Multimodal Biomedical Signal Processing End Abstracts Integrating Video and Accelerometer Signals for Nocturnal Epileptic Seizure Detection

Epileptic seizure detection is traditionally done using video/electroencephalogram (EEG) monitoring, which is not applicable in a home situation. In recent years, attempts have been made to detect the seizures using other modalities. In this research we investigate if a combined usage of accelerometers attached to the limbs and video data would increase the performance compared to a single modality approach. Therefore, we used two existing approaches for seizure detection in accelerometers and video and combined them using a linear discriminant analysis (LDA) classifier in a late integration. We compared these results also with an early integration of the accelerometer and video features. The single modality results give a sensitivity and PPV for the accelerometers of 83.33% and 100.00% and for the video of 70.00% and 97.22%, respectively. The early integration does not seem to improve performance (sens 83.33% and PPV 96.00%) where the late integration gives a small increase in sensitivity (86.67%), but a decrease in PPV (97.50%).