Search

As the means to display abstract concepts and provide interactive experience, augmented reality (AR) has shown unparalleled superiority in educational domain. A sample of 213 Chinese K-12 teachers participated in our study. The results show that: 1. The external environment, self-efficacy, perceived usefulness, and perceived ease of use directly affect the teachers’ intention to use AR; 2. System characteristics indirectly affect the teachers’ intention to use AR through intermediary variables. 3. Perceived ease of use indirectly affects the teachers’ intention to use AR by affecting perceived usefulness and self-efficacy. The research has certain theoretical significance for AR application in teaching.

With the rapid development of artificial intelligence (Al) technology, machine understanding math word problems (MWPs) has received growing attention. However, existing methods of automatic understanding MWPs are hardly integrated into cognitive intelligent systems used for individual learning. To address the integration problem, this paper firstly clarified the relationship between understanding MWPs and discourse comprehension. According to the trait of discourse comprehension models, the existing methods were divided into knowledge schema-based methods and mental processing-based methods. Then we shortly presented the construction-integration model and proposed a conceptual framework for machine understanding MWPs. The proposed conceptual framework was established from long and short-term memory, cognitive computing services, formal representation models, and human-computer interaction. Finally, we draw a conclusion that integrating cognitive models of human understanding discourse into the process of machine understanding MWPs is conducive to developing a humanized cognitive intelligence system for personalized learning.

Mental models have been deeply concerned by researchers and practitioners since it plays a crucial role in problem-solving. In this study, we proposed mental models for random sampling word problems. On basis of the proposed mental models, we further performed a mental simulation with a rule-based mental reasoning method and a template-based approach to generate human-style explanations. And then we established an experiment on a prototype intelligent tutoring system. Experimental results showed that: the proposed mental models were available for most random sampling word problems; and a solution with human-style explanations to the problem encoded in mental models was produced effectively by means of mental reasoning. Based on these results, we concluded that our mental models can be used to encode essential information for solving random sampling word problems effectively, and it is profitable to take mental models into account when developing intelligent tutoring systems.

Magnetic field is an important knowledge point in junior high school physics discipline. Due to its invisible feature, students require to concretely perceive the magnetic field through experiments. However, the traditional experiment has some defects such as inconvenient operation and insignificant effect. Computer simulation technologies can solve these problems by virtualizing them, but it currently has some shortcoming in terms of its experience and credibility. Based on augmented reality technology and the idea of inquiry learning, this paper designs and implements an AR courseware for magnetic field teaching. The experimental experience is enhanced by the fusion of virtual and real while visualizing the magnetic line. Finally, a preliminary application is carried out.

In recent years, with the rapid progress of game development technology as well as human-computer interaction technology, game-based learning (GBL) has not only drew the attention of increasing number of researchers but this method has also been implemented into classrooms by teachers around the world. And the improvement for knowledge acquisition is being reported as the most frequently occurring outcome of GBL across a wide range of subjects like mathematics, physics, health etc. However, there are very limited cases where GBL being employed into music class especially for Chinese traditional musical instruments which are facing the danger of being lost since children today are far less likely to have a chance to play or listen to those beautiful instruments because schools usually focus more on the education of mainstream instruments like pianos and violins. Therefore, the present paper designs and develops an interactive virtual dulcimer auxiliary teaching system based on musical instrument digital interface, which in the future can be utilized as a tool in class to assist teaching or can be promoted as a self-teaching instrument.

Adaptive learning requires the learning contents to be presented to students dynamically in a personalized fashion. Multiple displays on cross-platform devices can meet the diverse needs for content presentation. Current practices approach web page design for multi-terminal devices on a trial-and-error basis. This paper discusses a web page design method that uses the client resolution adaptive table for multi-terminal devices. To obtain the table, we calculate the character size and other elements for the best visual effect by adapting to the client's device resolution.

With the scale of educational resources construction continues to expand, how to achieve the semantic description and sharing of educational resources, and provide users with semantic-level resource support services, is a key problem which we should pay attention to in the field of knowledge services. This paper proposes a solution on description and retrieval of educational resources metadata based on domain ontology. It can achieve the semantic sharing and service of educational resources. We give the relevant implementation using the major of “Educational Technology” as an example which has shown good effect.

As the main approach of distance education, the key point of Network Learning research has turned to getting the learners' personality characteristics and constructing the virtual learning environment based on theories of modern education and psychics. Currently, the characteristics of learners are stored in database statically. We can't timely acquire the latest interests of learners. The paper proposes an approach to get learners' characteristics dynamically. The approach uses data mining technology to analyse learners' network learning behaviors. The experiment result sugguests it is useful for acquisition of learners' characteristics.

With the sudden growth of information technology, network resources and resource search technology have been developed rapidly. However, general search engines such as Google and Baidu are difficult to satisfy our retrieval requirements in professional field because the lack of professionalism. This paper constructs a vertical educational resource oriented search engine based on the circumstances of educational field. This search engine adds the professional vocabulary on the basis of general search engine, and puts forward an improved sequencing algorithm based on specialized vocabulary. These measures improved the recall and precision of resource search and achieved good effect in practical application.

When the traditional text classification technologies classify academic dissertations, the dimension of extracted feature terms is high, and they can't represent the theme of thesis. it makes the efficiency is very low and the accuracy rate is not high. The topic words are small in quantity and can reflect the theme of thesis well. Accordingly, the paper proposes to extract the topic words with topic word list and uses topic words as feature terms. Then using the Bayesian Classification method classifies vast texts. The experiments show that the Bayesian Classification method using topic words as feature terms can greatly reduce the dimension and improve the efficiency of classification, when the dimension of feature terms is equivalent, the accuracy of Bayesian Classification method using topic words as feature terms is also higher than the traditional Bayesian text classification methods.

Because of its important application value in almost every region, early-warning has received extensive concern. This paper puts forward a study early-warning mechanism based on association rules. It uses an Apriori mining algorithm with some corresponding restrictions to dig out the latent school record association rules from former students' scores which are viewed as a history resource. Then these rules will be used to match up the data sets that need to monitor. Once a record is matched to one of these rules, the student of this record will receive an early-warning. This kind of early-warning mechanism changes the situation that problems with study can only be detected after knowing the scores. It has a predictable and forward-looking capability and has been proved to obtain a good early-warning effect during actual verification.

XML is widely used in development of educational resources database system (ERDS) because of its natural traits: easy-to-interpreted, criterion-opened, extensive, cross-platform compatible. But there are some limitations naturally when we use the relational database to store and search XML data. SQL SERVER 2005 and ASP.NET 2.0 provide stronger function to support XML. Through analyzing the criterion, functions and structure about ERDS, this paper gives us a solution about ERDS based on SQL SERVER 2005 and ASP.NET 2.0. Also this paper discusses the technology and realization about how to construct, store, access and present the educational resources.