首页|New Findings on Artificial Intelligence from Department of Architectural Science s Summarized (Exploring Artificial Intelligence Methods for Energy Prediction In Healthcare Facilities: an In-depth Extended Systematic Review)
New Findings on Artificial Intelligence from Department of Architectural Science s Summarized (Exploring Artificial Intelligence Methods for Energy Prediction In Healthcare Facilities: an In-depth Extended Systematic Review)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Artificial Intelligenc e is the subject of a report. According to news reporting out of Toronto, Canada , by NewsRx editors, research stated, "Hospitals, due to their complexity and un ique requirements, play a pivotal role in global energy consumption patterns. Th is study conducted a comprehensive literature review, utilizing the PRISMA frame work, of articles that employed machine learning and artificial intelligence tec hniques for predicting energy consumption in hospital buildings." Our news journalists obtained a quote from the research from the Department of A rchitectural Sciences, "Of the 2,157 publications identified, 35 specifically ad dressed this domain and were thoroughly reviewed to establish the state-of-the-a rt and identify research gaps. The review revealed a diverse range of data input s influencing energy prediction, with occupancy and meteorological data emerging as significant predictors. However, many studies did not delve deeply into the implications of their data choices, highlighting gaps in understanding time dyna mics, operational status, and preprocessing methods. Machine learning, especiall y deep learning models like artificial neural networks (ANNs), showed potential in this domain but faced challenges, including interpretability and computationa l demands. Our study emphasized the necessity for detailed daily activity data a nd a broader spectrum of meteorological inputs to enhance prediction accuracy. A dvanced data preprocessing and feature engineering techniques were identified as crucial for improving model performance. The integration of real-time data into Intelligent Energy Management Systems (IEMS) and longterm energy forecasting ar e areas that future research should prioritize for holistic sustainability in he althcare facilities. Additionally, the exploration of hybrid optimization strate gies and enhancing model interpretability were recognized as pivotal for advanci ng the application of AI in this field. By addressing these areas, future resear ch can significantly contribute to developing more efficient and sustainable ene rgy management practices in hospitals."
TorontoCanadaNorth and Central Ameri caArtificial IntelligenceCyborgsEmerging TechnologiesHospitalsMachine LearningDepartment of Architectural Sciences
NETL
NSTL
