PulseExploreJournal ClubTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
August 8, 2026Journal of Measurements in EngineeringOpen Access

Spatiotemporal feature extraction of regional building energy consumption combining residual network and convolutional attention mechanism

View Full Paper
Ask AI
Bookmark
Share

Authors

QGQiongmin GaoJYJian Yin

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved accuracy in predicting regional building energy consumption using advanced AI methods, suggesting effective applications in energy management.

Key Points

  • The aim is to develop a method that effectively extracts spatiotemporal features of regional building energy consumption.
  • Utilized a residual network structure to separately extract temporal and spatial features.
  • Introduced a graph attention module and channel attention mechanism to optimize feature representation.
  • Conducted experiments to validate the method's effectiveness in capturing energy consumption patterns.
  • Achieved a prediction deviation as low as 2.41%.
  • Observed an average energy saving rate of 33.20%.
  • Demonstrated significant superiority over traditional U-Net encoder and histogram analysis methods.

Cite This Study

Gao et al. (2026) studied this question.

synapsesocial.com/papers/6a76da7cf12abadc79814cfdhttps://doi.org/10.21595/jme.2026.25960
View Full Paper
Ask AI
Bookmark
Share