COMPUTATIONAL APPROACH FOR MOBILE IMAGE-BASED LANGUAGE LEARNING

O. Starostenko, V. Alarcon-Aquino, A. Sanchez, C. Cruz-Perez

University de las Americas Puebla (MEXICO)
Most theories of traditional pedagogy require a teacher to assist the learning process in a two-way conversation or through the mediating tools such as reference textual and audiovisual material and lab equipment. However, these theories fail to capture the distinctiveness of mobile learning because they are predicated on the assumption that learning occurs in a classroom environment, mediated by a trained teacher. Actual migration of traditional learning from school to the network now is characterized by using heterogeneous comprehensive, searchable, relevant learning media in social, collaborative learning environment available for open community through personalization of customizable tools, content options and learning objects for particular individual.
Taking into account the convergence occurring between new conceptions of learning and new mobile technologies, the main objective of this paper is to evaluate novel pedagogical aspects of mobile learning and to propose appropriate wireless distributed infrastructures, which may support users on the move operating in informal situations considering the ubiquitous nature of learning, its constructive and social activity and its dynamic context providing people with knowledge and skills they need to succeed in a rapidly changing world.
Computer assisted language learning systems, particularly, for image-based languages (IBL) such as Japanese kanji, Egyptian hieroglyphs, Mayan glyphs, etc., require data base with indexed reference symbols and software for pattern classification, recognition and interpretation. Well-known visual information processing and retrieval approaches cannot be easy migrated to mobile device due to its limited resources, processing speed and reduced display. Thus, another objective of this paper is to design computational approach for multimedia documents processing, recognition, and retrieval suitable for mobile devices optimizing and adapting their user interfaces with limited resources and visualization capabilities to mobile language learning activities. The proposed approach has been tested using designed framework for interpretation of Mayan glyphs and Japanese kanji on cell phones. The obtained results demonstrated the effectiveness of the developed approach, particularly, its high processing speed and acceptable symbol recognition grade in applications on mobile devices with limited resources and restricted networking capabilities. Obviously, the particular language learning goes beyond symbol recognition, but the ability to download support resources, information, and services to carry out actions according to specific behavioral model empower users to become active learners responsible for their own knowledge acquisition and decision making anywhere, anytime. Our proposal could be considered as alternative way for the development of visual information retrieval facilities in wireless environment which can act as a learning assistant that suggest ways of studying and organizing resources, provide long-term guidance on developing skills, and support experiential learning solutions and recommendations for IBL learning.

Acknowledgments. This research is sponsored by European Grant #247083: Security, Services, Networking and Performance of Next Generation IP-based Multimedia Wireless Networks and by Mexican National Council of Science and Technology, CONACyT, project #154438.