Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection
Anomaly detection of time series has been widely used in various fields. Most detection methods depend either on assumptions about data distribution or manual threshold setting. If the assumption is incorrect, the effectiveness of detection technology will be greatly reduced. To deal with this probl...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8924632/ |
| _version_ | 1819174668176719872 |
|---|---|
| author | Yan Huang Fuyu Du Jian Chen Yan Chen Qicong Wang Maozhen Li |
| author_facet | Yan Huang Fuyu Du Jian Chen Yan Chen Qicong Wang Maozhen Li |
| author_sort | Yan Huang |
| collection | DOAJ |
| description | Anomaly detection of time series has been widely used in various fields. Most detection methods depend either on assumptions about data distribution or manual threshold setting. If the assumption is incorrect, the effectiveness of detection technology will be greatly reduced. To deal with this problem, we propose a maximum likelihood estimation method based on particle swarm optimization for generalized Pareto model to detect outliers of time series, which can be called Generalized Pareto Model Based on Particle Swarm Optimization (GPMPSO). Because the generalized Pareto model is multidimensional, we introduce a comprehensive learning strategy to improve search ability of particle swarm algorithm. Due to the multiple peaks of the log-likelihood function of generalized Pareto model, we apply dynamic neighbors to reduce the possibility of particle swarm optimization falling into local optimum. Moreover, we propose a new processing model Big Drift Streaming Peak Over Threshold (BDSPOT) to enhance the capability of the data stream processor. Our algorithm is tested on various real-world datasets which demonstrate its very competitive performance. |
| first_indexed | 2024-12-22T20:42:38Z |
| format | Article |
| id | doaj.art-f109e860247143c6b608319d6b6ca005 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:42:38Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f109e860247143c6b608319d6b6ca0052022-12-21T18:13:18ZengIEEEIEEE Access2169-35362019-01-01717632917633810.1109/ACCESS.2019.29578068924632Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly DetectionYan Huang0https://orcid.org/0000-0001-7868-093XFuyu Du1https://orcid.org/0000-0001-9651-971XJian Chen2https://orcid.org/0000-0002-0760-0338Yan Chen3https://orcid.org/0000-0003-0409-9485Qicong Wang4https://orcid.org/0000-0001-7324-0433Maozhen Li5https://orcid.org/0000-0002-0820-5487Shenzhen Research Institute, Xiamen University, Shenzhen, ChinaDepartment of Computer Science, Xiamen University, Xiamen, ChinaThird Institute of Oceanography Ministry of Natural Resources, Xiamen, ChinaCollege of Business and Management, Xiamen Huaxia University, Xiamen, ChinaShenzhen Research Institute, Xiamen University, Shenzhen, ChinaDepartment of Electronic and Computer Engineering, Brunel University, London UB83PH, U.K.Anomaly detection of time series has been widely used in various fields. Most detection methods depend either on assumptions about data distribution or manual threshold setting. If the assumption is incorrect, the effectiveness of detection technology will be greatly reduced. To deal with this problem, we propose a maximum likelihood estimation method based on particle swarm optimization for generalized Pareto model to detect outliers of time series, which can be called Generalized Pareto Model Based on Particle Swarm Optimization (GPMPSO). Because the generalized Pareto model is multidimensional, we introduce a comprehensive learning strategy to improve search ability of particle swarm algorithm. Due to the multiple peaks of the log-likelihood function of generalized Pareto model, we apply dynamic neighbors to reduce the possibility of particle swarm optimization falling into local optimum. Moreover, we propose a new processing model Big Drift Streaming Peak Over Threshold (BDSPOT) to enhance the capability of the data stream processor. Our algorithm is tested on various real-world datasets which demonstrate its very competitive performance.https://ieeexplore.ieee.org/document/8924632/Anomaly detectiongeneralized pareto distributionparticle swarm optimizationtime series |
| spellingShingle | Yan Huang Fuyu Du Jian Chen Yan Chen Qicong Wang Maozhen Li Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection IEEE Access Anomaly detection generalized pareto distribution particle swarm optimization time series |
| title | Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection |
| title_full | Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection |
| title_fullStr | Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection |
| title_full_unstemmed | Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection |
| title_short | Generalized Pareto Model Based on Particle Swarm Optimization for Anomaly Detection |
| title_sort | generalized pareto model based on particle swarm optimization for anomaly detection |
| topic | Anomaly detection generalized pareto distribution particle swarm optimization time series |
| url | https://ieeexplore.ieee.org/document/8924632/ |
| work_keys_str_mv | AT yanhuang generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection AT fuyudu generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection AT jianchen generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection AT yanchen generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection AT qicongwang generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection AT maozhenli generalizedparetomodelbasedonparticleswarmoptimizationforanomalydetection |