• 한국BIM학회 논문집
• /
• 제12권2호
• /
• pp.12-25
• /
• 2022

To increase the usability of Building Information Modeling (BIM) in construction projects, it is critical to ensure the interoperability of data between heterogeneous BIM software. The Industry Foundation Classes (IFC), an international ISO format, has been established for this purpose, but due to its structural complexity, geometric information and properties are not always transmitted correctly. Recently, deep learning approaches have been used to learn the shapes of the BIM elements and thereby verify the mapping between BIM elements and IFC entities. These models performed well for elements with distinct shapes but were limited when their shapes were highly similar. This study proposed a method to improve the performance of the element type classification by using an Ensemble model that leverages not only shapes characteristics but also the relational information between individual BIM elements. The accuracy of the Ensemble model, which merges MVCNN and MLP, was improved 0.03 compared to the existing deep learning model that only learned shape information.

• 스마트미디어저널
• /
• 제11권3호
• /
• pp.9-17
• /
• 2022

알고리즘을 이용하여 금융 상품을 거래하는 알고리즘 트레이딩은 시장의 많은 요인들로 인해 그 결과가 안정적이지 못한 문제가 있다. 이 문제를 완화시키기 위해 트레이딩 알고리즘들을 조합한 앙상블 기법들이 제안되었다. 하지만 이 앙상블 방법에도 여러 문제가 존재한다. 첫째, 앙상블의 필요 요건인 앙상블에 포함된 알고리즘의 최소 성능 요건(랜덤 이상)을 만족시키도록, 트레이딩 알고리즘을 선택하지 못할 수 있다는 점이다. 둘째, 과거에 우수한 성능을 보인 앙상블 모델이 미래에도 우수한 성능을 보일 것이라는 보장이 없다는 점이다. 이 문제점들을 해결하기 위해 앙상블 모델에 포함되는 트레이딩 알고리즘들을 선택하는 방법을 다음과 같이 제안한다. 과거의 데이터를 기반으로 상위 성능의 앙상블 모델들에 포함된 트레이딩 알고리즘들의 기여도를 측정한다. 그러나 이 과거 데이터에만 기반 된 기여도들은 과거의 데이터가 충분히 많지 않고 과거 데이터의 불확실성이 반영되어 있지 않기 때문에 디리클레 분포를 사용하여 기여도 분포를 근사시키고, 기여도 분포에서 기여도 값들을 샘플하여 불확실성을 반영한다. 과거 데이터로부터 구한 트레이딩 알고리즘의 기여도 분포를 기반으로 Transformer을 훈련하여 미래의 기여도를 예측한다. 예측된 미래 기여도가 높은 트레이딩 알고리즘들을 앙상블 모델에 선택하여 포함시킨다. 실험을 통하여 제안된 앙상블 방법이 기존 앙상블 방법들과 비교하여 우수한 성능을 보임을 입증하였다.

• International Journal of Computer Science & Network Security
• /
• 제23권1호
• /
• pp.89-95
• /
• 2023

Analyzing breast cancer patient files is becoming an exciting area of medical information analysis, especially with the increasing number of patient files. In this paper, breast cancer data is collected from Khartoum state hospital, and the dataset is classified into recurrence and no recurrence. The data is imbalanced, meaning that one of the two classes have more sample than the other. Many pre-processing techniques are applied to classify this imbalanced data, resampling, attribute selection, and handling missing values, and then different classifiers models are built. In the first experiment, five classifiers (ANN, REP TREE, SVM, and J48) are used, and in the second experiment, meta-learning algorithms (Bagging, Boosting, and Random subspace). Finally, the ensemble model is used. The best result was obtained from the ensemble model (Boosting with J48) with the highest accuracy 95.2797% among all the algorithms, followed by Bagging with J48(90.559%) and random subspace with J48(84.2657%). The breast cancer imbalanced dataset was classified into recurrence, and no recurrence with different classified algorithms and the best result was obtained from the ensemble model.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.641-651
• /
• 2023

Malicious hate speech and gender bias comments are common in online communities, causing social problems in our society. Gender bias and hate speech detection has been investigated. However, it is difficult because there are diverse ways to express them in words. To solve this problem, we attempted to detect malicious comments in a Korean hate speech dataset constructed in 2020. We explored bidirectional encoder representations from transformers (BERT)-based deep learning models utilizing hyperparameter tuning, data sampling, and logits ensembles with a label distribution. We evaluated our model in Kaggle competitions for gender bias, general bias, and hate speech detection. For gender bias detection, an F1-score of 0.7711 was achieved using an ensemble of the Soongsil-BERT and KcELECTRA models. The general bias task included the gender bias task, and the ensemble model achieved the best F1-score of 0.7166.

• 한국IT서비스학회지
• /
• 제19권6호
• /
• pp.131-144
• /
• 2020

As the blockchain technology attracts attention, interest in cryptocurrency that is received as a reward is also increasing. Currently, investments and transactions are continuing with the expectation and increasing value of cryptocurrency. Accordingly, prediction for cryptocurrency price has been attempted through artificial intelligence technology and social sentiment analysis. The purpose of this paper is to develop a deep learning ensemble model for predicting the price fluctuations and one-day lag price of cryptocurrency based on the design science research method. This paper intends to perform predictive modeling on Ethereum among cryptocurrencies to make predictions more efficiently and accurately than existing models. Therefore, it collects data for five years related to Ethereum price and performs pre-processing through customized functions. In the model development stage, four LSTM models, which are efficient for time series data processing, are utilized to build an ensemble model with the optimal combination of hyperparameters found in the experimental process. Then, based on the performance evaluation scale, the superiority of the model is evaluated through comparison with other deep learning models. The results of this paper have a practical contribution that can be used as a model that shows high performance and predictive rate for cryptocurrency price prediction and price fluctuations. Besides, it shows academic contribution in that it improves the quality of research by following scientific design research procedures that solve scientific problems and create and evaluate new and innovative products in the field of information systems.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.287-287
• /
• 2023

Surface water-groundwater interaction (SWGI) is an important hydrological process that influences both the quantity and quality of water resources. However, regional scale SWGI model calibration and uncertainty analysis have been a challenge because integrated models inherently carry a vast number of parameters, modeling assumptions, and inputs, potentially leaving little time and budget to explore questions related to model performance and forecasting. In this study, we have proposed the application of iterative ensemble smoother (IES) for uncertainty analysis and calibration of the widely used integrated surface-subsurface model, SWAT-MODFLOW. SWAT-MODFLOW integrates Soil and Water Assessment Tool (SWAT) and a three-dimensional finite difference model (MODFLOW). The model was calibrated using a parameter estimation tool (PEST). The major advantage of the employed IES is that the number of model runs required for the calibration of an ensemble is independent of the number of adjustable parameters. The pilot point approach was followed to calibrate the aquifer parameters, namely hydraulic conductivity, specific storage, and specific yield. The parameter estimation process for the SWAT model focused primarily on surface-related parameters. The uncertainties both in the streamflow and groundwater level were assessed. The work presented provides valuable insights for future endeavors in coupled surface-subsurface modeling, data collection, model development, and informed decision-making.

• 한국수자원학회논문집
• /
• 제52권9호
• /
• pp.603-613
• /
• 2019

본 연구에서는 shot noise process 기반 강우-유출 모형(이하 강우-유출 모형)을 이용하여 유출 앙상블 멤버를 생성하는 방법을 제안하였다. 아울러 제안된 방법을 적용하여 대림 2, 구로 1, 중동 빗물펌프장 등 3개 배수유역에 대한 유출 앙상블 멤버를 생성하고, 이를 관측 유출량과 비교해 보았다. 강우-유출 모형의 매개변수는 Kerby 공식, Kraven II 공식, Russel 공식 및 수정합리식의 개념을 이용하여 추정하였다. 강우-유출 모형 매개변수의 난수 발생을 위해서는 감마분포와 지수분포를 이용하였다. 특히, 감마분포의 경우에는 평균과 표준편차의 관계를 어떻게 설정하느냐에 따라 다양한 난수 발생이 가능함을 확인하였다. 생성된 유출 앙상블과 관측 유출량과의 비교 결과, 표준편차가 평균의 두 배인 감마 분포를 이용하여 만든 유출 앙상블이 관측 유출량을 가장 적절히 포괄함을 확인하였다.

• Journal of the Korean Wood Science and Technology
• /
• 제47권3호
• /
• pp.265-276
• /
• 2019

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

• Asian Journal of Atmospheric Environment
• /
• 제4권3호
• /
• pp.150-156
• /
• 2010

Inter-comparison of chemical transport models (CTMs) was conducted among four modeling research groups. Model performance of the ensemble approach to $O_3$ and $PM_{2.5}$ simulation was evaluated by using observational data with a time resolution of 1 or 6 hours at four sites in the Kanto area, Japan, in summer 2007. All groups applied the Community Multiscale Air Quality model. The ensemble average of the four CTMs reproduced well the temporal variation of $O_3$ (r=0.65-0.85) and the daily maximum $O_3$ concentration within a factor of 1.3. By contrast, it underestimated $PM_{2.5}$ concentrations by a factor of 1.4-2, and did not reproduce the $PM_{2.5}$ temporal variation at two suburban sites (r=~0.2). The ensemble average improved the simulation of ${SO_4}^{2-}$, ${NO_3}^-$, and ${NH_4}^+$, whose production pathways are well known. In particular, the ensemble approach effectively simulated ${NO_3}^-$, despite the large variability among CTMs (up to a factor of 10). However, the ensemble average did not improve the simulation of organic aerosols (OAs), underestimating their concentrations by a factor of 5. The contribution of OAs to $PM_{2.5}$ (36-39%) was large, so improvement of the OA simulation model is essential to improve the $PM_{2.5}$ simulation.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제8권3호
• /
• pp.57-67
• /
• 2018

앙상블 기법은 기계학습에서 다수의 알고리즘을 사용하여 더 좋은 성능을 내기 위해 사용하는 방법이다. 본 논문에서는 앙상블 기법에서 많이 사용되는 부스팅과 배깅에 대해 소개를 하고, 서포트벡터 회귀, 방사기저함수 네트워크, 가우시안 프로세스, 다층 퍼셉트론을 이용하여 설계한다. 추가적으로 순환신경망과 MOHID 수치모델을 추가하여 실험을 진행한다. 실험적 검증를 위해 사용하는 뜰개 데이터는 7 개의 지역에서 관측된 683 개의 관측 자료다. 뜰개 관측 자료를 이용하여 6 개의 알고리즘과의 비교를 통해 앙상블 기법의 성능을 검증한다. 검증 방법으로는 평균절대오차를 사용한다. 실험 방법은 배깅, 부스팅, 기계학습을 이용한 앙상블 모델을 이용하여 진행한다. 각 앙상블 모델마다 동일한 가중치를 부여한 방법, 차등한 가중치를 부여한 방법을 이용하여 오류율을 계산한다. 가장 좋은 오류율을 나타낸 방법은 기계학습을 이용한 앙상블 모델로서 6 개의 기계학습의 평균에 비해 61.7%가 개선된 결과를 보였다.