Building and Urban Data Science (BUDS) Group's repositories
building-data-genome-project-2
Whole building non-residential hourly energy meter data from the Great Energy Predictor III competition
ashrae-great-energy-predictor-3-solution-analysis
Analysis of top give winning solutions of the ASHRAE Great Energy Predictor III competition
building-prediction-benchmarking
An array of open source ML models applied to long-term hourly energy prediction for institutional buildings
google-trends-for-buildings
Data and Code for the Paper "Using Google Trends to Predict Building Energy"
buds-lab.github.io
BUDS Lab Website
build2vec-thermal-comfort
code for Build2Vec 1.0 reproducibility
LEAD-1st-solution
1st winning solution in Large-scale Energy Anomaly Detection (LEAD) competition
humans-as-a-sensor-for-buildings
Implementation of the Humans-as-a-Sensor for Buildings paper.
ComfortLearn
This repository is the official implementation of ComfortLearn: Enabling agent-based occupant-centric building controls
psychrometric-chart-makeover
Adding more dimension to the psychrometric chart
aldiplusplus
This repository is the official implementation of ALDI++: Automatic and parameter-less discorddetection for daily load energy profiles
comfortGAN
This repository is the official implementation of Balancing thermal comfort datasets: We GAN, but should we?
longitudinal-personal-thermal-comfort
Official repository for Dataset: Longitudinal personal thermal comfort preference data in the wild
data-driven-greenmark
Dataset on Singapore's Green Mark Buildings
ashrae-great-energy-predictor-3-error-analysis
Analysis of the Time Series Residuals of the Great Energy Predictor III competition
generative-methods-for-human-comfort
Human comfort datasets are widely used for multiple scenarios in smart buildings. From thermal comfort prediction to personalized indoor environments, labelled subjective responses from participants in a experiment are required to feed different machine learning models. However, many of these dataset are small in samples per participants, number of participants, or suffer from a class-imbalanced of its subjective responses. In this work we explore the use of Generative Adversarial Networks to generate synthetic samples to be used in combination with real ones for data-driven applications in the built environment.
ema-for-occupant-wellness-and-privacy
Cozie deployment for Indoor Air 2022 Paper on Occupant Wellness and Privacy
annex79-2022-sg
Annex79 website
annex79-sg
Website for the RLEM Workshop
calma-esse-heat-stress-public
Private repository for the Cozie-Apple deployment leady be Ben
cisbat-learning-trail-paper
CISBAT Learning Trail Publication 2019 - Latex Assets, Graphics, and Data
occupant-interactions-workspaces
Pilot data on identifying and contextualising occupant interactions within hybrid workspaces