• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• Nuclear Engineering and Technology
• /
• 제55권9호
• /
• pp.3409-3416
• /
• 2023

Licensing the next-generation of nuclear reactor designs requires extensive use of Modeling and Simulation (M&S) to investigate system response to many operational conditions, identify possible accidental scenarios and predict their evolution to undesirable consequences that are to be prevented or mitigated via the deployment of adequate safety barriers. Deep Learning (DL) and Artificial Intelligence (AI) can support M&S computationally by providing surrogates of the complex multi-physics high-fidelity models used for design. However, DL and AI are, generally, low-fidelity 'black-box' models that do not assure any structure based on physical laws and constraints, and may, thus, lack interpretability and accuracy of the results. This poses limitations on their credibility and doubts about their adoption for the safety assessment and licensing of novel reactor designs. In this regard, Physics Informed Neural Networks (PINNs) are receiving growing attention for their ability to integrate fundamental physics laws and domain knowledge in the neural networks, thus assuring credible generalization capabilities and credible predictions. This paper presents the use of PINNs as surrogate models for accidental scenarios simulation in Nuclear Power Plants (NPPs). A case study of a Loss of Heat Sink (LOHS) accidental scenario in a Nuclear Battery (NB), a unique class of transportable, plug-and-play microreactors, is considered. A PINN is developed and compared with a Deep Neural Network (DNN). The results show the advantages of PINNs in providing accurate solutions, avoiding overfitting, underfitting and intrinsically ensuring physics-consistent results.

• Wind and Structures
• /
• 제36권6호
• /
• pp.393-404
• /
• 2023

Skewness and kurtosis are important higher-order statistics for simulating non-Gaussian wind pressure series on low-rise buildings, but their predictions are less studied in comparison with those of the low order statistics as mean and rms. The distribution gradients of skewness and kurtosis on roofs are evidently higher than those of mean and rms, which increases their prediction difficulty. The conventional artificial neural networks (ANNs) used for predicting mean and rms show unsatisfactory accuracy in predicting skewness and kurtosis owing to the limited capacity of shallow learning of ANNs. In this work, the deep neural networks (DNNs) model with the ability of deep learning is introduced to predict the skewness and kurtosis on a low-rise building. For obtaining the optimal generalization of the DNNs model, the hyper parameters are automatically determined by Bayesian Optimization (BO). Moreover, for providing a benchmark for future studies on predicting higher order statistics, the data sets for training and testing the DNNs model are extracted from the internationally open NIST-UWO database, and the prediction errors of all taps are comprehensively quantified by various error metrices. The results show that the prediction accuracy in this study is apparently better than that in the literature, since the correlation coefficient between the predicted and experimental results is 0.99 and 0.75 in this paper and the literature respectively. In the untrained cornering wind direction, the distributions of skewness and kurtosis are well captured by DNNs on the whole building including the roof corner with strong non-normality, and the correlation coefficients between the predicted and experimental results are 0.99 and 0.95 for skewness and kurtosis respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• Geomechanics and Engineering
• /
• 제37권1호
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• Structural Engineering and Mechanics
• /
• 제91권5호
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• 지능정보연구
• /
• 제22권1호
• /
• pp.139-157
• /
• 2016

앙상블 분류기란 개별 분류기보다 더 좋은 성과를 내기 위해 다수의 분류기를 결합하는 것을 의미한다. 이와 같은 앙상블 분류기는 단일 분류기의 일반화 성능을 향상시키는데 매우 유용한 것으로 알려져 있다. 랜덤 서브스페이스 앙상블 기법은 각각의 기저 분류기들을 위해 원 입력 변수 집합으로부터 랜덤하게 입력 변수 집합을 선택하며 이를 통해 기저 분류기들을 다양화 시키는 기법이다. k-최근접 이웃(KNN: k nearest neighbor)을 기저 분류기로 하는 랜덤 서브스페이스 앙상블 모형의 성과는 단일 모형의 성과를 개선시키는 데 효과적인 것으로 알려져 있으며, 이와 같은 랜덤 서브스페이스 앙상블의 성과는 각 기저 분류기를 위해 랜덤하게 선택된 입력 변수 집합과 KNN의 파라미터 k의 값이 중요한 영향을 미친다. 하지만, 단일 모형을 위한 k의 최적 선택이나 단일 모형을 위한 입력 변수 집합의 최적 선택에 관한 연구는 있었지만 KNN을 기저 분류기로 하는 앙상블 모형에서 이들의 최적화와 관련된 연구는 없는 것이 현실이다. 이에 본 연구에서는 KNN을 기저 분류기로 하는 앙상블 모형의 성과 개선을 위해 각 기저 분류기들의 k 파라미터 값과 입력 변수 집합을 동시에 최적화하는 새로운 형태의 앙상블 모형을 제안하였다. 본 논문에서 제안한 방법은 앙상블을 구성하게 될 각각의 KNN 기저 분류기들에 대해 최적의 앙상블 성과가 나올 수 있도록 각각의 기저 분류기가 사용할 파라미터 k의 값과 입력 변수를 유전자 알고리즘을 이용해 탐색하였다. 제안한 모형의 검증을 위해 국내 기업의 부도 예측 관련 데이터를 가지고 다양한 실험을 하였으며, 실험 결과 제안한 모형이 기존의 앙상블 모형보다 기저 분류기의 다양화와 예측 성과 개선에 효과적임을 알 수 있었다.

• 과학교육연구지
• /
• 제33권1호
• /
• pp.12-30
• /
• 2009

이 연구의 목적은 과학 영재 학생들의 사고 양식에 따른 지구시스템에 대한 인지 특성을 분석하는 것이다. 연구 대상은 광역시 소재 대학 부설 과학영재교육원에 재학 중인 24명이다. 연구 방법은 먼저 과학 영재 학생들을 대상으로 Sternberg의 정신자치제 이론에 근거로 사고양식 측정 검사를 실시한 후, 그 유형에 따라 Type I(입법적, 사법적, 전체적, 진보적)과 Type II(행정적, 지엽적, 보수적)집단으로 구분하였다. 그 후 각 집단에 대해 설문지 3종(A, B, C형), 단어 연상, 그림 분석, 개념 지도, 숨겨진 차원파악하기 (hidden dimension inventory), 자료해석 및 그 결과에 대한 심층 면담을 실시하였다. 과학 영재 학생들의 사고양식 유형은 입법적, 사법적, 무정부적, 전체적, 외부적, 그리고 진보적 사고 양식의 특성을 나타내어 새로운 과제를 선호하며, 창의적인 방식으로 문제를 해결하려는 경향을 보여주었다. 사고 유형에 따른 지구시스템에 대한 인지 특성에 대한 연구 결과는 다음과 같다. 첫째, '시스템 이해'에서 Type I, II 집단의 양적 측정치는 비슷하였으나, 세부적으로 살펴보면 상당한 차이가 존재한다. 둘째, '시스템 내 관계 파악'은 사고양식 유형과 상당히 밀접한 관계를 가지고 있으며, Type I집단이 보다 다각적, 역동적, 순환적으로 접근하여 보다 유리하다. 셋째, '시스템 일반화'에서 시스템에 대한 단순 해석 능력은 두 집단 모두 비슷하나, 숨겨진 차원 요소를 가미하여 추정할 경우 일반화 경향이 Type I집단이 우수하다. 하지만 시스템 예측 측면에서는 집단에 관계없이 미약하다. 이러한 결과를 볼 때 시스템 학습 프로그램 개발과 적용에 있어 다양한 대상에 대한 구체적인 개발 전략이 요구되며, 이를 통한 시스템 인지와 관련된 여러 분야에서의 활용성과 기대 효과가 클 것이라 생각된다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제44권3호
• /
• pp.457-475
• /
• 2005

We have inquired on what the statistical classes of the secondary schools had been aiming to, say the epistermlogical objects. And we now appreciate that the main obstacle to the systematic articulation is the lack of anticipation on what the statistical concepts are. This study focuses on the ingredients of the statistical concepts. Those are to be the ground of the systematic articulation of statistic courses, especially of the one for the school kids. Thus we required that those ingredients must satisfy the followings. i) directly related to the contents of statistics ii) psychologically developing iii) mutually exclusive each other as much as possible iv) exhaustive enough to cover all statistical concepts We examined what and how statisticians had been doing and the various previous views on these. After all we suggest the following three concepts are the core of conceptual developments of statistic, say the concept of distributions, the summarizing ability and the concept of samples. By the concepts of distributions we mean the frequency views on each random categories and that is developing from the count through the probability along ages. Summarizing ability is another important resources to embed his probe with the data set. It is not only viewed as a number but also to be anticipated as one reflecting a random phenomena. Inductive generalization is one of the most hazardous thing. Statistical induction is a scientific way of challenging this and this starts from distinguishing the chance with the inevitable consequences. One's inductive logic grows up along with one's deductive arguments, nevertheless they are different. The concept of samples reflects' one's view on the sample data and the way of compounding one's logic with the data within one's hypothesis. With these three in mind we observed Korean Statistic Curriculum from K to 12. Distributional concepts are dealt with throughout but not sequenced well. The way of summarization has been introduced in the 1 st, 5th, 7th and the 10th grade as a numerical value only. One activity on the concept of sample is given at the 6th grade. And it jumps into the statistical reasoning at the selective courses of ' Mathematics I ' or of ' Probability and Statistics ' in the grades of 11-12. We want to suggest further studies on the developing stages of these three conceptual features so as to obtain a firm basis of successive statistical articulation.

• 대한화학회지
• /
• 제62권5호
• /
• pp.398-411
• /
• 2018

본 연구의 목적은 탐구적 과학 글쓰기(Science Writing Heuristic)를 적용한 과제연구의 활동이 고등학생의 과학 탐구 능력 및 과학에 대한 태도에 미치는 영향을 알아보는 것이다. 이를 위하여 전남 소재의 고등학교 과학중점과정 2학년 학생 73명을 대상으로 의문 만들기, 실험 설계, 관찰, 주장과 증거, 읽기, 반성의 단계로 구성된 탐구적 과학 글쓰기를 적용한 과제연구 프로그램을 실시하였다. 프로그램의 효과 분석을 위해 과학 탐구 능력과 과학에 대한 태도를 검사하였고, 탐구적 과학 글쓰기를 적용한 과제 연구 수업에 대한 인식을 조사하였으며, 결과 해석의 어려움이 있을 경우 면담을 실시하였다. 연구 결과는 다음과 같다. 첫째, 과학 탐구 능력 중 추리, 가설 설정, 변인 찾기, 조작적 정의, 실험설계, 그래프화 및 데이터 해석, 일반화 능력은 통계적으로 유의미하게 향상되었으나(p<.05), 예상 능력은 향상되었으나 통계적으로 유의미하지 않았다(p>.05). 둘째, 과학에 대한 태도 중 과학에 대한 취미로서의 관심, 과학 수업의 즐거움, 과학 직업에 대한 관심은 통계적으로 유의미하게 향상되었으나(p<.05), 과학 탐구에 대한 태도는 통계적 유의하지 않았지만 점수가 감소했다. 탐구적 과학 글쓰기를 적용한 고등학교 과제 연구 수업은 과학 탐구 능력 및 과학 태도에 긍정적인 효과가 있었지만 오랜 기간 동안 일반 과학 수업과는 다른 형태로 학생이 주도하며 진행되기 때문에 학생들에게 부담이 된다. 그래서 이러한 단점을 최소화하고 장점을 최대화한 과제 연구 수업 전략에 대한 지속적인 연구가 필요하다.