• Nuclear Engineering and Technology
• /
• 제56권2호
• /
• pp.558-567
• /
• 2024

Diagnostic support systems are being researched to assist operators in identifying and responding to abnormal events in a nuclear power plant. Most studies to date have considered single abnormal events only, for which it is relatively straightforward to obtain data to train the deep learning model of the diagnostic support system. However, cases in which multiple abnormal events occur must also be considered, for which obtaining training data becomes difficult due to the large number of combinations of possible abnormal events. This study proposes an approach to maintain diagnostic performance for multiple abnormal events by training a deep learning model with data on single abnormal events only. The proposed approach is applied to an existing algorithm that can perform feature selection and multi-label classification. We choose an extremely randomized trees classifier to select dedicated monitoring parameters for target abnormal events. In diagnosing each event occurrence independently, two-channel convolutional neural networks are employed as sub-models. The algorithm was tested in a case study with various scenarios, including single and multiple abnormal events. Results demonstrated that the proposed approach maintained diagnostic performance for 15 single abnormal events and significantly improved performance for 105 multiple abnormal events compared to the base model.

• 한국산학기술학회논문지
• /
• 제22권5호
• /
• pp.7-14
• /
• 2021

토마토 작물은 병해충의 영향을 많이 받기 때문에 이를 예방하지 않으면 농업 경제에 막대한 손실을 초래할 수 있다. 따라서 토마토의 다양한 병해충의 진단을 빠르고 정확하게 진단하는 시스템이 요구된다. 본 논문에서는 ImageNet 데이터 셋 상에서 다양하게 사전 학습된 딥러닝 기반 CNN 모델을 적용하여 토마토의 9가지 병해충 및 정상인 경우의 클래스를 분류하는 시스템을 제안한다. PlantVillage 데이터 셋으로부터 발췌한 토마토 잎의 이미지 셋을 3가지 딥러닝 기반 CNN 구조를 갖는 ResNet, Xception, DenseNet의 입력으로 사용한다. 기본 CNN 모델 위에 톱-레벨 분류기를 추가하여 제안 모델을 구성하였으며, 훈련 데이터 셋에 대해 5-fold 교차검증 기법을 적용하여 학습시켰다. 3가지 제안 모델의 학습은 모두 기본 CNN 모델의 계층을 동결하여 학습시키는 전이 학습과 동결을 해제한 후 학습률을 매우 작은 수로 설정하여 학습시키는 미세 조정 학습 두 단계로 진행하였다. 모델 최적화 알고리즘으로는 SGD, RMSprop, Adam을 적용하였다. 실험 결과는 RMSprop 알고리즘이 적용된 DenseNet CNN 모델이 98.63%의 정확도로 가장 우수한 결과를 보였다.

• 상하수도학회지
• /
• 제37권5호
• /
• pp.271-279
• /
• 2023

Fouling is an inevitable problem in membrane water treatment plant. It can be measured by trans-membrane pressure (TMP) in the constant flux operation, and chemical cleaning is carried out when TMP reaches a critical value. An early fouilng alarm is defined as warning the critical TMP value appearance in advance. The alarming method was developed using one of machine learning algorithms, decision tree, and applied to a ceramic microfiltration (MF) pilot plant. First, the decision tree model that classifies the normal/abnormal state of the filtration cycle of the ceramic MF pilot plant was developed and it was then used to make the early fouling alarm method. The accuracy of the classification model was up to 96.2% and the time for the early warning was when abnormal cycles occurred three times in a row. The early fouling alram can expect reaching a limit TMP in advance (e.g., 15-174 hours). By adopting TMP increasing rate and backwash efficiency as machine learning variables, the model accuracy and the reliability of the early fouling alarm method were increased, respectively.

• 스마트미디어저널
• /
• 제8권2호
• /
• pp.46-57
• /
• 2019

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data demands an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

• Nuclear Engineering and Technology
• /
• 제54권1호
• /
• pp.193-206
• /
• 2022

Several algorithms for nuclear power plant (NPP) break event detection, isolation, localization, and size estimation are proposed. A break event can be promptly detected and isolated after its occurrence by simultaneously monitoring changes in the sensing readings and by employing an interquartile range-based isolation scheme. By considering the multi-sensor data block of a break to be rank-one, it can be located as the position whose lead field vector is most orthogonal to the noise subspace of that data block using the Multiple Signal Classification (MUSIC) algorithm. Owing to the flexibility of deep neural networks in selecting the best regression model for the available data, we can estimate the break size using multiple-sensor recordings of the break regardless of the sensor types. The efficacy of the proposed algorithms was evaluated using the data generated by Maanshan NPP simulator. The experimental results demonstrated that the MUSIC method could distinguish two near breaks. However, if the two breaks were close and of small sizes, the MUSIC method might wrongly locate them. The break sizes estimated by the proposed deep learning model were close to their actual values, but relative errors of more than 8% were seen while estimating small breaks' sizes.

• 한국문헌정보학회지
• /
• 제57권2호
• /
• pp.435-452
• /
• 2023

이 연구는 딥러닝 기법의 전이학습 모형인 BERT를 이용하여 주제명의 자동 분류를 실험하고 그 성능을 평가하였으며, 더 나아가 주제명이 부여된 KDC 분류체계와 주제명의 범주 유형에 따른 성능을 분석하였다. 실험 데이터는 국가서지를 이용하여 주제명의 부여 횟수에 따라 6개의 데이터셋을 구축하고 분류 자질로 서명을 이용하였다. 그 결과, 분류 성능으로 3,506개의 주제명이 포함된 데이터셋(레코드 1,539,076건)에서 마이크로 F1과 매크로 F1 척도가 각각 0.6059와 0.5626 값을 보였다. 또한 KDC 분류체계에 따른 분류 성능은 총류, 자연과학, 기술과학, 그리고 언어 분야에서 좋은 성능을 보이며 종교와 예술 분야는 낮은 성능을 보였다. 주제명의 범주 유형에 따른 성능은 '식물', '법률명', '상품명'이 높은 성능을 보인 반면, '국보/보물' 유형의 주제명에서 낮은 성능을 보였다. 다수의 주제명을 포함하는 데이터셋으로 갈수록 분류기가 주제명을 제대로 부여하지 못하는 비율이 늘어나 최종 성능의 하락을 가져오기 때문에, 저빈도 주제명에 대한 분류 성능을 높이기 위한 개선방안이 필요하다.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• 한국자원식물학회지
• /
• 제35권2호
• /
• pp.192-200
• /
• 2022

본 연구에서는 부지화 잎의 무기양분 농도 측정 결과를 바탕으로 질소를 제외한 다른 무기양분의 함량을 통해서 잎의 질소 결핍 여부를 구분하는 머신러닝 모델을 개발하였다. 그러기 위해서 부지화의 질소결핍구와 대조구의 잎 샘플을 분석한 36개의 데이터를 부트스트랩핑 방법을 통해서 학습용 데이터셋 1,000 여 개로 증량시켰다. 이를 이용해 학습한 각 모델을 테스트한 결과, gradient boosting 모델이 가장 우수한 분류성능을 보여주었다. 본 모델을 이용해 질소함량을 직접적으로 분석할 수 없는 경우, 잎의 무기성분 함량에 기반하여 질소결핍 가능성 여부를 판단해 질소가 부족한 부지화 나무를 분별하고, 정확한 질소함량을 측정하게 유도하여 그에 기초한 적정 질소비료 시비를 가능케 하고자 하였다.

• 한국시뮬레이션학회논문지
• /
• 제29권4호
• /
• pp.1-7
• /
• 2020

농작물 질병에 대한 조기 진단은 질병의 확산을 억제하고 농업 생산성을 증대하는 데에 있어 중요한 역할을 하고 있다. 최근 합성곱신경망(convolutional neural network, CNN)과 같은 딥러닝 기법을 활용하여 농작물 잎사귀 이미지 데이터세트를 분석하여 농작물 질병을 진단하는 다수의 연구가 진행되었다. 이와 같은 연구를 통해 농작물 질병을 90% 이상의 정확도로 분류할 수 있지만, 사전 학습된 농작물 질병 외에는 진단할 수 없다는 한계를 갖는다. 본 연구에서는 미학습 농작물에 대해 효율적으로 질병 여부를 진단하는 모델을 제안한다. 이를 위해, 먼저 VGG16을 활용한 농작물 질병 분류기(CDC)를 구축하고 PlantVillage 데이터세트을 통해 학습하였다. 이어 미학습 농작물의 질병 진단이 가능하도록 수정된 질병 분류기(mCDC)의 구축방안을 제안하였다. 실험을 통해 본 연구에서 제안한 수정된 질병 분류기(mCDC)가 미학습 농작물의 질병진단에 대해 기존 질병 분류기(CDC)보다 높은 성능을 보임을 확인하였다.

• 한국자원식물학회:학술대회논문집
• /
• 한국자원식물학회 2019년도 추계학술대회
• /
• pp.87-87
• /
• 2019

The consumption of herbal medicine and related products (herbal products) have increased in South Korea. At the same time the quality, safety, and efficacy of herbal products is being raised. Currently, the herbal products are standardized and controlled according to the requirements of the Korean Pharmacopoeia, the National Institute of Health and the Ministry of Public Health and Social Affairs. The validation of herbal products and their medicinal component is important, since many of these herbal products are composed of two or more medicinal plants. However, there are no tools to support the validation process. Interest in deep learning has exploded over the past decade, for herbal medicine using algorithms to achieve herb recognition, symptom related target prediction, and drug repositioning have been reported. In this study, individual images of four herbs (Panax ginseng C.A. Meyer, Atractylodes macrocephala Koidz, Poria cocos Wolf, Glycyrrhiza uralensis Fischer), actually sold in the market, were achieved. Certain image preprocessing steps such as noise reduction and resize were formatted. After the features are optimized, we applied GoogLeNet_Inception v4 model for herb image recognition. Experimental results show that our method achieved test accuracy of 95%. However, there are two limitations in the current study. Firstly, due to the relatively small data collection (100 images), the training loss is much lower than validation loss which possess overfitting problem. Secondly, herbal products are mostly in a mixture, the applied method cannot be reliable to detect a single herb from a mixture. Thus, further large data collection and improved object detection is needed for better classification.