2,683 Hits in 4.8 sec

Cross-Subject Seizure Detection in EEGs Using Deep Transfer Learning

Baocan Zhang, Wennan Wang, Yutian Xiao, Shixiao Xiao, Shuaichen Chen, Sirui Chen, Gaowei Xu, Wenliang Che
2020 Computational and Mathematical Methods in Medicine  
We propose three deep transfer convolutional neural networks (CNN) for automatic cross-subject seizure detection, based on VGG16, VGG19, and ResNet50, respectively.  ...  On those results of experiments, our method could prove to be an effective method for cross-subject seizure detection.  ...  Acknowledgments This work was supported in part by the Youth Teacher Education and Research Funds of Fujian (Grant No. JAT191152).  ... 
doi:10.1155/2020/7902072 pmid:32454884 pmcid:PMC7231423 fatcat:b64r7lbuqfbjnh4fpuhjfz3jtu

Patient-independent Epileptic Seizure Prediction using Deep Learning Models [article]

Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes
2020 arXiv   pre-print
However, little attention has been given for designing such models to adapt to the high inter-subject variability in EEG data.  ...  Early detection of seizures can help to mitigate injuries, and can be used to aid the treatment of patients with epilepsy.  ...  The second category is seizure detection (or abnormal EEG detection), where a model is designed to classify between seizure (ictal) and non-seizure (interictal) EEG segments [7] , [8] .  ... 
arXiv:2011.09581v1 fatcat:xatyekr3kvdxvaaanlrbvgmaly

Convolutional Neural Network for Seizure Detection of Nocturnal Frontal Lobe Epilepsy

Fabio Pisano, Giuliana Sias, Alessandra Fanni, Barbara Cannas, António Dourado, Barbara Pisano, Cesar A. Teixeira
2020 Complexity  
Moreover, the same CNN architecture has been used to develop a cross-patient seizure detection system, resorting to the transfer-learning paradigm.  ...  In other forms of epilepsy, the commonly used clinical approach mainly involves manual inspection of encephalography (EEG) signals, a laborious and time-consuming process which often requires the contribution  ...  In this case, the deep cross-patient transfer learning framework is applied to classify EEG data of a patient using the CNN trained with the EEG of another subject.  ... 
doi:10.1155/2020/4825767 fatcat:h33ewhkvdngcvdfyyau64sw2my

Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network [article]

Mustafa Talha Avcu, Zhuo Zhang, Derrick Wei Shih Chan
2019 arXiv   pre-print
We conduct leave-one-out cross validation for all subjects.  ...  This work aims to develop an end-to-end solution for seizure onset detection. We design the SeizNet, a Convolutional Neural Network for seizure detection.  ...  SVM classifier is trained using radial basis function (RBF) kernel. Deep learning method -SeizNet We develop a deep CNN network named SeizNet for endto-end seizure detection solution.  ... 
arXiv:1901.05305v1 fatcat:yb4tmwljdzdynox5kq3ucnlc3u

Deep Learning in EEG: Advance of the Last Ten-Year Critical Period

Shu Gong, Kaibo Xing, Andrzej Cichocki, Junhua Li
2021 IEEE Transactions on Cognitive and Developmental Systems  
Subsequently, the applications of deep learning in EEG are reviewed by categorizing them into groups such as brain-computer interface, disease detection, and emotion recognition.  ...  They are followed by the discussion, in which the pros and cons of deep learning are presented and future directions and challenges for deep learning in EEG are proposed.  ...  Another study comparing cross-session transferring and cross-subject transferring demonstrated that the cross-session transferring was feasible and the cross-subject transferring was inefficient [44]  ... 
doi:10.1109/tcds.2021.3079712 fatcat:5rck4hvysfhe5o2tfjywytr5o4

Robust Prior Stage Epileptic Seizure Diagnosis System using Resnet and Backpropagation Techniques

Priti N
2020 International Journal of Emerging Trends in Engineering Research  
These observations find out the patient early-stage epileptic seizure detection. The ResNet learning model trains the suspicious raises in the EEG signal, but clear classification required.  ...  Which includes two steps, at first step EEG signal has preprocessed with ResNet deep learning mechanism.  ...  Figure 11 : 11 Figure 11: peak detection plot.As in figure11 falls alarmed, peaks are identified using ResNet deep learning process; this indication alert the patients for epileptic seizures.  ... 
doi:10.30534/ijeter/2020/120852020 fatcat:xoy6cr3cw5gsnbzog7ycvwakiu

A Robust Deep Learning Approach for Automatic Classification of Seizures Against Non-seizures [article]

X. Yao, X. Li, Q. Ye, Y. Huang, Q. Cheng, G.-Q. Zhang
2019 arXiv   pre-print
The obtained average sensitivity of 87.00%, specificity of 88.60% and precision of 88.63% in cross-validation experiments are higher than using the current state-of-the-art methods, and the standard deviations  ...  One of the challenges in automatic seizure/non-seizure classification is that seizure morphologies exhibit considerable variabilities.  ...  Mixing-Patients Seizure Detection The deep learning approach in [18] uses LSTM as a main module (shortly, LSTM approach) to detect seizures.  ... 
arXiv:1812.06562v2 fatcat:taqlp6qcofdyfntlf7njfk52me

MS4PS: A Mentor-Student Architecture for Patient-Specific Seizure Detection With Combination of Transfer Learning and Active Learning

Shun Ma, Haojie Liu, Xiaogang Zhu, Yufeng Fan, Caixia Su, Yongfeng Cao
2022 IEEE Access  
It also contains a new method of active learning, which uses both an experienced mentor model and a quick-learning student model to select high-quality samples for doctors to label.  ...  Privacy protection, high labeling cost, and varying characteristics of seizures among patients and at different times are the main obstacles to building seizure detection models.  ...  Che, ''Cross-subject seizure detection in EEGs using deep transfer learning,'' Comput. Math. Methods Med., vol. 2020, 2020, Art. no. 7902072, doi: 10.1155/2020/7902072. [14] S. Raghu, N. Sriraam, Y.  ... 
doi:10.1109/access.2022.3158348 fatcat:552uo5veyvdhpehydgrpp233pu

A Novel Independent RNN Approach to Classification of Seizures against Non-seizures [article]

Xinghua Yao, Qiang Cheng, Guo-Qiang Zhang
2019 arXiv   pre-print
In order to capture essential seizure features, this paper leverages an emerging deep learning model, the independently recurrent neural network (IndRNN), to construct a new approach for the seizure/non-seizure  ...  Evaluations are conducted with cross-validation experiments across subjects over the noisy data of CHB-MIT.  ...  As a future research line, we will investigate the problem of how to use the IndRNN approach for real-time seizure detection.  ... 
arXiv:1903.09326v1 fatcat:p3it4o4qrbedbixo47tfapkhbm

Essentials of Predicting Epileptic Seizures Based on EEG Using Machine Learning: A Review

Vibha Patel, Jaishree Tailor, Amit Ganatra
2021 Open Biomedical Engineering Journal  
Methods: The challenge to predict seizures using modern machine learning algorithms and computing resources would be a boon to a person with epilepsy and its caregivers.  ...  It also gives a detailed comparative analysis of datasets used by different researchers, tools and technologies used, different machine learning algorithm considerations, and evaluation parameters.  ...  The concept of domain adaptation and transfer learning can be used for cross-patient research, i.e. generalized models [28] .  ... 
doi:10.2174/1874120702115010090 fatcat:g53gb7dbunh2zke3e7avamfnpa

Automatic seizure detection based on imaged-EEG signals through fully convolutional networks

Catalina Gómez, Pablo Arbeláez, Miguel Navarrete, Catalina Alvarado-Rojas, Michel Le Van Quyen, Mario Valderrama
2020 Scientific Reports  
We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals.  ...  We used fully convolutional neural networks to automatically detect seizures.  ...  Transfer learning in EPILEPSIAE. For the EPILEPSIAE dataset, we evaluated a cross-patient model in the First Seizures setup for the scalp recordings.  ... 
doi:10.1038/s41598-020-78784-3 pmid:33311533 fatcat:tgigm3ldybfs7k4akigcow6zge

EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications [article]

Xiaotong Gu, Zehong Cao, Alireza Jolfaei, Peng Xu, Dongrui Wu, Tzyy-Ping Jung, Chin-Teng Lin
2020 arXiv   pre-print
Furthermore, we demonstrate state-of-art computational intelligence techniques, including interpretable fuzzy models, transfer learning, deep learning, and combinations, to monitor, maintain, or track  ...  Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI  ...  In the medical area, EEG recordings are used for screening seizures of epilepsy patients with an automated seizure detection system.  ... 
arXiv:2001.11337v1 fatcat:cmurfjykjja3rdifr7e7cqq3wy

Deep Learning Algorithms in EEG Signal Decoding Application: A Review

Ramesh Babu Vallabhaneni, Pankaj Sharma, Vinit Kumar, Vyom Kulshreshtha, Koya Jeevan Reddy, S Selva Kumar, V Sandeep Kumar, Surendra Kumar Bitra
2021 IEEE Access  
Firstly, the basic principles of deep learning algorithms used in EEG decoding is briefly described, including convolutional neural network, deep belief network, autoencoder and recurrent neural network  ...  This paper overviews current application of deep learning algorithms in various EEG decoding tasks, and introduces commonly used algorithms, typical application scenarios, important progresses and existing  ...  LEARNING ALGORITHMS IN CLINICAL DISEASE DETECTION APPLICATIONS Neural Networks Application Features/characterist ics Refere nces AE Seizure detection Cross-energy matrix [69] DBN Seizure  ... 
doi:10.1109/access.2021.3105917 fatcat:rsl44hjcu5cw5mxy5xye5owzuy

Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering [article]

Aaqib Saeed, David Grangier, Olivier Pietquin, Neil Zeghidour
2020 arXiv   pre-print
Our work is motivated by Electroencephalography (EEG), where data collection protocols from different headsets result in varying channel ordering and number, which limits the feasibility of transferring  ...  Moreover, our method improves the transfer of pre-trained representations between datasets collected with different protocols.  ...  Now, we evaluate the proposed methods in handling inconsistent channels in a real cross-dataset transfer learning setting.  ... 
arXiv:2010.13694v1 fatcat:53txrfyf2fbgzelkrg3rt3rfre

An Interpretable Deep Learning Classifier for Epileptic Seizure Prediction Using EEG Data

Imene Jemal, Neila Mezghani, Lina Abou-Abbas, Amar Mitiche
2022 IEEE Access  
The purpose of this study is to investigate an interpretable deep learning classifier for epileptic EEG-driven seizure prediction.  ...  INDEX TERMS Epileptic seizure prediction, deep neural networks, interpretable decisions, EEG signal.  ...  Furthermore, it is highly useful to study how to transfer learning for cross-patient modelling, which could help to learn new representations shared between-data subjects that would transfer knowledge  ... 
doi:10.1109/access.2022.3176367 fatcat:vs2c7fzwgzb43fuakppscuq3wu
« Previous Showing results 1 — 15 out of 2,683 results