Poster Abstract: Investigating Occupancy Profiles Using Convolutional Neural Networks: Preprint

Xin Jin, Jianli Chen, Zoltan Nagy

Research output: Contribution to conferencePaper

Abstract

In this paper, we implement a convolutional neural networks based autoencoder to investigate occupancy profiles. We use the American time use survey data, which contains 191,558 schedules with binary occupancy information. Our results suggest that the trained filters provide an important insight of occupancy profiles (i.e., dominant and distinct patterns), and the latent space compresses the profiles with representative information.
Original languageAmerican English
Number of pages5
StatePublished - 2020
Event6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys 2019) - New York, New York
Duration: 13 Nov 201914 Nov 2019

Conference

Conference6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys 2019)
CityNew York, New York
Period13/11/1914/11/19

NREL Publication Number

  • NREL/CP-5500-74892

Keywords

  • autoencoder
  • convolutional neural networks
  • occupant behavior

Fingerprint

Dive into the research topics of 'Poster Abstract: Investigating Occupancy Profiles Using Convolutional Neural Networks: Preprint'. Together they form a unique fingerprint.

Cite this