Using deep-learning to automatically detect epileptic seizure in a wearable device

• Levi de Albuquerque IFCE
• Elias da Silva IFCE

Resumo

Epilepsy is a chronic disease which affects over 40 million people worldwide. The majority of these people are able to keep the symptoms under control; however, some still suffer with frequent seizures. As such, methods for detecting the occurrences of these episodes are required. The main source of data for detecting seizures is the electroencephalogram (EEG) signal. Machine Learning algorithms, for instance, can be applied to these signals to perform such a task. Moreover, Deep Learning techniques, such as Convolutional Neural Networks, have been proven to be effective to the problem with some results achieving an accuracy of 93% or more. Nevertheless, there is little exploration towards applying these types of networks in an embedded system environment and even less with the aim of building a wearable device, which could forewarn a patient of impeding episodes. This article presents the steps taken to evaluate an architecture that can be applied to intra-patient data considering a low resource environment. We consider the application of said architecture in an embedded platform with estimates for time and memory consumption to build a wearable device. An architectural overview of such a device is also discussed.

Palavras-chave: Embedded systems, Convolutional Neural Networks, Epilepsy

Referências

T. V. et al. "Global regional and national incidence prevalence and years lived with disability for 310 diseases and injuries" 1990-2015: a systematic analysis for the global burden of disease study 2015 2016.

B. Chang and D. Lowenstein "Epilepsy" New England Journal of Medicine vol. 349 pp. 1257-1266 2003.

C. Elger and D. Schmidt "Modern management of epilepsy: A practical approach" Epilepsy Behavior vol. 4 pp. 501-539 2008.

A. Shoeb and J. Guttag pplication of machine learning to epileptic seizure detection pp. 975-982 2010.

M. Zhou C. Tian R. Cao B. Wang Y. Niu T. Hu et al. "Epileptic seizure detection based on EEG signals and CNN" Frontiers in Neuroinformatics vol. 12 Dec. 2018.

A. L. Goldberger L. A. N. Amaral L. Glass J. M. Hausdorff P. C. Ivanov R. G. Mark et al. "Physio Bank Physio Toolkit and PhysioNet" Circulation vol. 101 no. 23 Jun. 2000.

M. T. Avcu Z. Zhang and D. W. S. Chan "Seizure detection using least eeg channels by deep convolutional neural network" ICASSP 2019-2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) May 2019.

G. Muhammad M. Masud S. U. Amin R. Alrobaea and M. F. Alhamid "Automatic seizure detection in a mobile multimedia framework" IEEE Access vol. 6 pp. 45372-45383 2018.

D. Sopic A. Aminifar and D. Atienza "e-glass: A wearable system for real-time detection of epileptic seizures" 2018 IEEE International Symposium on Circuits and Systems (ISCAS) 2018.

E. T. Silva F. Sampaio L. C. da Silva D. S. Medeiros and G. P. Correia "A method for embedding a computer vision application into a wearable device" Microprocessors and Microsystems vol. 76 Jul. 2020.

S. Wang G. Ananthanarayanan Y. Zeng N. Goel A. Pathania and T. Mitra "High-throughput CNN inference on embedded ARM big. LITTLE multi-core processors" IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems pp. 1-1 2019.

S. I. Venieris A. Kouris and C.-S. Bouganis "Toolflows for mapping convolutional neural networks on FPGAs" ACM Computing Surveys vol. 51 no. 3 pp. 1-39 Jun. 2018.

G. Korol and F. G. Moraes "A FPGA parameterizable multi-layer architecture for CNNs" Proceedings of the 32nd Symposium on Integrated Circuits and Systems Design - SBCCI '19 2019 [online] Available: https://doi.org/10.1145/3338852.3339840.

S. Ioffe and C. Szegedy Batch normalization: Accelerating deep network training by reducing internal covariate shift 2015.

F. Chollet et al. Keras 2015.

D. P. Kingma and J. Ba Adam: A method for stochastic optimization 2014.

"Stmcubemx" STMicroelectronics [online] Available: https://www.st.com/en/development-tools/stm32cubemx.html.

S. J. Nowlan and G. E. Hinton "Simplifying neural networks by soft weight-sharing" Neural Computation vol. 4 no. 4 pp. 473-493 1992.

G. M. Rojas C. Alvarez C. E. Montoya M. de la Iglesia-Vayá J. E. Cisternas and M. Gálvez "Study of resting-state functional connectivity networks using EEG electrodes position as seed" Frontiers in Neuroscience vol. 12 Apr. 2018.