当前位置: X-MOL 学术Stat. Anal. Data Min. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Online embedding and clustering of evolving data streams
Statistical Analysis and Data Mining ( IF 2.1 ) Pub Date : 2022-07-06 , DOI: 10.1002/sam.11590
Alaettin Zubaroğlu 1 , Volkan Atalay 1
Affiliation  

Number of connected devices is steadily increasing and this trend is expected to continue in the near future. Connected devices continuously generate data streams and the data streams may often be high dimensional and contain concept drift. Clustering is one of the most suitable methods for real-time data stream processing, since clustering can be applied with less prior information about the data. Also, data embedding makes the visualization of high dimensional data possible and may simplify clustering process. There exist several data stream clustering algorithms in the literature; however, no data stream embedding method exists. Uniform Manifold Approximation and Projection (UMAP) is a data embedding algorithm that is suitable to be applied on stationary (stable) data streams, though it cannot adapt concept drift. In this study, we describe a novel method EmCStream, to apply UMAP on evolving (nonstationary) data streams, to detect and adapt concept drift and to cluster embedded data instances using a distance or partitioning-based clustering algorithm. We have evaluated EmCStream against the state-of-the-art stream clustering algorithms using both synthetic and real data streams containing concept drift. EmCStream outperforms DenStream and CluStream, in terms of clustering quality, on both synthetic and real evolving data streams. Datasets and code of this study are available online at https://gitlab.com/alaettinzubaroglu/emcstream.

中文翻译:

进化数据流的在线嵌入和聚类

连接设备的数量正在稳步增加,预计这种趋势在不久的将来会持续下去。连接的设备不断地产生数据流,并且数据流通常可能是高维的并且包含概念漂移。聚类是最适合实时数据流处理的方法之一,因为聚类可以在有关数据的先验信息较少的情况下应用。此外,数据嵌入使高维数据的可视化成为可能,并可以简化聚类过程。文献中存在几种数据流聚类算法;但是,不存在数据流嵌入方法。均匀流形逼近和投影 (UMAP) 是一种数据嵌入算法,适用于固定(稳定)数据流,但它不能适应概念漂移。在这项研究中,我们描述了一种新方法 EmCStream,将 UMAP 应用于不断发展的(非平稳)数据流,检测和适应概念漂移,并使用基于距离或分区的聚类算法对嵌入式数据实例进行聚类。我们使用包含概念漂移的合成和真实数据流,针对最先进的流聚类算法评估了 EmCStream。EmCStream 在聚类质量方面优于 DenStream 和 CluStream,无论是在合成数据流还是真实演化数据流上。本研究的数据集和代码可在 https://gitlab.com/alaettizzbaroglu/emcstream 在线获取。我们使用包含概念漂移的合成和真实数据流,针对最先进的流聚类算法评估了 EmCStream。EmCStream 在聚类质量方面优于 DenStream 和 CluStream,无论是在合成数据流还是真实演化数据流上。本研究的数据集和代码可在 https://gitlab.com/alaettizzbaroglu/emcstream 在线获取。我们使用包含概念漂移的合成和真实数据流,针对最先进的流聚类算法评估了 EmCStream。EmCStream 在聚类质量方面优于 DenStream 和 CluStream,无论是在合成数据流还是真实演化数据流上。本研究的数据集和代码可在 https://gitlab.com/alaettizzbaroglu/emcstream 在线获取。
更新日期:2022-07-06
down
wechat
bug