Browsing by Author "Chen, Wei-Chou"

Now showing 1 - 4 of 4

A novel feature selection method for large-scale data sets
(2005)
Chen, Wei-Chou
;
Yang, Ming-Chun
;
Tseng, Shian-Shyong
;
資訊工程學系
;
Department of Computer Science
Feature selection is about finding useful (relevant) features to describe an application domain. The problem of finding the minimal subsets of features that can describe all of the concepts in the given data set is NP-hard. In the past, we had proposed a feature selection method, which originated from rough set and bitmap indexing techniques, to select the optimal (minimal) feature set for the given data set efficiently. Although our method is sufficient to guarantee a solution's optimality, the computation cost is very high when the number of features is huge. In this paper, we propose a nearly optimal feature selection method, called bitmap-based feature selection method with discernibility matrix, which employs a discernibility matrix to record the important features during the construction of the cleansing tree to reduce the processing time. And the corresponding indexing and selecting algorithms for such feature selection method are also proposed. Finally, some experiments and comparisons are given and the result shows the efficiency and accuracy of our proposed method.
An efficient bit-based feature selection method
(2008-05-04)
Chen, Wei-Chou
;
Tseng, Shian-Shyong
;
Hong, Tzung-Pei
;
資訊工程學系
;
Department of Computer Science
Feature selection is about finding useful (relevant) features to describe an application domain. Selecting relevant and enough features to effectively represent and index the given dataset is an important task to solve the classification and clustering problems intelligently. This task is, however, quite difficult to carry out since it usually needs a very time-consuming search to get the features desired. This paper proposes a bit-based feature selection method to find the smallest feature set to represent the indexes of a given dataset. The proposed approach originates from the bitmap indexing and rough set techniques. It consists of two-phases. In the first phase, the given dataset is transformed into a bitmap indexing matrix with some additional data information. In the second phase, a set of relevant and enough features are selected and used to represent the classification indexes of the given dataset. After the relevant and enough features are selected, they can be judged by the domain expertise and the final feature set of the given dataset is thus proposed. Finally, the experimental results on different data sets also show the efficiency and accuracy of the proposed approach. (c) 2007 Elsevier Ltd. All rights reserved.
METHOD FOR DETECTION OF MANUFACTURE DEFECTS
(2005-07-07)
Tseng, Shian-Shyong
;
Chen, Wei-Chou
;
Wang, Ching-Yao
A novel method for detection of manufacture defects is disclosed. The invented method is designed to discover root cause machine sets that cause defects in product manufactured in a process wherein a plurality of machines is involved. The method comprises obtaining manufacture data that relate to manufacture of products in the manufacture process, generating a candidate list of machine set by analyzing the manufacture data wherein the machine set includes machines relative to defects in the products, and identifying root cause machine sets from the list of machine set wherein the root cause machine sets include machines highly related to the defects.
The Application of the Sawtooth Photonic Crystal on Producing Polarized Light
(2011-09-15)
Pei, Ting-Hang
;
Chen, Wei-Chou
;
Yang, Kei-Hsiung
;
光電學院
;
College of Photonics
We have proposed a sawtooth photonic crystal formed by Si-SiO(2) periodic layers designed on a planar medium as a polarizer. The polarizer can produce H-polarized light very efficiently because the frequency of E-polarized light is chosen at the photonic band gap but that of H-polarized light at the photonic conduction band. The best polarization ratio is as high as 2.56 x 10(5) : 1 when the normalized frequency a/lambda is 0.24 and the incident angle is about 13 degrees. Highly polarized light can be produced in a normalized frequency range from 0.23 to 0.25, and this can possibly be applied to an LED with a certain bandwidth.