Tutorial

Detectors

This tutorial presents several HFO detectors: the Line Length detector, Root Mean Squared Detector.

• Tutorial on Computing HFOs (Part 1)
• 1 Simulated Data
  • 1.1 Simulate the HFO data
    • 1.1.1 Create and plot the simulated HFOs
    • 1.1.2 Add other “simulated” EEG data
    • 1.1.3 Combine the simulated data with sample data
  • 1.2 Detect the HFOs
    • 1.2.1 Line Length Detector
    • 1.2.2 Check Results
    • 1.2.3 Repeat for RMS Detector
    • 1.2.4 Repeat for the fast ripple dataset
    • 1.2.5 More complex Example
• Tutorial on Computing HFOs (Part 2)
  • Dataset Preprocessing
  • References
• 1 Working with Real Data
  • 1.1 Load in Real Data
    • 1.1.1 Define dataset paths and load the data
    • 1.1.2 Convert to bipolar referencing scheme
    • 1.1.3 Load Annotated HFOs
  • 1.2 Detect HFOs
    • 1.2.1 Line Length Detector
    • 1.2.2 RMS Detector
  • 1.3 Compare Results
    • 1.3.1 Find matches
• 2 Optimizing the Detectors
  • 2.1 Set up the data
  • 2.2 Set up the GridSearchCV function
  • 2.3 Perform the Search and Print Output
• Tutorial on Computing HFOs (Part 3)
  • Dataset Preprocessing
  • References
• 1 Working with Real Data
  • 1.1 Load in Real Data
  • 1.2 Perform pre-processing steps
  • 1.3 Perform Detection with Both Detectors
• 2 Compare detections
  • 2.1 Perform the comparisons
  • 2.2 Visualize the comparisons
    • 2.1.1 Extract the right values
    • 2.1.2 Visualize the mutual info
    • 2.1.3 Visualize the Kappa score
• Hilbert Detector

mne_hfo.simulate.simulate_hfo Tutorial on Computing HFOs (Part 1)