Document Type
Article
Publication Date
11-30-2021
Publication Source
European Journal of Advances in Engineering and Technology
Abstract
This study investigates the utilization of Artificial Neural Networks (ANNs) for occupancy detection to optimize Heating, Ventilating, and Air Conditioning (HVAC) energy consumption. Leveraging environmental factors such as temperature, humidity, light, and CO2 levels, alongside occupancy status, various ANN architectures' efficacy in accurately predicting room occupancy is evaluated. The research involves comprehensive data analysis, including exploratory data analysis (EDA) and model evaluation on training, validation, and test datasets. The study demonstrates the potential of ANN-based occupancy detection in enhancing HVAC system efficiency by dynamically adjusting heating, cooling, and ventilation settings based on real-time occupancy information. Practical implications and future research directions for integrating ANN-based occupancy detection into HVAC control systems to achieve energy savings and environmental sustainability are discussed.
ISBN/ISSN
2394-658X
Copyright
This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Volume
8
Issue
11
Keywords
HVAC energy efficiency, Artificial Neural Networks (ANNs), occupancy detection, environmental factors, temperature, humidity, light, CO2 levels, room occupancy prediction, data analysis, Exploratory data analysis (EDA), model evaluation, training, validation, and test datasets, energy savings, environmental sustainability, building automation, optimization strategies
eCommons Citation
Sharma, Vibhu, "Enhancing HVAC Energy Efficiency Using Artificial Neural Network-Based Occupancy Detection" (2021). Mechanical and Aerospace Engineering Graduate Student Publications. 20.
https://ecommons.udayton.edu/mee_grad_pub/20
COinS
Comments
The document available for download is the published version, provided in compliance with the publisher's open-access policy. Permission documentation is on file. DOI: https://doi.org/10.5281/zenodo.11103770