Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System
The biggest problem with conventional anomaly signal detection using features was that it was difficult to use it in real time and it requires processing of network signals. Furthermore, analyzing network signals in real-time required vast amounts of processing for each signal, as each protocol cont...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/12/4237 |
| _version_ | 1797529398738419712 |
|---|---|
| author | Hoon Ko Kwangcheol Rim Isabel Praça |
| author_facet | Hoon Ko Kwangcheol Rim Isabel Praça |
| author_sort | Hoon Ko |
| collection | DOAJ |
| description | The biggest problem with conventional anomaly signal detection using features was that it was difficult to use it in real time and it requires processing of network signals. Furthermore, analyzing network signals in real-time required vast amounts of processing for each signal, as each protocol contained various pieces of information. This paper suggests anomaly detection by analyzing the relationship among each feature to the anomaly detection model. The model analyzes the anomaly of network signals based on anomaly feature detection. The selected feature for anomaly detection does not require constant network signal updates and real-time processing of these signals. When the selected features are found in the received signal, the signal is registered as a potential anomaly signal and is then steadily monitored until it is determined as either an anomaly or normal signal. In terms of the results, it determined the anomaly with 99.7% (0.997) accuracy in <i>f(4)(S0)</i> and in case <i>f(4)(REJ)</i> received 11,233 signals with a normal or 171anomaly judgment accuracy of 98.7% (0.987). |
| first_indexed | 2024-03-10T10:13:17Z |
| format | Article |
| id | doaj.art-0bc3496df0b3462bbfc320a94fcc3269 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:13:17Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0bc3496df0b3462bbfc320a94fcc32692023-11-22T01:00:01ZengMDPI AGSensors1424-82202021-06-012112423710.3390/s21124237Influence of Features on Accuracy of Anomaly Detection for an Energy Trading SystemHoon Ko0Kwangcheol Rim1Isabel Praça2Instituto Superior de Engenharia do Porto, Instituto Politecnico do Porto, R. Dr. Antonio Bernardino de Almeida, 431, 4249-015 Porto, PortugalCollege of Basic & General Education, Chosun University, 309 Pilmundae-ro, Dong-Gu, Gwangju 61452, KoreaInstituto Superior de Engenharia do Porto, Instituto Politecnico do Porto, R. Dr. Antonio Bernardino de Almeida, 431, 4249-015 Porto, PortugalThe biggest problem with conventional anomaly signal detection using features was that it was difficult to use it in real time and it requires processing of network signals. Furthermore, analyzing network signals in real-time required vast amounts of processing for each signal, as each protocol contained various pieces of information. This paper suggests anomaly detection by analyzing the relationship among each feature to the anomaly detection model. The model analyzes the anomaly of network signals based on anomaly feature detection. The selected feature for anomaly detection does not require constant network signal updates and real-time processing of these signals. When the selected features are found in the received signal, the signal is registered as a potential anomaly signal and is then steadily monitored until it is determined as either an anomaly or normal signal. In terms of the results, it determined the anomaly with 99.7% (0.997) accuracy in <i>f(4)(S0)</i> and in case <i>f(4)(REJ)</i> received 11,233 signals with a normal or 171anomaly judgment accuracy of 98.7% (0.987).https://www.mdpi.com/1424-8220/21/12/4237anomaly signalanomaly detectionfeature analysiscyber-attack |
| spellingShingle | Hoon Ko Kwangcheol Rim Isabel Praça Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System Sensors anomaly signal anomaly detection feature analysis cyber-attack |
| title | Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System |
| title_full | Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System |
| title_fullStr | Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System |
| title_full_unstemmed | Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System |
| title_short | Influence of Features on Accuracy of Anomaly Detection for an Energy Trading System |
| title_sort | influence of features on accuracy of anomaly detection for an energy trading system |
| topic | anomaly signal anomaly detection feature analysis cyber-attack |
| url | https://www.mdpi.com/1424-8220/21/12/4237 |
| work_keys_str_mv | AT hoonko influenceoffeaturesonaccuracyofanomalydetectionforanenergytradingsystem AT kwangcheolrim influenceoffeaturesonaccuracyofanomalydetectionforanenergytradingsystem AT isabelpraca influenceoffeaturesonaccuracyofanomalydetectionforanenergytradingsystem |