Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/23746
Title: | Machine learning for text classification in building management systems |
Authors: | Mesa-Jiménez, JJ Stokes, L Yang, Q Livina, VN |
Keywords: | free-text classification;building management systems;haystack data standard;sensor tagging |
Issue Date: | 12-May-2022 |
Publisher: | Vilnius Gediminas Technical University |
Citation: | Mesa-Jiménez, J.J. et al. (2022) 'Machine learning for text classification in building management systems', Journal of Civil Engineering and Management, 28 (5), pp. 408 - 421 (14). doi: 10.3846/jcem.2022.16012. |
Abstract: | Copyright © 2022 The Author(s). In building management systems (BMS), a medium building may have between 200 and 1000 sensor points. Their labels need to be translated into a naming standard so they can be automatically recognised by the BMS platform. The current industrial practices often manually translate these points into labels (this is known as the tagging process), which takes around 8 hours for every 100 points. We introduce an AI-based multi-stage text classification that translates BMS points into formatted BMS labels. After comparing five different techniques for text classification (logistic regression, random forests, XGBoost, multinomial Naive Bayes and linear support vector classification), we demonstrate that XGBoost is the top performer with 90.29% of true positives, and use the prediction confidence to filter out false positives. This approach can be applied in sensors networks in various applications, where manual free-text data pre-processing remains cumbersome. |
URI: | https://bura.brunel.ac.uk/handle/2438/23746 |
DOI: | https://doi.org/10.3846/jcem.2022.16012 |
ISSN: | 1392-3730 |
Other Identifiers: | ORCiD: J.J. Mesa-Jiménez https://orcid.org/0000-0003-0822-2700 ORCiD: Qingping Yang https://orcid.org/0000-0002-2557-8752 |
Appears in Collections: | Dept of Mechanical and Aerospace Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © 2022 The Author(s). Published under licence by Vilnius Gediminas Technical University. This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). | 812.69 kB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License