• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• 한국인터넷방송통신학회논문지
• /
• 제20권2호
• /
• pp.29-37
• /
• 2020

기존에 사용되던 방화벽들은 기본적으로 정책을 수동적으로 입력해 주는 방식으로 되어 있어 공격이 오는 즉시 대응하기 쉽지 않다. 왜냐하면 전문 보안 관리자가 이를 분석하고 해당 공격에 대한 방어 정책을 입력해 주어야하기 때문이다. 또한, 기존 방화벽 정책은 공격을 막기 위해 정상 접속까지 차단하는 경우가 많다. 패킷 자체는 정상적이지만 유입량이 많아 서비스 거부를 발생시키는 공격이 많기 때문이다. 본 논문에서는 방어 정책을 입력하는 부분을 인공지능으로 대체하여 정책을 자동으로 생성하고, 정상 접속 학습을 통해 생성된 화이트리스트 정책으로 정상 접속은 가능하면서 Flooding, Spoofing, Scanning과 같은 공격만을 차단하는 방법을 제안한다.

• Nuclear Engineering and Technology
• /
• 제54권2호
• /
• pp.644-652
• /
• 2022

During the pyroprocessing operation, various signals can be collected by process monitoring (PM). These signals are utilized to diagnose process states. In this study, feasibility of using PM for nuclear safeguards of electrorefining operation was examined based on the use of machine learning for detecting off-normal operations. The off-normal operation, in this study, is defined as co-deposition of key elements through reduction on cathode. The monitored process signal selected for PM was cathode potential. The necessary data were produced through electrodeposition experiments in a laboratory molten salt system. Model-based cathodic surface area data were also generated and used to support model development. Computer models for classification were developed using a series of recurrent neural network architectures. The concept of transfer learning was also employed by combining pre-training and fine-tuning to minimize data requirement for training. The resulting models were found to classify the normal and the off-normal operation states with a 95% accuracy. With the availability of more process data, the approach is expected to have higher reliability.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.438-455
• /
• 2024

Recently, many unsupervised learning-based models have emerged for Just Noticeable Difference (JND) estimation, demonstrating remarkable improvements in accuracy. However, these models suffer from a significant drawback is that their heavy reliance on handcrafted priors for guidance. This restricts the information for estimating JND simply extracted from regions that are highly related to handcrafted priors, while information from the rest of the regions is disregarded, thus limiting the accuracy of JND estimation. To address such issue, on the one hand, we extract the information for estimating JND in an Adversarial Complementary Learning (ACoL) way and propose an ACoL-JND network to estimate the JND by comprehensively considering the handcrafted priors-related regions and non-related regions. On the other hand, to make the handcrafted priors richer, we take two additional priors that are highly related to JND modeling into account, i.e., Patterned Masking (PM) and Contrast Masking (CM). Experimental results demonstrate that our proposed model outperforms the existing JND models and achieves state-of-the-art performance in both subjective viewing tests and objective metrics assessments.

• KEPCO Journal on Electric Power and Energy
• /
• 제8권2호
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• 한국압력기기공학회 논문집
• /
• 제19권2호
• /
• pp.93-101
• /
• 2023

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권1호
• /
• pp.13-20
• /
• 2016

본 논문에서는 계층적 특징 학습을 이용하여 물체의 컬러 영상과 깊이 영상으로부터 해당 물체가 속한 범주와 개체, 그리고 다양한 속성들을 효과적으로 인식할 수 있는 시스템을 제안한다. 본 시스템의 전처리 단계에서는 물체의 깊이 영상을 물체의 모양 정보를 좀 더 효과적으로 표현할 수 있는 표면 법선 벡터 데이터로 변환하고, 특징 학습 단계에서는 물체의 컬러 영상과 표면 법선 벡터 데이터로부터 두 단계에 걸쳐 패치 단위 특징과 이미지 단위의 특징을 추출해낸다. 그리고 추출된 특징 벡터들과 SVM 학습 알고리즘을 이용하여 각기 독립적인 다수의 분류 모델들을 학습한다. 미국 워싱턴 대학의 RGB-D 물체 데이터 집합을 이용한 실험을 통해, 본 논문에서 제안하는 물체 인식 시스템의 높은 성능을 확인할 수 있었다.

• Educational Technology International
• /
• 제17권1호
• /
• pp.59-85
• /
• 2016

The purpose of the study is to report differences in the effects of learner characteristics on the self-regulated learning (SRL) abilities between Chinese and Korean distance learners by using a structured SRL scale. A standardized 54-item self-regulated learning scale (SRAS) was used. The reliability was tested both in China and Korea which showed the scale had good reliability. The comparative study were conducted by administering the SRAS on 1999 Chinese distance learners from the Open Distance Education Center of Beijing Normal University and 1941 Korean distance learners from H Cyber University. Data on four dimensions of SRL - planning, control, regulating, and evaluation - were analyzed using 't-test' and 'ANOVA' with regards to the learner characteristics such as gender, age, prior education level, semesters, location and major. Results indicated that the average participant had an above medium level of SRL ability in all of the four dimensions. There were significant differences in the self-regulated learning ability between Chinese and Korean distance learners. Chinese distance learners scored higher in SRAS than Korean distance learners. The effects of learner characteristics on the SRL ability showed different patterns in the two countries. As for gender, male learners scored better in SRL than female learners in China, whereas it was just the opposite in Korea. No age differences were found in China, but Korean data exhibited a consistent age effect in all dimensions. In Korea, the age group older than 46 scored the highest, followed by the group between 35 to 45 years old, the group between 26 to 35 years old and the group younger than 25. As for location, Korean distance students from metropolitan were better than those from other regions, whereas it was on the contrary in China, albeit the location effect was not statistically significant. Prior education level had a clear and consistent effect on the SRL ability in both countries: the distance learners from junior colleges had better planning, regulating and evaluating abilities than those who came from senior high schools. These results have been discussed in various contexts of distance/online education as well as in relation to different culture between China and Korea. The results will also have implications for designing distance and online learning generally.