material by using visualized domain ontology as scaffolding on a Content Repository Management System (CRMS). Although the domain ontology of mathematics at the secondary school level in Taiwan provides structured vocabularies for describing domain content, for those teachers who want to create a knowledge-rich description of domain knowledge, such as required by the “semantic Web, using ontology turns out to provide only part of the knowledge required. In the article, we examine problems related to capturing the learning resources or Learning Objects (LOs) on the CRMS. To construct ontology for a subset of mathematics course descriptions, the representation requirements by Resource Description Framework/Resource Description Framework Schema (RDF/RDFS) was implemented. Furthermore, a Visualized Online Authoring Tool (VOAT) is designed for authoring teaching materials on the Web. Finally, discussion and future research are addressed.
The purpose of this research is to understand the expectations and behaviors of business aviation pilots toward online learning. The authors believe that the company able to offer an integrated, individualized and useful online training experience will gain a significant competitive advantage. To that end, the authors have researched and synthesized studies that are currently available and relate to this important future product. In addition, an exploratory survey of business aviation pilots and interviews with key aviation industry players are used to determine current attitudes and expectations toward online learning. The scope of this paper will be limited to exploring the niche market of business aviation pilots using the aviation training company CAE SimuFlite and their new SimfinityTM .technology. However, the authors consider the concepts discussed to be applicable to all business aviation pilots.
Distance learning brings convenience, stability and flexibility. People can learn anytime and anywhere. Designing a distance course and assessing the learner becomes the key issue. In order to solve the disadvantage, a systematic assessment mechanism is proposed to enhance interaction between students and teachers. This paper combines the concept and influence diagram as a courseware diagram which can be implemented as a new authoring tool. First, a course flow chart can be systematically built and student learning performance can be improved by taking different levels of remedial courses based on student performance. Second, course content can be adjusted to maximize students’ learning results with analyzing student’s learning performance. Thirdly, the courseware diagram can be generated with the international distance learning standard, Sharable Content Object Reference Model (SCORM). Finally, this mechanism can be easily used by the instructor. With its user-friendly interface, the instructor will receive prompt feedback from students.
In this chapter we present a system supporting instruction designers in the design and deployment of e-learning courses. The system includes integrated modules for several authoring activities, such as the definition of knowledge content objects, and the creation of assessment and self-assessment tests. The distinguishing characteristics of the proposed system is that it is based on a suite of visual languages, enabling the modelling of different aspects of the construction process for Web-based distance courses. The languages include a Learning Activity Diagram, which extends UML Activity Diagrams to make them suitable for modelling distance course structures; a Self-Consistent Learning Object language used to define knowledge contents; and a Test Maker Language for specifying assessment and self-assessment tests. The use of visual languages provides an intuitive and friendly system user interface that allows instruction designer to easily compose and analyze the distance course structure and keep track of the knowledge acquisition process individually for each learner.
We are involved in the development of a time/knowledge exchange-based system. One of the objectives of the system is to improve the effectiveness of e-learning and distance education. The system envisioned is a chronobot-based system. In this chapter, we discuss the architecture of such a time/knowledge exchange based system. We propose a constraint satisfaction algorithm for time/knowledge exchange in order to solve the time/knowledge exchange problem, which interoperates with the various chronobots, coordinates the settlement of a bid in a distributed manner, and selects the best bid using a metric known as the QoB (Quality of Bid).
E-learning plays a key enabling role in knowledge management for individuals, schools, and enterprises. Nevertheless, the lack of standards in content and learning management systems (LMSs) makes the reusability and interoperability of learning resources infeasible. The emergence of the SCORM specification has shed light on the standardization of e-learning. Unfortunately, the existing SCORM-compliant asset model is simplified; only a few asset types are allowed. On the other hand, W3C’s declarative-style SMIL (Synchronized Multimedia Integration Language) is becoming prevalent in designing Web-based instructions with the consideration of temporality and spatiality of presentations. In addition, advances in real-time multimedia technologies can vitalize further these instructions. In this study, we propose an SMIL-enabled asset model with the enhancement of multimedia streaming. To render SCORM-compliant SMIL-enabled streaming contents, a Java applet-based SMIL RTP/RTSP LMS system is designed. We develop the proposed system in the Java EJB environment to tackle the issue of platform interoperability. The resulting system demonstrates an encouraging direction towards a more vivid and interactive SCORM-compliant e-learning.
This paper introduces the main features of LEZI, a software tool oriented to the production of indexed videos (hypervideos), enriched with hypertextual and multimedia elements. In certain types of educational applications, the quality of educational content may compensate easily for a user interface limited to the essentials or a reduced set of multimedia features. Production of this kind of multimedia application can be high quality, even with short production cycles, at a very low cost. This work concentrates on this particular field with LEZI, a conventional conference/lesson that can be transformed effectively into a powerful multimedia product based on a very simple and regular structure. The authors hope that the LEZI environment, which does not require specific expertise in information technology, will allow the author of an educational multimedia product to work at a higher level than conventional authoring tools in a short time and at a low cost.
The chronobot is a device for time and knowledge exchange. The concept of the chronobot first appeared in a science fiction short story, “Nocturne,” written by the author some 20 years ago . Recently, the Industry Technology Research Institute (ITRI) and Institute for Information Industry (III), two leading research institutes in Taiwan, invited the author to lead a pioneering project to put the ideas into practice to build a realistic device. The chronobot thus was conceived. The chronobot allows a group of people to exchange time and knowledge. This paper describes the basic concept of the chronobot, its mechanism for time/knowledge exchange, and its application to e-learning. Research issues are also discussed.
It is desirable to build up a lecture video library to enable students to view past lectures at any time and from anywhere on their PCs. For this purpose, we have developed a lecture video player/maker system (Yoshida, 2002, 2003). In developing this system, we considered the usability for students and operability for teachers. The player includes a keyword access function, which enables the student to jump to scenes where one of the registered keywords was spoken. For this purpose, the maker realizes automatic index generation after continuous speech recognition of the whole lecture stream. In this paper, we discuss the structure and functions of an ideal lecture video player and the importance of the index corresponding to the scenes in which the related keywords are spoken. We also will present experimental results regarding keyword extraction from three lecture streams. Evaluations of the lecture videos and the player by students are also discussed.