A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets
The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series tasks due to difficulties in fusing temporal data from multiple sources. However, in a...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10290724/ |
_version_ | 1797635397387288576 |
---|---|
author | Ayman Elhalwagy Tatiana Kalganova |
author_facet | Ayman Elhalwagy Tatiana Kalganova |
author_sort | Ayman Elhalwagy |
collection | DOAJ |
description | The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series tasks due to difficulties in fusing temporal data from multiple sources. However, in a commercial environment, generalisation can effectively utilise available data and computational power which is essential to Green AI, the sustainable development of AI models. This paper introduces “Dataset Fusion,” a novel dataset composition algorithm for fusing periodic signals from multiple homogeneous datasets whilst retaining unique features for generalised anomaly detection. The proposed approach, tested on a case study of three-phase current data from two different homogeneous Induction Motor (IM) fault datasets on anomaly detection, outperforms conventional training approaches with an Average F1 score of 0.879 and effectively generalises across all datasets. Furthermore, when tested with varying percentages of the training data, results show that using only 6.25% of the training data, translating to a 93.7% reduction in computational power, results in only a 4.04% decrease in performance, demonstrating the advantages of the proposed approach in terms of both performance and computational efficiency. Moreover, the algorithm’s effectiveness under imperfect conditions highlights its potential for use in real-world applications. |
first_indexed | 2024-03-11T12:21:29Z |
format | Article |
id | doaj.art-2c3a85b1776048b3a5120924f3e979ab |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-11T12:21:29Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-2c3a85b1776048b3a5120924f3e979ab2023-11-07T00:01:12ZengIEEEIEEE Access2169-35362023-01-011112121212123010.1109/ACCESS.2023.332672510290724A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series DatasetsAyman Elhalwagy0https://orcid.org/0000-0003-0772-9059Tatiana Kalganova1https://orcid.org/0000-0003-4859-7152Department of Electronic and Electrical Engineering, CEDPS, Brunel University London, Uxbridge, U.K.Department of Electronic and Electrical Engineering, CEDPS, Brunel University London, Uxbridge, U.K.The generalisation of Neural Networks (NN) to multiple datasets is often overlooked in literature due to NNs typically being optimised for specific data sources. This becomes especially challenging in time-series tasks due to difficulties in fusing temporal data from multiple sources. However, in a commercial environment, generalisation can effectively utilise available data and computational power which is essential to Green AI, the sustainable development of AI models. This paper introduces “Dataset Fusion,” a novel dataset composition algorithm for fusing periodic signals from multiple homogeneous datasets whilst retaining unique features for generalised anomaly detection. The proposed approach, tested on a case study of three-phase current data from two different homogeneous Induction Motor (IM) fault datasets on anomaly detection, outperforms conventional training approaches with an Average F1 score of 0.879 and effectively generalises across all datasets. Furthermore, when tested with varying percentages of the training data, results show that using only 6.25% of the training data, translating to a 93.7% reduction in computational power, results in only a 4.04% decrease in performance, demonstrating the advantages of the proposed approach in terms of both performance and computational efficiency. Moreover, the algorithm’s effectiveness under imperfect conditions highlights its potential for use in real-world applications.https://ieeexplore.ieee.org/document/10290724/Generalisationdataset fusiondata reductionanomaly detectionneural network traininggreen AI |
spellingShingle | Ayman Elhalwagy Tatiana Kalganova A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets IEEE Access Generalisation dataset fusion data reduction anomaly detection neural network training green AI |
title | A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets |
title_full | A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets |
title_fullStr | A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets |
title_full_unstemmed | A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets |
title_short | A Dataset Fusion Algorithm for Generalised Anomaly Detection in Homogeneous Periodic Time Series Datasets |
title_sort | dataset fusion algorithm for generalised anomaly detection in homogeneous periodic time series datasets |
topic | Generalisation dataset fusion data reduction anomaly detection neural network training green AI |
url | https://ieeexplore.ieee.org/document/10290724/ |
work_keys_str_mv | AT aymanelhalwagy adatasetfusionalgorithmforgeneralisedanomalydetectioninhomogeneousperiodictimeseriesdatasets AT tatianakalganova adatasetfusionalgorithmforgeneralisedanomalydetectioninhomogeneousperiodictimeseriesdatasets AT aymanelhalwagy datasetfusionalgorithmforgeneralisedanomalydetectioninhomogeneousperiodictimeseriesdatasets AT tatianakalganova datasetfusionalgorithmforgeneralisedanomalydetectioninhomogeneousperiodictimeseriesdatasets |