RODA: A Fast Outlier Detection Algorithm Supporting Multi-Queries

Abstract

Outlier detection is an important task in the field of big data analysis. The technology has been extensively used in network security, sensor data analysis, public health and so on. In an outlier detection system, with the continuous expansion of upper-layer applications, a system needs to process a large number of query requests in a very short time, which places high requirements on the timeliness of outlier detection algorithms. To solve this problem, in this paper, an efficient algorithm, R-tree based Outlier Detection Algorithm (RODA), is proposed, which can effectively support single query and multiple query processing. For single query processing, we first extended the R-tree index and proposed a new outlier estimation method. Using the techniques above, the algorithm greatly reduces the retrieval space by preferentially scanning data points with high outlier-degrees. For multiple query processing, the algorithm deeply analyzes the sharing mechanism between multiple queries in order to handle multiple detection tasks within one processing. Finally, experiment results show that the RODA proposed in this paper has improved operating efficiency, and has good applicability and practical significance.