Browsing by Author "Yang, Wei-Pang"

Now showing 1 - 15 of 15

A decision tree-based approach to mining the rules of concept drift
(2007)
Lee, Chien-, I
;
Tsai, Cheng-Jung
;
Wu, Jhe-Hao
;
Yang, Wei-Pang
;
資訊工程學系
In a database, the concept of an example might change along with time, which is known as concept drift. When the concept drift occurs, the classification model built by using old dataset is not suitable for predicting new coming dataset. Although many algorithms had been proposed to solve this problem, they focus only on updating the classification model. However in a real life users might be very interested in the rules of concept drift. For example, doctors would desire to know the main causes more for disease variation since such rules would enable them to diagnose patients more correctly and quickly. In this paper we propose a Concept Drift Rule mining Tree to accurately discover the rule of concept drift. The main contributions of this paper are: a) we address the problem of mining concept-drifting rule which was ignored in the past; b) our method can accurately mine the rule of concept drift.
A discretization algorithm based on Class-Attribute Contingency Coefficient
(2008-02-01)
Tsai, Cheng-Jung
;
Lee, Chien-I.
;
Yang, Wei-Pang
;
資訊工程學系
;
Department of Computer Science
Discretization algorithms have played an important role in data mining and knowledge discovery. They not only produce a concise summarization of continuous attributes to help the experts understand the data more easily, but also make learning more accurate and faster. In this paper, we propose a static, global, incremental, supervised and top-down discretization algorithm based on Class-Attribute Contingency Coefficient. Empirical evaluation of seven discretization algorithms on 13 real datasets and four artificial datasets showed that the proposed algorithm could generate a better discretization scheme that improved the accuracy of classification. As to the execution time of discretization, the number of generated rules, and the training time of C5.0, our approach also achieved promising results. (c) 2007 Elsevier Inc. All rights reserved.
A top-down and greedy method for discretization of continuous attributes
(2007)
Lee, Chien-, I
;
Tsai, Cheng-Jung
;
Yang, Ya-Ru
;
Yang, Wei-Pang
;
資訊工程學系
Experiments show that CAIM discretization algorithm is superior to all the other top-down discretization algorithms. However CAIM algorithm does not take the data distribution into account. The discretization formula used in CAIM also gives a high factor to the numbers of generated intervals. The two disadvantages make CAIM may generate irrational discrete results in some cases and further leads to the decrease of predictive accuracy of a classifier In this paper we propose the Class-Attribute Contingency Coefficient discretization algorithm. The experimental results showed that compared with CAIM, our method can generate a better discretization scheme to bring on the improvement of accuracy of classification. With regard to the number of generated rules and execution time of a classifier CACC and CAIM achieve comparable results.
A two-level relevance feedback mechanism for image retrieval
(2008-04-01)
Cheng, Pei-Cheng
;
Chien, Been-Chian
;
Ke, Hao-Ren
;
Yang, Wei-Pang
;
資訊工程學系
Content-based image retrieval (CBIR) is a group of techniques that analyzes the visual features (such as color, shape, texture) of an example image or image subregion to find similar images in an image database. Relevance feedback is often used in a CBIR system to help users express their preference and improve query results. Traditional relevance feedback relies on positive and negative examples to reformulate the query. Furthermore, if the system employs several visual features for a query, the weight of each feature is adjusted manually by the user or system predetermined and fixed by the system. In this paper we propose a new relevance feedback model suitable for medical image retrieval. The proposed method enables the user to rank the results in relevance order. According to the ranking, the system can automatically determine the importance ranking of features, and use this ranking to automatically adjust the weight of each feature. The experimental results show that the new relevance feedback mechanism outperforms previous relevance feedback models. (c) 2007 Elsevier Ltd. All rights reserved.
Access Control in XML Repositories Using a Role-Based Approach
(2010-12-01)
Chen, Shihn-Yuarn
;
Ke, Hao-Ren
;
Tsai, Wen-Nung
;
Yang, Wei-Pang
;
資訊工程學系
Nowadays, more and more Internet and Web applications store data in XML documents, which are more structured than unstructured plain text files. Administrators of an XML repository want to control the accessibility of both an XML file and an element within an XML file. However, traditional access control methods do not consult the semi-structure characteristics of XML documents. In view of this, this work proposes Integrated Role-based and XML document Access Control (IRXAC), which encompasses the Role Based Access Control phase and the XML Document Access Control phase, as a solution of access control on an XML repository. The former phase performs file-level access control and decides the accessibility of an XML file. The latter phase performs element-level access control and decides the accessibility of an element. Besides the details of IRXAC, the comparisons of IRXAC with other access control methods are shown.
Access Control in XML Repositories Using a Role-Based Approach
(2010-12-01)
Chen, Shihn-Yuarn
;
Ke, Hao-Ren
;
Tsai, Wen-Nung
;
Yang, Wei-Pang
;
資訊工程學系
Nowadays, more and more Internet and Web applications store data in XML documents, which are more structured than unstructured plain text files. Administrators of an XML repository want to control the accessibility of both an XML file and an element within an XML file. However, traditional access control methods do not consult the semi-structure characteristics of XML documents. In view of this, this work proposes Integrated Role-based and XML document Access Control (IRXAC), which encompasses the Role Based Access Control phase and the XML Document Access Control phase, as a solution of access control on an XML repository. The former phase performs file-level access control and decides the accessibility of an XML file. The latter phase performs element-level access control and decides the accessibility of an element. Besides the details of IRXAC, the comparisons of IRXAC with other access control methods are shown.
An approach to mining the multi-relational imbalanced database
(2008-05-04)
Lee, Chien-I
;
Tsai, Cheng-Jung
;
Wu, Tong-Qin
;
Yang, Wei-Pang
;
資訊工程學系
The class imbalance problem is an important issue in classification of Data mining. For example, in the applications of fraudulent telephone calls, telecommunications management, and rare diagnoses, users would be more interested in the minority than the majority. Although there are many proposed algorithms to solve the imbalanced problem, they are unsuitable to be directly applied on a multi-relational database. Nevertheless, many data nowadays such as financial transactions and medical anamneses are stored in a multi-relational database rather than a single data sheet. On the other hand, the widely used multi-relational classification approaches, such as TILDE, FOIL and CrossMine, are insensitive to handle the imbalanced databases. In this paper, we propose a multi-relational g-mean decision tree algorithm to solve the imbalanced problem in a multi-relational database. As shown in our experiments, our approach can more accurately mine a multi-relational imbalanced database. (c) 2007 Elsevier Ltd. All rights reserved.
An efficient and sensitive decision tree approach to mining concept-drifting data streams
(2008)
Tsai, Cheng-Jurig
;
Lee, Chien-I
;
Yang, Wei-Pang
;
資訊工程學系
;
Department of Computer Science
Data stream mining has become a novel research topic of growing interest in knowledge discovery. Most proposed algorithms for data stream mining assume that each data block is basically a random sample from a stationary distribution, but many databases available violate this assumption. That is, the class of an instance may change over time, known as concept drift. In this paper, we propose a Sensitive Concept Drift Probing Decision Tree algorithm (SCRIPT), which is based on the statistical X(2) test, to handle the concept drift problem on data streams. Compared with the proposed methods, the advantages of SCRIPT include: a) it can avoid unnecessary system cost for stable data streams b) it can immediately and efficiently corrects original classifier while data streams are instable; c) it is more suitable to the applications in which a sensitive detection of concept drift is required.
Classifier design with feature selection and feature extraction using layered genetic programming
(2008-02-01)
Lin, Jung-Yi
;
Ke, Hao-Ren
;
Chien, Been-Chian
;
Yang, Wei-Pang
;
資訊工程學系
This paper proposes a novel method called FLGP to construct a classifier device of capability in feature selection and feature extraction. FLGP is developed with layered genetic programming that is a kind of the multiple-population genetic programming. Populations advance to an optimal discriminant function to divide data into two classes. Two methods of feature selection are proposed. New features extracted by certain layer are used to be the training set of next layer's populations. Experiments on several well-known datasets are made to demonstrate performance of FLGP. (C) 2007 Elsevier Ltd. All rights reserved.
Combining textual and visual features for cross-language medical image retrieval
(2006)
Cheng, Pei-Cheng
;
Chien, Been-Chian
;
Ke, Hao-Ren
;
Yang, Wei-Pang
;
資訊工程學系
In this paper we describe the technologies and experimental results for the medical retrieval task and automatic annotation task. We combine textual and content-based approaches to retrieve relevant medical images. The content-based approach containing four image features and the text-based approach using word expansion are developed to accomplish these tasks. Experimental results show that combining both the content-based and text-based approaches is better than using only one approach. In the automatic annotation task we use Support Vector Machines (SVM) to learn image feature characteristics for assisting the task of image classification. Based on the SVM model, we analyze which image feature is more promising in medical image retrieval. The results show that the spatial relationship between pixels is an important feature in medical image data because medical image data always has similar anatomic regions. Therefore, image features emphasizing spatial relationship have better results than others.
Designing a classifier by a layered multi-population genetic programming approach
(2007-08-01)
Lin, Jung-Yi
;
Ke, Hao-Ren
;
Chien, Been-Chian
;
Yang, Wei-Pang
;
資訊工程學系
This paper proposes a method called layered genetic programming (LAGEP) to construct a classifier based on multi-population genetic programming (MGP). LAGEP employs layer architecture to arrange multiple populations. A layer is composed of a number of populations. The results of populations are discriminant functions. These functions transform the training set to construct a new training set. The successive layer uses the new training set to obtain better discriminant functions. Moreover, because the functions generated by each layer will be composed to a long discriminant function, which is the result of LAGEP, every layer can evolve with short individuals. For each population, we propose an adaptive mutation rate tuning method to increase the mutation rate based on fitness values and remaining generations. Several experiments are conducted with different settings of LAGEP and several real-world medical problems. Experiment results show that LAGEP achieves comparable accuracy to single population GP in much less time. (C) 2007 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
iSpreadRank: Ranking sentences for extraction-based summarization using feature weight propagation in the sentence similarity network
(2008-10-01)
Yeh, Jen-Yuan
;
Ke, Hao-Ren
;
Yang, Wei-Pang
;
資訊工程學系
;
圖書館
Sentence extraction is a widely adopted text summarization technique where the most important sentences are extracted from document(s) and presented as a summary. The first step towards sentence extraction is to rank sentences in order of importance as in the summary. This paper proposes a novel graph-based ranking method, iSpreadRank, to perform this task. iSpreadRank models a set of topic-related documents into a sentence similarity network. Based on such a network model, iSpreadRank exploits the spreading activation theory to formulate a general concept from social network analysis: the importance of a node in a network (i.e., a sentence in this paper) is determined not only by the number of nodes to which it connects, but also by the importance of its connected nodes. The algorithm recursively re-weights the importance of sentences by spreading their sentence-specific feature scores throughout the network to adjust the importance of other sentences. Consequently, a ranking of sentences indicating the relative importance of sentences is reasoned. This paper also develops in approach to produce a generic extractive summary according to the inferred sentence ranking. The proposed summarization method is evaluated using the DUC 2004 data set, and found to perform well. Experimental results show that the proposed method obtains a ROUGE-1 score of 0.38068, which represents a slight difference of 0.00156, when compared with the best participant in the DUC 2004 evaluation. (C) 2007 Elsevier Ltd. All rights reserved.
Knowledge-based mobile learning framework for museums
(2006)
Hsu, Tien-Yu
;
Ke, Hao-Ren
;
Yang, Wei-Pang
;
圖書館
;
Library
Purpose - The purpose of this study is to propose a knowledge-based mobile learning framework that integrates various types of museum-wide content, and supports ubiquitous, context-aware, personalized learning for museums. Design/methodology/approach - A unified knowledge base with multi-layer reusable content structures serves as the kernel component to integrate content from exhibitions for education and collection in a museum. The How-Net approach is adopted to build a unified natural and cultural ontology. The ontology functions as a common and sharable knowledge concept that denotes each knowledge element in the unified knowledge base, and associates each learner's learning context and usage with a content and usage profile respectively. Data mining algorithms, e.g. association mining and clustering, are applied to discover useful patterns for ubiquitous personalization from these content and usage profiles. Findings - A pilot project based on the proposed framework has been successfully implemented in the Life Science Hall of the National Museum of Natural Science (NMNS), Taiwan, demonstrating the feasibility of this framework. Originality/value - This study proposes a mobile learning framework that can be replicated in many museums. This framework improves learners' learning experiences with rich related content, and with ubiquitous, proactive and adaptive services. Museums can also benefit from implementing this framework through outreach services for educational, promoting and usability needs from combining mobile and Internet communication technologies and learning services.
Mining decision rules on data streams in the presence of concept drifts
(2009-03-01)
Tsai, Cheng-Jung
;
Lee, Chien-I.
;
Yang, Wei-Pang
;
資訊工程學系
;
Department of Computer Science
In a database, the concept of all example might change along with time, which is known as concept drift. When the concept drift occurs, the classification model built by using the old dataset is not suitable for predicting a new dataset. Therefore, the problem of concept drift has attracted a lot of attention in recent years. Although many algorithms have been proposed to solve this problem, they have not been able to provide users with a satisfactory solution to concept drift. That is, the current research about concept drift focuses only on updating the classification model. However, real life decision makers might be very interested in the rules of concept drift. For example, doctors desire to know the root causes behind variation in the causes and development of disease. In this paper, we propose a concept drift rule mining tree, called CDR-Tree, to accurately discover the underlying rule governing concept drift. The main contributions of this paper are: (a) we address the problem of mining concept-drifting rules which has not been considered in previously developed classification schemes; (b) we develop a method that call accurately mine rules governing concept drift: (c) we develop a method that should classification models be required, call efficiently and accurately generate such models via a simple extraction procedure rather than constructing them anew; and (d) we propose two strategies to reduce the complexity of concept-drifting, rules mined by our CDR-Tree. (C) 2007 Elsevier Ltd. All rights reserved.
Structure clustering for Chinese patent documents
(2008-05-04)
Huang, Su-Hsien
;
Ke, Hao-Ren
;
Yang, Wei-Pang
;
資訊工程學系
;
Department of Computer Science
This paper aims to cluster Chinese patent documents with the structures. Both the explicit and implicit structures are analyzed to represent by the proposed structure expression. Accordingly, an unsupervised clustering algorithm called structured self-organizing map (SOM) is adopted to cluster Chinese patent documents with both similar content and structure. Structured SOM clusters the similar content of each sub-part structure, and then propagates the similarity to upper level ones. Experimental result showed the maps size and number of patents are proportional to the computing time, which implies the width and depth of structure affects the performance of structured SOM. Structured clustering of patents is helpful in many applications. In the lawsuit of copyright, companies are easy to find claim conflict in the existent patents to contradict the accusation. Moreover, decision-maker of a company can be advised to avoid hot-spot aspects of patents, which can save a lot of R&D effort. (c) 2007 Elsevier Ltd. All rights reserved.