• Proceedings of the KIEE Conference
• /
• 2002.11a
• /
• pp.223-224
• /
• 2002

본 논문에서는 운전중인 변전소접지계의 분류전류를 측정하는 기법을 개발하고자 한다. 접지계의 안전성을 진단하기 위해서는 분류전류의 정확한 측정이 필수적이다. 모델변전소로 최근 부하 밀집지역인 도시지역에 가장 많이 채택하고 있는 옥내 지중변전소를 선정하였다. 가장 악조건인 1차측 지중선로 1회선인 경우 지중선로 분류율의 계산치 및 실측치가 각각 85.60[%]및 84.43[%]로 잘 일치하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04a
• /
• pp.361-363
• /
• 2000

기존의 웹 기반 의료 서비스는 환자 자신이 직접 해당 사이트를 찾아 읽어보고 의사들과 e-mail로 상담하는 수준이었다. 환자는 자신의 증상과 유사한 정보가 어디에 있는지 알아야하고 의사들은 e-mail을 일일이 읽고 답해 주어야만 한다. 그러나 메일 에이전트, 진단 에이전트 등이 존재하는 멀티 에이전트 시스템이 개발된다면 기존의 web 기반 의료 서비스의 단점을 보완할 수 있다. 본 논문에서는 JATLite 기반의 멀티 에이전트 시스템을 설계하여 자동으로 e-mail을 분석, 분류, 전달, 진단하는 시스템을 설계하였다. 제안된 멀티 에이전트 메일 에이전트, 진단 에이전트, 중재 에이전트 등으로 구성된다. 메일 에이전트는 환자를 상담, 요청, 증상 등을 분석하여 해당하는 진단 에이전트에게 전달하는 일을 한다. 진단 에이전트는 지식베이스를 이용하여 환자의 요구사항에 적절한 진단을 하게 된다. 중재 에이전트는 에이전트의 상태를 파악하여 작업을 지시하고 메일 에이전트와 진단 에이전트간의 통신을 관리한다.

• Journal of Yeungnam Medical Science
• /
• v.16 no.1
• /
• pp.76-84
• /
• 1999

The differentiation between malignancy-related ascites(MRA) and non-malignant ascites (NMA) is important for further diagnostic and therapeutic purposes. Although many parameters were investigated, none has provided a complete distinction between MRA and NMA. We investigated several ascitic fluid parameters to determine the differential power, and to differentiate malignant-related from nonmalignant-related ascites with a sequence of sensitive parameters followed by specific parameters. For the present study, 80 patients with ascites were divided into two groups: MRA and NMA, The MRA group was consisted of 27 patients with proven malignancy by image study, biopsy, and follow up: 21 of these patients had peritoneal carcinomatosis, but the remaining 6 showed no evidence of peritoneal carcinomatosis. The NMA group was consisted of 53 patients with no evidence of malignancy: among these patients, one had SLE, and others had liver cirrhosis, The samples of blood and ascites were obtained simultaneously, and then the levels of ascites cholesterol, CEA. protein and LDH, cytology, albumin gradient, ascites/serum concen-tration ratios of LDH(LDH A/S), and ascites/serum concentration ratios of protein(protein A/S) were measured. Applying cut-off limits for determined parameters, we estimated the diagnostic efficacy of each parameter, Among the eight parameters investigated, ascites fluid cholesterol yielded the best sensitive value of 93%(cut-off value 30mg/dl), and cytologic examination and the protein A/S(cut-off value 0.5) showed the most specific value of 100% and 96%, respectively. Based on the above results, the diagnostic sequence with cholesterol as a sensitive parameter followed by the combination of cytologic examination and protein A/S as specific parameters, was tested in 80 patients. This diagnostic sequence identified 81.5% of patients with malignancy, and all patients with peritoneal carcinomatosis were classified as malignancy-related ascites. In spite of many limitations, this proposed diagnostic sequence may permit a cost-effective and simple differentiation of malignancy-related ascites from nonmalignant ascites.

• ICROS
• /
• v.16 no.3
• /
• pp.21-27
• /
• 2010

본 논문에서는 지금까지 이루어진 전립선 암 진단 및 치료를 위한 로봇기술 적용 사례 관련 연구들을 조사하여 체계적인 분류 및 분석 작업을 수행함으로써 현재 기술 동향을 파악하고, 앞으로 나아갈 연구 방향을 제시하고자 한다.

• The Journal of Korean Medicine
• /
• v.17 no.2 s.32
• /
• pp.337-393
• /
• 1996

The purpose of this study is to evaluate and standardize the four scales of Questionnaire for the Sasang Constitution Classification 　II (QSCCII). QSCCII is newly prepared by statistical item analysis and is designed to examine its diagnostic discriminability. QSCCII is administered to 1366 random informants. From the survey, we could get the data for the standardization. The criteria of standardization are based on the data from 265 informants who are examined by professionals. Collectted data are analyzed by internal consistency, variation analysis(ANOVA), Duncan test and discrimination analysis of SPSS PC+ V4.0 program. The results are as follows reliability of four scales for QSCCII is relatively valid. The internal consistency of Tae-yang(太陽) (太陽) scale is Cronbach's a=0.5708. That of So-yang(少陽) scale is a=0.5708. That of Tae-eum(太陰) scale is a =0.5922. That of So-eum(少陰) scale is a=0.6319. 2. There is a significant difference between each group through variation analysis of four scales. 3. The process of standardization is based on the average value and standard deviation with respect to age and sex difference of each criteria 4. This study suggests a source of standardization of Sasang Constitution Classification by providing norms in which the differences of age, sex, and number of items are taken into deep consideration. QSCC Ⅱ, therefore, can be applied to every age(the 10's to the 60's) and sex groups. 5. The recalculation of the raw-score to standard value (T-score) shows that the diagnostic discriminability (Hit-ratio: 70.08%) of QSCC Ⅱ brings about 37% improvement than proportional chance criteria (33.33%). Especially, Hit-ratios of Tae-eum In(74.5%) and So-eum In(70.8%) are higher than that of So-yang In(60.0%). 6. QSCC has discriminability only to male informants. Compared with QSCC, however, QSCC II has relatively efficient discriminability both to male and female informants. 7. These results would be a demonstration of the fact that the QSCC II could be used as a tool for sasang constitution classification.

• Journal of Sasang Constitutional Medicine
• /
• v.8 no.1
• /
• pp.187-246
• /
• 1996

The purpose of this study is to evaluate and standardize the four scales of Questionnaire for the Sasang Constitution ClassificationII (QSCCII). QSCCII is newly prepared by statistical item analysis and is designed to examine its diagnostic discriminability. QSCCII is administered to 1366 random informants. From the survey, we could get the data for the standardization. The criteria of standardization are based on the data from 265 informants who are examined by professionals. Collected data are analyzed by internal consistency, variation analysis(ANOVA), Duncan test and discrimination analysis of SPSS PC+ V4.0 program. The results are as follows 1) The reliability of four scales for QSCCII is relatively valid. The internal consistency of Tae-yang(太陽) scale is Cronbach's ${\alpha}=0.5708$. That of So-yang(少陽) scale is ${\alpha}=0.5708$. That of Tae-eum(太陰) scale is ${\alpha}=0.5922$. That of So-eum(少陰) scale is ${\alpha}=0.6319$. 2) There is a significant difference between each group through variation analysis of four scales. 3) The process of standardization is based on the average value and standard deviation with respect to age and sex difference of each criteria. 4) This study suggests a source of standardization of Sasang Constitution Classification by providing norms in which the differences of age, sex, and number of items are taken into deep consideration. QSCCII, therefore, can be applied to every age(the 10's to the 60's) and sex groups. 5) The recalculation of the raw-score to standard value (T-score) shows that the diagnostic discriminability (Hit-ratio : 70.08%) of QSCCII brings about 37% improvement than proportional chance criteria(33.33%). Especially, Hit-ratios of Tae-eum In(74.5%) and So-eum In(70.8%) are higher than that of So-yang In(60.0%). 6) QSCC has discriminability only to male informants. Compared with QSCC, however, QSCCII has relatively efficient discriminability both to male and female informants. 7) These results would be a demonstration of the fact that the QSCCII could be used as a tool for sasang constitution classification.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.5
• /
• pp.115-131
• /
• 2004

As dual port memories are being frequently used, test and diagnosis for dual port memories becomes more important. In this paper, anew diagnosis algerian which can classify faults in detail when the fault is detected during test process is developed. The new algerian increases its efficiency by using the information that can be obtained by test results as well as results using additional diagnostic pattern set. In addition the algorithm can diagnose various fault models for dual port memories.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.208-211
• /
• 2006

본 논문에서는 3상 유도전동기의 고장진단을 수행하기 위해 패턴인식에 기반을 둔 진단 알고리즘을 제안한다. 실험 장치는 유도전동기 구동의 고장신호를 얻기 위하여 구축하였으며, 취득된 데이터를 이용하여 진단 알고리즘을 구축하였다. 취득된 데이터 중에서 진단을 위해 사용될 훈련데이터는 퍼지 기반 클러스터링 기법을 이용하여 신뢰성 높은 데이터를 선택하여 고장별 신호를 추출하였다. 진단 알고리즘으로는 데이터를 주성분 분석기법을 적용하였으며, 최종 분류를 위해 Euclidean 기반 거리척도 기법을 이용하였다. 다양한 부하 및 고장신호에 대하여 제안된 방법을 적용하여 타당성을 검증하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8S
• /
• pp.2650-2662
• /
• 2000

기존의 웹 기반 의료 서비스는 환자 자신이 직접 해당 사이트를 찾아 읽어보고 의사들과 e-mail로 상담하는 수준이었다. 환자는 자신의 증상과 유사한 정보가 어디에 있는지 알아야 하고 의사들은 e-mail을 일일이 읽고 답해 주어야만 한다. 그러나 메일 에이전트, 진단 에이전트 등이 존재하는 멀티 에이전트 시스템이 개발된다면 기존의 web 기반 의료 서비스의 단점을 보완할 수 있다. 본 논문에서는 JATLite 기반의 멀티 에이전트 시스템을 설계하여 자동으로 e-mail을 분석, 분류, 전달, 진단하는 시스템을 개발하였다. 제안된 멀티 에이전트는 메일 에이전트, 진단 에이전트, 중재 에이전트 등으로 구성된다. 메일 에이전트는 환자의 상담, 요청, 증상 등을 분석하여 해당하는 진단 에이전트에게 전달하는 일을 한다. 진단 에이전트는 지식베이스를 이용하여 환자의 요구사항에 가장 적절한 진단을 하게 된다. 중재 에이전트는 에이전트의 상태를 파악하여 작업을 지시하고 메일 에이전트와 진단에이전트간의 통신을 관리한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.6
• /
• pp.13-21
• /
• 2016

Feature selection is the one of important issue in the field of data mining and machine learning. It is the technique to find a subset of features which provides the best classification performance, from the source data. We propose a feature subset selection method using the neighborhood rough set model based on information granularity. To demonstrate the effectiveness of proposed method, it was applied to select the useful features associated with breast tumor diagnosis of 298 shape features extracted from 5,252 breast ultrasound images, which include 2,745 benign and 2,507 malignant cases. Experimental results showed that 19 diagnostic features were strong predictors of breast cancer diagnosis and then average classification accuracy was 97.6%.