• 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.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권4호
• /
• pp.247-275
• /
• 2021

Purpose This study attempted to predict corporate innovation and business performance using ensemble learning. Design/methodology/approach The ensemble techniques uses weak learning to create robust learning, which combines several weak models to derive improved performance. In this study, XGboost, LightGBM, and Catboost were used among ensemble techniques. It was compared and evaluated with traditional machine learning methods. Findings The summary of the research results is as follows. First, the type of innovation is expanding from technical innovation to non-technical areas. Second, it was confirmed that LightGBM performed best for radical innovation prediction, and XGboost performed best for incremental innovation prediction. Third, Catboost performed best for firm performance prediction. Although there was no significant difference in predictive power between ensemble techniques, we found that comparative analysis was necessary to confirm better prediction performance.

• Communications for Statistical Applications and Methods
• /
• 제30권5호
• /
• pp.485-499
• /
• 2023

This study aimed to predict the number of meals served in a group cafeteria using machine learning methodology. Features of the menu were created through the Word2Vec methodology and clustering, and a stacking ensemble model was constructed using Random Forest, Gradient Boosting, and CatBoost as sub-models. Results showed that CatBoost had the best performance with the ensemble model showing an 8% improvement in performance. The study also found that the date variable had the greatest influence on the number of diners in a cafeteria, followed by menu characteristics and other variables. The implications of the study include the potential for machine learning methodology to improve predictive performance and reduce food waste, as well as the removal of subjective elements in menu classification. Limitations of the research include limited data cases and a weak model structure when new menus or foreign words are not included in the learning data. Future studies should aim to address these limitations.

• 산경연구논집
• /
• 제13권10호
• /
• pp.1-8
• /
• 2022

Purpose: Support vector machines (SVMs) ensemble has been proposed to improve classification performance of Credit risk recently. However, currently used fusion strategies do not evaluate the importance degree of the output of individual component SVM classifier when combining the component predictions to the final decision. To deal with this problem, this paper designs a support vector machines (SVMs) ensemble method based on fuzzy integral, which aggregates the outputs of separate component SVMs with importance of each component SVM. Research design, data, and methodology: This paper designs a personal credit risk evaluation index system including 16 indicators and discusses a support vector machines (SVMs) ensemble method based on fuzzy integral for designing a credit risk assessment system to discriminate good creditors from bad ones. This paper randomly selects 1500 sample data of personal loan customers of a commercial bank in China 2015-2020 for simulation experiments. Results: By comparing the experimental result SVMs ensemble with the single SVM, the neural network ensemble, the proposed method outperforms the single SVM, and neural network ensemble in terms of classification accuracy. Conclusions: The results show that the method proposed in this paper has higher classification accuracy than other classification methods, which confirms the feasibility and effectiveness of this method.

• Journal of Korea Artificial Intelligence Association
• /
• 제2권1호
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1142-1146
• /
• 2009

A rainfall simulation and forecasting technique that can generate daily rainfall sequences conditional on multi-model ensemble GCMs is developed and applied to data in Korea for the major rainy season. The GCM forecasts are provided by APEC climate center. A Weather State Based Downscaling Model (WSDM) is used to map teleconnections from ocean-atmosphere data or key state variables from numerical integrations of Ocean-Atmosphere General Circulation Models to simulate daily sequences at multiple rain gauges. The method presented is general and is applied to the wet season which is JJA(June-July-August) data in Korea. The sequences of weather states identified by the EM algorithm are shown to correspond to dominant synoptic-scale features of rainfall generating mechanisms. Application of the methodology to seasonal rainfall forecasts using empirical teleconnections and GCM derived climate forecast are discussed.

• 지능정보연구
• /
• 제21권4호
• /
• pp.93-110
• /
• 2015

기존의 협업필터링 추천시스템 연구는 상품에 대한 고객의 평점(rating)이나 구매 여부 데이터로부터 하나의 프로파일을 생성하고 이를 기반으로 추천 성능을 향상시킬 수 있는 새로운 알고리즘을 개발하는 위주로 진행되어 왔다. 그러나 빅데이터 환경이 도래하면서 기업이 수집할 수 있는 고객 데이터가 풍부해지고 다양해짐에 따라, 보다 정확하게 고객의 선호도나 행태를 파악하는 것이 가능하게 되었고 이러한 데이터, 즉 퍼스널 빅데이터(personal big data)를 추천시스템에 활용하는 연구의 필요성이 대두되고 있다. 본 연구에서는 마케팅의 시장세분화 이론에 근거하여 퍼스널 빅데이터로부터 고객의 선호도나 행태를 다양한 관점에서 표현할 수 있는 5종의 다중 프로파일(multimodal profile)을 개발하고, 이를 활용하여 협업필터링 추천시스템의 성능을 개선하고자 한다. 제안하는 5종의 다중 프로파일은 프로파일 통합 유사도, 개별 프로파일 유사도 평균, 개별 프로파일 유사도 가중 평균이라는 세 가지 앙상블 기법을 통해 협업필터링의 이웃(neighborhood) 탐색과정에 적용된다. 실제 퍼스널 빅데이터에 본 연구에서 제안하는 방법론을 적용한 결과, 단일 프로파일을 사용하는 협업필터링 알고리즘보다 추천 성능이 상당히 개선되었으며 앙상블 방법 중에서는 개별 프로파일 유사도 가중 평균 기법이 가장 높은 추천 성능을 보여주었다. 본 연구는 빅데이터 환경에서 추천시스템을 개발하고자 할 때, 어떠한 성격의 데이터로부터 고객의 특성을 규명하는 프로파일을 만들고 이를 어떻게 결합하여 사용하는 것이 효과적인 지 처음으로 제안하였다는 점에서 그 의의가 있다.

• 한국수자원학회논문집
• /
• 제51권11호
• /
• pp.1031-1041
• /
• 2018

본 연구에서는 ANFIS 기반 GloSea5 앙상블 기상전망 개선 기법을 개발하고 평가하였다. 대상유역은 국내 주요 다목적댐인 충주댐 유역을 선정하였으며, 개선 기법은 ANFIS 기반의 전 후처리기법으로 구성된다. 전처리 기법에서 GloSea5의 앙상블 멤버에 가중치를 부여하며(OWM), 후처리 과정에서는 전처리결과를 편의보정 한다(MOS). 평가결과 편의보정된 GloSea5에 비해 예측성능이 개선되었으며, CASE3, CASE1, CASE2 순으로 모의성능이 우수하였다. 전처리 기법은 강수의 변동성이 큰 계절에 개선효과가 우수하였으며, 후처리 기법은 전처리로 개선하지 못한 오차를 줄 일 수 있는 것으로 나타났다. 따라서 본 연구에서 개발한 ANFIS 기반 GloSea5 앙상블 기상전망 개선 기법은 전 후처리 기법을 함께 사용하는 것이 가장 좋으며, 특히 여름철과 같이 강수의 변동성이 큰 계절에 활용성이 높을 것으로 판단된다.

• 스마트미디어저널
• /
• 제12권2호
• /
• pp.36-41
• /
• 2023

지원자 추적 시스템의 등장으로 온라인 채용이 활성화되면서 채용 사기가 심각한 문제로 대두되고 있다. 이 연구는 온라인 채용 환경에서 채용 사기를 탐지할 수 있는 신뢰할 수 있는 모델을 개발하여 비용 손실을 줄이고 개인 사생활 보호를 강화하고자 한다. 이 연구의 주요 기여는 데이터를 탐색적으로 분석하여 얻은 통찰력을 활용하여 어떤 채용 정보가 사기인지, 아니면 합법적인지를 구분할 수 있는 자동화된 방법론을 제공하는데 있다. 캐글에서 제공하는 채용 사기 데이터 집합인 EMSCAD를 사용하여 다양한 단일 분류기 및 앙상블 분류기 기반 머신러닝 모델을 훈련하고 평가하였으며, 그 결과로 앙상블 분류기인 랜덤 포레스트 분류기가 정확도 98.67%, F1 점수 0.81로 가장 좋은 결과를 보이는 것을 알 수 있었다.

• Computers and Concrete
• /
• 제32권3호
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.