Abstract
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.
Highlights
Detection has been one of the most important research topics for a long time because it has the nature of ubiquity
Based on the above analysis, we develop the Particle Swarm Optimization (PSO) algorithm based on dynamic neighbors and comprehensive learning strategy to solve the optimal solution of Maximum Likelihood Estimation (MLE)
We propose a Big Drift Streaming Peak Over Threshold (BDSPOT) detection model, which can update the drift according to the distribution of data
Summary
Detection has been one of the most important research topics for a long time because it has the nature of ubiquity. It is sometimes difficult to find its root by calculation We treat it as an optimal problem, and take advantage of Particle Swarm Optimization (PSO) to find the optimal solution. In PSO algorithm, every particle represents a probable solution. It tends to trap in local optimal solutions To this end, many researchers proposed improved PSO algorithms [17]–[19]. It is known that the topological structure in traditional PSO algorithm is static, the learning sample of each particle is fixed as well. Based on the above analysis, we develop the PSO algorithm based on dynamic neighbors and comprehensive learning strategy to solve the optimal solution of MLE. We propose a BDSPOT detection model, which can update the drift according to the distribution of data
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
