• Journal of KIBIM
• /
• v.12 no.2
• /
• 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.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.9-17
• /
• 2022

Algorithmic trading, which uses algorithms to trade financial products, has a problem in that the results are not stable due to many factors in the market. To alleviate this problem, ensemble techniques that combine trading algorithms have been proposed. However, there are several problems with this ensemble method. First, the trading algorithm may not be selected so as to satisfy the minimum performance requirement (more than random) of the algorithm included in the ensemble, which is a necessary requirement of the ensemble. Second, there is no guarantee that an ensemble model that performed well in the past will perform well in the future. In order to solve these problems, a method for selecting trading algorithms included in the ensemble model is proposed as follows. Based on past data, we measure the contribution of the trading algorithms included in the ensemble models with high performance. However, for contributions based only on this historical data, since there are not enough past data and the uncertainty of the past data is not reflected, the contribution distribution is approximated using the Dirichlet distribution, and the contribution values are sampled from the contribution distribution to reflect the uncertainty. Based on the contribution distribution of the trading algorithm obtained from the past data, the Transformer is trained to predict the future contribution. Trading algorithms with high predicted future contribution are selected and included in the ensemble model. Through experiments, it was proved that the proposed ensemble method showed superior performance compared to the existing ensemble methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• 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
• /
• v.19 no.5
• /
• 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.

• Journal of Information Technology Services
• /
• v.19 no.6
• /
• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• 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.

• Journal of Korea Water Resources Association
• /
• v.52 no.9
• /
• pp.603-613
• /
• 2019

This study proposes a method to generate runoff ensemble members using a rainfall-runoff model based on the shot noise process (hereafter the rainfall-runoff model). The proposed method was applied to generate runoff ensemble members for three drainage basins of Daerim 2, Guro 1 and the Jungdong, whose results were then compared with the observed. The parameters of the rainfall-runoff model were estimated using the empirical formulas like the Kerby, Kraven II and Russel, also the concept of modified rational formula. Gamma and exponential distributions were used to generate random numbers of the parameters of the rainfall-runoff model. Especially, the gamma distribution is found to be useful to generate various random numbers depending on the pre-assigned relationship between mean and standard deviation. Comparison between the generated runoff ensemble members and the observed shows that those runoff ensemble members generated using the gamma distribution with its standard deviation twice of the mean properly cover the observed runoff.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.3
• /
• 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
• /
• v.4 no.3
• /
• 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.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.