Low Latency Real-Time Seizure Detection Using Transfer Deep Learning

02/16/2022
by   Vahid Khalkhali, et al.
0

Scalp electroencephalogram (EEG) signals inherently have a low signal-to-noise ratio due to the way the signal is electrically transduced. Temporal and spatial information must be exploited to achieve accurate detection of seizure events. Most popular approaches to seizure detection using deep learning do not jointly model this information or require multiple passes over the signal, which makes the systems inherently non-causal. In this paper, we exploit both simultaneously by converting the multichannel signal to a grayscale image and using transfer learning to achieve high performance. The proposed system is trained end-to-end with only very simple pre- and postprocessing operations which are computationally lightweight and have low latency, making them conducive to clinical applications that require real-time processing. We have achieved a performance of 42.05 false alarms per 24 hours on the development dataset of v1.5.2 of the Temple University Hospital Seizure Detection Corpus. On a single-core CPU operating at 1.7 GHz, the system runs faster than real-time (0.58 xRT), uses 16 Gbytes of memory, and has a latency of 300 msec.

READ FULL TEXT

page 2

page 4

research
12/28/2017

Deep Architectures for Automated Seizure Detection in Scalp EEGs

Automated seizure detection using clinical electroencephalograms is a ch...
research
01/21/2022

Real-Time Seizure Detection using EEG: A Comprehensive Comparison of Recent Approaches under a Realistic Setting

Electroencephalogram (EEG) is an important diagnostic test that physicia...
research
01/17/2023

Real-time, low latency virtual DBA hypervisor for SLA-compliant multi-service operations over shared Passive Optical Networks

We present a heuristic algorithm for a PON upstream scheduling hyperviso...
research
05/03/2023

Scheduling Network Function Chains Under Sub-Millisecond Latency SLOs

Network Function Virtualization (NFV) seeks to replace hardware middlebo...
research
09/29/2019

FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing

Beamforming has been extensively investigated for multi-channel audio pr...
research
03/18/2021

Hazelcast Jet: Low-latency Stream Processing at the 99.99th Percentile

Jet is an open-source, high-performance, distributed stream processor bu...
research
08/31/2020

ROS-Neuro Integration of Deep Convolutional Autoencoders for EEG Signal Compression in Real-time BCIs

Typical EEG-based BCI applications require the computation of complex fu...

Please sign up or login with your details

Forgot password? Click here to reset