Brick-by-Brick 2024 Competition

A global challenge to automate building data classification, unlocking more intelligent, energy-efficient buildings for a sustainable future.

Buildings are among the largest energy consumers in the modern world, making energy efficiency essential. However, managing building system data across diverse facilities is time-consuming and costly due to inconsistent data formats. This time-series classification problem transformed building management by creating a solution that automatically classifies building data, promoting standardised, energy-efficient management for a more sustainable world.

In this workshop, selected teams present their top solutions to advance smart buildings.

Official Website: https://www.aicrowd.com/challenges/brick-by-brick-2024

Post-competition Archival Repository: https://github.com/cruiseresearchgroup/DIEF_BTS/tree/main/competition1

[The Web Conf. 25] Brick-by-Brick 2024 competition workshop details:

• Date: Tuesday, 29th April 2025
• Time: 13:30 - 17:00
• Location: ICC Sydney: International Convention & Exhibition Centre, Sydney, Australia
• Room: C4.7
• This is a part of The Web Conference 2025

Schedule

13:30 - 15:00: Session 1

• 13:30 - UNSW: Brick-by-Brick: Cyber-Physical Building Data Classification Challenge
• 14:00 - FLAME: A simple feature extraction based approach to solving the Brick by Brick 2024 challenge.
• 14:15 - Chan Jun Hao: BrickMIR: A Minimal, Imbalance-tuned, and Ratio-based Framework for Brick Metadata Classification.
• 14:30 - Bram: Another Brick in the Wall: Leveraging Feature Extraction and Ensemble Learning for Building Data Classification.
• 14:45 - NaiveBaes: Hierarchical Multi-Label Classification of Building Management System Time-Series Data.

15:00 - 15:30: Break

15:30 - 17:00: Session 2

• 15:30 - XiaoBaiLan: Winning Brick by Brick with Daily Slices: A 94-Task Unified XGBoost Solution for Brick Schema Classification.
• 15:55 - YDDM: A Unified CatBoost Framework for IoT Data Classification Using Multi-Level Feature Extraction.
• 16:20 - UNSW: Awards, Photos and Certificate.
• 16:30 - UNSW: Discussion on future collaborations.

Contact Us

• Arian Prabowo: arian dot prabowo at unsw dot edu dot au
• Hao Xue: hao dot xue1 at unsw dot edu dot au
• Flora D. Salim: flora dot salim at unsw dot edu dot au

Acknowledgement

This research is supported by the NSW Government through the CSIRO’s NSW Digital Infrastructure Energy Flexibility (DIEF) project, funded under the Net Zero Plan Stage 1: 2020-2030. This project is also funded by the Reliable Affordable Clean Energy for 2030 (RACE for 2030) Cooperative Research Centre. This competition is organised by UNSW Sydney with special thanks to UOW. This competition is hosted on AIcrowd.