Project: Time-series search: to index or not to index
Description
Time series data is widely generated and used across various fields, including healthcare, finance, and surveillance. For example, in the stock market, the changes in stock prices throughout the day form a time series. In such contexts, it is often important to perform searches—either to find time series that are similar to a given example (the query), or to identify sub-sequences within time series that resemble the query. To support these tasks, many indexing methods and exhaustive search algorithms have been proposed in the literature. Choosing the most suitable approach for a specific use case is a challenging problem. In this thesis, you will: (a) review relevant literature, (b) design and implement a model that uses statistical characteristics of the time series data and the workload to decide which search method is most appropriate for each scenario, and (c) evaluate this model.
Requirements: Coding in java, ability to read and understand scientific papers that describe algorithms.
Details
- Supervisor
-
Odysseas Papapetrou
- Interested?
- Get in contact