Comparing human and algorithmic anomaly detection for HVAC systems applications

This paper reports the first results of a comparison of human and algorithmic anomaly detection. We are interested in how human and automated anomaly detection can be combined in the most beneficial way to improve how fault detection is practiced in building maintenance. Open source datasets with se...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE Eighth International Conference on Big Data Computing Service and Applications (BigDataService) pp. 155 - 160
Main Authors Borrison, Reuben, Syndicus, Marc, Orth, Andre, Markovic, Romana, Dix, Marcel, Liguori, Antonio, Berning, Matthias, Wagner, Andreas, Van Treeck, Christoph
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.08.2022
Subjects
Annotation
Anomaly detection
Buildings
Fault detection
HVAC
Maintenance engineering
Measurement
Neural networks
Predictive fault detection and diagnosis
Predictive maintenance
Time series analysis
Online AccessGet full text
DOI10.1109/BigDataService55688.2022.00032

Cover

More Information
Summary:This paper reports the first results of a comparison of human and algorithmic anomaly detection. We are interested in how human and automated anomaly detection can be combined in the most beneficial way to improve how fault detection is practiced in building maintenance. Open source datasets with sensor data were annotated by persons with low subject matter experience, and compared with a Convolutional Autoencoder Neural Network (CAE) as well as a dedicated time series algorithm (DeepAnT), and detection metrics of human and algorithmic procedures are compared. Future comparisons will include higher levels of expertise on the human side, and more sophistication/training amount on the algorithm side. We close by discussing the advantages and caveats of our approach.
DOI:10.1109/BigDataService55688.2022.00032