Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Fresh data on artificial intelligence are present ed in a new report. According to news reporting originating from Nanjing, People 's Republic of China, by NewsRx correspondents, research stated, "Metamodeling i s a promising technique for alleviating the computational burden of building ene rgy simulation." Financial supporters for this research include National Natural Science Foundati on of China; Jiangsu Province Natural Science Foundation; Ministry of Education of The People's Republic of China Humanities And Social Sciences Youth Foundatio n. The news journalists obtained a quote from the research from Nanjing Tech Univer sity: "Although various machine learning (ML) algorithms have been applied, the interactive effects of multiple factors on ML algorithm performance remain uncle ar. In this study, six popular ML algorithms, including ridge regression, random forest, extreme gradient boosting (XGBoost), support vector regression (SVR), k-nearest neighbor (KNN) regression and multi-layer perceptron (MLP), were analyz ed for a benchmark metamodeling problem in building energy simulation under the impacts of four factors: input dimension, sample size, degree of input-output se nsitivity and hyperparameter optimization (HPO) technique. The results indicated that XGBoost had high model precision and strong robustness, while KNN and SVR performed poorly on the two metrics. Increasing the sample size could mitigate t he impact of the other three factors on model precision, especially for MLP."
NETL
NSTL