We describe a system for pronunciation training that dynamically generates CG animations to express pronunciation visually from speech based on articulatory features. The system specifically displays the results of phoneme recognition and CG animations of articulatory movements of both learners and a teacher that are estimated from their speech. Learners can thus notice their mispronunciation movements and find the correct method of pronunciation by comparing their incorrect pronunciation movements with the correct ones on the animations. We conducted an experiment to evaluate the effectiveness of the animated pronunciations and we acquired a correctness of 93% for articulatory features with our proposed system. As a result, we clarified that CG animations could adequately visualize the teacher's articulatory movements and those of learners. Further, the improvement to the pronunciation score with the proposed system was double that with the existing system. These results verified that the new system was an effective training system.

View full abstract

Competency information can be used to support quality management in e-Learning and assessment. This paper focuses on the exploration of two methodologies that were developed using a competency semantics information model in order to support quality management of learning content and assessment. Learning content including testing content and assessment events were analyzed in detail using the model. Both methodologies were based on a quantitative analysis approach as defined within the field of quality engineering. The two methodologies were used in a complementary manner and the gaps were identified between learning and test activities and between competency definition and assessments used. The resulting gap information from the implementation of these two methodologies can be used to support quality management.

View full abstract

Researchers often present their ideas using presentation tools such as Microsoft Office PowerPoint. However, listeners sometimes cannot follow the story and cannot understand what the speakers intend, even if topics are appropriately selected and arranged. Such situations are caused by inappropriate representation of sentences that describe topics. The audience cannot re-organize topic structures based on the descriptions on the slides. Our research is aimed at developing a system that automatically detects differences in the speaker's (or author's) intention for topics and a topic structure that can be estimated from created slides. We focus on a mechanism for automatic estimation of the relationships between slides, especially sequential and inclusive relationships. Relationships between slides can be inferred by the change in focus in the topic structure, and the topic structure is estimated using lexical information on the slides. Therefore, we introduce a topic graph that represents the relationships among topics on slides, which is formed using lexical and layout information of slides. Relationships between created slides are detected by the change in their focused topics in the topic graph. Based on an experiment, we validated the detected relationships with a prototype system when slides mainly consist of typical topics of a presentation and do not contain compound nouns.

View full abstract

The purposes of this study are: to utilize students' data to forecast their future grades; and to identify the students who would require academic counseling. To achieve these purposes, we propose Bayesian network models as a forecasting method. A Bayesian network is a graphical model that presents the dependence relationship among some variables in a graph structure. By calculating the probability value using the models, it is possible to make forecasts. Moreover, in this study, to facilitate the construction of the Bayesian network models, we introduce data mining. Data mining is the process of discovering new patterns from large amounts of data. In this paper, we use information gain and a decision tree as the data mining methods.

View full abstract

With rapid advances in IT, online systems are playing a major role in the expansion of health-related information management and education. In the field of health education, face-to-face interventions are still the mainstay in Japan, with online systems playing only a very minor role in providing people with health information. We have developed “Caring for your eyes”, a health education system based on the transtheoretical model of behaviour change to further extend the reach of health education. The intervention targeted eye strain in office workers who use visual display terminals. Subjects were divided into one group using our system and another group using printed educational material, and the effectiveness of these two approaches was compared. The results confirmed that our education system was more effective in getting office workers to establish habits for alleviating eye strain.

View full abstract

Much courseware has been developed recently; but not all of it is of high quality, nor is all of it based on educational theories. Our purpose in this study is to support the design of high quality courseware that reflects instructional strategies and supports the design easily, especially for novice designers. The instructional model ontology of expert knowledge and experience is constructed using SMARTIES, an authoring tool. Designers can develop their courseware efficiently using this instructional model ontology. We demonstrate the efficacy of the courseware development through an experimental study that included experimental and comparative groups. We found from survey results of the experimental group that designing courseware through the instructional model ontology of SMARTIES improves the quality of the courseware and it is much more helpful for inexperienced designers. Overall, our method led to the design of courseware that was more concrete and more faithful to instructional strategies.

View full abstract

Niche-Learning is a learning style using digital signage (DS) that lets students learn by viewing short digital learning materials (NL materials) on a large public display during class break times. At the author's university, a simple DS system has delivered NL materials for about 4 years, but many students do not view the NL materials. One cause of this undesirable situation may be that NL materials are one-sidedly delivered. Therefore, the author made the DS system interactive. The interactive DS system called “IVS” superimposes students standing in front of the display on quiz slideshows. In addition, the IVS enables the students to answer quiz questions in a slideshow by their simple body movement.

View full abstract