• 한국컴퓨터정보학회논문지
• /
• 제17권5호
• /
• pp.21-28
• /
• 2012

최근 들어, 네트워크 트래픽 공격에 대한 탐지 기술의 필요성이 꾸준히 증가되고 있는 실정이다. 본 논문에서는 네트워크 트래픽 데이터의 헤더파일에서 송신자의 IP와 포트, 그리고 수신자의 IP와 포트 정보를 2차원의 영상으로 시각화하고 분석하여 이상패턴을 효과적으로 분석하는 새로운 방법을 제안한다. 제안된 방법에서는 먼저 송신자와 수신자의 IP 정보를 받아들여 4개의 2차원 영상을 생성하고, 포트 정보를 받아들여 1개의 2차원 영상을 생성한다. 그런 다음, 각 영상 내의 트래픽 데이터를 분석하여 패턴의 주요 특징을 추출하는데, 트래픽의 공격을 나타내는 선형 패턴과 높은 명암값을 가지는 패턴을 추출하여 트래픽의 유형이 정상 트래픽, DDoS, 그리고 DoS인지를 자동으로 검출한다. 성능을 비교 분석하기 위한 실험에서는 제안된 네트워크 트래픽의 이상현상 검출 방법이 기존의 방법에 비해서 보다 우수하다는 것을 보여준다.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.67-73
• /
• 2021

본 논문에서는 드론의 추락을 예방하기 위해 드론의 프로펠러와 연결된 모터로부터 진동 데이터를 수집하고 순환 신경망(recurrent neural network, RNN)과 long short term memory (LSTM)을 사용하여 드론의 비정상 진동을 예측하는 연구를 진행하였다. 드론의 비정상 진동 데이터를 수집하기 위해 드론의 프로펠러와 연결된 모터에 진동 센서를 부착하여 정상, 바(bar) 손상, 로터(rotor) 손상, 축 휨에 대한 진동 데이터를 수집하고 LSTM과 RNN을 통해 비정상 진동을 예측한 결과의 평균 제곱근 오차 (root mean square error, RMSE) 값을 비교분석 하였다. 시뮬레이션 비교 결과, RNN과 LSTM을 통해 예측한 결과 모두 비정상 진동 패턴을 매우 정확하게 예측하는 것을 확인하였으며 LSTM을 통해 예측한 진동이 RNN을 통해 예측한 진동보다 RMSE값이 평균 15.4% 낮은 것을 확인하였다.

• 한국해안·해양공학회논문집
• /
• 제26권5호
• /
• pp.314-326
• /
• 2014

2007년 3월 31일 서해안에서 발생했던 이상파랑의 발생원인 및 증폭과정을 이해하기 위해 관측자료 분석과 선형 천수방정식 및 선형 Boussinesq 모형을 이용한 1차원 수치모형 실험을 수행하였다. 기존의 연구에서 제안된 여러 형태의 압력점프에 대해 검토한 결과 기존의 압력점프는 관측된 이상파랑의 특성을 제대로 재현할 수 없었다. 본 연구에서는 새로운 형태의 압력점프를 제안하였다. 본 연구에서 제안한 압력점프의 타당성을 검토하기 위한 수치모의를 수행한 결과, 계산된 이상파랑의 주기와 최대 수면고가 관측치와 상당히 일치함을 보여주었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• 한국IT서비스학회지
• /
• 제9권1호
• /
• pp.113-125
• /
• 2010

Recently, a smart space with Ubiquitous Environment is expanding rapidly due to the development of Ubiquitous Sensor Network. Therefore, more appropriate and intelligent services of the context awareness system is being required. The previous context awareness system can provide a service to the user through the inference only on the current situation. But, it does not handle certain situation properly when the system provides abnormal result. Also it does not have any proper method of generating reliable semantic data from sensed raw data. In this paper, we are trying to solve the problems as the following approaches. First, the system recognizes abnormal result and corrects it by learning feedback from the user. Second, we suggest a method of converting sensed data into more reliable semantic data. Third, we build the system based on an Ontological context model that is capable of interoperability and reusability. Therefore, the context awareness system of our study can enhance the previous system that can generate more reliable context data, can provide more effective inference method, and can provide more intelligent system structure.

• 한국정보통신학회논문지
• /
• 제26권2호
• /
• pp.313-316
• /
• 2022

In this paper, we implement a system that detects abnormalities in the charging data transmitted from the charger during the charging process of electric vehicles and controls them remotely. Using classification algorithms such as logistic regression, KNN, SVM, and decision trees, to do this, an analysis model is created that judges the data received from the charger as normal and abnormal. In addition, a model is created to determine the cause of the abnormality using the existing charging data based on the analysis of the type of charger abnormality. Finally, it is solved using unsupervised learning method to find new patterns of abnormal data.

• Nuclear Engineering and Technology
• /
• 제52권9호
• /
• pp.2009-2016
• /
• 2020

A nuclear power plant is a large complex system with tens of thousands of components. To ensure plant safety, the early and accurate diagnosis of abnormal situations is an important factor. To prevent misdiagnosis, operating procedures provide the anticipated symptoms of abnormal situations. While the more severe emergency situations total less than ten cases and can be diagnosed by dozens of key plant parameters, abnormal situations on the other hand include hundreds of cases and a multitude of parameters that should be considered for diagnosis. The tasks required of operators to select the appropriate operating procedure by monitoring large amounts of information within a limited amount of time can burden operators. This paper aims to develop a system that can, in a short time and with high accuracy, select the appropriate operating procedure and sub-procedure in an abnormal situation. Correspondingly, the proposed model has two levels of prediction to determine the procedure level and the detailed cause of an event. Simulations were conducted to evaluate the developed model, with results demonstrating high levels of performance. The model is expected to reduce the workload of operators in abnormal situations by providing the appropriate procedure to ultimately improve plant safety.

• 대한임상검사과학회지
• /
• 제49권1호
• /
• pp.15-21
• /
• 2017

C-reactive protein (CRP) levels are not generally associated with viral infections. This study investigated the changes in the CRP level caused by an infection from respiratory virus (RV). Nasopharyngeal samples from hospitalized patients with suspected RV infection were used to measure the CRP levels, virus load, virus-virus co-infection, age, sex, and length of hospital stay (LOS). Abnormal CRP levels were detected in 62.3% (3,608 out of 5,788) of all RV-positive samples. The percentage of patients with abnormal CRP levels tended to increase with age. Furthermore, LOS in patients with abnormal CRP levels was significantly longer than that in patients with normal CRP levels. The frequency of elevated CRP levels differed according to the causative virus and the frequency of abnormal levels increased with age. Moreover, LOS was longer in those with abnormal CRP levels. These data provide important insights into the role of CRP levels in RV infection.

• 보건의료산업학회지
• /
• 제5권4호
• /
• pp.1-13
• /
• 2011

The purpose of this study is to analyze the medical care utilization behavior of patients to whom treatment (surgery) is recommended after they are diagnosed with abnormal findings on health screening and factors affecting the selection of the medical institute for treatment. The data was collected from 291 patients who need treatment or surgery, according to the abnormal findings on the additional examination such as cardiac CT, brain MRI, Gastroscopy and Colonoscopy since four diseases are suspected among of 2,752 people who receive health screening. The results are as follows. First, the most common disease of patients who have abnormal findings by the diagnosis through the results of first testing is colon disease based on through the additional examination. The most common disease of patients who will get treatment (surgery) based on final diagnosis by a doctor who determines the result of health screening on the basis of diagnosis from the first testing is cardiovascular disease. Second, in terms of diseases, patients with cardiovascular disease select the medical institute where they get the health screenings as a place for treatment. Patients with cerebrovascular disease select another medical institute for treatment. Finally, the affective factors of selectivity treatment facility on health screening satisfaction were human, facility, health screening and revisit factors.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.169-176
• /
• 2021

Maritime monitoring requirements have been beyond human operators capabilities due to the broadness of the coverage area and the variety of monitoring activities, e.g. illegal migration, or security threats by foreign warships. Abnormal vessel movement can be defined as an unreasonable movement deviation from the usual trajectory, speed, or other traffic parameters. Detection of the abnormal vessel movement requires the operators not only to pay short-term attention but also to have long-term trajectory trace ability. Recent advances in deep learning have shown the potential of deep learning techniques to discover hidden and more complex relations that often lie in low dimensional latent spaces. In this paper, we propose a deep autoencoder-based clustering model for automatic detection of vessel movement anomaly to assist monitoring operators to take actions on the vessel for more investigation. We first generate gridded trajectory images by mapping the raw vessel trajectories into two dimensional matrix. Based on the gridded image input, we test the proposed model along with the other deep autoencoder-based models for the abnormal trajectory data generated through rotation and speed variation from normal trajectories. We show that the proposed model improves detection accuracy for the generated abnormal trajectories compared to the other models.