提出了快速的基于距离的数据流离群点检测算法。该算法使用滑动窗口模型处理数据流,并利用向量内积不等式进行剪枝,在保证正确性的前提下,显著的提高了执行效率。实验表明,该算法是有效可行的。
A fast distance-based outlier detection algorithm for stream data (FDODS) is proposed, under sliding-window model. By using the pretreatment of vectors' inner-product, some redundant calculation process is reduced with good correctness. The experiments show that, this algorithm is feasible and effective.