RCGKA를 이용한 최적 퍼지 예측 시스템 설계

방영근,심재선,이철희 江原大學校 産業技術硏究所 2009 産業技術硏究 Vol.29 No.B

In the case of traditional binary encoding technique, it takes long time to converge the optimal solutions and brings about complexity of the systems due to encoding and decoding procedures. However, the ROGAs (real-coded genetic algorithms) do not require these procedures, and the k-means clustering algorithm can avoid global searching space. Thus, this paper proposes a new approach by using their advantages. The proposed method constructs the multiple predictors using the optimal differences that can reveal the patterns better and properties concealed in non- stationary time series where the k-means clustering algorithm is used for data classification to each predictor, then selects the best predictor. After selecting the best predictor, the cluster centers of the predictor are tuned finely via RCGKA in secondary tuning procedure. Therefore, performance of the predictor can be more enhanced. Finally, we verifies the prediction performance of the proposed system via simulating typical time series examples.

계층 구조 클러스터링 알고리즘 설계 및 그 응용

방영근,박하용,이철희 江原大學校 産業技術硏究所 2009 産業技術硏究 Vol.29 No.B

In many cases, clustering algorithms have been used for extracting and discovering useful information from non-linear data. They have made a great effect on performances of the systems dealing with non-linear data. Thus, this paper presents a new approach called hierarchically structured clustering algorithm, and it is applied to the prediction system for non-linear time series data. The proposed hierarchically structured clustering algorithm (called HCKA: Hierarchical Cross- correlation and K-means clustering Algorithms) in which the cross-correlation and k-means clustering algorithm are combined can accept the correlationship of non-linear time series as well as statistical characteristics. First, the optimal differences of data are generated, which can suitably reveal the characteristics of non-linear time series. Second, the generated differences are classified into the upper clusters for their predictors by the cross-correlation clustering algorithm, and then each classified differences are classified again into the lower fuzzy sets by the k-means clustering algorithm. As a result, the proposed method can give an efficient classification and improve the performance. Finally, we demonstrates the effectiveness of the proposed HCKA via typical time series examples.

HCBKA를 이용한 Interval Type-2 퍼지 논리시스템 기반 예측 시스템 설계

방영근,이철희 江原大學校 産業技術硏究所 2010 産業技術硏究 Vol.30 No.A

To improve the performance of the prediction system, the system should reflect well the uncertainty of nonlinear data. Thus, this paper presents multiple prediction systems based on Type-2 fuzzy sets. To construct each prediction system, an Interval Type-2 TSK Fuzzy Logic System and difference data were used, because, in general, it has been known that the Type-2 Fuzzy Logic System can deal with the uncertainty of nonlinear data better than the Type-1 Fuzzy Logic System, and the difference data can provide more steady information than that of original data. Also, to improve each rule base of the fuzzy prediction systems, the HCBKA (Hierarchical Correlation Based K-means clustering Algorithm) was applied because it can consider correlationship and statistical characteristics between data at a time. Subsequently, to alleviate complexity of the proposed prediction system, a system selection method was used. Finally, this paper analyzed and compared the performances between the Type-1 prediction system and the Interval Type-2 prediction system using simulations of three typical time series examples.

다중모델 퍼지 시스템을 위한 적응 모델선택 기법과 시계열 예측에의 응용

방영근,이철희 강원대학교 정보통신연구소 2009 정보통신논문지 Vol.13 No.-

Difference data are very useful for a prediction system because they can reveal the characteristics of non-stationary time series. Also, they can protect fuzzy clustering from a biased situation toward one side among fuzzy sets. But it is not easy to determine optimal difference intervals revealing patterns and regularities of time series. To overcome this problem, this paper proposes the data preprocessing procedure based on correlation analysis. Then, multiple model fuzzy systems are constructed by using the determined optimal intervals. To reflect the performances of each fuzzy system, this paper also proposes the adaptive model selection technique. The proposed technique can improve the prediction quality of fuzzy system that depends to the characteristics of input data because it is possible to control system output corresponding to system input via the adaptive model selection rules based on rough set theory. Thus, the proposed methods are more effective for prediction of non-stationary and/or chaos time series than traditional methods. In simulation and conclusion section, this paper verifies that the prediction performances of the proposed methods are very good and that the proposed methods are very effective to control the hybrid systems or multiple systems.

[논문]비소로 오염된 토양의 고형화에 관한 연구

오방일,노경환,조기철,정영헌,오광중 부산대학교 환경문제연구소 2004 環境硏究報 Vol.22 No.-

A Study on the Solidification of Soi1 Contaminated by Arsenite

골관절염 무릎 관절의 활액막 비후에 관한 자기공명영상과 활액막 생검 소견의 상관성

김철민,허방 고신대학교의과대학 2008 고신대학교 의과대학 학술지 Vol.23 No.2

Background : Synovium is a main target of rheumatoid arthritis. Synovial changes, however, have been overlooked in degenerative osteoarthritis (OA). In intraarticular tissues, especially cartilage, pain conducting fibers or vasculatures are normally absent, therefore, periarticular soft tissue changes, such as synovial pathology may be an important clue to understand the progression of OA. In addition. MRI was established as an excellent modality to characterize the articular changes of OA. However, synovial changes detected by MRI have not been evaluated based on histopathologic features of synovium. Methods and Materials : Total twenty six patients (male 11, female 15) of OA involving knee joint were collected in Kupo Sumgsim Hospital. MRI features of 24 cases were reviewed and its severity including synovial thickening and joint effusion were graded as 3 groups. Through arthroscopic examination, synovial biopsy was performed. Histologic features of the synovium, emphasizing on the synovial cell hyperplasia, inflammatory cell infiltration, fibrosis and vascularity were evalutated in accordance with MRI severity. Results : 1) Considrable MRI changes, joint effusion, and synovial hypertrophy (≥2mm) were noted in 12 cases (50.0%), 16 cases (66.7%), and 20 cases (83.3%) respectively. In 12 of 13 Gd-DTPA contrast studies, T1 enhanced image was achieved, and irregular or villous pattern was noted in 8 cases (40.0%) of 20 hypertrophied synovium. 2) Synovial cell hyperplasia (>2 cells in layer) was noted in 9 cases (34.6%) and lymphocytic infiltration (with minimal or mild degree) was noted in 11 cases (42.3%). Microvessel density was variable from case to case (MVD=12.4±2.7, Nikon Labophot, area=0.73 mm2, x200) and pattern of collagen deposition (loose or dense) was in equal proportion. 3) Although MRI changes and synovial hypertrophy were not correlated with various histopathologic changes, such as synovial cell hyperplasia, lymphocytic infiltration, collagen deposition and vascular proliferation, joint effusion was significantly correlated with TGF-α expression of synovial cells, collagen deposition and microvessel density. 4) Degree of MRI was more severe in female than male, in old than young age group, and in long duration (>1 year). Conclusion : Synovial hypertrophy detected by MRI is not correlated with histopathologic changes of synovium in knee OA. Both synovial effusion and hypertrophy, however, are correlated with vascular proliferation in some degree, which is remained to be clarified in more accumulated cases.

유도선수의 여가 참여형태에 따른 만족도 분석

조방현,김영환,이철원 연세대학교 체육연구소 2002 체육연구논문집 Vol.9 No.1

본 연구는 엘리트 유도선수들이 과연 여가시간을 어떠한 방법으로 활용하는지에 대한 의문을 바탕으로 문제해결을 시도하였으며 이를 통하여 여가 참여 형태와 여가 만족에 대한 측면을 분석하였다. 이러한 과정을 통하여 유도선수들의 여가활동에 대한 의식 및 만족도를 파악할 수 있었으며 또한 유도선수들이 효율적인 여가시간을 가질 수 있는 방안을 고안하고자 하였다. 구체적으로 이와 같은 연구 목적을 달성하기 위해 본 연구에서는 중, 고등학교와 대학교에 재학 중인 유도선수들을 대상으로 설문조사를 실시하여 여러가지 각도, 참여정도, 여가경비, 여가제약, 여가동기, 선호여가형태 등을 조사하였고, 아울러 여가만족도를 심리적 요인, 휴식적 요인, 교육적 요인, 사회적 요인, 환경적 요인, 그리고 생리적 요인으로 구분하여 교차분석과 분산분석을 실시하였다. 사후검증은 Turkey(표준화검정)을 실시하여 분석하였다. 이러한 연구 과정을 통하여 다음과 같은 결론을 얻었다. 첫째, 유도선수들의 여가참여정도에 따라 여가만족도는 교육적 요인, 사회적 요인, 그리고 환경적 요인에서 유의한 차이를 보였다. 둘째, 유도선수들의 선호여가형태에 따라 여가만족도는 교육적 요인과 생리적 요인에서 유의한 차이를 보였다. 셋째, 유도선수들의 여가제약에 따라 여가만족도는 유의한 차이가 없었다. 넷째, 유도선수들의 여가경비에 따라 여가만족도는 사회적 요인에서 유의한 차이를 보였다. 마지막으로 유도선수들의 여가동기에 따라 여가만족도는 유의한 차이가 없었다. The purpose of this study was to explain the judo players' leisure time and satisfaction through analyzing their leisure participation patterns and satisfaction. This also pursuits effective understanding of the leisure time and relationship between training and leisure time of Judo players. For the purpose of the study, the research participants (315 out of 355) were conducted from groups of middle school, high school and college judo players with questions of perception, frequency of participation, involved expense, limitations, motivation, and preferences toward leisure activities. These variables were used to quantify the tendency of leisure satisfaction. In the data analysis, frequency test, Chi-square test, and One-way ANOVA were executed. Furthermore the data was grouped into psychological, resting condition, educational, social , environmental, and physical factors to analyze the degree and tendency of leisure satisfaction. The results were shown as follows: 1. There were shown significant differences from the leisure participation of Judo players about leisure satisfaction on the educational, social, and environment factors. 2. There were indicated as significant differences of the preferred patterns of Judo players about leisure satisfaction on educational and physiological factors. 3. There were not shown significant differences leisure constrains of Judo players about leisure satisfaction. 4. There were shown significant differences about the expenses for leisure of Judo players about leisure satisfaction on the social factor. 5. There were not suggested significant differences of the leisure motive of Judo players about leisure satisfaction.

일부 공업지역 근로자들의 가정의학에 대한 인식도에 관한 소고

윤방부,강성규,김철수 의학교육출판사 1988 Korean Journal of Family Medicine Vol.4 No.12

The Copepods(Calanoida, Cyclopoida and Harpacticoida)around Cheju Island, Korea(Crustacea)

오봉철,고유봉,고방연 제주대학교 해양연구소 1994 해양자원연구소연구보고 Vol.18 No.-

리눅스를 기반으로 한 홈오토메이션 서버의 구현

성한용,김규칠,방철원,김용석 江原大學校 産業技術硏究所 2002 産業技術硏究 Vol.22 No.B

It becomes common to use computers to control electronic devices and security facilities in newly constructed buildings and house. There are many home application devices in the market which can be controlled by computers. But they are expensive and managed by specialized companies. This paper is focused on personal computers which are available in most homes and can be used to control home electronic appliances and home security facilities. We implemented a home automation server based on Linux. The standard parallel port of personal computer is used to connect sensors and actuators. Therefore, the cost of the server is very low. Moreover, the server is connected to Internet and anywhere we can control and monitor the home security facilities and home automation systems.