Visual analysis system for association-based outlier detection for data streams

Abstract

The existence of outliers will reduce the reliability of original data streams, thus adversely affecting data-based operations. Through the interpretation and analysis of outliers, users can clarify the difference between the normal data and outliers, thus clearing outliers to improve the reliability of original data streams. However, there are few explanations and analyses on the reasons of outliers. The contribution of this paper is that we have designed a visual analysis system for outlier detection of data streams based on association, VooddS, which can reasonably explain and analyze outliers from two aspects of algorithm operation process and data distribution, and better show users why data instances are judged as outliers. VooddS system starts from the running process of the algorithm and designs a visual forms according to the running process of outlier detection algorithm, so as to reasonably explain the reason for determining outliers to users; From the point of view of data distribution, a combination of box graph, broken line and histogram is designed, and the correlation between data and outlier degree is analyzed from two levels of data attribute and data tuple, which helps users to explore the influence of context data on outlier judgment. In addition, the effectiveness of the system is verified by real data sets, and the results show that VooddS can reasonably explain abnormal values, and the interactive mode of the system can bring better experience to users.