Systematic Assessment of Hyperdimensional Computing for Epileptic Seizure Detection

Abstract

Hyperdimensional computing is a promising novel paradigm for low-power embedded machine learning. It has been applied on different biomedical applications, and particularly on epileptic seizure detection. Unfortunately, due to differences in data preparation, segmentation, encoding strategies, and performance metrics, results are hard to compare, which makes building upon that knowledge difficult. Thus, the main goal of this work is to perform a systematic assessment of the HD computing framework for the detection of epileptic seizures, comparing different feature approaches mapped to HD vectors. More precisely, we test two previously implemented features as well as several novel approaches with HD computing on epileptic seizure detection. We evaluate them in a comparable way, i.e., with the same preprocessing setup, and with the identical performance measures. We use two different datasets in order to assess the generalizability of our conclusions. The systematic assessment involved three primary aspects relevant for potential wearable implementations: 1) detection performance, 2) memory requirements, and 3) computational complexity. Our analysis shows a significant difference in detection performance between approaches, but also that the ones with the highest performance might not be ideal for wearable applications due to their high memory or computational requirements. Furthermore, we evaluate a post-processing strategy to adjust the predictions to the dynamics of epileptic seizures, showing that performance is significantly improved in all the approaches and also that after post-processing, differences in performance are much smaller between approaches.

Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices

“…Once occurring, epileptic seizures are expected to last multiple seconds. As in [23], we apply moving-averages to the labels with a window of 4s, performing majority voting, thus effectively smoothing out the predictions. The low-pass filtering effect of the moving average gives a great benefit in terms FP reduction, since it basically eliminates the fluctuations of the classifier output.…”

Ensemble learning using individual neonatal data for seizure detection

“…Besides a few segments at the beginning and end of each recording, for each 4 sec long segment there are 4 overlapping 16 sec long segments. Prediction for a 4 sec segment was obtained by averaging predictions from overlapping 16 sec long segments [18,31]. Seizures with duration less than 10 sec were excluded and considered normal brain activity as by definition seizures are longer than 10 sec [49].…”

Ensemble Learning Using Individual Neonatal Data for Seizure Detection

“…Besides a few segments at the beginning and end of each recording, for each 4 sec long segment there are 4 overlapping 16 sec long segments. Prediction for a 4 sec segment is obtained by averaging predictions from overlapping 16 sec long segments [44,45]. Seizures with duration less than 10 sec are excluded and considered normal brain activity as by definition seizures are longer than 10 sec [46].…”