Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy
This paper proposes a novel network anomaly detection framework based on data balance and feature selection. Different from the previous binary classification of network intrusion, the network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/13/4751 |
| _version_ | 1797480193431961600 |
|---|---|
| author | Yong Sun Huakun Que Qianqian Cai Jingming Zhao Jingru Li Zhengmin Kong Shuai Wang |
| author_facet | Yong Sun Huakun Que Qianqian Cai Jingming Zhao Jingru Li Zhengmin Kong Shuai Wang |
| author_sort | Yong Sun |
| collection | DOAJ |
| description | This paper proposes a novel network anomaly detection framework based on data balance and feature selection. Different from the previous binary classification of network intrusion, the network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network intrusion. Regarding the common data imbalance of a network intrusion detection set, a resampling strategy generated by random sampling and Borderline SMOTE data is developed for data balance. According to the features of the intrusion detection dataset, feature selection is carried out based on information gain rate. Experiments are carried out on three basic machine learning algorithms (K-nearest neighbor algorithm (KNN), decision tree (DT), random forest (RF)), and the optimal feature selection scheme is obtained. |
| first_indexed | 2024-03-09T21:56:32Z |
| format | Article |
| id | doaj.art-434e90f917554ad996f92b4f87dde2d1 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T21:56:32Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-434e90f917554ad996f92b4f87dde2d12023-11-23T19:56:47ZengMDPI AGEnergies1996-10732022-06-011513475110.3390/en15134751Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection StrategyYong Sun0Huakun Que1Qianqian Cai2Jingming Zhao3Jingru Li4Zhengmin Kong5Shuai Wang6Metrology Center of Guangdong Power Grid Co., Ltd., Guangzhou 510600, ChinaMetrology Center of Guangdong Power Grid Co., Ltd., Guangzhou 510600, ChinaMetrology Center of Guangdong Power Grid Co., Ltd., Guangzhou 510600, ChinaMetrology Center of Guangdong Power Grid Co., Ltd., Guangzhou 510600, ChinaMetrology Center of Guangdong Power Grid Co., Ltd., Guangzhou 510600, ChinaSchool of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, ChinaChina Southern Power Grid Power Technology Co., Ltd., Guangzhou 510600, ChinaThis paper proposes a novel network anomaly detection framework based on data balance and feature selection. Different from the previous binary classification of network intrusion, the network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network intrusion. Regarding the common data imbalance of a network intrusion detection set, a resampling strategy generated by random sampling and Borderline SMOTE data is developed for data balance. According to the features of the intrusion detection dataset, feature selection is carried out based on information gain rate. Experiments are carried out on three basic machine learning algorithms (K-nearest neighbor algorithm (KNN), decision tree (DT), random forest (RF)), and the optimal feature selection scheme is obtained.https://www.mdpi.com/1996-1073/15/13/4751network intrusion detectionmachine learningborderline SMOTEinformation gain ratio |
| spellingShingle | Yong Sun Huakun Que Qianqian Cai Jingming Zhao Jingru Li Zhengmin Kong Shuai Wang Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy Energies network intrusion detection machine learning borderline SMOTE information gain ratio |
| title | Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy |
| title_full | Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy |
| title_fullStr | Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy |
| title_full_unstemmed | Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy |
| title_short | Borderline SMOTE Algorithm and Feature Selection-Based Network Anomalies Detection Strategy |
| title_sort | borderline smote algorithm and feature selection based network anomalies detection strategy |
| topic | network intrusion detection machine learning borderline SMOTE information gain ratio |
| url | https://www.mdpi.com/1996-1073/15/13/4751 |
| work_keys_str_mv | AT yongsun borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT huakunque borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT qianqiancai borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT jingmingzhao borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT jingruli borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT zhengminkong borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy AT shuaiwang borderlinesmotealgorithmandfeatureselectionbasednetworkanomaliesdetectionstrategy |