Huan-Chao Keh

An object-oriented database for intelligent multimedia presentations

We have developed an intelligent multimedia presentation design system earlier. Based on the system, we develop a multimedia database system that supports the reuse of multimedia presentations and resources. The database consists of two layers: the frame layer and the resource layer. A frame group in the first layer is the basic presentation unit to be reused. A resource group in the second layer is a collection of resources to be used by a frame or a frame group. In these two layers, we use four types of links in the database to group frames and/or resources. Also, multimedia resources are associated with a number of properties. Using these properties, we allow the user to search for resources via a database browser. The database is built on the top of a commercial object-oriented database server and run under a windowing system.

Chinese text classification by the Naïve Bayes Classifier and the associative classifier with multiple confidence threshold values

Each type of classifier has its own advantages as well as certain shortcomings. In this paper, we take the advantages of the associative classifier and the Naive Bayes Classifier to make up the shortcomings of each other, thus improving the accuracy of text classification. We will classify the training cases with the Naive Bayes Classifier and set different confidence threshold values for different class association rules (CARs) to different classes by the obtained classification accuracy rate of the Naive Bayes Classifier to the classes. Since the accuracy rates of all selected CARs of the class are higher than that obtained by the Naive Bayes Classifier, we could further optimize the classification result through these selected CARs. Moreover, for those unclassified cases, we will classify them with the Naive Bayes Classifier. The experimental results show that combining the advantages of these two different classifiers better classification result can be obtained than with a single classifier.

Intelligent Postoperative Morbidity Prediction of Heart Disease Using Artificial Intelligence Techniques

Endovascular aneurysm repair (EVAR) is an advanced minimally invasive surgical technology that is helpful for reducing patients’ recovery time, postoperative morbidity and mortality. This study proposes an ensemble model to predict postoperative morbidity after EVAR. The ensemble model was developed using a training set of consecutive patients who underwent EVAR between 2000 and 2009. All data required for prediction modeling, including patient demographics, preoperative, co-morbidities, and complication as outcome variables, was collected prospectively and entered into a clinical database. A discretization approach was used to categorize numerical values into informative feature space. Then, the Bayesian network (BN), artificial neural network (ANN), and support vector machine (SVM) were adopted as base models, and stacking combined multiple models. The research outcomes consisted of an ensemble model to predict postoperative morbidity after EVAR, the occurrence of postoperative complications prospectively recorded, and the causal effect knowledge by BNs with Markov blanket concept.

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%.

On fault-tolerant embedding of Hamiltonian cycles, linear arrays and rings in a Flexible Hypercube

Abstract The Hamiltonian cycle of a Flexible Hypercube graph network is investigated in this paper. The result can readily be used in the optimal embedding of a linear array (or a ring) of processors in a faulty Flexible Hypercube. There are embedding algorithms proposed in this paper. These embedding algorithms show a ring with any number of nodes that can be embedded into a faulty Flexible Hypercube with load 1, congestion 1 and dilation 3 such that O( n 2 −(⌊log 2 m ⌋) 2 ) faults can be tolerated, where n is the dimension of the Flexible Hypercube and m is the number of nodes of the ring.

Distance-Learning for Advanced Military Education: Using Wargame Simulation Course as an Example

Distance learning in advanced military education can assist officers around the world to become more skilled and qualified for future challenges. Through well-chosen technology, the efficiency of distance-learning can be improved significantly. In this paper we present the architecture of Advanced Military Education – Distance Learning (AME-DL) prototype for advanced military distance-learning, it combines advanced e-learning tool, simulation technology, and Web technology to provide a set of military learning and training subjects that can be accessed easily anywhere, anytime through a Web browser. The major goal of AME-DL is to provide a common standard framework for military training program, and the major contribution for such a prototype is to reduce training cost while providing high quality learning experience.

A Design and Implementation of a SCORM-Based Courseware System Using Influence Diagram

Distance learning brings convenience, stability and flexibility. People can learn anytime and anywhere. Designing a distance course and assessing the learner becomes the key issue. In order to solve the disadvantage, a systematic assessment mechanism is proposed to enhance interaction between students and teachers. This paper combines the concept and influence diagram as a courseware diagram which can be implemented as a new authoring tool. First, a course flow chart can be systematically built and student learning performance can be improved by taking different levels of remedial courses based on student performance. Second, course content can be adjusted to maximize students’ learning results with analyzing student’s learning performance. Thirdly, the courseware diagram can be generated with the international distance learning standard, Sharable Content Object Reference Model (SCORM). Finally, this mechanism can be easily used by the instructor. With its user-friendly interface, the instructor will receive prompt feedback from students.

Building Long-Distance Health Care Network Using Minimized Portable Sensors and Active Alert System

The accelerated aging population around the world will be more obvious. In the USA, there will be about 72 million people aged 65 by 2030, There will have nearly 36.98% of the elderly population in Taiwan until 2050. Those people will need health care too. Nowadays, the current health care focus on the passive home care in Taiwan, however, the devices which can provide elder to carrying in outdoor will be huge and heavy, and also the devices will hard to actively send the alert message for the medical units when the patient have problem in their health. Therefore, the proposed of this study is to miniaturized vital sign detection and active alert system. The system will give elder the privacy, convenience, and security as well. Hoping this study can not only reduce the medical units work but lower the medical resources cost, moreover, it will also enhance the quality of life for the patients.

A 3D Campus on the Internet --- A Networked Mixed Reality Environment

This paper presents a study of networking the mobile augmented reality system with the conventional networked virtual environment and it is called the networked mixed reality environment in this study. The 3D virtual campus is an ongoing project aiming to explore the techniques how to design such a networked mixed reality environment. This study starts with investigating the temporal and spatial synchronization issues between the mobile computing system and the conventional networked virtual reality system. The proposed solutions are then followed by a demonstration prototyping system, called Multiplayer Mobile Mixed Reality(M3R) system. The tips of implementing the M3R system are presented in the end. The 3D virtual campus project successfully demonstrates the promise of building a pervasive virtual environment between the live player and the virtual player. Inspired by the preliminary success, further experiments and application are currently being examined.

Reconfiguration of Complete Binary Trees in Full IEH Graphs and Faulty Hypercubes

The incrementally extensible hypercube (IEH) graph is a generalization of binary hypercube networks in that the number of nodes can be arbitrary in contrast to a strict power of 2. In this paper, the authors present an efficient model to fulfill the embedding of a full binary tree into a full IEH graph. As the model the authors proposed, an algorithm is developed for the embedding with expansion 1, load 1, congestion 2, and dilation 2. Moreover, the embedding algorithm can be also applied into hypercubes with one faulty node.