Exporting Data Sets From Graphs

dFL allows multiple graph types to be opened at a time, with many different signals able to be loaded into different graphs, and each graph able to be customized independently (e.g. using different normalizations, smoothing, resampling, etc.). See Project Layouts for details on how to generate and save custom graph layouts, etc. Once project layouts have been populated with graph types and graph customizations, these datasets may be exported to save all data utilizing the customizations in each graph independently, alongside a json metadata file that stores all data harmonization settings. One thing to keep in mind is that if a signal is loaded into more than one graph, the signal will appear in the data set multiple times (however many graphs it appears in), as well as the metadata/customization info for each graph.

dFL is also be readily integrated with HPE's Common Metadata Framework (CMF), which allows provenance metadata to be recorded at fine granularity whether during batch exports, individual label creation, or automated labeling runs, capturing timestamps, personnel identifiers, data versions, processing history, etc.