Jun 09


Multivariate times series refer to time series data that has multiple variables. Surprisingly, research on MTS search is very limited. Most existing work only supports queries with the same length of data, or queries on a fixed set of variables. However, there are many multivariate time series data sets in aviation, for instance, a data base might include: flights of multivariate time series that show the settings of the control surfaces (usually discrete signals), the pilot inputs (discrete), as well as the heading, speed, and readings from the propulsion systems (all usually continuous). In many such databases, the number of recorded parameters from a modern aircraft is nearly 1000. MTS allows safety analysts to search for specific patterns in this type of data by querying on a very small subset of the features. The search result is returned in a matter of seconds, compared to hours it might take to execute the same search in typical FOQA databases.

In order to use this tool the data needs to be saved as comma separated values (.csv) files with one flight data per file. Rows of each file corresponds to instances or time samples and columns correspond to features or variables. Also, all the flight files need to stored in one folder.

For more information, please visit here


Add New Comment