• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.1033-1042
• /
• 2023

본 논문은 네트워크에서 침입 행위를 하는 플로우를 탐지하는 네트워크 침입 탐지 시스템을 제안한다. 대다수 연구에 활용되는 데이터세트는 시계열 정보를 포함하고 있지 않으며, 공격 사례가 적은 공격은 샘플 데이터 수가 부족해 탐지율 향상이 어렵다. 하지만 탐지 방안에 대해 연구 결과가 부족한 상황이다. 본 연구에서는 ANN(Artificial Neural Network) 모델과 스택 앙상블 기법을 활용한 선행 연구를 토대로 하였다. 앞서 언급한 문제점을 해결하기 위해 인접 플로우를 활용하여 시계열 정보를 추가하고 희소 공격의 샘플을 강화하여 학습하여 탐지율을 보강하였다.

• 전자공학회논문지CI
• /
• 제37권2호
• /
• pp.31-43
• /
• 2000

본 논문은 얼굴영상에서 눈과 입 부위를 추출하기 위한 알고리즘을 제안하였다. 첫째로, 눈과 입의 에지 이진 화소 집합의 고유 값 (Eigenvalue) 과 고유 벡터 (Eigenvector) 로 부터 추출한 정보들은 눈과 입을 찾기 위한 좋은 특징이 된다. 눈과 입 부위의 긍정적 샘플과 부정적 샘플로부터 추출한 고유 특징들로 다층 신경망을 학습하여 특정 영역이 눈과 입 부위 포함하는 정도를 나타내도록 하였다. 둘째로, 시스템의 강건성 확보를 위해 서로 다른 구조의 단일 MLP를 묶어서 그 결과를 이용하는 Ensemble network 구조를 사용하였다. 두 눈과 입에 각각 별도의 Ensemble network을 사용하였고, 각 Ensemble network내 MLP들의 출력이 최대가 되는 영역의 중심 좌표들을 평균하여 최종 위치를 결정하였다. 셋째로, 특징 정보 추출 검색 영역을 즐기기 위해 얼굴 영상 에지 정보와 눈과 입의 위치 관계를 이용해 눈과 입의 대략적인 영역을 추출하였다. 제안된 시스템은 적은 수의 정면 얼굴에서 추출한 고유 특징들로 학습된 Ensemble network을 사용하여 학습에 사용되지 않은 다른 사람들의 정면얼굴 뿐만 아니라 일정한 범위 내 자세 변화에서도 좋은 일반화 성능을 얻고 있으며, 작은 범위 내에서의 얼굴 크기 변화나 좌우 20°이내의 자세 변화에 대해서도 신경망의 일반화 기능을 이용하여 강건한 결과를 얻고 있음을 확인하였다.

• Smart Structures and Systems
• /
• 제32권1호
• /
• pp.61-81
• /
• 2023

This study presents an ensemble learning based Bayesian model updating approach for structural damage diagnosis. In the developed framework, the structure is initially decomposed into a set of substructures. The autoregressive moving average (ARMAX) model is established first for structural damage localization based structural motion equation. The wavelet packet decomposition is utilized to extract the damage-sensitive node energy in different frequency bands for constructing structural surrogate models. Four methods, including Kriging predictor (KRG), radial basis function neural network (RBFNN), support vector regression (SVR), and multivariate adaptive regression splines (MARS), are selected as candidate structural surrogate models. These models are then resampled by bootstrapping and combined to obtain an ensemble model by probabilistic ensemble. Meanwhile, the maximum entropy principal is adopted to search for new design points for sample space updating, yielding a more robust ensemble model. Through the iterations, a framework of surrogate ensemble learning based model updating with high model construction efficiency and accuracy is proposed. The specificities of the method are discussed and investigated in a case study.

• 한국음향학회지
• /
• 제42권4호
• /
• pp.305-312
• /
• 2023

기포 크기 분포를 음파 감쇄 손실을 이용하여 역산하기 위해 Physics-Informed Neural Network(PINN)을 사용하였다. 역산에 사용되는 선형시스템을 풀기 위해 이미지 처리 분야에서 선형시스템 문제를 해결한 Adaptive Learned Iterative Shrinkage Thresholding Algorithm(Ada-LISTA)를 PINN의 신경망 구조로 이용하였다. 더 나아가, PINN의 손실함수에 선형시스템 기반의 정규항을 포함함으로써 PINN의 해가 기포 물리 법칙을 만족하여 더 높은 일반화 성능을 가지도록 하였다. 그리고 기포 추정값의 불확실성을 계산하기 위해 딥앙상블 기법을 이용하였다. 서로 다른 초기값을 갖는 20개의 Ada-LISTA는 같은 훈련데이터를 이용하여 학습되었다. 이 후 테스트시 훈련데이터와 다른 경향의 감쇄 손실을 입력으로 사용하여 기포 크기 분포를 추정하였고, 추정값과 이에 대한 불확실성을 20개 추정값의 평균과 분산으로 각각 구하였다. 그 결과 딥앙상블이 적용된 Ada-LISTA는 기존 볼록 최적화 기법인 CVX보다 기포 크기 분포를 역산하는데 더 우수한 성능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제22권11호
• /
• pp.111-116
• /
• 2017

This paper proposes a data mining approach to predicting stock price direction. Stock market fluctuates due to many factors. Therefore, predicting stock price direction has become an important issue in the field of stock market analysis. However, in literature, there are few studies applying data mining approaches to predicting the stock price direction. To contribute to literature, this paper proposes comparing single classifiers and ensemble classifiers. Single classifiers include logistic regression, decision tree, neural network, and support vector machine. Ensemble classifiers we consider are adaboost, random forest, bagging, stacking, and vote. For the sake of experiments, we garnered dataset from Korea Stock Exchange (KRX) ranging from 2008 to 2015. Data mining experiments using WEKA revealed that random forest, one of ensemble classifiers, shows best results in terms of metrics such as AUC (area under the ROC curve) and accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4557-4572
• /
• 2020

The Alaska competition provides an opportunity to study the practical problems of real-world steganalysis. Participants are required to solve steganalysis involving various embedding schemes, inconsistency JPEG Quality Factor and various processing pipelines. In this paper, we propose a method to ensemble multiple deep learning steganalyzers. We select SRNet and RESDET as our base models. Then we design a three-layers model ensemble network to fuse these base models and output the final prediction. By separating the three colors channels for base model training and feature replacement strategy instead of simply merging features, the performance of the model ensemble is greatly improved. The proposed method won second place in the Alaska 1 competition in the end.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1250-1257
• /
• 2020

The early detection of diseases is important in agriculture because diseases are major threats of reducing crop yield for farmers. The shape and color of plant leaf are changed differently according to the disease. So we can detect and estimate the disease by inspecting the visual feature in leaf. This study presents a vision-based leaf classification method for detecting the diseases of tomato crop. ResNet-50 model was used to extract the visual feature in leaf and classify the disease of tomato crop, since the model showed the higher accuracy than the other ResNet models with different depths. We propose a new ensemble approach using several DCNN classifiers that have the same structure but have been trained at different ranges in the DCNN layers. Experimental result achieved accuracy of 97.19% for PlantVillage dataset. It validates that the proposed method effectively classify the disease of tomato crop.

• Journal of information and communication convergence engineering
• /
• 제16권3호
• /
• pp.148-152
• /
• 2018

Adversarial attacks on artificial intelligence (AI) systems use adversarial examples to achieve the attack objective. Adversarial examples consist of slightly changed test data, causing AI systems to make false decisions on these examples. When used as a tool for attacking AI systems, this can lead to disastrous results. In this paper, we propose an ensemble of degraded convolutional neural network (CNN) modules, which is more robust to adversarial attacks than conventional CNNs. Each module is trained on degraded images. During testing, images are degraded using various degradation methods, and a final decision is made utilizing a one-hot encoding vector that is obtained by summing up all the output vectors of the modules. Experimental results show that the proposed ensemble network is more resilient to adversarial attacks than conventional networks, while the accuracies for normal images are similar.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.489-497
• /
• 2000

After IMF situation, the money market environment is changing rapidly. Therefore, many companies including financial institutions and many individual investors are concerned about forecasting the money market, and they make an effort to insure the various profit and hedge methods using derivatives like option, futures and swap. In this research, we developed a prototype of forecasting system for KOSPI 200 option, especially call option, trading using artificial neural networks(ANN), To avoid the overfitting problem and the problem involved int the choice of ANN structure and parameters, we employed the ANN ensemble approach. We conducted two types of simulation. One is conducted with the hold signals taken into account, and the other is conducted without hold signals. Even though our models show low accuracy for the sample set extracted from the data collected in the early stage of IMF situation, they perform better in terms of profit and stability than the model that uses only the theoretical price.