http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
점진적 샘플링과 정규 상호정보량을 이용한 온라인 기계학습 공조기 급기온도 예측 모델 개발
추한경(Chu, Han-Gyeong),신한솔(Shin, Han-Sol),안기언(Ahn, Ki-Uhn),라선중(Ra, Seon-Jung),박철수(Park, Cheol Soo) 대한건축학회 2018 大韓建築學會論文集 : 構造系 Vol.34 No.6
The machine learning model can capture the dynamics of building systems with less inputs than the first principle based simulation model. The training data for developing a machine learning model are usually selected in a heuristic manner. In this study, the authors developed a machine learning model which can describe supply air temperature from an AHU in a real office building. For rational reduction of the training data, the progressive sampling method was used. It is found that even though the progressive sampling requires far less training data (n=60) than the offline regular sampling (n=1,799), the MBEs of both models are similar (2.6% vs. 5.4%). In addition, for the update of the machine learning model, the normalized mutual information (NMI) was applied. If the NMI between the simulation output and the measured data is less than 0.2, the model has to be updated. By the use of the NMI, the model can perform better prediction (5.4% → 1.3%).
설명가능한 인공지능을 이용한 건물 에너지 사용량 민감도 분석
추한경(Chu, Han-Gyeong),신한솔(Shin, Han-Sol),조성권(Cho, Seong-Kwon),유영서(Yoo, Young-Seo),박철수(Park, Cheol-Soo) 대한건축학회 2022 대한건축학회논문집 Vol.38 No.11
Classical sensitivity methods such as Morris and Sobol methods have been widely used in the decision making of building design and retrofit. However, these methods require a large number of samples to obtain reliable results as well as detailed information on input variables. On the other hand, the explainable AI technique can convert the relationship between input and output variables to a degree that can be understood by humans as well as provide more meaningful sensitivity analysis results for rational decision-making. In this paper, three XAI-based analyses were selected including Feature Importance, LIME, and SHAP. The five methods of Morris, Sobol, Feature Importance, LIME, and SHAP were applied to a medium office building provided by US DOE. As a result, it was found that XAI-based sensitivity analyses could provide better results than the classical methods.