Options
Epileptic seizure detection on an ultra-low-power embedded risc-v processor using a convolutional neural network
Citation Link: https://doi.org/10.15480/882.4303
Publikationstyp
Journal Article
Date Issued
2021-06-23
Sprache
English
TORE-DOI
Journal
Volume
11
Issue
7
Article Number
203
Citation
Biosensors 11 (7): 203 (2021-06)
Publisher DOI
Scopus ID
PubMed ID
34201480
Publisher
MDPI
The treatment of refractory epilepsy via closed-loop implantable devices that act on seizures either by drug release or electrostimulation is a highly attractive option. For such implantable medical devices, efficient and low energy consumption, small size, and efficient processing architectures are essential. To meet these requirements, epileptic seizure detection by analysis and classification of brain signals with a convolutional neural network (CNN) is an attractive approach. This work presents a CNN for epileptic seizure detection capable of running on an ultra-low-power microprocessor. The CNN is implemented and optimized in MATLAB. In addition, the CNN is also implemented on a GAP8 microprocessor with RISC-V architecture. The training, optimization, and evaluation of the proposed CNN are based on the CHB-MIT dataset. The CNN reaches a median sensitivity of 90% and a very high specificity over 99% corresponding to a median false positive rate of 6.8 s per hour. After implementation of the CNN on the microcontroller, a sensitivity of 85% is reached. The classification of 1 s of EEG data takes t = 35 ms and consumes an average power of P ≈ 140 µW. The proposed detector outperforms related approaches in terms of power consumption by a factor of 6. The universal applicability of the proposed CNN based detector is verified with recording of epileptic rats. This results enable the design of future medical devices for epilepsy treatment.
Subjects
Convolutional neural network
EEG
Epileptic seizure detection
RISC-V
Ultra-low-power
DDC Class
600: Technik
Publication version
publishedVersion
Loading...
Name
biosensors-11-00203-v2.pdf
Size
1022.03 KB
Format
Adobe PDF