Related Experiment Video
Updated: May 7, 2026

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
Published on: January 29, 2018
Event driven neural network on a mixed signal neuromorphic processor for EEG based epileptic seizure detection
Jim Bartels1,2, Olympia Gallou1, Hiroyuki Ito2
1Institute of Neuroinformatics, University of Zurich and ETH Zurich, Zurich, Switzerland.
This study introduces a novel brain-inspired spiking neural network (SNN) for ultra-low power, always-on epilepsy seizure detection using wearable devices. The system successfully processes real-time EEG data, paving the way for "wear and forget" neurological monitoring.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Computer Science
Background:
- Long-term monitoring of biomedical signals is crucial for managing neurological conditions like epilepsy.
- Current wearable technology faces challenges in achieving long-lasting operation for seizure detection and analysis.
- Brain-inspired spiking neural networks (SNNs) offer a promising solution for ultra-low power signal processing on neuromorphic systems.
Purpose of the Study:
- To introduce and validate a novel SNN architecture for always-on epilepsy monitoring.
- To demonstrate the potential of SNNs deployed on neuromorphic hardware for real-time seizure detection.
- To advance the development of embedded intelligent systems for resource-constrained environments.
Main Methods:
- Co-design and validation of a novel SNN architecture on a mixed-signal neuromorphic chip.
- Real-time processing of analog Electroencephalographic (EEG) seizure data using a custom asynchronous mixed-signal neuromorphic platform.
- Integration of an analog front-end (AFE) and asynchronous delta modulation (ADM) circuit for direct spike generation from EEG signals.
- Utilizing a linear classifier for seizure detection based on SNN-extracted features.
Main Results:
- The hardware-implemented SNN successfully captured partial synchronization in neural activity during seizures.
- The neuromorphic chip processed analog EEG signals in real-time, generating spike streams directly from the data.
- A post-processing linear classifier reliably detected seizures using SNN-extracted local features.
- Demonstrated feasibility of full on-chip seizure monitoring.
Conclusions:
- The developed SNN architecture and neuromorphic platform show significant potential for always-on epilepsy monitoring.
- This research advances the creation of intelligent, low-power wearable units for autonomous EEG event detection.
- The findings open new possibilities for patient care and management of neurological disorders in out-of-hospital settings.
More Related Videos
09:16Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
Published on: June 21, 2019
06:28Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
Published on: September 27, 2024
Related Concept Videos
Epilepsy and Seizures: Overview
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
Seizures: Classification
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types: