Lawrence Y. Deng

Real-time Hand Gesture Recognition by Shape Context Based Matching and Cost Matrix

How to recognize the shape gesture for new human-computer interface without controller required and bring entertainment, games industries and information appliances in new ways. In this paper, we would illustrate a real-time hand gesture recognition system by using shape context matching and cost matrix. The shape context is taken as a basis description for shape matching. It can be regarded as a global characterization descriptor to represent the distribution of points in a set with scale and rotation invariance. In this paper, we developed a perceptual interface for human-computer-interaction based on real-time hand gesture recognition. User could interact with computer program by performing body gesture instead of physical contact. The image of hand gesture was captured from CCD. The hand gesture image was transformed into proper instruction according to the shape information respectively. The instruction was transferred to an appropriate program to execute. The experience of our preliminary results shown the precision rates was up to 70% ~ 90%.

One-to-One Complementary Collaborative Learning Based on Blue-Red Multi-Trees of Rule-Space Model for MTA Course in Social Network Environment

It has become increasingly important that applies and develops an intelligent e-learning system in a social network environment. In this paper, we used the combination of Rule-Space Model and multi-tree to infer reasonable learning effects of Blue-Red multi-trees and their definitions through analyzing all learning objects of MTA courses. We can derive one-to-one complementary collaborative learning algorithm from previous definitions. Finally, a MTA course is used to the analysis of Rule-Space Model, and the definition and analysis of learning performance for the MTA Course. From this MTA course, they can create twenty-one learning effects of Blue-Red multi-trees and recommend those specific Blue-Red multi-trees that satisfy one-to-one complementary collaborative learning group algorithm and analyze these learning performances of all Blue-Red multi-trees. They will be the basis of verification for one-to-one complementary collaborative learning.

The Development of Image-based Distance Measurement System

In this paper, a novel image-based method of distance measurement is proposed. Traditionally, the parallax method is frequently used to measure the distance between the camera and the measured surface. But for diminishing the computational complexity and inaccuracy cause by image processing procedure, the proposed system only using two parallel laser beams project to the measured surface then analyze the information of a captured image to compute the distance. Furthermore, in order to improve the accuracy of the experiment, the proposed algorithm also provides a mechanism to make sure the results will not be influenced by the angle between the optical axis of the camera and measured surface. The experimental results showed the proposed method provided precise measuring results in several different distances.

Ontology-Based Multimedia Authoring Tool for Adaptive E-Learning

More video streaming technologies supporting distance learning systems are becoming popular among distributed network environments. In this paper, the authors develop a multimedia authoring tool for adaptive e-learning by using characterization of extended media streaming technologies. The distributed approach is based on an ontology-based model. Suppose a well-known teacher is giving a lecture/presentation to his student. Because of time constraints and other commitments, many students cannot attend. The main goal of the authors system is to provide a feasible method to record and represent a lecture/presentation using a browser with the windows media services. This system requires flexible support for the modeling of multimedia content models and supports possible interactivity, transfer of streams multimedia data such as audio, video, text, and annotations using network facilities. The authors propose a new approach for the modeling of reusable and adaptable multimedia content. A comprehensive system for advanced multimedia content production is also developed. This approach significantly impacts and supports the multimedia presentation authoring processes in terms of methodology and commercial aspects.

Extended timed petri nets for distributed multimedia presentation

Building a web-based distributed multimedia presentation system environment is a technical challenge .In this paper, we described how to present different multimedia objects on a web presentation system with floor control mechanism as a result of the distributed environment indispensably. The distributed approach is based on an extended timed Petri net model. Using characterization of extended time Petri net, we introduce the concepts of user interaction. The main goal of our system is to provide a feasible method to represent different multimedia objects with user interaction and floor control mode. In addition, users can dynamically request different kinds of conditions during the presentation. To verify the structural mechanism, we implement an algorithm using the Extend Time Petri net model. Futhremore, we consider the interactive facilities to support the distributed communication requirement. We specified a floor control algorithm based on Z notation, which provides four types of control (free access, equal control, group discussion, and direct contact). These control mechanisms are sufficient to the use of distance learning environment.

Ontology-Based Multimedia Adaptive Learning System for U-Learning

More and more video streaming technologies supporting for E-learning systems are popular among distributed network environment. The Web’s Information Seeking System as the main provider of information is indisputable. How to provide multimedia Information seeking support E-learning system is becoming more and imperative. In this paper, we provided a multimedia information system for e-learning. This system requires adaptable and reusable support for the modeling of multimedia content models and also supports possible interactive, transfer of streams multimedia data such as audio, video, text and annotations using with network facilities. However, we investigated these existed standards and applications for multimedia documents models such as HTML, MHEG, SMIL, HyTime, RealPlay and MS Windows Media that let us to find that these standards and applications models do not provide adequate support for advanced reuse and adaptation. Consequently, we proposed a new approach for the modeling of reusable and adaptable multimedia content. We developed a comprehensive system for advanced multimedia content production: support for recording the presentation, retrieving the content, summarizing the presentation, weaving the presentation and customizing the representation. This approach significantly impacts and supports the multimedia presentation authoring processes in terms of methodology and commercial aspects.

Cognitive assessment evaluation based on Blue-Red trees Inference of Rule-Space Model and social network learning

It is getting important that learning reciprocally from social network to intelligent e-learning system. In this paper, we used the Rule-Space Model to infer reasonable Blue-Red trees of learning performance and their definitions through analyzing learning objects of courses within system. We can derive social network learning grouping algorithms from previous definitions. They include one-to-one group collaborative learning algorithms. Further, we use these algorithms to build a social network learning system and apply to the Online Learning and Test System based on Analysis of Learning Performance and Social Network Learning Feedback. Besides learners are able to self-learning through Recommended Table to the Remedial Learning Objects for the Course, they can find out reasonable mutual learning targets by the suggestion of Blue-Red Trees Database of Learning Performance from the Social Network Learning System. There are the same results to improve the self-learning direction of learners and remedy the weaker learning objects for the course by internal cyclic feedback, and can also improve learning materials and items of the ITE Licenses Course by external cyclic feedback.

Using Decision Tree Analysis for Personality to Decisions of the National Skills Competition Participants

The article aims to find the pivotal personality traits which can influence on winning a prize, compare the difference between the winning participants and the non-winning participants, and finally construct decision trees to achieve classification and prediction by using the Big Five personality traits to analyze the performance of senior and vocational high school students in Taiwan in National Skills Competition. The research utilizes t-Test and C4.5 Decision Tree to analyze commerce-related and home economics-related students. The experiment results showed that it has statistical significances on several personalities in statistical analysis between commerce-related and home economics-related students. However, because the personalities which have statistical significances are the key factor to affect whether a participant can win a prize, I go one step further to construct decision trees to predict the winner of National Skills Competition effectively in the future.

The Analysis of the Participants’ Personality for the Contestants of the National Skills Competition

The article aims to analyze the personality traits between the winners from the Golden Hands Award of National Skills Competition and the other students under the Industry-Related, Agriculture-Related, and Marine Fisheries-Related. This paper undergoes the Independent Samples t Test and One-Way ANOVA on the data by using SPSS. The experiment results showed that there are a number of variations in personality traits for different vocational categories. The forward personality of skills competition award winners are significantly higher than the student without participating in the skills competition training. Moreover, the profile data on gender under different vocational categories, family background, and birth order, were also observed with several personality traits showing significant differences. Hence, this study aims to find out the personality traits of the previous award winners and recommend suitable students to participate in the National Skills Competition.

Vocational professional certification learning cognitive assessment evaluation based on rule-space model and relevance feedback

The more professional licenses, the more jobs for student can easily get in Taiwan. It is very important to promote some professional certification for students in vocational education. In this paper, we used the rule-space model to diagnose the cognitive skills for assessment evaluation and also considered the users relevance feedback to improve the learners learning achievement in ITE (Information Technology Expert) course. The rule-space model approach supports cognitive analysis of students network technologies skill. And then to comprehensive what learning tops are weaknesses or strengths by individuals. The learners relevance feedback provided users evaluation that contained the item difficulty. We implemented a web testing application for ITE testing simulation. In our experiences, this approach can provide to understand the learning characteristic for e-learning achievement and to explore better educational application. The learner can fit Self-Regulation processing of the Scaffolding Theory and achieving social learning effectiveness, simultaneously.