TY - JOUR
T1 - Real-time sub-milliwatt epilepsy detection implemented on a spiking neural network edge inference processor
AU - Li, Ruixin
AU - Zhao, Guoxu
AU - Muir, Dylan Richard
AU - Ling, Yuya
AU - Burelo, Karla
AU - Khoe, Mina
AU - Wang, Dong
AU - Xing, Yannan
AU - Qiao, Ning
N1 - Copyright © 2024. Published by Elsevier Ltd.
PY - 2024/12
Y1 - 2024/12
N2 - Analyzing electroencephalogram (EEG) signals to detect the epileptic seizure status of a subject presents a challenge to existing technologies aimed at providing timely and efficient diagnosis. In this study, we aimed to detect interictal and ictal periods of epileptic seizures using a spiking neural network (SNN). Our proposed approach provides an online and real-time preliminary diagnosis of epileptic seizures and helps to detect possible pathological conditions. To validate our approach, we conducted experiments using multiple datasets. We utilized a trained SNN to identify the presence of epileptic seizures and compared our results with those of related studies. The SNN model was deployed on Xylo, a digital SNN neuromorphic processor designed to process temporal signals. Xylo efficiently simulates spiking leaky integrate-and-fire neurons with exponential input synapses. Xylo has much lower energy requirements than traditional approaches to signal processing, making it an ideal platform for developing low-power seizure detection systems. Our proposed method has a high test accuracy of 93.3% and 92.9% when classifying ictal and interictal periods. At the same time, the application has an average power consumption of 87.4 μW (IO power) + 287.9 μW (compute power) when deployed to Xylo. Our method demonstrates excellent low-latency performance when tested on multiple datasets. Our work provides a new solution for seizure detection, and it is expected to be widely used in portable and wearable devices in the future.
AB - Analyzing electroencephalogram (EEG) signals to detect the epileptic seizure status of a subject presents a challenge to existing technologies aimed at providing timely and efficient diagnosis. In this study, we aimed to detect interictal and ictal periods of epileptic seizures using a spiking neural network (SNN). Our proposed approach provides an online and real-time preliminary diagnosis of epileptic seizures and helps to detect possible pathological conditions. To validate our approach, we conducted experiments using multiple datasets. We utilized a trained SNN to identify the presence of epileptic seizures and compared our results with those of related studies. The SNN model was deployed on Xylo, a digital SNN neuromorphic processor designed to process temporal signals. Xylo efficiently simulates spiking leaky integrate-and-fire neurons with exponential input synapses. Xylo has much lower energy requirements than traditional approaches to signal processing, making it an ideal platform for developing low-power seizure detection systems. Our proposed method has a high test accuracy of 93.3% and 92.9% when classifying ictal and interictal periods. At the same time, the application has an average power consumption of 87.4 μW (IO power) + 287.9 μW (compute power) when deployed to Xylo. Our method demonstrates excellent low-latency performance when tested on multiple datasets. Our work provides a new solution for seizure detection, and it is expected to be widely used in portable and wearable devices in the future.
KW - Electroencephalogram
KW - Neuromorphic processor
KW - Seizure detection
KW - Spiking neural network
KW - Ultra-low power
UR - http://www.scopus.com/inward/record.url?scp=85206238340&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2024.109225
DO - 10.1016/j.compbiomed.2024.109225
M3 - Article
C2 - 39413626
SN - 0010-4825
VL - 183
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 109225
ER -