HCCVOct 30, 2019

Outliagnostics: Visualizing Temporal Discrepancy in Outlying Signatures of Data Entries

arXiv:1910.13656v111 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of interactively exploring abnormalities in large time series for users in data analysis, but it appears incremental as it builds on existing outlier detection methods.

The paper tackles the problem of identifying significant observations in temporal datasets by monitoring discrepant temporal signatures of data entries, and presents a prototype called Outliagnostics that improves performance through parallel processing, validated on real-world datasets of various sizes.

This paper presents an approach to analyzing two-dimensional temporal datasets focusing on identifying observations that are significant in calculating the outliers of a scatterplot. We also propose a prototype, called Outliagnostics, to guide users when interactively exploring abnormalities in large time series. Instead of focusing on detecting outliers at each time point, we monitor and display the discrepant temporal signatures of each data entry concerning the overall distributions. Our prototype is designed to handle these tasks in parallel to improve performance. To highlight the benefits and performance of our approach, we illustrate and validate the use of Outliagnostics on real-world datasets of various sizes in different parallelism configurations. This work also discusses how to extend these ideas to handle time series with a higher number of dimensions and provides a prototype for this type of datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes