Export Labeled Signal Sets and Features

Step 4 of 4 in Use Signal Feature Extractor App

• 2
• 3
• 4

At the end of a feature extraction session, you can export labeled signal sets with all the extracted features or any signal features that you extracted. You can export labeled signal sets to MAT files or to the MATLAB^® workspace. You can also export signal features to the MATLAB workspace or to Classification Learner (Statistics and Machine Learning Toolbox). Signal Feature Extractor exports labeled signals as labeledSignalSet objects.

Export Labeled Signal Sets

To export new labeled signal sets, click Export on the Extract Features tab and select To Workspace or To File under Labeled Signal Set. In the dialog box, specify the name of a variable or MAT file and an optional brief description. The variable or file contains a labeledSignalSet object that merges all the signals, feature tables, and response labels that you created, imported, and modified in the current Signal Feature Extractor session. All signals that contain time information are converted to MATLAB timetables.

Note

When exporting labeled signal sets, Signal Feature Extractor converts all signals with time information to timetables. This conversion results in a deeper hierarchy of nested channels in the exported labeledSignalSet object. You can see the deeper hierarchy if you import the labeled signal set again into the app.

Export Features

As you generate features in the current Signal Feature Extractor session, you can export these features to the MATLAB Workspace or to the Classification Learner (Statistics and Machine Learning Toolbox) app. You can use the createFeatureData function to create a table of features that you can then import to Classification Learner.

Export to MATLAB Workspace

To export features to the MATLAB Workspace, click Export on the Extract Features tab and select To Workspace under Features. In the Export Features to Workspace dialog box, select the response labels and feature labels you want to export and then click Export.

Tip

Use Ctrl+click to select multiple features.

Before the app exports the selected features, you must specify a name and format for the output. You can output the features as either a table or matrix, where each column corresponds to a feature label and each row corresponds to a member.

Export to Classification Learner App

To export features to the Classification Learner (Statistics and Machine Learning Toolbox) app, click Export on the Extract Features tab and select To Classification Learner under Features. In the Export Features to Classification Learner dialog box, select the response labels and feature labels you want to export and then click Export. Once you export the selected features, the Classification Learner app opens automatically with the feature table visible in the new session dialog box. In this workflow, Classification Learner considers the features as predictors.