Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection

  title={Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection},
  author={Una Pale and Tom{\'a}s Teijeiro and David Atienza Alonso},
  journal={Frontiers in Neurology},
Long-term monitoring of patients with epilepsy presents a challenging problem from the engineering perspective of real-time detection and wearable devices design. It requires new solutions that allow continuous unobstructed monitoring and reliable detection and prediction of seizures. A high variability in the electroencephalogram (EEG) patterns exists among people, brain states, and time instances during seizures, but also during non-seizure periods. This makes epileptic seizure detection very… 

Figures from this paper

Exploration of Hyperdimensional Computing Strategies for Enhanced Learning on Epileptic Seizure Detection
Results show that the bestperforming algorithm, which is a combination of multi-centroid and multi-pass, can indeed reach the performance of the random forest model on a highly unbalanced dataset imitating a real-life epileptic seizure detection application.
Hyperdimensional computing encoding for feature selection on the use case of epileptic seizure detection
This work explores the not yet addressed topic of optimal encoding of spatio-temporal data, such as electroencephalogram (EEG) signals, and all information it entails to the HD vectors, and demonstrates how the HD computing framework can be used to perform feature selection by choosing an adequate encoding.
EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor
This study exploits HDC as an alternative computational model that mimics important brain functionalities toward high-efficiency and noise-tolerant neuromorphic computing, and presents EventHD, an end-to-end learning framework based on HDC for robust, efficient learning from neuromorphic sensors.
HDTorch: Accelerating Hyperdimensional Computing with GP-GPUs for Design Space Exploration
This work introduces HDTorch, an opensource, PyTorch-based HDC library with CUDA extensions for hypervector operations, and performs the first-ever HD training and inference analysis of the entirety of the CHB-MIT EEG epilepsy database.


Systematic Assessment of Hyperdimensional Computing for Epileptic Seizure Detection
A systematic assessment of the HD computing framework for the detection of epileptic seizures, comparing different feature approaches mapped to HD vectors 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.
An Ensemble of Hyperdimensional Classifiers: Hardware-Friendly Short-Latency Seizure Detection With Automatic iEEG Electrode Selection
The suitability of the proposed algorithm for detecting epileptic seizures to deployment on low-cost embedded hardware platforms is demonstrated, thanks to its robustness to noise/artifacts affecting the signal, its low computational complexity, and the small memory-footprint on a RISC-V microcontroller.
Detection of Epileptic Seizures from Surface EEG Using Hyperdimensional Computing
A novel technique based on hyperdimensional (HD) computing to detect epileptic seizures from 2-channel surface EEG recordings is proposed that improves the accuracy compared to state-of-the-art techniques while consuming smaller or comparable power.
One-shot Learning for iEEG Seizure Detection Using End-to-end Binary Operations: Local Binary Patterns with Hyperdimensional Computing
This paper presents an efficient binarized algorithm that surpasses the state-of-the-art methods for detecting 65 novel seizures with higher specificity and sensitivity, and lower memory footprint.
Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate
A robust seizure detection methodology for a wearable platform is proposed and validated on the CHB-MIT Scalp EEG database and the battery lifetime of the wearable system is evaluated including the feasibility of using it in real time for up to 40.87 hours on a single battery charge.
Application of machine learning to epileptic seizure onset detection and treatment
The feasibility of using the algorithm to control the Vagus Nerve Stimulator, to initiate ictal SPECT (a functional neuroimaging modality useful for localizing the cerebral site of origin of a seizure), and to enable delay-sensitive therapeutic and diagnostic applications are demonstrated.
e-Glass: A Wearable System for Real-Time Detection of Epileptic Seizures
e-Glass, a wearable system based on four electroencephalogram (EEG) electrodes for the detection of epileptic seizures, and it is possible to notify caregivers for rescue to avoid epilepsy-related death due to the underlying neurological disorders, sudden unexpected death in epilepsy, or accidents during seizures.
Hyperdimensional Computing for Blind and One-Shot Classification of EEG Error-Related Potentials
The use of HD computing to classify electroencephalography (EEG) error-related potentials for noninvasive brain–computer interfaces is described and achieves on average 5% higher single-trial classification accuracy compared to a conventional machine learning method on this task.
Seizure prediction: the long and winding road.
A critically discuss the literature on seizure prediction and address some of the problems and pitfalls involved in the designing and testing of seizure-prediction algorithms, and point towards possible future developments and propose methodological guidelines for future studies on seizure predictions.
Interictal spikes and epileptic seizures: their relationship and underlying rhythmicity.
It is found that spike rate was significantly altered prior to seizure in 9 out of 15 subjects and the pre-ictal decrease in spike rate is not consistent with spikes promoting seizures, however, the fact that spikes and seizures demonstrate similar probability distributions suggests they are not wholly independent processes.