• 대한정형외과 초음파학회지
• /
• 제4권1호
• /
• pp.1-6
• /
• 2011

목적: 자기 공명 영상 시행 전에 내측 반월상 연골의 파열 진단에서의 초음파 검사의 유용성을 알아보고자 하였다. 대상 및 방법: 2009년 4월부터 2010년 9월까지 본원 정형외과 외래를 방문하여 내측 반월상 연골 파열 의심 하에 초음파 검사를 시행한 341예 중 자기 공명 영상 검사를 시행한 147예를 대상으로 하였다. 초음파 검사상 이상 소견을 보이지 않는 16예, 비균질성(inhomogeneity)만을 보인 12예, 무리(cluster)를 보인 4예, 실질 내에 틈(cleavage)을 보인 60예, 5 mm 이상의 내측 탈출(extrusion)을 보인 55예를 자기 공명 영상 검사 결과와 비교 하였다. 통계학적으로 민감도와 특이도, 양성 예측률과 음성 예측률을 구하였다. 결과: 자기 공명 영상에서 파열을 보인 경우는 104예였다. 초음파 검사는 자기 공명 영상에 대하여 민감도가 94.2%, 특이도는 23.3%로 측정 되었다. 양성 예측률은 74.8%, 음성 예측률은 62.5%로 측정되었다. 초음파 영상에 따른 양성 예측률은 비균질성이 보이는 경우 58.3%, 무리를 보이는 경우에는 100%, 실질 내에 틈을 보이는 경우 75%, 내측 탈출을 보이는 경우 80%로 나타났다. 결론: 내측 반월상 연골 파열의 진단에 있어 고가의 자기 공명 영상을 시행하기 전 초음파 검사는 파열 가능성 여부를 사전에 아는데 유용하였다.

• International Journal of Safety
• /
• 제11권2호
• /
• pp.22-25
• /
• 2012

This paper deals with the problem of fault diagnosis for identifying a single fault when the number of assumed faults is larger than that of predictive variables. Principal component analysis (PCA) is employed to isolate and identify a single fault. PCA is a method to extract important information as reducing the number of large dimension in a process. The patterns of all assumed faults can be recognized by PCA and these can be employed whether a new fault is one of predefined faults or not. Through PCA, empirical models for analyzing patterns can be trained. When a single fault occurs, the pattern generated by PCA can be obtained and this is used to identify a fault. The performance of the proposed approach is illustrated in the actuator benchmark problem.

• 조명전기설비학회논문지
• /
• 제12권4호
• /
• pp.47-54
• /
• 1998

발전설비에 있어 고신뢰성이 요구됨에 따라 진행되는 고장을 조기에 발견하는 예방 보전적 진단 시스템이 요구되고 있다. 본 논문에서는 발전설비 중에서 회전체의 절연진단과 진동진단에 대한 지식을 지식 베이스로 구성하고 이것을 다표정 언어를 이용하여 전문가 시스템을 구성하였다. 이 전문가 시스템은 진단 룰의 수정과 추가가 용이하며, 사용자와의 인터페이스도 양호한 구조를 취하고 있다.

• 한국산학기술학회논문지
• /
• 제10권11호
• /
• pp.3465-3472
• /
• 2009

본 병원에 축적된 의무기록과 데이터베이스에 있는 퇴원 환자 정보를 이용하여 이탈에 영향을 미치는 특성을 파악하여 활용 가능한 예측모형을 제시하고자 한다. 외래진료 방문환자 3,503명 중 충성고객 2,118명 60.5%, 이탈 고객 1,385명 39.5%을 추출하여 분석에 사용하였다. 생존한 변수는 성별, 연령(연령대), 지역, 보험구분, 입원경로, 진료과, 퇴원과, 퇴원형태, 협진여부, 수술여부, 진료예약여부, 환자구분을 기반으로 예측모형을 만들었다. 로지스틱 회귀분석을 실시한 결과 66.0%의 정확도를 나타냈고, 신경망을 통하여 예측한 결과 분석용 결과는 정분율은 69.79%이고, 검정용 결과 정분율은 63.64%였다. CHAID를 통하여 예측한 결과 분석용 결과 정분율을 83.75% 이고, 검정용 결과 정분율은 42.74%였다. 예측 모형을 활용한 이탈고객을 위한 관리와 병원의 신뢰를 높여야 할 것이다.

• 한국콘텐츠학회논문지
• /
• 제19권1호
• /
• pp.634-647
• /
• 2019

본 연구는 12차년도(2017년) 한국복지패널에 참여한 11,755명을 대상으로 자살충동에 관련된 예측변인들의 영향력을 분석한 선행연구와는 달리 자살충동에 관련된 예측변인들의 구성요인의 영향력을 통합적인 연구틀에서 살펴보고자 수행되었다. 연구방법은 SPSS 23.0 버전을 적용하여 자살충동에 영향을 미치는 예측 변인들의 구성요인 간 다중공선성 진단 후, 자살충동에 영향을 미치는 예측변인들의 구성요인의 상대적 영향력을 로지스틱 회귀 분석하였다. 연구 결과, 가부장적인 역할이 증가할수록, 언어폭력이 증가할수록, 외로움을 더 느낄수록, 사람들이 자신을 차갑게 대할수록. 음주 후 블랙아웃(black-out)이 증가할수록 자살충동의 승산비가 증가하는 반면, 삶의 사다리 점수가 증가할수록 자살충동의 승산비가 감소하였다. 이를 근거로 자살충동을 축소 예방하기 위한 사회복지적 함의를 제시하고, 이 연구의 제한점, 그리고 추후 연구에서 고려할 점을 논의하였다.

• Clinical and Experimental Pediatrics
• /
• 제64권4호
• /
• pp.180-187
• /
• 2021

Background: Severe perinatal asphyxia results in multiple organ involvement, neonate hospitalization, and eventual death. Purpose: This study aimed to investigate the predictive factors of death in newborns with hypoxic-ischemic encephalopathy (HIE) receiving selective head cooling. Methods: This cross-sectional descriptive-retrospective study was conducted from 2013 to 2018 in Fatemieh Hospital of Hamadan and included 51 newborns who were admitted to the neonatal intensive care unit with a diagnosis of HIE. Selective head cooling for patients with moderate to severe HIE began within 6 hours of birth and continued for 72 hours. The required data for the predictive factors of death were extracted from the patients' medical files, recorded on a premade form, and analyzed using SPSS ver. 16. Results: Of the 51 neonates with moderate to severe HIE who were treated with selective head cooling, 16 (31%) died. There were significant relationships between death and the need for advanced neonatal resuscitation (P=0.002), need for mechanical ventilation (P=0.016), 1-minute Apgar score (P=0.040), and severely abnormal amplitude-integrated electroencephalography (a-EEG) (P=0.047). Multiple regression of variables or data showed that the need for advanced neonatal resuscitation was an independent predictive factor of death (P=0.0075) and severely abnormal a-EEG was an independent predictive factor of asphyxia severity (P=0.0001). Conclusion: All cases of neonatal death in our study were severe HIE (stage 3). Advanced neonatal resuscitation was an independent predictor of death, while a severely abnormal a-EEG was an independent predictor of asphyxia severity in infants with HIE.

• 한국소음진동공학회논문집
• /
• 제21권11호
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• 한국안전학회지
• /
• 제34권4호
• /
• pp.59-67
• /
• 2019

Since it is really hard to construct process models based on prior process knowledges, various statistical approaches have been employed to build fault diagnosis models. However, the crucial drawback of these approaches is that the solutions may vary according to the fault magnitude, even if the same fault occurs. In this study, the parameter monitoring approach is suggested. When a fault occurs in a chemical process, this leads to trigger the change of a process model and the monitoring parameters of process models is able to provide the efficient fault diagnosis model. A few important variables are selected and their predictive models are constructed by partial least square (PLS) method. The Euclidean norms of parameters of PLS models are estimated and a fault diagnosis can be performed as comparing with parameters of PLS models based on normal operational conditions. To improve the monitoring performance, cumulative summation (CUSUM) control chart is employed and the changes of model parameters are recorded to identify the type of an unknown fault. To verify the efficacy of the proposed model, Tennessee Eastman (TE) process is tested and this model can be easily applied to other complex processes.

• Radiation Oncology Journal
• /
• 제32권3호
• /
• pp.116-124
• /
• 2014

Purpose: To investigate the frequency and clinical significance of detected incidental lung nodules found on computed tomography (CT) simulation images for hepatocellular carcinoma (HCC) using computer-aided diagnosis (CAD) and a physician review. Materials and Methods: Sixty-seven treatment-$na{\ddot{i}}ve$ HCC patients treated with transcatheter arterial chemoembolization and radiotherapy (RT) were included for the study. Portal phase of simulation CT images was used for CAD analysis and a physician review for lung nodule detection. For automated nodule detection, a commercially available CAD system was used. To assess the performance of lung nodule detection for lung metastasis, the sensitivity, negative predictive value (NPV), and positive predictive value (PPV) were calculated. Results: Forty-six patients had incidental nodules detected by CAD with a total of 109 nodules. Only 20 (18.3%) nodules were considered to be significant nodules by a physician review. The number of significant nodules detected by both of CAD or a physician review was 24 in 9 patients. Lung metastases developed in 11 of 46 patients who had any type of nodule. The sensitivities were 58.3% and 100% based on patient number and on the number of nodules, respectively. The NPVs were 91.4% and 100%, respectively. And the PPVs were 77.8% and 91.7%, respectively. Conclusion: Incidental detection of metastatic nodules was not an uncommon event. From our study, CAD could be applied to CT simulation images allowing for an increase in detection of metastatic nodules.

• Advances in pediatric surgery
• /
• 제10권2호
• /
• pp.117-122
• /
• 2004

Diagnosis of acute appendicitis in children is sometimes difficult. The aim of this study is to validate a clinical scoring system and ultrasonography for the early diagnosis and treatment of appendicitis in childhood. This is a prospective study on 59 children admitted with abdominal pain at St. Mary's Hospital, the Catholic University of Korea from July 2002 to August 2003. We applied Madan Samuel's Pediatric Appendicitis Score (PAS) based on preoperative history, physical examination, laboratory finding and ultrasonography. This study was designed as follows: patients with score 5 or less were observed regardless of the positive ultrasonographic finding, patients with score 6 and 7 were decided according to the ultrasonogram and patients above score 8 were operated in spite of negative ultrasonographic finding. The patients were divided into two groups, appendicitis (group A) and non-appendicitis groups (group B). Group A consisted of 36 cases and Group B, 23 cases. Mean score of group A was 8.75 and group B was 6.13 (p<0.001). Comparing the diagnostic methods in acute appendicitis by surveying sensitivity, specificity, positive predictive value, negative predictive value, and accuracy, PAS gave 1.0000, 0.3043, 0.6923, 1.0000, and 0.7288, and ultrasonography gave 0.7778, 0.9130, 0.9333, 0.7241, and 0.8300 while the combined test gave 1.0000, 0.8696, 0.9231, 1.0000, and 0.9490, respectively. Negative laparotomy rate was 3 %. In conclusion, the combination of PAS and ultrasonography is a more accurate diagnostic tool than either PAS or ultrasonography.