.png){kind=icon}
.png){kind=icon}
Return
Optimizing energy efficiency and occupant comfort in smart buildings using SMOTE-augmented deep learning approaches
.png){kind=icon}
OA
AI
S
J
A
E
S
M
DOI：10.1016/j.jare.2026.08.035.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposes a novel deep learning approach to optimize energy efficiency and occupant comfort in smart buildings. • Addresses class imbalance issues in datasets like ASHRAE RP-884 using the SMOTE technique for enhanced model performance. • Implements advanced deep learning models including DNN, Deep Flatten Layers DNN, Bi-LSTM, and Attention LSTM for improved predictions. • Achieves 91% accuracy in thermal comfort forecasting using the Attention LSTM model, surpassing previous methods. • Enhances scalability, accuracy, and generalization of energy management systems for sustainable and smarter buildings.
Keywords:
Sustainable building comfort
Energy efficient
Smart buildings
Artificial intelligence
Deep learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13
Papers:
2.8K
Citations:
1.4W
Organization
Cited Papers