Kosuke Takano

A multimedia tennis instruction system: tracking and classifying swing motions

Advances in data acquisition, human computer interface, and artificial intelligence have enabled the development of e-learning systems for educational and instructional purposes. Sport instruction, in particular, is a very attractive domain for computer-based learning as compared to the traditional human coaching approach, potentially saving space, time, and cost. A tennis instruction system has been designed and developed. In order to have a practical sport instructional system, motion-sensed input data must be accurately captured, cleansed, clustered, and classified, before further processing can be performed. This work presents the tennis instruction prototype and the issues associated with motion capture and identification.

An Adaptive e-Learning Recommender Based on User's Web-Browsing Behavior

In this study, we propose a recommender system for e-learning by utilizing a hybrid feedback method that extracts a user’s preference and Web-browsing behavior. This system is capable of recommending learning content of potential interest to a user and also the likely Web-browsing action on the current item using a novel similarity measure approach. The recommender is adaptive to individual user’s preference as well as one’s changing interest in Web-based learning activity. A proof-of-concept system has been designed and is being implemented. Experiments are being formulated to illustrate the system’s capability to acquire knowledge from user feedback and Web-browsing behavior, and to provide personalized recommendation adaptively in an e-learning environment.

An Adaptive Personalized Recommender Based on Web-Browsing Behavior Learning

In order to identify a users personal preference in navigating the Web or to recommend collected Web information, it is very useful to analyze the users Web-browsing behavior. However, it is difficult to determine which Web-browsing behaviors are influential on predicting a users interest because each individual has his/her own habit and personal manner in surfing the Web and locating documents of interest. In this study, we propose an adaptive personalized recommender system based on a preference-thesaurus constructed by learning a users Web-browsing behavior. The major components of the proposed recommender system are the Web-browsing behavior monitor, preference-thesaurus constructor, relevant document recommender, and user feedback learner. The adaptive nature of the proposed system allows the personalization of recommendation and the identification of the ever-changing influential Web-browsing behaviors. A proof-of-concept system is implemented and experiments are performed to verify the systems capability to personalize recommendation and to learn through users feedbacks.

The Design of a Web-Based Multimedia Sport Instructional System

With the advances in computer technology, many systems have been developed for educational and instructional purposes. In particular, a computer-based system is very attractive in sports instruction and training as compared to the traditional human coaching approach, saving time, space, and cost. Among several important technical issues to be resolved in such sports instructional systems, motion or gesture capture and the organization of the database are the major ones. Of course, the most successful implementations are the systems from the gaming industry. In this work, we briefly discuss these commercial technologies and systems. A prototype system for learning tennis is introduced. Various techniques for motion capture are described and discussed. An event-based motion detecting and matching algorithm for capturing tennis swings from people of different size is presented. Finally, a framework for a Web-based generic sport system is presented.

Real-Time Classification of Sports Movement Using Adaptive Clustering

Computer-based instructional systems provide an ideal setting for learning certain types of sports. In particular, the sports that require premium space could leverage the widely available computing and Internet facilities to teach individual users anywhere and anytime. An e-learning tennis instruction system is currently being designed and developed. The Nintendo Wii Remote is selected as the input device for its low cost and racket-handle like shape. After the data from motion sensors are captured, they have to be cleansed, normalised clustered and classified. Data of three common swings, backhand, forehand, and overhand, have been recorded from fifty people of various levels of tennis skill. Experiments are carried out to identify the most suitable techniques to classify a tennis swing. The adaptive nature of a prototype system is also introduced.

Classifying Sports Gesture Using Event-Based Matching in a Multimedia E-learning System

Computer-based multimedia instructional systems are ideal for e-learning in many domains. For applications such as sport instruction, the central issue is to capture motions accurately and correctly for further processing. A Web-based tennis instruction system is under investigation and being designed and developed. To capture the motion of a tennis swing, the Nintendo Wii Remote is used as the input device. The current focus of the project is the various issues associated with motion-sensing input data: capturing, cleansing, classification and clustering of some basic tennis swings, and the subsequent swing matching and identification which can then be used to index into a multimedia database for instructional purpose. In this work, classification of a tennis swing using event-based matching is presented and illustrated with examples. Results from experiments with 50 people are analyzed. The accuracy and the suitability of the matching algorithms are evaluated and discussed.

Impression-Oriented Music Courseware and Its Application in Elementary Schools.

Purpose – The purpose of this paper is to present the design and implementation of music courseware that features a music search system that uses impression keywords. The paper applies the courseware to Kansei (sensibility) development for elementary and junior high school students. The objectives of this courseware are to cultivate childrens sensitivity to the mood of a music selection; an understanding of the effects of tonality on the mood of the music; and) an ability to appreciate and express music through activities such as searching, selecting, and listening while also utilizing information about musical impression. The courseware is also designed to support teachers who do not specialize in music education.Design/methodology/approach – Music courseware is designed containing the following three components: a semantic associative search engine that enables the retrieval of media data related to impression keywords selected by users; interfaces and tools for music retrieval and learning, which supp...

A Personalized Learning System with an AR Augmented Reality Browser for Ecosystem Fieldwork

In this paper, we present a mobile learning tool for ecosystem study using an augmented reality user interface. Our system provides a recommender function of learning content according to a learners interest, which is extracted in the form of a feature term set that is based on the users browsing behavior of learning content and its related objects, which are displayed through the augmented reality user interface. Using a prototype, we confirmed that our system can properly personalize the recommended results for ecosystem-related learning content, and we have the promising vision that our system can be utilized in a practical way for mobile learning in fieldwork for ecosystem studies.

An adaptive learning book system based on user's study interest

In this study, we present the prototype of an adaptive learning book system according to a users learning behavior. The system consists of a paper textbook and a 3D CG content viewer on a smart phone display. In this hybrid learning book system, a learners learning history and behavior are stored in a study profile database using the smart phones monitoring functions. A users study interest is extracted in the form of a weighted term set by analyzing the study profile database so that learning contents related to the users study interest can be adaptively provided in a series of learning opportunities.

Motion Tracking and Processing for Multimedia Sport E-Learning

Computer-based Multimedia instructional systems are ideal for e-learning in many domains. For applications such as sport instruction, the central issue is to capture motions accurately and correctly for further processing. Many gesture capturing techniques, including light, video and motion tracking, are employed in commercial products, research systems, and the game industry. A tennis e-learning system is under study and being designed. To capture the motion of a tennis swing, the Nintendo Wii Remote is used as the input device. This work examines the various issues associated with motion-sensing input data: capturing, cleansing, classification and clustering. Results from the classification and clustering of some basic tennis swings, and the subsequent swing matching and identification are presented.