Anomaly detection algorithm based on Gaussian mixture variational auto encoder network
Anomalous data, which deviates from a large number of normal data, has a negative impact and contains a risk on various systems.Anomaly detection can detect anomalies in the data and provide important support for the normal operation of various systems, which has important practical significance.An...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2021-04-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021044/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529069810745344 |
|---|---|
| author | Huahua CHEN Zhe CHEN Chunsheng GUO Na YING Xueyi YE Jianwu ZHANG |
| author_facet | Huahua CHEN Zhe CHEN Chunsheng GUO Na YING Xueyi YE Jianwu ZHANG |
| author_sort | Huahua CHEN |
| collection | DOAJ |
| description | Anomalous data, which deviates from a large number of normal data, has a negative impact and contains a risk on various systems.Anomaly detection can detect anomalies in the data and provide important support for the normal operation of various systems, which has important practical significance.An anomaly detection algorithm based on Gaussian mixture variational auto encoder network was proposed, in which a variational autoencoder was built to extract the features of the input data based on Gaussian mixture distribution, and using this variational autoencoder to construct a deep support vector network to compress the feature space and find the minimum hyper sphere to separate the normal data and the abnormal data.Anomalies can be detected by the score from the Euclidean distance from the feature of data to the center of the hypersphere.The proposed algorithm was evaluated on the benchmark datasets MNIST and Fashion-MNIST, and the corresponding average AUC are 0.954 and 0.937 respectively.The experimental results show that the proposed algorithm achieves preferable effects. |
| format | Article |
| id | doaj-art-125733ab3a094cf893a7dd47e66a3a84 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2021-04-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-125733ab3a094cf893a7dd47e66a3a842025-01-15T03:26:06ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012021-04-0137546159807605Anomaly detection algorithm based on Gaussian mixture variational auto encoder networkHuahua CHENZhe CHENChunsheng GUONa YINGXueyi YEJianwu ZHANGAnomalous data, which deviates from a large number of normal data, has a negative impact and contains a risk on various systems.Anomaly detection can detect anomalies in the data and provide important support for the normal operation of various systems, which has important practical significance.An anomaly detection algorithm based on Gaussian mixture variational auto encoder network was proposed, in which a variational autoencoder was built to extract the features of the input data based on Gaussian mixture distribution, and using this variational autoencoder to construct a deep support vector network to compress the feature space and find the minimum hyper sphere to separate the normal data and the abnormal data.Anomalies can be detected by the score from the Euclidean distance from the feature of data to the center of the hypersphere.The proposed algorithm was evaluated on the benchmark datasets MNIST and Fashion-MNIST, and the corresponding average AUC are 0.954 and 0.937 respectively.The experimental results show that the proposed algorithm achieves preferable effects.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021044/anomaly detectionvariational autoencoderGaussian mixture distributionhypersphere |
| spellingShingle | Huahua CHEN Zhe CHEN Chunsheng GUO Na YING Xueyi YE Jianwu ZHANG Anomaly detection algorithm based on Gaussian mixture variational auto encoder network Dianxin kexue anomaly detection variational autoencoder Gaussian mixture distribution hypersphere |
| title | Anomaly detection algorithm based on Gaussian mixture variational auto encoder network |
| title_full | Anomaly detection algorithm based on Gaussian mixture variational auto encoder network |
| title_fullStr | Anomaly detection algorithm based on Gaussian mixture variational auto encoder network |
| title_full_unstemmed | Anomaly detection algorithm based on Gaussian mixture variational auto encoder network |
| title_short | Anomaly detection algorithm based on Gaussian mixture variational auto encoder network |
| title_sort | anomaly detection algorithm based on gaussian mixture variational auto encoder network |
| topic | anomaly detection variational autoencoder Gaussian mixture distribution hypersphere |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021044/ |
| work_keys_str_mv | AT huahuachen anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork AT zhechen anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork AT chunshengguo anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork AT naying anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork AT xueyiye anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork AT jianwuzhang anomalydetectionalgorithmbasedongaussianmixturevariationalautoencodernetwork |