Discriminative Ratio of Spectral Power and Relative Power Features Derived via Frequency-Domain Model Ratio with Application to Seizure Prediction

Keyphrases

• Seizure Prediction 100%
• Spectral Power 100%
• Relative Power 100%
• Power Features 100%
• Frequency Domain Model 100%
• Band Power 66%
• Autoregressive Model 50%
• High Signal-to-noise Ratio 33%
• Relative Band Power 33%
• Patient-specific 16%
• Scalp EEG 16%
• Two-state 16%
• Frequency Response 16%
• Ranking Algorithm 16%
• Two-frequency 16%
• Power Spectral Density 16%
• Binary Classification 16%
• Discriminative Features 16%
• EEG Data 16%
• Non-stationary Environments 16%
• Specific Bands 16%
• Synthesized Data 16%
• Total Power 16%
• PhysioNet 16%

Engineering

• Frequency Domain 100%
• Domain Model 100%
• Signal-to-Noise Ratio 66%
• Discriminator 66%
• Patient Specific 33%
• Sufficient Condition 33%
• Frequency Response 33%
• Power Spectral Density 33%