• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.290-291
• /
• 2023

Outlier(이상치) 분석을 통한 등부표 선회안전반경 정보 제공에 관한 연구는 AIS 또는 RTU가 설치된 등부표에 대한 이탈 위험 인지, 항해안전 사고 예방 등 안전대책을 강화하기 위한 연구이다. 등부표는 조류, 바람 등 외력에 의해 이출거리가 발생하여 일정한 패턴으로 선회반경이 형성되나 외력으로 인하여 정상범위에서 벗어나 유실, 위치이동 등이 발생할 수 있고 이는 선박추돌 등 항해안전 사고로도 이어질 수 있다. 이러한 등부표 사고는 물적 피해비용과 이용자의 안전운항에 대한 심리적 부담감 또는 위험감수 등의 추가적인 행정소요 비용이 발생할 수 있다. Outlier(이상치)란 외력 등으로 인해 최대 이출거리 이내 정상범위에서 벗어나거나 존재할 수 없는 극단적인 위치 값으로써 21년도 등부표 위치 데이터를 일정 단위 방위별로 분석해 본 결과 Outlier(이상치)가 식별되었다. 따라서 등부표의 안전한 위치 상태를 시스템적으로 모니터링 하기 위해 Outlier(이상치) 분석을 통한 등부표 선회안전반경 정보 제공에 관한 연구를 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.370-372
• /
• 2023

신용카드 부정 사용은 고객 및 기업의 신용과 재산에 막대한 손실을 미치고 있다. 이에 따라 금융사들은 이상금융거래탐지시스템을 도입하였으나 이상 거래 발생 여부를 지속적으로 모니터링하고 있기 때문에 시스템 유지에 많은 비용이 따른다. 따라서 본 논문에서는 컴퓨팅 리소스를 절약함과 동시에 성능 개선 효과를 보인 신용카드 이상 거래 탐지 알고리즘을 제안한다. CTGAN 을 활용하여 정상 거래와 이상 거래의 비율을 일부 완화하였고 XAI 기법인 SHAP 를 활용하여 유의미한 속성값을 선택하였다. 이것을 기반으로 LSTM Autoencoder를 사용하여 이상데이터를 탐지하였다. 그 결과 전통적인 비지도 학습 기법에 비해 제안 알고리즘이 우수한 성능을 보였음을 확인하였다.

• Clinical and Experimental Pediatrics
• /
• v.48 no.4
• /
• pp.416-424
• /
• 2005

Purpose : To find the risk factors associated with coronory artery lesions, non-responsiveness to intravenous immunoglobulin(IVIG) treatment, and recurrences in Kawasaki disease patients. Methods : We retrospectively analyzed 1,000 Kawasaki disease patients who were admitted to Yonsei University Medical Center from September 1990 to December 2003. We compared between responder and non-responder groups to IVIG treatment as well as between relapsed and non-relapsed groups, and as to the relapsed group, we also compared variables between patients in their first and second attack states. Finally, factors associated with longer-fever duration from disease onset were evaluated. Results : Longer fever durations before and after IVIG treatment, male sex, lower Hgb and Hct level, higher WBC count and segmented WBC proportion, and higher CRP and Harada's score were related with coronary artery lesions. Non-responsiveness was related to higher WBC count, segmented WBC proportion, CRP, SGPT, Harada's score, and pyuria. Moderate-to-severe coronary artery dilatations and recurrences were more commonly seen among the non-responder group. No significant predictive factors for recurrence were found. In the relapsed group, lower WBC count, CRP, and shorter fever duration from disease onset were observed in their second attack state. Fever duration from disease onset showed positive correlation with WBC count, CRP, and Harada's score and negative correlation with Hgb levels. Conclusion : Higher WBC count, CRP, and higher Harada's score were related to both higher incidences of coronary artery lesions and non-responsiveness to IVIG treatment, and these factors were also related with longer fever duration. Non-responders to IVIG treatment showed higher recurrence rate and more moderate-to-severe coronary artery dilatations than responders.

• The Monthly Diabetes
• /
• s.205
• /
• pp.17-22
• /
• 2006

20세 이상의 성인은 매5년마다 적어도 1회 이상 혈장 총콜레스테롤 농도측정이 필요하다. 또한 각종 검진 또는 진찰을 위해 의료기관을 처음 방문하는 모든환자에 대해서 총 코레스테롤 측정은 필수적이다.

• Journal of KIISE:Information Networking
• /
• v.33 no.3
• /
• pp.201-217
• /
• 2006

In this paper, we collected the physical traces from high speed Internet backbone traffic and analyze the various characteristics of the underlying packet traces. Particularly, our work is focused on analyzing the characteristics of an anomalous traffic. It is found that in our data, the anomalous traffic is caused by UDP session traffic and we determined that it was one of the Denial of Service attacks. In this work, we adopted the unsupervised machine learning algorithm to classify the network flows. We apply the k-means clustering algorithm to train the learner. Via the Cramer-Yon-Misses test, we confirmed that the proposed classification method which is able to detect anomalous traffic within 1 second can accurately predict the class of a flow and can be effectively used in determining the anomalous flows.

• Journal of Convergence for Information Technology
• /
• v.10 no.9
• /
• pp.15-21
• /
• 2020

This paper presents the outlier detection algorithm in the estimation method of a source location and velocity based on two-step weighted least-squares method using time difference of arrival(TDOA) and frequency difference of arrival(FDOA) data. Since the accuracy of the estimated location and velocity of a moving source can be reduced by the outliers of TDOA and FDOA data, it is important to detect and remove the outliers. In this paper, the method to find the minimum inlier data and the method to determine whether TDOA and FDOA data are included in inliers or outliers are presented. The results of numerical simulations show that the accuracy of the estimated location and velocity is improved by removing the outliers of TDOA and FDOA data.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.19 no.2
• /
• pp.92-98
• /
• 2015

Recently, buildings tend to be large size, complex shape and functional. As the size of buildings is becoming massive, the need for structural health monitoring (SHM) technique is increasing. Various SHM techniques have been studied for buildings which have different dynamic characteristics and influenced by various external loads. "Abnormal behavior point" is a moment when the structure starts vibrating abnormally and this can be detected by comparing between before and after abnormal behavior point. In other words, anomalous behavior is a sign of damage on structures and estimating the abnormal behavior point can be directly related to the safety of structure. Abnormal behavior causes damage on structures and this leads to enormous economic damage as well as damage for humans. This study proposes an estimating technique to find abnormal behavior point using Hilber-Huang Transform which is a time-frequency signal analysis technique and the proposed algorithm has been examined through laboratory tests with a bridge model using a shaking table.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.841-852
• /
• 2010

An integrated process control (IPC) procedure is a scheme which simultaneously applies the engineering control procedure (EPC) and statistical control procedure (SPC) techniques to reduce the variation of a process. In the IPC procedure, the observed deviations are monitored during the process where adjustments are repeatedly done by its controller. Because the effects of the noise, the special cause, and the adjustment are mixed, the use and properties of the SPC procedure for the out-of-control process are complicated. This paper considers efficiency of EWMA charts for detecting special causes in an ARMA(1,1) noise model with a minimum mean squared error adjustment policy. And we propose the readjustment procedure after having a true signal. This procedure can be considered when the elimination of the special cause is not practically possible.

• Environmental Analysis Health and Toxicology
• /
• v.24 no.1
• /
• pp.43-52
• /
• 2009

Fullerene의 유전독성을 평가하기 위하여 Chinese hamster유래의 난소유아세포(CHO-K1 cell)를 이용하여 직접법(-S9)과 대사활성화법(+S9 mix)의 염색체이상시험을 실시하였다. 시험물질은 1% CMC 나트륨염의 현탁액(1% CMC 용액)에 희석하여 조제하였다. 대사활성화를 시키지 않은 직접법의 염색체이상시험에서 24시간 투여군은 8단계의 농도(0.078, 0.156, 0.313, 0.625, 1.25, 2.5, 5, 10 mM)로 투여하여 실시하였다. 투여 농도 증가에 따른 염색체이상의 빈도가 증가하는 양상이 나타나지 않았다. 48시간의 투여군에서는 8단계의 농도(0.078, 0.156, 0.313, 0.625, 1.25, 2.5, 5, 10 mM)로 투여하여 실시하였는데 투여 농도 증가에 따른 염색체이상의 빈도가 증가하는 양상이 나타나지 않았다. 배수체의 염색체이상은 직접법에서 관찰되지 않았다. 대사활성화법을 이용하여 6시간 시험물질을 투여한 시험에 있어서는 8단계의 용량단계(0.078, 0.156, 0.313, 0.625, 1.25, 2.5, 5, 10mM)를 설정하였는데 투여 농도가 증가함에 따른 염색체이상빈도의 증가양상이 관찰되지 않았다. 이상의 결과를 종합할 때 본 시험물질은 본 시험 조건하에서 CHO-K1세포에서 대사활성화를 시켰을 때 염색체이상을 유발하지 않는 것으로 판단된다.

• Journal of the Korean GEO-environmental Society
• /
• v.16 no.5
• /
• pp.43-53
• /
• 2015

In this study, detection methods of outlier in various monitoring data that fit into big data category were developed and outlier detections were conducted for both artificial data and real field monitoring data. Rule-based methods applied rate of change and probability of error for monitoring data are effective to detect a large-scale short faults and constant faults having no change within a certain period. There are however, problems with misjudgement that consider the normal data with a large scale variation as outlier caused by using independent single dataset. Rule-based methods for noise faults detection have a limit to application of real monitoring data due to the problem with a choice of proper window size of data and finding of threshold for outlier judgment. A correlation analysis among different two datasets were very effective to detect localized outlier and abnormal variation for short and long-term monitoring dataset if reasonable range of training data could be selected.