Situating students to learn from the real world has been recognized as an important and challenging issue. However, in a real-world learning environment, there are usually many physical constraints that affect the learning performance of students, such as the total learning time, the limitation of the number of students who can visit a learning target, and the time needed for moving from one learning location to another. It is essential to guide the students along an efficient learning path to maximize their learning performance according to the current situation. In this paper, an Active LEarning Support System (ALESS) for context-aware ubiquitous learning environments is designed and developed. ALESS can provide learning guidance when conducting ubiquitous learning activities. A great deal of context information is used in ALESS, including the location, the current capacity of the learning object, the time available etc. ALESS is able to actively provide the required learning support to individual students when they approach the corresponding real-world learning targets. To evaluate the performance of ALESS, an experiment was conducted in the National Science Museum of Taiwan. The experimental results showed that, with the help of ALESS, the students learned more efficiently, and achieved better learning performance.

No abstract

Purpose The purpose of this paper is to develop a blended mobile game-based learning service called CoboChild Mobile Exploration Service (hereinafter CoboChild) to support children’s learning in an environment blending virtual game worlds and a museum’s physical space. The contextual model of learning (CML) was applied to consider the related influential factors affecting museum learning and to promote children’s continuous learning and revisit motivations. Design/methodology/approach CoboChild provides a thematic game-based learning environment to facilitate children’s interactions with exhibits and other visitors. A practical system has been implemented in the National Museum of Natural Science (NMNS), Taiwan. A questionnaire was used to examine whether CoboChild can effectively fulfill the CML and to evaluate the impacts on museum learning. Findings CoboChild effectively fulfilled the CML to facilitate children’s interactive experiences and re-visit motivations in the blended mobile game-based learning environment. Most children described the system as providing fruitful playfulness while improving their interpretations of exhibitions and learning experiences. Practical implications CoboChild considers the related contextual influences on the effective support of children’s learning in a museum, and builds a child-centered museum learning environment with highly integrated blended learning resources for children. CoboChild has been successfully operating in the NMNS since 2011. Originality/value This study developed a blended mobile game-based learning service to effectively support children’s learning in museum contexts. The related issues are shown to improve the design of blended museum learning services. This innovative approach can be applied to the design of other child-centered services for engaging children’s interactive experiences in museums.

Purpose -The purpose of this study is to describe a framework of ontological techniques to restrengthen current content management systems of a natural science museum. The ontological approach is utilized to extend the service level from information to knowledge. Design/methodology/approach -Two ontologies have been established to perform vascular plant and herbal drug knowledge bases that further facilitate knowledge integration and inference. Furthermore, this study presented ontology development processes, including knowledge acquisition, representation, and retrieval. Findings -Empirical lessons related to development techniques are concluded as follows: first, the formal concept analysis can be used as a knowledge acquisition approach to acquire concepts and attributes from expertise. Second, the Ontology Web Language represents an XML-based language which provides formal logic expressions for describing knowledge concepts. Finally, the Jena APIs can be further developed as an ontology reasoner to facilitate knowledge inference and retrieval.Research limitations/implications -The development of ontological knowledge base is time-consuming and requires seamless collaboration among specialists, knowledge engineers, and information systems. Practical implications -Empirical lessons indicate that ontological techniques provide potential approaches for library and museum communities to apply for next generation knowledge building. Originality/value -This study indicates that ontological techniques have excellent potential for knowledge building.

The project constructs a stock selection model by machine learning methods to enhance the performance of the benchmark index for individual investors. Stock returns prediction is a highly researched topic. However, it is a difficult problem because the stock prices are complex, non-linear, and chaotic. Moreover, overfitting is always an important issue in machine learning field. In this article, it shows that how to solve these problems by dealing with time series data, feature engineering, and model construction. We apply the stock selection model on S&P 500 index and FTSE 100 index. The result shows that the portfolios with stock selection model outperform the benchmarks, and 2% of the number of constitution stocks is the best choice for the stock selection model. Besides, feature importance analysis shows that the stock selection model can measure import features appropriately, which means it has the ability to adapt to different economic environments. In addition, the portfolios with fewer stocks usually outperform the portfolios with more stocks shows the good prediction of the stock selection model. The results imply that machine learning techniques have a good application in stock markets.