Epileptic Seizure Detection Based on Stockwell Transform and Bidirectional Long Short-Term Memory

Geng, Minxing; Zhou, Weidong; Liu, Guoyang; Li, Chaosong; Zhang, Yanli

doi:10.1109/tnsre.2020.2966290

Cited by 65 publications

(24 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study was reproduced in 46 with an empirical observation that 1DCNN performs elegantly for seizure detection using EEG data. Secondly, there are a lot of seizure detection models that use LSTM in the literature 37,[47][48][49] . LSTM offers an elegant choice for seizure classification for time-series data that can exploit the hidden relationship between currently acquired data with the one at previous instants.…”

Section: Seizure / Seizure Onset Detection Algorithmsmentioning

confidence: 99%

A deep learning-based automated closed-loop optogenetic system for neuromodulation during seizures

Batabyal

Brodovskaya

Williamson

2022

Preprint

View full text Add to dashboard Cite

Closed-loop electrical brain stimulation is becoming a popular technique proposed for use as a treatment alternative to surgical resection of brain tissue for drug-resistant seizures in epilepsy patients. Closed-loop optogenetic stimulation is an experimental alternative to electrical stimulation since it can stimulate or inhibit neurons. The closed-loop part contains an online seizure detection algorithm, which, based on the design, can detect the onset of a seizure or evaluate a running window for seizure membership. Conventional configurations of closed-loop optogenetics have several limitations, ranging from the adaptability of hardware-based implementation to inadequate, customized feature selection of seizures, among others. Here we provide a detailed description of our closed-loop components. We used a sequential, fully convolutional neural network regressor for complex feature selection of seizures against the controls from local field potential recordings. Our modular design kept the local field potential-recording headset and optical probe separate. The seizure detection and execution of light delivery are fast and can be precisely timed. This automated system is robust to noise, modular in design, flexible in use, and simple execution. When applied in vivo, the proposed work shows efficacy over the state of the arts in terms of improved seizure detection and reduction in false positives.

show abstract

Section: Seizure / Seizure Onset Detection Algorithmsmentioning

confidence: 99%

A deep learning-based automated closed-loop optogenetic system for neuromodulation during seizures

Batabyal

Brodovskaya

Williamson

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The study had a sensitivity for each section of 97.01%. The study of Geng et al [19] provided a good method for detecting epileptic seizures, by combining the Stockwell transform with bidirectional long short-term memory (BiLSTM), applied to an EEG dataset collected at the Epilepsy Center at the University Hospital Freiburg, Germany. The study was carried out in three stages: in the first stage, Sconvert was applied to the EEG signals, to obtain timefrequency blocks that would be used as inputs in the second stage.…”

Section: Related Workmentioning

confidence: 99%

Seizure Detection Based on Adaptive Feature Extraction by Applying Extreme Learning Machines

Baykara¹,

Abdulrahman²

2021

View full text Add to dashboard Cite

Epilepsy is one of the most common chronic disorder which negatively affects the patients' life. The functionality of the brain can be obtained from brain signals and it is vital to analyze and examine the brain signals in seizure detection processes. In this study, we performed machine learning-based and signal processing methods to detect epileptic signals. To do that, we examined three different EEG signals (healthy, ictal, and interictal) with two different classes (healthy ones and epileptic ones). Our proposed method consists of three stages which are preprocessing, feature extraction, and classification. In the preprocessing phase, EEG signals normalized to scale all samples into [0,1] range. After Stockwell Transform was applied and chaotic features and Parseval's Energy collected from each EEG signal. In the last part, EEG signals were classified with ELM (Extreme Learning Machines) with different parameters. Our study shows the best classification accuracy obtained from the Sigmoid activation function with the number of 100 hidden neurons. The highlights of this study are: Stockwell Transform is used; Entropy values are selected based on the adaptive process. Threshold values are determined according to the error rates; ELM classifier algorithm is applied.

show abstract

“…Another important part of automatic seizure detection methods or systems is classifier. Support vector machine, random forest and various artificial neural networks have exhibited different performance in distinguishing seizure EEG [18]- [25]. However, the robustness and generalization ability of many classifiers are unsatisfactory when the testing data has a different probability distribution with that of the training data.…”

Section: Introductionmentioning

confidence: 99%

Epileptic Seizure Detection Based on Bidirectional Gated Recurrent Unit Network

Zhang

Yao

Yang

et al. 2022

IEEE Trans. Neural Syst. Rehabil. Eng.

Self Cite

View full text Add to dashboard Cite

Epileptic Seizure Detection Based on Stockwell Transform and Bidirectional Long Short-Term Memory

Cited by 65 publications

References 60 publications

A deep learning-based automated closed-loop optogenetic system for neuromodulation during seizures

A deep learning-based automated closed-loop optogenetic system for neuromodulation during seizures

Seizure Detection Based on Adaptive Feature Extraction by Applying Extreme Learning Machines

Epileptic Seizure Detection Based on Bidirectional Gated Recurrent Unit Network

Contact Info

Product

Resources

About