• Title/Summary/Keyword: 선별 탐색

Search Result 237, Processing Time 0.024 seconds

Neural Network Handwriting Recognition Using Middle Point Algorithm (중간점 알고리즘을 이용한 신경회로망 필기체 패턴인식)

  • So, A-Ram;Shin, Byeong-Seok
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2007.10c
    • /
    • pp.394-397
    • /
    • 2007
  • 본 논문에서는 문자 인식의 특징 선별 방법으로 중간점 알고리즘을 이용하는 방법을 제안한다. 영상자료의 특징들로부터 중간점을 선별하고 심볼패턴을 이용하여 필기체 문자를 인식한다. 이 방법은 사전에 많은 심볼 패턴을 학습해야 하지만 한글과 영어의 높은 인식률을 보이고 있으며, 특히 복잡한 문자들의 경우 좋은 결과를 낸다. 여기서는 중간점 알고리즘으로 입력된 데이터를 심볼 패턴과 비교하고, 심볼 영역에 의해 최적 판별 기저를 탐색한 후, 그것을 특징으로 선택한다. 또한 사전 기능과 투명도 기능을 구현하여 필기체 인식을 이용한 여러 활용 방안을 제시한다.

  • PDF

한우 6번 염색체의 Bootstrap기법을 이용한 우수 DNA 탐색

  • Lee, Je-Yeong;Yeo, Jeong-Su;Kim, Jae-Woo;Lee, Yong-Won;Kim, Mun-Jeong
    • 한국데이터정보과학회:학술대회논문집
    • /
    • 2003.05a
    • /
    • pp.41-47
    • /
    • 2003
  • 한우 6번 염색체 유전자 지도에서 한우의 질을 높이기 위한 QTL(quantitative trait loci)분석을 실시하여 선별된 Loci 값을 Permutation Test를 이용하여 계산하였다. 한편, 경제적으로 주요한 한우의 특성부위(질적부위와 육량등)에 따른, 우수 경제형질 DNA marker를 K-평균 군집법을 실시 파악하였다. 이들 QTL과 K-평균법에 의해 한우의 염색체 6번, ILST035의 주요 경제 형질별 DNA marker들을 선별하여, Bootstrap BCa방법을 이용하여 각 DNA marker들의 신뢰구간을 구했다.

  • PDF

Use of cccDNA Breakage Assay and Sulforhodamine B Assay for the Prescreening of Antitumor Agents from Microbial Sources (미생물 배양액으로부터 항암제의 예비선별을 위한 cccDNA Breakage 활성검정과 Assay Sulforhodamine B 활성검정의 이용)

  • Lee, Sang-Han;Lee, Dong-Sun;Kim, Jong-Guk;Hong, Soon-Duck
    • Journal of Life Science
    • /
    • v.8 no.1
    • /
    • pp.67-71
    • /
    • 1998
  • In order to develop new antitumor agents from fermentation broths, we used cccDNA breakage assay abd sulforhodamine B assay for prescreening. As a result, it was shown that sample reach 3.3% when using cccDNA breakage assay. In sulforhodamine B assay, we obtained 4 acive fraction against A549 (a cell line of human lung carcinoma) and SK-OV-3 (a cell line of human adenocarcinoma). These results suggest that these assay would be a promising method for antitumor prescreening from microbial sources.

  • PDF

Feature Selection for a Hangul Text Document Classification System (한글 텍스트 문서 분류시스템을 위한 속성선택)

  • Lee, Jae-Sik;Cho, You-Jung
    • Proceedings of the Korea Inteligent Information System Society Conference
    • /
    • 2003.05a
    • /
    • pp.435-442
    • /
    • 2003
  • 정보 추출(Information Retrieval) 시스템은 거대한 양의 정보들 가운데 필요한 정보의 적절한 탐색을 도와주기 위한 도구이다. 이는 사용자가 요구하는 정보를 보다 정확하고 보다 효과적이면서 보다 효율적으로 전달해주어야만 한다. 그러기 위해서는 문서내의 무수히 많은 속성들 가운데 해당 문서의 특성을 잘 반영하는 속성만을 선별해서 적절히 활용하는 것이 절실히 요구된다. 이에 본 연구는 기존의 한글 문서 분류시스템(CB_TFIDF)[1]의 정확도와 신속성 두 가지 측면의 성능향상에 초점을 두고 있다. 기존의 영문 텍스트 문서 분류시스템에 적용되었던 다양한 속성선택 기법들 가운데 잘 알려진 세가지 즉, Information Gain, Odds Ratio, Document Frequency Thresholding을 통해 선별적인 사례베이스를 구성한 다음에 한글 텍스트 문서 분류시스템에 적용시켜서 성능을 비교 평가한 후, 한글 문서 분류시스템에 가장 적절한 속성선택 기법과 속성 선택에 대한 가이드라인을 제시하고자 한다.

  • PDF

Design of Omok AI using Genetic Algorithm and Game Trees and Their Parallel Processing on the GPU (유전 알고리즘과 게임 트리를 병합한 오목 인공지능 설계 및 GPU 기반 병렬 처리 기법)

  • Ahn, Il-Jun;Park, In-Kyu
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.37 no.2
    • /
    • pp.66-75
    • /
    • 2010
  • This paper proposes an efficient method for design and implementation of the artificial intelligence (AI) of 'omok' game on the GPU. The proposed AI is designed on a cooperative structure using min-max game tree and genetic algorithm. Since the evaluation function needs intensive computation but is independently performed on a lot of candidates in the solution space, it is computed on the GPU in a massive parallel way. The implementation on NVIDIA CUDA and the experimental results show that it outperforms significantly over the CPU, in which parallel game tree and genetic algorithm on the GPU runs more than 400 times and 300 times faster than on the CPU. In the proposed cooperative AI, selective search using genetic algorithm is performed subsequently after the full search using game tree to search the solution space more efficiently as well as to avoid the thread overflow. Experimental results show that the proposed algorithm enhances the AI significantly and makes it run within the time limit given by the game's rule.

Methodology of Prior Art Search Based on Hierarchical Citation Analysis (계층적 인용관계분석을 통한 선행기술 탐색방법론)

  • Kang, Jiho;Kim, Jongchan;Lee, Joonhyuck;Park, Sangsung;Jang, Dongsik
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.27 no.1
    • /
    • pp.72-78
    • /
    • 2017
  • Prior art search is a core process of technology management performed by inventors and applicants, patent examiners, and employees in the patent industry. As a result of insufficient academic research on a systematic prior art search methodology, the process has been often carried out depending on the subjective judgment of researchers. Previous studies on exploring prior arts based on semantics have also have the risk of underestimating the similarity of major prior arts due to the nature of patent documents where the same technical ideas are expressed in various terms. In this study, we propose an effective prior art search methodology based on hierarchical citation analysis, which provides a clear criterion for selecting core prior arts by calculating weights according to the relative importance of the collected patents. In order to verify the feasibility of the proposed methodology, a case study was conducted to explore the core prior art of one patent in the display field. As a result, 10 core prior art candidates were selected out of the 206 precedent patents.

Validation of the Internet, Game, and Smartphone Overuse Screening Questionnaires on Adolescent Sample (인터넷, 게임, 스마트폰 과사용 선별 질문지의 청소년 대상 타당화 연구)

  • Park, Kyeongwoo;Chang, Hyein;Jeon, Hong Jin
    • Korean Journal of School Psychology
    • /
    • v.18 no.3
    • /
    • pp.317-349
    • /
    • 2021
  • This study was conducted to examine the reliability and validity of the internet (IOS-Q), Game (GOS-Q), and Smartphone (SOS-Q) Overuse Screening Questionnaires in a large community sample of adolescents. To achieve this goal, data from 9,336 middle school students (male: 4,796, female: 4,540) was divided into two groups and analyzed by conducting confirmatory factor analysis and exploratory factor analysis, respectively. We conducted another confirmatory factor analysis on a separate sample of data from 4,536 elementary school students (male: 2,260 male, female: 2,276) and 6,551 middle school students (male: 3,013, female: 3,538) from other populations. As a result of factor analysis, IOS-Q was consisted of 17 items, GOS-Q was consisted of 19 items, and SOS-Q was consisted of 18 items. The IOS-Q and GOS-Q factors were psychological dependence, failure to control use despite recognizing problems, dangerous use, and reduced interest in other areas while the SOS-Q factors were dangerous and obsessive use, failure to control use despite recognizing problems, reduced interest in other areas, and withdrawal/tolerance. Each factor reflected the major facets of behavioral addiction or impulse control disorder, and the questionnaires had good internal consistencies of .880-.915. Latent profile and ROC analyses were conducted to determine cutoff points for screening high-risk groups. Lastly, theoretical and practical implications as well as the limitations of this study were discussed.

User Preference based Intelligent Program Guide (사용자 선호도 기반 지능형 프로그램 가이드)

  • 류지웅;김문철;남제호;강경옥;김진웅
    • Journal of Broadcast Engineering
    • /
    • v.7 no.2
    • /
    • pp.153-167
    • /
    • 2002
  • With the advent of digital broadcasting, a large number of program channels become available at the user terminals such as set-top-box or PC. Channel navigation and searching become more difficult at TV terminal sides using a conventional device such as a TV remote controller. The MPEG-7 MDS (Multimedia Description Scheme) and TV Anytime set up a standard about how to describe user preferences for genre, channel, actor/actress, keyword, etc. of the TV programs, and how to describe usage history for user's program consumption behaviors and preferences. But they do not describe how to use them. In this paper, we describe an IPG (Intelligent Program Guider) system that provides TV program and channel information based on user preferences and suggest easy access to TV program that user wants. The IPG monitors user's behaviors of interacting to programs and automatically updates the user's preference changes according1y. The IPG utilizes user preferences description scheme specified in both MPEG-7 MDS and TV Anytime metadata specifications.

Solitude and Loneliness: Developmental Exploration of the Familiarity and Appropriateness of Words (고독과 외로움: 단어의 친숙성 및 적절성에 관한 발달적 탐색)

  • Hyejin Jang;Youngkeun Kim
    • Science of Emotion and Sensibility
    • /
    • v.27 no.1
    • /
    • pp.13-46
    • /
    • 2024
  • This study aimed to develop a Korean word tool related to solitude and loneliness. Because collecting the right words is very important, words that express the two emotions were selected from three language dictionaries. At this time, related words were collected to specifically reflect the increasing number of people seeking voluntary solitude. Consequently, 1,768 words were collected. From these, 684 words were selected based on specific criteria that everyone can understand and use, and they went through a six-iteration selection process, which extracted a total of 243 words. Considering the nature of the study, the meanings of the words collected must be clear and comprehensively represent the overall aspects of solitude and loneliness. Accordingly, a total of 243 words were selected, focusing on words that received the highest ratings in terms of familiarity and appropriateness. It is expected that this study will establish a clear concept of solitude and loneliness and provide basic data that can be used to understand the realistic and universal perception of Koreans from a developmental perspective.

A Scale on Attitudes of Home Education (가정교육의 태도 측정을 위한 척도개발 시안)

  • 이영호
    • Journal of Families and Better Life
    • /
    • v.12 no.2
    • /
    • pp.80-89
    • /
    • 1994
  • 본 연구에서는 "가족교육의 부재"를 경험하고 있는 현시점에서 가정교육의 정상성을 회복하고자 하는 노력의 일환으로 가정교육에 대한 기본태도와 가치성향을 규명할 수 있는 척도를 개발하는 것을 목적으로 하고 있다 본연구의 목적을 위하여 써스톤척도(Thurstone scale)에 근거하여 여러 가지 문항 탐색과정과 평가자 선별과정 및 통?거 절차를 거쳤으며 그 결과로서 24문항으로 구성된 척도가 마련되었다 본 척도는 가정교육에 대한 태도의 비교 연구 및 가정교육의 내용 방법론 등의 연구에 활용될 수 있을것이다.

  • PDF