http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
차윤경 ( Yoonkyung Cha ) 한국물환경학회 2020 한국물환경학회·대한상하수도학회 공동 춘계학술발표회 Vol.2020 No.-
The data deluge, increased computing power, and advances in analytical methods have all made data-driven approaches more applicable to various academic disciplines. Accordingly, these approaches have been increasingly adopted in water quality and ecological studies to model freshwater aquatic systems. A systematic review of the literature was performed to analyze the long-term changes in the relative number of data-driven modeling studies (in comparison to process-based modeling studies) and temporal patterns of frequently used methods within the data-driven modeling framework. Also, these trends in South Korea were compared with the global trends. Both advantages and potential challenges involved with data-driven modeling and how these have been addressed by previous studies were discussed. Furthermore, the motivations for exploiting data-driven approaches, which are expected to prosper with the emergence of new sources and types of data, toward the effective management of aquatic systems were highlighted.
베이지안 최적화를 통한 저서성 대형무척추동물 종분포모델 개발
고병건,신지훈,차윤경,Go, ByeongGeon,Shin, Jihoon,Cha, Yoonkyung 대한상하수도학회 2021 상하수도학회지 Vol.35 No.4
This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.