Self-Adaptive Occupancy Forecasting in CMU Classrooms (and Beyond!)

Hi, We are a team of researchers (Avi, Dharun, Stacy, Weronika) at Carnegie Mellon University working as part of (12-770) the Autonomous Sustainable Buildings Course. We are currently using thermal sensors to eventually predict occupancy behavior in CMU classrooms.

Here are some links to prior work in this area:

1. A review on occupancy prediction through machine learning for enhancing energy efficiency, air quality and thermal comfort in the built environment (2022) Read paper

2. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing (2021)
   Read paper

3. Modeling and Prediction of Occupancy in Buildings Based on Sensor Data Using Deep Learning Methods (2024)
   Read paper

4. Deep learning and multi-objective optimization for real-time occupancy-based energy control in smart buildings (2025)
   Read paper