RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제
      • 좁혀본 항목 보기순서

        • 원문유무
        • 원문제공처
          펼치기
        • 등재정보
        • 학술지명
          펼치기
        • 주제분류
        • 발행연도
          펼치기
        • 작성언어
        • 저자
          펼치기

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • GLVQ클러스터링을 위한 필기체 숫자의 효율적인 특징 추출 방법

        전종원,민준영,Jeon, Jong-Won,Min, Jun-Yeong 한국정보처리학회 1995 정보처리논문지 Vol.2 No.6

        The structure of a typical pattern recognition consists a pre-processing, a feature extraction(algorithm) and classification or recognition. In classification, when widely varying patterns exist in same category, we need the clustering which organize the similar patterns. Clustering algorithm is two approaches. Firs, statistical approaches which are k-means, ISODATA algorithm. Second, neural network approach which is T. Kohonen's LVQ(Learning Vector Quantization). Nikhil R. Palet al proposed the GLVQ(Generalized LVQ, 1993). This paper suggest the efficient feature extraction methods of handwritten numerals in GLVQ clustering network. We use the handwritten numeral data from 21's authors(ie, 200 patterns) and compare the proportion of misclassified patterns for each feature extraction methods. As results, when we use the projection combination method, the classification ratio is 98.5%. 패턴인식은 전처리, 특징추출, 식별의 과정을 거쳐 인식을 하게된다. 식별과정 에서 여러개의 패턴이 흩어져 있을 경우에 유사한 패턴끼리 클러스터링을 위하여 한 카테고리 내에서 패턴을 분할하게 된다. 클러스터링 방법에는 통계적인 방법으로 k-means 방법, ISODATA알고리즘등이 있으며〔1〕, 최근에는 신경망에 의한 클러스터링 방법으로 T, Kohonen의 LVQ(Learning Vector Quantization)가 주로 이용되었다〔6〕. Nikhil R, Pal. et al은 LVQ알고리즘을 보다 개선한 방법으로 GLVQ(Generalized LVQ, 1993)를 제안하였다〔4〕.본 논문은 GLVQ 알고니즘으로 패턴을 클러스터링 할 경우에 효율적인 특징추출 방법을 제안한다. 본 논문에서는 20명의 필기체 숫자 0에서 9까지 의 200개 패턴을 여러 가지 방법으로 특징 추출하여 GLVQ알고리즘으로 10개(0-9의 패턴) 의 클러스터로 구분하고, 해당 클러스터에서 오분류되는 패턴의 비율로서 그 효율성을 비교 하였다. 그 결과 투영조합 방법을 이용하였을 경우 98.5%의 분류율을 나타내었다.

      • 인체와 성덕대왕 신종의 진동 특성 비교 연구

        전종원,진용옥,Jeon, Jong-Won,Chin, Yong-Ohk 한국정보처리학회 2000 정보처리논문지 Vol.7 No.10

        본 논문은 성덕대왕 신종과 인체의 진동 특성의 상관관계를 분석함으로서 진동 특징 추출의 새로운 방안을 도출하기 위한 연구이다. 신종의 종, 움통, 울림통과 기타 비대칭적 요소들을 인체의 몸체, 성도, 횡경막과 인체구조의 비대칭적 요소들에 대비시켜 각각의 음향 특성들을 실험을 통하여 비교 분석하였다. 실험결과, 대비시킨 각 요소들의 음향 특성이 매우 흡사하여, 신종의 소리 특성에 관한 정보가 인체의 진동 전달 특성을 분석하는 데 있어서도 매우 유용하게 적용될 수 있다는 것을 확인하였다. This paper is a study to find a new method of feature selection for vibrationof buman body by analyzing correlationof vibration between King Songdok Bell and Human body. The vibration characteristics are analyzed by matching body, vocal tract, diaphragm and asymmetrical clements of human body with Bell, resonator, hole in the ground and asymmetical elements. In the result, the characteristics of sound vibrationof King Songdok Bell is useful to apply it to vibration characteristics of human body because the vibration characteristics of ech elements is alike.

      • 패턴인식 : GLVQ 클러스터링을 위한 필기체 숫자의 효율적인 특징 추출 방법

        전종원(Jeon Jong Won),민준영(Min Joon Young) 한국정보처리학회 1995 정보처리학회논문지 Vol.2 No.6

        패턴인식은 전처리, 특징추출, 식별의 과정을 거쳐 인식을 하게된다. 식별과정에서 여러개의 패턴이 흩어져 있을 경우에 유사한 패턴끼리 클러스터링을 하여 한 카테고리 내에서 패턴을 분할하게 된다. 클러스터링 방법에는 통계적인 방법으로 k-means방법, ISODATA 알고리즘등이 있으며[1], 최근에는 신경망에 의한 클러스터링 방법으로 T.Kohonen의 LVQ(Learning Vector Quantization)가 주로 이용되었다[6]. Nikhil R. Pal, et al은 LVQ 알고리즘을 보다 개선한 방법으로 GLVQ(Generalized LVQ, 1993)를 제안하였다[4]. 본 논문은 GLVQ 알고리즘으로 패턴을 클러스터링 할 경우에 효율적인 특징추출 방법을 제안한다. 본 논문에서는 20명의 필기체 숫자 0에서 9까지의 200개 패턴을 여러가지 방법으로 특징추출하여 GLVQ 알고리즘으로 10개(0-9의 패턴)의 클러스터로 구분하고, 해당 클러스터에서 오분류되는 패턴의 비율로서 그 효율성을 비교하였다. 그 결과 투영조합 방법을 이용하였을 경우 98.5%의 분류율을 나타내었다. The structure of a typical pattern recognition consists a pre-processing, a feature extraction(algorithm) and classification or recognition. In classification, when widely varying patterns exist in same category, we need the clustering which organize the similar patterns. Clustering algorithm is two approaches. First, statistical approaches which are k-means, ISODATA algorithm. Second, neural network approach which is T.Kohonen''s LVQ(Learning Vector Quantization). Nikhil R. Palet al proposed the GLVQ(Generalized LVQ, 1993). This paper suggest the efficient feature extraction methods of handwritten numerals in GLVQ clustering network. We use the handwritten numeral data from 20''s authors(ie, 200 patterns) and compare the proportion of misclassified patterns for each feature extraction methods. As results, when we use the projection combination method, the classification ratio is 98.5%.

      • 순환성 운동 프로그램을 통한 스트레스 호르몬 변화

        전종원 ( Jong Won Jeon ) 한국스포츠리서치 2007 한국 스포츠 리서치 Vol.18 No.4

        The objects for this study were students divided into group A (who are majoring in Gymnastics) and B (who are not). We selected 12 members in each group. We have found the following conclusions as results of measuring previous time to circulatory exercise, immediate time after circulatory exercise and the change of stress hormones in recovery time. 1. Epinephrine was compared by changes of previous time, the time after the exercise and recovery time in those groups. They all have the significant differences in Epinephrine. In the comparison of the groups, there were no significant differences before the exercise but there were the significant differences after the exercise and in recovery time. 2. Norepinephrine was compared by changes of previous time, the time after the exercise and recovery time in those groups. They all have the significant differences in Norepinephrine. In the comparison of the groups, there was no significant difference in recovery time but there were the significant differences before and after the exercise. 3. Cortisol was compared by changes of previous time, the time after the exercise and recovery time in those groups. They all have the significant differences in Cortisol. In the comparison of the groups, there were no significant differences after the exercise and in recovery time but there were the significant differences before the exercise. I would like to make the bellow suggestions to you by colligating the above results. The study of the circulatory exercise is becoming researched a lot recently but I think that it is still lacking in studies of various parts. Hence, in my opinion, the changes of various hormones and blood component need to be studied and the objects have also necessities to applied variously.

      • KCI등재
      • KCI등재

        YOLOv4를 이용한 차량파손 검출 모델 개선

        전종원(Jong Won Jeon),이효섭(Hyo Seop Lee),한희일(Hee Il Hahn) 한국전기전자학회 2021 전기전자학회논문지 Vol.25 No.4

        본 논문에서는 YOLOv4를 이용하여 차량의 부위별 파손현황을 검출하는 기법을 제안한다. 제안 알고리즘은 YOLOv4를 통해 차량의 부위와 파손을 각각 학습시킨 후 검출되는 바운딩 박스의 좌표 정보들을 추출하여 파손과 차량부위의 포함관계를 판단하는 알고리즘을 적용시켜 부위별 파손현황을 도출한다. 또한 성능비교의 객관성을 위하여 동일분야의 VGGNet을 이용한 기법, 이미지 분할과 U-Net 모델을 이용한 기법, Weproove.AI 딥러닝 모델 등을 대조 모델로 포함한다. 이를 통하여 제안 알고리즘의 성능을 비교, 평가하고 검출 모델의 개선 방안을 제안한다. This paper proposes techniques for detecting the damage status of each part of a vehicle using YOLOv4. The proposed algorithm learns the parts and their damages of the vehicle through YOLOv4, extracts the coordinate information of the detected bounding boxes, and applies the algorithm to determine the relationship between the damage and the vehicle part to derive the damage status for each part. In addition, the technique using VGGNet, the technique using image segmentation and U-Net model, and Weproove.AI deep learning model, etc. are included for objectivity of performance comparison. Through this, the performance of the proposed algorithm is compared and evaluated, and a method to improve the detection model is proposed.

      • KCI등재후보

        중량운동과 탄성저항운동이 여성노인의 신체구성, 활동체력, 혈액성분에 미치는 영향

        전종원(Jeon Jong-Won),황영란(Hwang Young-Ran) 한국체육과학회 2009 한국체육과학회지 Vol.18 No.4

        This research is to improve an old person's health considering physical strength of the old person and presents more effective sports program to the old person. It applied to elastic band program considering low weight of dumbbell exercise and elderly women physical strength and intended to get a positive results of body composition, physical fitness, blood. It was that over 60 years elderly women who lived in Seoul want to participate in a health program. It selected 8 experimental group, 8 controll group and conducted exercise program for 8 weeks. Exercise program practiced for 1<SUP>th</SUP>~4<SUP>th</SUP> weeks and 5<SUP>th</SUP>~8<SUP>th</SUP> weeks kind of program and change of powerfulness as well as frequency in the order of frequency a week per 3 times for 8 weeks. Training of one time makes up step of warm up, the main training, cool down and total training time makes up in 60 minutes. The procedure reached the following conclusions.

      • KCI등재

        지역 활성화를 위한 골프레저산업의 방향

        전종원(Jeon, Jong-Won),김도진(Kim, Do-Jin) 한국체육과학회 2014 한국체육과학회지 Vol.23 No.6

        The purpose of this study was to suggest the direction of golf leisure industry for the regional vitalization of Taebaek city in Gangwondo. This study was categorized into 4 aspects. First, exploration was conducted on the leisure business of the region. Second, it was about attracting golf leisure contests and events. Third, it was about the establishment of middle and high schools to cultivate subjects of golf leisure. Lastly, it was regarding the organic connection between universities and local government for the vitalization of golf leisure. It is anticipated for this study to make positive contribution to infra construction as the city of highlands leisure sports.

      • KCI등재

        골프동호인의 운동정서와 스트레스, 운동지속수행간의 관계

        전종원(Jeon, Jong-Won),김재원(Kim, Jae-Won) 한국체육과학회 2012 한국체육과학회지 Vol.21 No.2

        Goal of this research was to investigate differences of Exercise affect, Stress, and Exercise continuation performance of general golf enthusiastsl, and to analyze relationships among those three psychological factors. Research subjects were consisted of 231 participants with golf rounding experiences, and Stress, Korean model of exercise affect, and Korean model of exercise continuation performance measure were used as analysis tools. For analyzing data, Frequency analysis, Cronbach"s alpha, one-way ANOVA, Correlation, and Stepwise multiple regression analysis were conducted by using a SPSS Windows 12.0 statistical analysis program. Based on data analysis results were followed: Firstly, as Handicap level of the participants were lower, Financial pressure of the Stress, Competitive stress factor and Interest of exercise affect, Achievement factor, and Exercise continuation performance were showed higher. Secondly, Accompanying disrespect of Stress, Competitive stress, Exercise continuation performance, Interest and Achievement factor of Exercise affect were all correlated with most sub-factors. Thirdly, for analysis of Degree of influence on factors, Stress and several Exercise affect influenced on Exercise continuation performance, and Stress affected on Exercise affect.

      • 인체와 성덕대왕 신종의 진동 특성 비교 연구

        전종원 ( Jong Won Jeon ),진용옥 ( Yong Ohk Chin ) 한국정보처리학회 2000 정보처리학회논문지 Vol.7 No.10

        This paper is a study to find a new method of feature selection for vibration of human body by analyzing correlation of vibration between King Songdok Bell and Human body. The vibration characteristics are analyzed by matching body, vocal tract, diaphragm and asymmetrical clements of human body with Bell, resonator, hole in the ground and asymmetrical elements. In the result, the characteristics of sound vibration of King Songdok Bell is useful to apply it to vibration characteristics of human body because the vibration characteristics of each elements is alike.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼