EEG simulation using deep neural networks
DOI:
https://doi.org/10.34185/1562-9945-3-152-2024-06Keywords:
Keywords: neural network, electroencephalography, time series, recurrent layer, loss function, LSTM, DARNN, LSTnet, TPA, Julia, EDF, Flux.Abstract
Electroencephalography (EEG) is a method that measures the spatial distribution of voltage fields on the skin heads and their change over time. It is believed that the reason for this activity is fluctuating sum of excitatory and inhibitory postsynaptic potentials. Application of EEG monitoring methods becomes everything more important in the treatment of serious diseases. However, this process often requires considerable effort and can be crucial for the patient. In this context, the idea of using neural networks for analysis of electroencephalographic signals. They can effectively process large amounts of data and improve accuracy and speed brain activity analysis. Based on this research was developed software that allows EEG simulation and can serve as part of automated patient signal analysis and improve the speed of decision-making regarding patient treatment. For this kind of task, the prediction of EEG behavior by some varieties of neu-ral network LSTM model was evaluated and analyzed, namely, DARNN, LSTnet, TPA.
References
National Center of Artificial Intelligence, NUST, Islamabad. [Online] Available: https://dll.seecs.nust.edu.pk.
Lawrence J. Hirsch, Richard P. Brenner, Atlas of EEG in Critical Care// Wiley–Blackwell, New York, 2010. ISBN: 978-0-470-98786-5
Kemp, B., Värri, A., Rosa, A. C., Nielsen, K. D., & Gade, J. (1992). A simple format for exchange of digitized polygraphic recordings. Electroencephalography and Clini-cal Neurophysiology, 82(5), 391–393. https://doi.org/10.1016/0013-4694(92)90009-7
Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, and Garrison Cot-trell. 2017. Adual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:1704.02971(2017).
Lai, G., Chang, W.-C., Yang, Y., & Liu, H. (2018). Modeling long- and short-term temporal patterns with deep neural networks. The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.
Shih, SY., Sun, FK. & Lee, Hy. Temporal pattern attention for multivariate time series forecasting. Mach Learn 108, 1421–1441 (2019). https://doi.org/10.1007/s10994-019-05815-0
Belozyorov V. Y., Inkin O. A. (2023). Systems of singular differential equations as the basis for neural network modeling of chaotic processes. Journal of Optimization, Differential Equations and Their Applications, 31(2), 24. https://doi.org/10.15421/142309
Downloads
Published
Issue
Section
License
Copyright (c) 2024 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
