Authors: Amir Hussein, Marc Djandji, Reem A. Mahmoud, Mohamad Dhaybi, Hazem Hajj
Epilepsy is a chronic medical condition that involves abnormal brain activity causing patients to lose control of awareness or motor activity. As a result, detection of pre-ictal states, before the onset of a seizure, can be lifesaving. The problem is challenging because it is difficult to discern between electroencephalogram signals in pre-ictal states versus signals in normal inter-ictal states. There are three key challenges that have not been addressed previously: (1) the inconsistent performance of prediction models across patients, (2) the lack of perfect prediction to protect patients from any episode, and (3) the limited amount of pre-ictal labeled data for advancing machine learning methods. This article addresses these limitations through a novel approach that uses adversarial examples with optimized tuning of a combined convolutional neural network and gated recurrent unit. Compared to the state of the art, the results showed an improvement of 3x in model robustness as measured in reduced variations and superior accuracy of the area under the curve, with an average increase of 6.7%. The proposed method also exhibited superior performance with other advances in the field of machine learning and customized for epilepsy prediction including data augmentation with Gaussian noise and multitask learning.
Source Code Repository: https://github.com/aub-mind/Robust-Seizure-Prediction
Paper Link: https://dl.acm.org/doi/abs/10.1145/3386580
Model
Sample of Adversarial Examples
Results
Contacts
- Amir Hussein anh21@mail.aub.edu
- [Marc Djandji] mgd10@mail.aub.edu
Paper:
Cite our paper as:
@article{10.1145/3386580,
author = {Hussein, Amir and Djandji, Marc and Mahmoud, Reem A. and Dhaybi, Mohamad and Hajj, Hazem},
title = {Augmenting DL with Adversarial Training for Robust Prediction of Epilepsy Seizures},
year = {2020},
issue_date = {June 2020},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {1},
number = {3},
issn = {2691-1957},
url = {https://doi.org/10.1145/3386580},
doi = {10.1145/3386580},
journal = {ACM Trans. Comput. Healthcare},
month = jun,
articleno = {18},
numpages = {18},
}
Your content is consistently impressive. It’s evident that you put a lot of thought and effort into your posts. Thank you for sharing such valuable information!unboxwithkd
We aim at delivering excellent healthcare services to all our clients at WellNow Urgent Care center only. With multiple locations nearby, easy-to-use online features and a commitment towards high standards of care, we hope to become your reliable partner in healthcare.
Well Now Urgent Care
This study addresses key challenges in predicting seizures for epilepsy patients by introducing a novel machine learning approach that uses adversarial examples and optimizes a convolutional neural network with a gated recurrent unit. This method improves prediction accuracy and robustness, achieving a 6.7% increase in the area under the curve and 3x better model stability. Also Read: https://apkfrlegends.com
Thanks to this article I can learn more. Expand my knowledge and abilities. Actually the article is very real.
LiteBlue USPS portal
“Thank you for sharing this! I really appreciate the insight and thoughtfulness behind it. It’s always great to learn something new!”hp printer ink error
“Great post – it was exactly what was needed. I really appreciate your simple and clear way of explaining things!”How to fix canon printer error