0.25
0.5
0.75
1.25
1.5
1.75
2
Support Feature Machine for Classification of Abnormal Brain Activity
Published on Aug 14, 20076729 Views
In this study, a novel multidimensional time series classification technique, namely support feature machine (SFM), is proposed. SFM is inspired by the optimization model of support vector machine and
Related categories
Chapter list
Support Feature Machine for Classification of Abnormal Brain Activity 00:03
Agenda00:45
Objectives01:22
How Many People Having Epilepsy?02:12
Epilepsy and Seizures02:33
Intracranial EEG Acquisition03:12
Electroencephalogram (EEG)04:04
10-Second EEGs: Seizure Evolution04:48
Open Problems05:47
Data Transformation Using Chaos Theory06:17
Measure of Chaos07:08
Classification of Physiological States07:11
Support Vector Machine vs Support Feature Machine07:50
Nearest Neighbor for Time Series08:44
Similarity Measures09:40
Support Feature Machine10:23
Decision Rule: Basic Ideas11:24
Optimization Model I: Averaging12:04
Model I: Averaging Formulation13:09
Optimization Model II: Voting13:37
Decision Rule: Basic Ideas13:51
Model II: Voting Formulation13:55
Data Selection and Sampling14:04
Sensitivity and Specificity14:24
5-Fold Cross Validation Result14:28
DTW pt 115:18
DTW pt 215:23
Automated Seizure Prediction Paradigm15:24
Concluding Remarks15:40
Reference16:29
Acknowledgements16:32