Data-Driven End-to-End Lighting Automation Based on Human Residential Trajectory Analysis
Publication Date
1-1-2024
Document Type
Conference Proceeding
Publication Title
2024 International Conference on Smart Applications, Communications and Networking, SmartNets 2024
DOI
10.1109/SmartNets61466.2024.10577722
Abstract
Smart home automation, particularly in lighting, holds the potential to significantly improve comfort, energy efficiency, and security by centralizing control over internet-of-things (loT) devices. This paper introduces a smart lighting automation system that analyzes human movement trajectories using machine learning, deep learning, and reinforcement learning techniques integrated into the Home Assistant platform. In particular, we introduce a transformer-based deep neural network architecture with reward-based tuning as our backbone model. The system predicts the user's next location and adjusts the lighting accordingly based on the anticipated movement trajectories derived from data collected by loT devices distributed throughout a residential area. This enhances both convenience and energy efficiency. We deployed the system in a residential setting and conducted experiments to validate its accuracy.
Funding Number
RINGS-2148353
Keywords
Automation, Machine Learning, Smart Home, Transformer
Department
Computer Engineering
Recommended Citation
Jack Zhu, Jingwen Tan, and Wencen Wu. "Data-Driven End-to-End Lighting Automation Based on Human Residential Trajectory Analysis" 2024 International Conference on Smart Applications, Communications and Networking, SmartNets 2024 (2024). https://doi.org/10.1109/SmartNets61466.2024.10577722
