Imitates
Résumé
Imitates is a complete solution for similarity search over very large time series datasets (Terabytes). It implements two efficient approaches for time series indexing and querying: DPiSAX and parSketch. DPiSAX is a parallel solution developed to construct iSAX-based index over billions of time series by making the most of the parallel environment by carefully distributing the work load. The other approach, i.e., parSketch, is based on sketches / random projections to efficiently perform both the parallel indexing of large sets of time series and a similarity search on them. Our solutions take advantage of the computing power of distributed systems by using the Spark parallel framework. The experiments illustrate the high performance of our index construction solution with an indexing time of less than 2 hours for more than 1 billion time series, while the baseline centralized algorithm needs more than 5 days.
