• 대한한의학회지
• /
• 제38권3호
• /
• pp.185-196
• /
• 2017

Backgrounds: Inpatient Classification System for Korean Medicine (KDRG-KM) was developed and has been applied for monitoring the costs of KM hospitals. Yet severity of patients' condition is not applied in the KDRG-KM. Objectives: This study aimed to develop the severity classification methods for KDRG-KM and assessed the explanation powers of severity adjusted KDRG-KM. Methods: Clinical experts panel was organized based on the recommendations from 12 clinical societies of Korean Medicine. Two expert panel workshops were held to develop the severity classification options, and the Delphi survey was performed to measure CCL(Complexity and Comorbidity Level) scores. Explanation powers were calculated using the inpatient EDI claim data issued by hospitals and clinics in 2012. Results: Two options for severity classification were deduced based on the severity classification principle in the domestic and foreign DRG systems. The option one is to classify severity groups using CCL and PCCL(Patient Clinical Complexity Level) scores, and the option two is to form a severity group with patients who belonged principal diagnosis-secondary diagnosis combinations which prolonged length of stay. All two options enhanced explanation powers less than 1%. For third option, patients who received certain treatments for severe conditions were grouped into severity group. The treatment expense of the severity group was significantly higher than that of other patients groups. Conclusions: Applying the severity classifications using principal diagnosis and secondary diagnoses can advance the KDRG-KM for genuine KM hospitalization. More practically, including patients with procedures for severe conditions in a severity group needs to be considered.

• 한국산업정보학회논문지
• /
• 제27권6호
• /
• pp.95-103
• /
• 2022

원자력발전소의 중대사고 발생 시 신속하고 정확하게 사고 상황을 파악해야 하며, 이러한 사고진단 정보를 획득했을 때 적절한 사고관리 및 대응을 수행할 수 있다. 본 연구에서는 국가원자력 재난관리 시스템인 AtomCARE (Computerized technical Advisory system for a Radiological Emergency)로 전송되는 주요 발전소 정보로부터 중대사고 상황을 진단하는데 있어 딥러닝 기술의 접목을 고려하였다. 이를 위하여 주요 시나리오를 선정하고 사고 진행에 따른 상세 시나리오에 대하여 중대사고 해석 코드인 MAAP5 다량 계산을 통한 학습 DB를 구축하였다. 그리고 이 DB의 학습을 통하여 주요 발전소 정보로부터 중대사고 상세 시나리오를 분류할 수 있는, 즉 중대사고 상황을 진단할 수 있는 기술을 개발하였다. 또한 블라인드 테스트와 주성분분석을 통한 검증을 수행하였다. 본 연구에서 개발한 기술은 향후 전체 중대사고 시나리오로 확장 및 적용 가능할 것으로 판단되며 신속하고 정확한 사고진단의 기반기술로 활용 가치가 높을 것으로 기대된다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.430-433
• /
• 2003

Air-operated valve is one of principal valves that are using to control fluid flow. A period diagnosis for safety of power plants is necessary. But there are many difficulties such as economic loss caused by intone of high cost devices and a matter hard to deal with users. In this study we developed the diagnosis system that usersofpower plants are easy to handle. The diagnosis system is composed of database module, reliability analysis module, design safety nodule and diagnosis test and evaluation module.

• 동의생리병리학회지
• /
• 제19권6호
• /
• pp.1483-1490
• /
• 2005

This study was written in order to help understanding of visible diagnosis of appearance(形). Visible diagnosis of appearance(形) is a very important factor of diagnosis and a first step of visible diagnosis. appearance(形) is closely connection with spirit(神), so is house of spirit(神). If we make a visible diagnosis of appearance(形), we know the prosperousness of energy and the relative seriousness of an illness. Spirit(神) is understood by appearances and movements of patient, and influenced by seasons, lands, human's relationship and the grade of age. By visible diagnosis of appearance(形), we can conclude existence or nonexistence of spirit(神), As comparing spirit(神) with appearance(形), we can decide good or bad prognoses. One man's own appearance(形) is determined by the five human type(五形人). There are very various points of changing form. As divided into principal groups, there are three main groups, that is, sky(天), earth(地) and man(人). The age and sex belong 治 the factor of sky(天), a direction and configuration of the ground(地形) belong to the factor of earth(地), the five human type(五形人) and white fatness(肥白) and black emaciation(黑瘦) belong to the factor of man(人).

• 대한기계학회논문집A
• /
• 제31권9호
• /
• pp.975-980
• /
• 2007

Air-operated valve is one of principal valves that are used to control fluid flow in nuclear power plants. A periodic diagnosis for the safety of power plants is necessary. But there are many difficulties such as economic loss caused by income of high cost devices and a matter hard to deal with users. In this study, we developed the diagnostic system that users of power plants are easy to handle. The diagnostic system is composed of database module, diagnosis test module and analysis module.

• 센서학회지
• /
• 제22권4호
• /
• pp.276-280
• /
• 2013

The purpose of this paper is to diagnose osmidrosis visually and quantify the extent of osmidrosis. To achieve this, we designed the diagnosis method of osmidrosis using electronic nose system. The developed electronic nose system use principal component analysis for visualization of osmidrosis and fuzzy c-means algorithm for quantification. To confirm the efficiency of electronic nose system for osmidrosis diagnosis, we obtained samples from 34 volunteers and compared our experiment results with the doctor's diagnosis, and we met with successful results.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1063-1064
• /
• 2007

본 연구는 유도전동기 진단시스템을 개발하기 위하여 테스트 전동기 내부에 취부된 자속센서 신호를 사용한 알고리즘 적용 결과를 논한 것으로서 분류기별 고장 판별 정확도에 대하여 서술하였다. 특징추출은 Kernel Principal Component Analysis (KPCA) 방법을 이용 하였으며, 테스트 샘플들에 대해서는 LDA(Linear Discriminant Analysis)와 k-NN(k-Nearest neighbors) 분류기법을 이용하여 판별하였다. 회전자 바 손상이나 편심(동적/정적)인 경우는 두 가지 분류기 모두 95[%]이상의 높은 분류 정확도를 보였지만, LDA인 경우 정상상태를 비롯한 베이링 불량이나, 샤프트 변형인 경우는 낮은 분류율을 보였다.

• 한국가스학회:학술대회논문집
• /
• 한국가스학회 1997년도 추계학술발표회 논문집
• /
• pp.148-153
• /
• 1997

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.289-299
• /
• 2000

This study provides an application of datamining approach to CQI(Continuous Quality Improvement) using the discharge summary. First, we found a process variation in hospital infection rate by SPC (Statistical Process Control) technique. Second, importance of factors influencing hospital infection was inferred through the decision tree analysis which is a classification method in data-mining approach. The most important factor was surgery followed by comorbidity and length of operation. Comorbidity was further divided into age and principal diagnosis and the length of operation was further divided into age and chief complaint. 24 rules of hospital infection were generated by the decision tree analysis. Of these, 9 rules with predictive prover greater than 50% were suggested as guidelines for hospital infection control. The optimum range of target group in hospital infection control were Identified through the information gain summary. Association rule, which is another kind of datamining method, was performed to analyze the relationship between principal diagnosis and comorbidity. The confidence score, which measures the decree of association, between urinary tract infection and causal bacillus was the highest, followed by the score between postoperative wound disruption find postoperative wound infection. This study demonstrated how datamining approach could be used to provide information to support prospective surveillance of hospital infection. The datamining technique can also be applied to various areas fur CQI using other hospital databases.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제14권2호
• /
• pp.252-261
• /
• 2014

A Bayesian network (BN) based fault diagnosis framework for semiconductor etching equipment is presented. Suggested framework contains data preprocessing, data synchronization, time series modeling, and BN inference, and the established BNs show the cause and effect relationship in the equipment module level. Statistically significant state variable identification (SVID) data of etch equipment are preselected using principal component analysis (PCA) and derivative dynamic time warping (DDTW) is employed for data synchronization. Elman's recurrent neural networks (ERNNs) for individual SVID parameters are constructed, and the predicted errors of ERNNs are then used for assigning prior conditional probability in BN inference of the fault diagnosis. For the demonstration of the proposed methodology, 300 mm etch equipment model is reconstructed in subsystem levels, and several fault diagnosis scenarios are considered. BNs for the equipment fault diagnosis consists of three layers of nodes, such as root cause (RC), module (M), and data parameter (DP), and the constructed BN illustrates how the observed fault is related with possible root causes. Four out of five different types of fault scenarios are successfully diagnosed with the proposed inference methodology.