• Journal of Chest Surgery
• /
• 제11권2호
• /
• pp.129-134
• /
• 1978

Two hundred and seventeen patients underwent diagnostic rigid bronchoscopy or bionchofiberscopy to evaluate the cytologic diagnosis in the lung cancer patient at the department of chest surgery of Yon-Sei university, college of the medicine from 1971 to 1977 year. One hundred and twenty cases of these patients were taken rigid bronchoscopy and ninety four cases of these patient were taken bronchofiberscopy. Cytologic examination of the sputum was done in 214 cases and sputum cytology was positive in 50 cases [23.4%]. Rigid bronchoscopy was made in 120 cases and this bronchoscopic cytology including bronchial washing and bronchial biopsy was positive in 34 cases [28.5%]. Bronchofiberscopy was performed in 94 cases and was positive in 45 cases [47.5%]. Histopathologically, 41 cases [43.6%] were epidermoid cell carcinoma, 8 cases [8.5%]of undifferentiated cell type, 12 cases [12.8%]of adenocarcinoma, 8 cases [8.5%]of alveolar cell type, and the 25 cases were undetermined. Cytologic examination of the sputum lacks the accuracy of the bronchoscopies in terms of both localization and accurate histologic indentification of the type of neoplasm. Rigid bronchoscope has the advantage of permitting identification of a tumor in a central location and of providing a sufficient amount of biopsy material for accurate diagnosis of carcinoma. However, it has the disadvantage of limiting examination to the larger, more central portions of the tracheobronchial tree. Bronchofiberscope had the advantage of examine upper lobe as well as other portions of the tracheobronchial tree which could not be visualized with the rigid bronchoscopy. A positive diagnosis in bronchofiberscopy was obtained in the highest rate, 47. 8% [45 cases]. A1 last, if a bronchogenic carcinoma is suspected on the basis of either symptoms of an abnormality on the chest film the diagnostic work-up-sputum cytology, bronchial washing, bronchoscopic biopsy, scalene node biopsy, thoracentesis and mediastinoscopy explothoracotomy etc-should precede in an attempt not only to obtain the higher positive diagnosis but also to obtain a tissue diagnosis and to evaluate the stage of the disease and to ascertain the appropriate mode of therapy.

• 전자공학회논문지CI
• /
• 제47권4호
• /
• pp.102-108
• /
• 2010

태양광 발전 시스템은 태양 전지에 의해 태양 에너지를 직류로 변환하며 이 직류를 인버터에 의해 일반 가정에서 사용되는 교류로 변환한다. 최근 태양광 발전 시스템의 전력량이 증가하는 추세이므로 대전력을 전송하는 3상 시스템에 관한 연구가 중요하다. 본 논문에서는 태양광전지의 계통연계 시스템의 3상 PWM 인버터의 스위치 개방이 발생했을 경우, 이를 간단히 검출하고 식별하는 방법을 제안한다. 제안 방법은 $\alpha\beta$ 평면에서 전류 벡터의 궤적 영상의 패턴을 특징으로 하여 정상상태와 각각의 고장 상태를 결정하여 트리로 분류한다. 트리 구성을 위한 고장패턴은 21개로 하였으며 고장 패턴트리의 결정을 위한 분류 파라메터는 모양, 영역, 분산각, 벡터각으로 하였다. 각 고장에 대하여 제안방법의 성능을 평가한 결과 모든 고장요소를 정확히 분류하여 패턴 트리를 구성하였다.

• KIEE International Transactions on Electrophysics and Applications
• /
• 제11C권2호
• /
• pp.12-17
• /
• 2001

In this work, the correlation between the PD Patterns and the electrical tree propagation has been investigated by use of the specimen removed from the insulation of the real 154 kV XLPE underground power cables. As a result, it could be deduced that the PD pattern regarding electrical trees depends on their type which could be classified into three different distinct groups such as branch-bush mixed. Considering the results of our investigation, if the partial discharge magnitude is only considered for the diagnosis of the cable system, it is possible to draw a wrong decision. Therefore, it is possible to propose that the time characteristics of PD pattern should be taken into account for the diagnosis of the cable system in addition to the conventional $\Phi$-q-n characteristics.

• Industrial Engineering and Management Systems
• /
• 제10권4호
• /
• pp.272-278
• /
• 2011

Decision tree as a classification tool is being used successfully in many areas such as medical diagnosis, customer churn prediction, signal detection and so on. The main advantage of decision tree classifiers is their capability to break down a complex structure into a collection of simpler structures, thus providing a solution that is easy to interpret. Since decision tree is a top-down algorithm using a divide and conquer induction process, there is a risk of reaching a local optimal solution. This paper proposes a procedure of optimally determining thresholds of the chosen variables for a decision tree using an adaptive particle swarm optimization (APSO). The proposed algorithm consists of two phases. First, we construct a decision tree and choose the relevant variables. Second, we find the optimum thresholds simultaneously using an APSO for those selected variables. To validate the proposed algorithm, several artificial and real datasets are used. We compare our results with the original CART results and show that the proposed algorithm is promising for improving prediction accuracy.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.317-322
• /
• 2011

한국정보화진흥원에서 개발한 한국형 성인 인터넷 중독 자가진단 척도인 K-척도는 4가지 요인의 20 문항으로 구성되어 있으며, 사용자의 설문응답값으로 인터넷 중독을 진단한다. 기존의 연구는 대부분 인터넷 중독의 원인을 찾으려는 시도였으며, 청소년 대상으로 수집된 표본을 가지고 그들의 인터넷 중독진단이 수행되었다. 본 연구의 목적은 통계 기법의 주성분분석과 데이터마이닝 기법인 의사결정트리를 이용하여 K-척도의 사용자군 분류를 판정하는 주요인을 발견하는 것이다. 실험 결과로부터 K-척도를 구성하는 4가지 요인 중 내성 및 몰입 요인이 성인 인터넷 중독진단에 가장 큰 영향을 주는 요인임을 알 수 있었다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권7호
• /
• pp.1092-1100
• /
• 2004

This paper describes the application of fault tree technique to analyze of compressor failure. Fault tree analysis technique involves the decomposition of a system into the specific form of fault tree where certain basic events lead to a specified top event which signifies the total failure of the system. In this research. fault trees for failure analysis of screw type air compressor are made. This fault trees are used to obtain minimal cut sets from system failure and system failure rate for the top event occurrence can be calculated. It is Possible to estimate air compressor reliability by using constructed fault trees through compressor failure example. It is Proved that FTA is efficient to investigate the compressor failure modes and diagnose system.

• 사상체질의학회지
• /
• 제15권3호
• /
• pp.177-186
• /
• 2003

Objectives: This paper was for studying the constitutional differences between questionnaire and clinical diagnosis, and to be helpful to make a diagnosis Sasang constitution. Using the result of this study, it will be helpful to diagnose a Sasang constitution. Methods: There were 331 patients(135 men and 196 women) who answered questionnaire and were diagnosed by the Sasang constitution specialist at constitutional clinic of Dongguk Bundang Oriental Hospital. Using the response of questionnaire and several statistical techniques, we tried to find the characteristics of questionnaire response among each constitution and consistency between questionnaire and clinical diagnosis. Results: As a result of the analysis of the consistency between clinical diagnosis and questionnaire, the consistency was low degree(kappa value = 0.320) and Taeumin and Soeumin had more consistency than Soyangin.

• 한국콘텐츠학회논문지
• /
• 제9권10호
• /
• pp.249-257
• /
• 2009

사상의학은 체질에 따라 치료하는 방법을 달리하므로, 체질진단의 객관화가 절실히 요구되고 있다. 본 연구는 맥파를 이용하여 사상체질을 객관적으로 진단함에 있어서, 정확도가 높으면서 실용적인 체질분류 방법을 탐색하는 것이 목적이다. 한방병원에 건강검진을 목적으로 내원한 2848명의 피험자를 대상으로 전문의가 진단한 체질, 체질량지수, 혈압, 맥파 자료를 입수하였다. 자료의 선별과정을 통하여 최종적으로 1635명의 자료를 분석에 사용하였다. 판별분석, 회귀분석, 의사결정나무, 신경망으로 체질을 예측하고 전문의가 진단한 결과와 비교하여 분류방법의 정확도를 비교하였다. 판별분석은 체질별로 공분산 행렬이 동일해야 한다는 가정을 만족시키기 어려웠으며, 체질량지수를 고려하지 않은 의사결정나무와 신경망 분석의 결과는 분석표본의 변동에 민감했다. 체질분류에 결정적인 영향을 미치는 변수인 체질량지수가 고려된 로지스틱 회귀분석 또는 의사결정나무 방법이 체질분류 방법으로 추천할 만하다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권14호
• /
• pp.5593-5596
• /
• 2014

Background: The objective of this study was to determine a diagnostic classification scheme using a decision tree based model. Materials and Methods: The study was conducted as a retrospective case-control study in Imam Khomeini hospital in Tehran during 2001 to 2009. Data, including demographic and clinical-pathological characteristics, were uniformly collected from 624 females, 312 of them were referred with positive diagnosis of breast cancer (cases) and 312 healthy women (controls). The decision tree was implemented to develop a diagnostic classification scheme using CART 6.0 Software. The AUC (area under curve), was measured as the overall performance of diagnostic classification of the decision tree. Results: Five variables as main risk factors of breast cancer and six subgroups as high risk were identified. The results indicated that increasing age, low age at menarche, single and divorced statues, irregular menarche pattern and family history of breast cancer are the important diagnostic factors in Iranian breast cancer patients. The sensitivity and specificity of the analysis were 66% and 86.9% respectively. The high AUC (0.82) also showed an excellent classification and diagnostic performance of the model. Conclusions: Decision tree based model appears to be suitable for identifying risk factors and high or low risk subgroups. It can also assists clinicians in making a decision, since it can identify underlying prognostic relationships and understanding the model is very explicit.

• 동의생리병리학회지
• /
• 제25권5호
• /
• pp.894-899
• /
• 2011

Traditional Korean Medicine (TKM) has been actively researched through various approaches, including computational methods. This paper aims at providing an overview of domestic studies using the computational techniques in TKM field. A literature search was conducted in Korean publications using OASIS system, and major studies of data mining in TKM were identified. A review was presented in six diagnosis fields, including sasang constitution diagnosis, eight constitution diagnosis, tongue diagnosis, pattern diagnosis for stroke, diagnosis based on ontology, diagnosis for cause of disease. They collect clinical data themselves for experiments and primarily applied a algorithm of decision tree, SVM, neural network, case-based reasoning, ontology reasoning, discriminant analysis. In the future, there needs to identify which algorithm is suitable to diagnosis or other fields of TKM.