• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.19-21
• /
• 2022

자기 지도 학습을 이용한 이상 탐지는 일반적으로 합성 데이터를 생성해 정상과 이상을 학습하고, 실제 이상 데이터를 테스트 데이터로 사용하여 이상 탐지 성능을 측정한다. 정상 데이터와 유사한 합성 데이터를 생성하기 위해 기존 연구에서는 원본 이미지에서 특정 패치를 자르고 붙이는 식으로 합성 데이터를 생성한다. 이런 방식에서 정상 데이터와 유사한 정도는 패치 개수와 크기에 따라 달라지므로 이상 탐지 성능에 영향을 미칠 수 있다. 본 연구에서는 패치 크기 및 개수를 다르게 하여 합성 데이터를 생성한 뒤 사전 학습된 모델을 사용하여 정상 데이터와의 유사성 측정 및 분석을 진행하였고 모델을 학습시켜 이상 탐지 성능을 측정하여 보았다.

• Journal of Chest Surgery
• /
• 제25권8호
• /
• pp.826-831
• /
• 1992

Ebstein`s anomaly is characterized by a downward displacement of a malformed tricuspid valve, The ideal surgical management of Ebstein`s anomaly is not yet established. Recently we experience one case of Ebstein`s anomaly, which was treated sussessfully by partial artificial annulus formation, and tricuspid valve replacement with St. Jude Medical valve. We have achieved excellent results with mechanical valve replacement and partial artificial annulus formation using wessex pericardial patch. On follow up for 4 years, the patient is well and in functional class I.

• 천문학회지
• /
• 제46권2호
• /
• pp.75-91
• /
• 2013

We estimate the power spectra of the cosmic microwave background radiation (CMB) temperature anisotropy in localized regions of the sky using the Wilkinson Microwave Anisotropy Probe (WMAP) 7-year data. We find that the north and south hat regions at high Galactic latitude ($|b|{\geq}30^{\circ}C$) show an anomaly in the power spectrum amplitude around the third peak, which is statistically significant up to 3. We try to explain the cause of the observed anomaly by analyzing the low Galactic latitude ($|b|$ < $30^{\circ}C$) regions where the galaxy contamination is expected to be stronger, and the regions weakly or strongly dominated byWMAP instrument noise. We also consider the possible effect of unresolved radio point sources. We find another but less statistically significant anomaly in the low Galactic latitude north and south regions whose behavior is opposite to the one at high latitude. Our analysis shows that the observed north-south anomaly at high latitude becomes weaker on regions with high number of observations (weak instrument noise), suggesting that the anomaly is significant at sky regions that are dominated by the WMAP instrument noise. We have checked that the observed north-south anomaly has weak dependences on the bin-width used in the power spectrum estimation, and on the Galactic latitude cut. We also discuss the possibility that the detected anomaly may hinge on the particular choice of the multipole bin around the third peak. We anticipate that the issue of whether or not the anomaly is intrinsic one or due to WMAP instrument noise will be resolved by the forthcoming Planck data.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 춘계종합학술대회
• /
• pp.391-394
• /
• 2004

인터넷의 급속한 확장으로 인해 네트워크 공격기법의 패러다임의 변화가 시작되었으며 새로울 공격 형태가 나타나고 있으나 대부분의 침입 탐지 기술은 오용 탐지 기술을 기반으로 하는 시스템이주를 이루고 있어 알려진 공격 유형만을 탐지하고, 새로운 공격에 능동적인 대응이 어려운 실정이다. 이에 새로운 공격 유형에 대한 탐지력을 높이기 위해 인체 면역 메커니즘을 적용하려는 시도들이 나타나고 있다. 본 논문에서는 데이터 마이닝 기법을 이용하여 네트워크 패킷에 대한 정상 행위 프로파일을 생성하고 생성된 프로파일을 자기공간화 하여 인체면역계의 자기, 비자기 구분기능을 이용해 자기 인식 알고리즘을 구현하여 이상행위를 탐지하고자 한다. 자기인식 알고리즘의 하나인 Negative Selection Algorithm을 기반으로 anomaly detector를 생성하여 자기공간을 모니터하여 변화를 감지하고 이상행위를 검출한다. DARPA Network Dataset을 이용하여 시뮬레이션을 수행하여 침입 탐지율을 통해 알고리즘의 유효성을 검증한다.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1181-1190
• /
• 2020

Detection of an anomaly pattern deviating normal data distribution in streaming data is an important technique in many application areas. In this paper, a method for detection of an newly emerging pattern in text streaming data which is an ordered sequence of texts is proposed based on text embedding and anomaly pattern detection. Using text embedding methods such as BOW(Bag Of Words), Word2Vec, and BERT, the detection performance of the proposed method is compared. Experimental results show that anomaly pattern detection using BERT embedding gave an average F1 value of 0.85 and the F1 value of 1 in three cases among five test cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.1173-1192
• /
• 2015

The Support Vector Data Description (SVDD) has achieved great success in anomaly detection, directly finding the optimal ball with a minimal radius and center, which contains most of the target data. The SVDD has some limited classification capability, because the hyper-sphere, even in feature space, can express only a limited region of the target class. This paper presents an anomaly detection algorithm for mitigating the limitations of the conventional SVDD by finding the minimum volume enclosing ellipsoid in the feature space. To evaluate the performance of the proposed approach, we tested it with intrusion detection applications. Experimental results show the prominence of the proposed approach for anomaly detection compared with the standard SVDD.

• Journal of Chest Surgery
• /
• 제17권3호
• /
• pp.331-338
• /
• 1984

From 1959 to Jun. 30 84, 1144 cases of various cardiovascular diseases were operated consisting of 421 open heart surgery under extra-corporeal circulation or hypothermia and 723 conventional surgery at department of Thoracic and Cardiovascular Surgery in National Medical Center. There were 470 congenital anomaly and 674 acquired lesions. Out of 470 congenital anomaly, acyanotic anomaly was 289 and cyanotic anomaly was 181. Among 647 acquired lesions, 473 was cardiac lesion, 87 was pericardial lesion and 105 was vascular diseases. Over all operative mortality was 9.0%, consisting of 7.6% for acyanotic, 19.3% for cyanotic anomaly and 6.8% for acquired lesion. Mortality for 723 conventional surgery was 6.2%, and 421 open heart surgery was 13.8%.

• ETRI Journal
• /
• 제34권2호
• /
• pp.288-291
• /
• 2012

In this letter, a new online anomaly detection approach for software systems is proposed. The novelty of the proposed approach is to apply a new semantic kernel function for a support vector machine (SVM) classifier to detect fault-suspicious execution paths at runtime in a reasonable amount of time. The kernel uses a new sequence matching algorithm to measure similarities among program execution paths in a customized feature space whose dimensions represent the largest common subpaths among the execution paths. To increase the precision of the SVM classifier, each common subpath is given weights according to its ability to discern executions as correct or anomalous. Experiment results show that compared with the known kernels, the proposed SVM kernel will improve the time overhead of online anomaly detection by up to 170%, while improving the precision of anomaly alerts by up to 140%.

• Korean Journal of Radiology
• /
• 제22권9호
• /
• pp.1441-1450
• /
• 2021

Anomalous origin of the coronary artery from the pulmonary artery is a rare and potentially fatal congenital heart defect. Up to 90% of infants with an anomaly involving the left coronary artery die within the first year of life if left untreated. Patients who survive beyond infancy are at risk of sudden cardiac death. Cardiac CT and MRI are increasingly being used for the accurate diagnosis of this anomaly for prompt surgical restoration of the dual coronary artery system. Moreover, life-long imaging surveillance after surgery is necessary for these patients. In this pictorial review, multimodal cardiac imaging findings of this rare and potentially fatal coronary artery anomaly are comprehensively discussed, and representative images are provided to facilitate the understanding of this anomaly.