Autoencoder and Incremental Clustering-Enabled Anomaly Detection
Many machine-learning-enabled approaches towards anomaly detection depend on the availability of vast training data. Our data are formed from power readings of cycles from domestic appliances, such as dishwashers or washing machines, and contain no known examples of anomalous behaviour. Moreover, we...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/1970 |
| _version_ | 1797602733638811648 |
|---|---|
| author | Andrew Charles Connelly Syed Ali Raza Zaidi Des McLernon |
| author_facet | Andrew Charles Connelly Syed Ali Raza Zaidi Des McLernon |
| author_sort | Andrew Charles Connelly |
| collection | DOAJ |
| description | Many machine-learning-enabled approaches towards anomaly detection depend on the availability of vast training data. Our data are formed from power readings of cycles from domestic appliances, such as dishwashers or washing machines, and contain no known examples of anomalous behaviour. Moreover, we are limited to the machine’s voltage, amperage, and current readings, drawn from a retrofitted power outlet in 60-s samples. No rich sensor data or previous insights are available as a training basis, limiting our ability to leverage the existing work. We design a system to monitor the behaviour of electrical appliances. This system requires special consideration as different power cycles from the same machine can exhibit different behaviours, and it accounts for this by clustering unseen cycle patterns into siloed training datasets and corresponding learned parameters. They are then passed in real-time to an autoencoder ensemble for reconstruction-based anomaly detection, using the error in reconstruction as a means to flag anomalous points in time. The system correctly identifies and trains appropriate cycle clusters of data streams on a real-world machine dataset injected with stochastic, proportionate anomalies. |
| first_indexed | 2024-03-11T04:20:47Z |
| format | Article |
| id | doaj.art-07e8a980723f493e9b380949deef9f80 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:20:47Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-07e8a980723f493e9b380949deef9f802023-11-17T22:46:56ZengMDPI AGElectronics2079-92922023-04-01129197010.3390/electronics12091970Autoencoder and Incremental Clustering-Enabled Anomaly DetectionAndrew Charles Connelly0Syed Ali Raza Zaidi1Des McLernon2School of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UKSchool of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UKSchool of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UKMany machine-learning-enabled approaches towards anomaly detection depend on the availability of vast training data. Our data are formed from power readings of cycles from domestic appliances, such as dishwashers or washing machines, and contain no known examples of anomalous behaviour. Moreover, we are limited to the machine’s voltage, amperage, and current readings, drawn from a retrofitted power outlet in 60-s samples. No rich sensor data or previous insights are available as a training basis, limiting our ability to leverage the existing work. We design a system to monitor the behaviour of electrical appliances. This system requires special consideration as different power cycles from the same machine can exhibit different behaviours, and it accounts for this by clustering unseen cycle patterns into siloed training datasets and corresponding learned parameters. They are then passed in real-time to an autoencoder ensemble for reconstruction-based anomaly detection, using the error in reconstruction as a means to flag anomalous points in time. The system correctly identifies and trains appropriate cycle clusters of data streams on a real-world machine dataset injected with stochastic, proportionate anomalies.https://www.mdpi.com/2079-9292/12/9/1970autoencoderanomaly detectionclusteringtime seriesunsupervised |
| spellingShingle | Andrew Charles Connelly Syed Ali Raza Zaidi Des McLernon Autoencoder and Incremental Clustering-Enabled Anomaly Detection Electronics autoencoder anomaly detection clustering time series unsupervised |
| title | Autoencoder and Incremental Clustering-Enabled Anomaly Detection |
| title_full | Autoencoder and Incremental Clustering-Enabled Anomaly Detection |
| title_fullStr | Autoencoder and Incremental Clustering-Enabled Anomaly Detection |
| title_full_unstemmed | Autoencoder and Incremental Clustering-Enabled Anomaly Detection |
| title_short | Autoencoder and Incremental Clustering-Enabled Anomaly Detection |
| title_sort | autoencoder and incremental clustering enabled anomaly detection |
| topic | autoencoder anomaly detection clustering time series unsupervised |
| url | https://www.mdpi.com/2079-9292/12/9/1970 |
| work_keys_str_mv | AT andrewcharlesconnelly autoencoderandincrementalclusteringenabledanomalydetection AT syedalirazazaidi autoencoderandincrementalclusteringenabledanomalydetection AT desmclernon autoencoderandincrementalclusteringenabledanomalydetection |