<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

A Comparative Analysis of Class Imbalance Handling Techniques for Deep Models in the Detection of Anomalies in Energy Consumption

dc.creatorAIRCC
dc.date2024-12-18
dc.date.accessioned2026-11-02T10:55:02Z
dc.description&lt;p&gt;Detecting anomalies in energy consumption is critical for efficient energy management, fault detection, and&lt;br&gt;sustainability. However, the challenge of class imbalance, where normal consumption data vastly&lt;br&gt;outweighs anomalous instances, presents significant difficulties in building accurate predictive models.&lt;br&gt;This paper conducts a comparative analysis of class imbalance handling techniques for deep models in&lt;br&gt;detecting anomalies in energy consumption data. Specifically, controlled experiments are used to evaluate&lt;br&gt;the performance of deep learning models, such as convolution neural networks (CNN), long short-term&lt;br&gt;memory (LSTM) and BiLSTM deep algorithms as well as synthetic data generation (SMOTE), costsensitive learning, and generative adversarial networks (GAN) tailored to address the imbalance issue.&lt;br&gt;Through a comprehensive empirical study using a real-world energy dataset, we assess the models'&lt;br&gt;effectiveness based on area under the curve (AUC), precision, recall, F1-score, and their ability to&lt;br&gt;generalize across different levels of imbalance. This research contributes to improving model selection for&lt;br&gt;practitioners facing the class imbalance challenge in the energy sector.&nbsp;&lt;/p&gt;
dc.identifierhttps://doi.org/10.5121/ijaia.2024.15602
dc.identifieroai:zenodo.org:14511611
dc.identifierhttps://doi.org/10.5121/ijaia.2024.15602
dc.identifier.urihttps://library.dare.co.zw/handle/123456789/4687
dc.languageeng
dc.publisherZenodo
dc.relationhttps://doi.org/10.5121/ijaia.2024.15602
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightsCreative Commons Attribution 4.0 International
dc.rightshttps://creativecommons.org/licenses/by/4.0/legalcode
dc.sourceInternational Journal of Artificial Intelligence & Applications (IJAIA), 15(6), 13-29, (2024-12-18)
dc.titleA Comparative Analysis of Class Imbalance Handling Techniques for Deep Models in the Detection of Anomalies in Energy Consumption
dc.typeinfo:eu-repo/semantics/article

Files

Collections