Data Series Indexing Gone Parallel

TL;DR

This paper introduces parallel indexing methods for data series similarity search that leverage multi-core architectures, significantly improving processing times for large datasets and enabling real-time data exploration.

Contribution

First to propose multi-core optimized indexing solutions for data series similarity search on both disk and memory, vastly outperforming existing methods.

Findings

On-disk solution answers 100GB queries in seconds

In-memory solution answers in milliseconds

Enables real-time interactive data exploration

Abstract

Data series similarity search is a core operation for several data series analysis applications across many different domains. However, the state-of-the-art techniques fail to deliver the time performance required for interactive exploration, or analysis of large data series collections. In this Ph.D. work, we present the first data series indexing solutions, for both on-disk and in-memory data, that are designed to inherently take advantage of multi-core architectures, in order to accelerate similarity search processing times. Our experiments on a variety of synthetic and real data demonstrate that our approaches are up to orders of magnitude faster than the alternatives. More specifically, our on-disk solution can answer exact similarity search queries on 100GB datasets in a few seconds, and our in-memory solution in a few milliseconds, which enables real-time, interactive data exploration on very large data series collections.