Browsing by Author "Chuang, SC"

Now showing 1 - 7 of 7

Automated information. mining on multimedia TV news archives
(2005)
Lai, PS
;
Cheng, SS
;
Sun, SY
;
Huang, TY
;
Su, JM
This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison.
Cluster-based support vector machines in text-independent speaker identification
(2004)
Sun, SY
;
Tseng, CL
;
Chen, YH
;
Chuang, SC
;
Fu, HC
Based on Statistical learning theory, Support Vector Machines(SVM) is a powerful tool for various classification problems, such as pattern recognition and speaker identification etc. However, Training SVM consumes large memory and long computing time. This paper proposes a cluster-based learning methodology to reduce training time and the memory size for SVM. By using k-means based clustering technique, training data at boundary of each cluster were selected for SVM learning. We also applied this technique to text-independent speaker identification problems. Without deteriorating recognition performance, the training data and time can be reduced up to 75% and 87.5% respectively.
Cognitive-metacognitive and content-technical aspects of constructivist Internet-based learning environments: a LISREL analysis
(2004-11-01)
Wen, MCL
;
Tsai, CC
;
Lin, HM
;
Chuang, SC
;
教育研究所
Through a LISREL analysis, this study validated the Constructivist Internet-based Learning Environment Survey (CILES). CILES consisted of six scales, sorted by two aspects. The first aspect, the cognitive-metacognitive aspect, included the scales of student negotiation, inquiry learning, and reflective thinking, whereas the second aspect, the content-technical aspect, involved the scales of Relevance, Ease of Use, and Challenge. A LISREL structural model was also proposed to examine the relationships between students' responses across these two aspects. Survey responses gathered from 483 high school students in Taiwan were the research data for this study. The results from the LISREL confirmatory analysis showed that CILES had highly satisfactory validity and reliability to assess students' preferences for constructivist Internet-based learning environments. Moreover, the structural model indicated that the Internet learning environments that challenged students' existing concepts could facilitate their preferences for student negotiation.. inquiry learning and reflective thinking activities. It is proposed that the Internet can have rich connections with numerous resources and a variety of perspectives, thus constructing appropriate learning environments to provide different kinds of challenges for learners. (C) 2003 Elsevier Ltd. All rights reserved.
Forecasting electricity market prices: A neural network based approach
(2004)
Xu, YY
;
Hsieh, R
;
Lu, Y
;
Shen, YC
;
Chuang, SC
This paper presents a neural network approach to forecast the Phelix Base (PB) electricity market prices for European Energy Exchange (EEX). Up to now there has been little scientific work on forecasting the price development on the electricity markets. In this study, the Phelix Base moving average (PBMA), the moving difference (PBMD), and multilayer feedforward neural networks (MLNN) are used to predict various period for 7, 14, 21, 28, 63, 91, 182, and 273 days ahead of electric prices. The experimental results of forecasting by MLNNs and linear methods (autoregressive error model) are compared and discussed. The MLNNs outperform from 11.4% to 64.6% superior to the traditional linear regression method. It seems that the proposed MLNN can be very useful in predicting the electricity market prices of EEX.
Neural network based image retrieval with multiple instance leaning techniques
(2005)
Chuang, SC
;
Xu, YY
;
Fu, HC
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose a Generalized Probabilistic decision based Neural Network (GPDNN) for content-based image retrieval (CBIR). Instead of receiving the numerical values of each data points as the input, the proposed GPDNN models the I/O relationship via the distribution of input data and their corresponding outputs. The GPDNN involves the Multiple-Instance learning techniques to learn a desired concept. A set of exemplar images are selected by a user, each of which is labeled as conceptual related (positive) or conceptual unrelated (negative) image. Then, by using the proposed learning algorithm, an image classification system can learn the user's preferred image class from the positive and negative examples. The experimental results show that for only a few times of relearning, a user can use the prototype system to retrieve favor images from the database.
Preferences toward the constructivist Internet-based learning environments among high school students in Taiwan
(2005-03-01)
Chuang, SC
;
Tsai, CC
;
教育研究所
;
師資培育中心
;
Institute of Education
This paper explored students' preferences toward the constructivist Internet-based learning environments. A Constructivist Internet-based Learning Environment Survey (CILES) was developed. The CILES consisted of six scales, including student negotiation, inquiry learning, reflective thinking, relevance, ease of use and challenge. Questionnaire responses gathered from more than 700 high school students in Taiwan suggested that the survey showed adequate reliability in assessing students' preferences. Students showed stronger preferences for the learning environments, which were easy to use or navigate and integrate complex real-life problems with relevant knowledge in a meaningful way. In addition, males and females shared similar preferences toward the Internet-based learning environments. Students having moderate Internet experiences seemed to be more critical to the preferences of the Internet-based learning environments, in which they may have demanded authentic and facilitated Internet-based learning environments, while their inquiry and reflective thinking should be promoted. (C) 2004 Elsevier Ltd. All rights reserved.
The correlation between epistemological beliefs and preferences toward Internet-based learning environments
(2005-01-01)
Tsai, CC
;
Chuang, SC
;
教育研究所
;
師資培育中心
;
Institute of Education