WITHDRAWN: Prediction of epileptic seizures using Grey Wolf Optimized Model Driven mathematical approach

Prathaban, Banu Priya; Balasubramanian, R.

doi:10.1016/j.micpro.2020.103370

Cited by 9 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As is shown in Figure 4, the results have shown the dependence of cortical function on the thalamic one in the initiation, propagation, and termination of epileptic seizures. Recent studies Chang et al (2020) and Prathaban and Balasubramanian (2020) did not consider the thalamus and its synaptic connectivity with other neuronal populations such as EI in the cortical models they worked with. However, based on the bifurcation analysis obtained from the hybrid modulation of intra-EI excitatory and inhibitory synaptic strength in the extended neural mass model, the pathway from the thalamic relay nucleus to the EI facilitates the transitions between different types of epileptic activities, either from interictal to ictal or between clonic, absence, and tonic seizures.…”

Section: Discussionmentioning

confidence: 99%

The Critical Modulatory Role of Spiny Stellate Cells in Seizure Onset Based on Dynamic Analysis of a Neural Mass Model

2021

View full text Add to dashboard Cite

Growing evidence suggests that excitatory neurons in the brain play a significant role in seizure generation. Nonetheless, spiny stellate cells are cortical excitatory non-pyramidal neurons in the brain, whose basic role in seizure occurrence is not well understood. In the present research, we study the critical role of spiny stellate cells or the excitatory interneurons (EI), for the first time, in epileptic seizure generation using an extended neural mass model inspired by a thalamocortical model originally introduced by another research group. Applying bifurcation analysis on this modified model, we investigated the rich dynamics corresponding to the epileptic seizure onset and transition between interictal and ictal states caused by EI connectivity to other cell types. Our results indicate that the transition between interictal and ictal states (preictal signal) corresponds to a supercritical Hopf bifurcation, and thus, the extended model suggests that before seizure onset, the amplitude and frequency of neural activities gradually increase. Moreover, we showed that (1) the altered function of GABAergic and glutamatergic receptors of EI can cause seizure, and (2) the pathway between the thalamic relay nucleus and EI facilitates the transition from interictal to ictal activity by decreasing the preictal period. Thereafter, we considered both sensory and cortical periodic inputs to study model responses to various harmonic stimulations. Bifurcation analysis of the model, in this case, suggests that the initial state of the model might be the main cause for the transition between interictal and ictal states as the stimulus frequency changes. The extended thalamocortical model shows also that the amplitude jump phenomenon and non-linear resonance behavior result from the preictal state of the modified model. These results can be considered as a step forward to a deeper understanding of the mechanisms underlying the transition from normal activities to epileptic activities.

show abstract

Section: Discussionmentioning

confidence: 99%

The Critical Modulatory Role of Spiny Stellate Cells in Seizure Onset Based on Dynamic Analysis of a Neural Mass Model

2021

View full text Add to dashboard Cite

show abstract

“…As it can be observed in Fig. 4, the results have shown the dependence of cortical function on the thalamic one in initiation, propagation and termination of epileptic seizures Recent studies [58,59] did not consider thalamus and its synaptic connectivity with other neuronal populations such as excitatory interneurons in the cortical models they worked with. However, based on the bifurcation analysis obtained from hybrid modulation of intra-EI excitatory and inhibitory synaptic strength in the extended neural mass model, the pathway from thalamic relay nucleus to the excitatory interneurons facilitates the transitions between different types of epileptic activities, either from interictal to ictal or between clonic, absence and tonic seizures.…”

Section: Without Ei With Eimentioning

confidence: 97%

The critical modulatory role of spiny stellate cells in seizure onset based on dynamic analysis of a neural mass model

Tabatabaee

Bahrami

Janahmadi

2021

Preprint

View full text Add to dashboard Cite

Increasing evidence has shown that excitatory neurons in the brain play a significant role in seizure generation. However, spiny stellate cells are cortical excitatory non-pyramidal neurons in the brain which their basic role in seizure occurrence is not well understood. In the present research, we study the critical role of spiny stellate cells or the excitatory interneurons (EI), for the first time, in epileptic seizure generation using an extended neural mass model introduced originally by Taylor and colleagues in 2014. Applying bifurcation analysis on this modified model, we investigated the rich dynamics corresponding to the epileptic seizure onset and transition between interictal and ictal states due to the EI. Our results indicate that the transition is described by a supercritical Hopf bifurcation which shapes the preictal activity in the model and suggests why before seizure onset, the amplitude and frequency of neural activities increase gradually. Moreover, we showed that 1) the altered function of GABAergic and glutamatergic receptors of EI can cause seizure, and 2) the pathway between the thalamic relay nucleus and EI facilitates the transition from interictal to the ictal activity by decreasing the preictal period. Thereafter, we considered both sensory and cortical periodic inputs to drive the model responses to various harmonic stimulations. Our results from the bifurcation analysis of the model suggest that the initial stage of the brain might be the main cause for the transition between interictal and ictal states as the stimulus frequency changes. The extended thalamocortical model shows also that the amplitude jump phenomenon and nonlinear resonance behavior result from the preictal stage of the brain. These results can be considered as a step forward to a deeper understanding of the mechanisms underlying the transition from brain normal activities to epileptic activities.

show abstract

“…Ratnaprabha Ravindra Borhade et al [11] worked on Deep Recurrent Neural Network (Deep-RNN) with Quick rate of convergence, easy implementation, less complexity, and increased speed but it need high cost for initial set up and expensive in training complex data sets. Banu Priya Prathaban et al [12] introduced Grey Wolf Optimized Model Driven (GWO-MD) method which reduced the time needed for computation and less complexity but it has slow rate of convergence. Mustafa Sameer and Bharat Gupta [13] worked with combination of Alpha features, KNN, NB, DT, SVM, Adaboost, Random forest classi er to enhance the accuracy and high classi cation capability.…”

Section: Motivation For the Researchmentioning

confidence: 99%

Ensemble Modelling for Predicting the Relation between Bio-psychosocial Signals and Seizures using the Gradient Boosting Method

Kapoor

Nagpal

2022

Preprint

View full text Add to dashboard Cite

In recent years, research in the fields of brain-computer interfacing techniques and related areas are developing at a very rapid rate with the help of exploding of Artificial Intelligence, Machine Learning and Deep Learning. A new concept of Ensemble Learnings has become popular research area among the researchers related to the field of automatic classification of electroencephalograph signals for predication of mental health issues like seizures. However effective feature extraction from EEG and accurately classify them with efficient classifiers is still an important task and attracted wide attention in this area. Therefore in this paper, we presented the detailed mathematical analysis of these methods and Ensemble Learnings based EEG signals classification method for seizures using Extreme Gradient Boosting Model.Time-frequency domain based non-linear features are selected from preprocessed EEG Dataset, and PCA (Principal Component Analysis) is used for dimensionality reduction for features engineering, then optimized feature based training and testing is done for two class classification in ensemble learning method (XGBoost) and Random Forest method. Finally, both models are tested with dataset of University of Bonn, Germany to classify the signals. In addition this paper highlights the Correlation Analysis Methodology to Identify Strong Predictor and Attributes Correlation-based Attribute Ranking for the Feature Engineering which has proved to be more efficient in EEG signals Classification and provide comparative analysis with other existing models for performance evaluation in terms of accuracy, specificity and sensitivity.

show abstract

WITHDRAWN: Prediction of epileptic seizures using Grey Wolf Optimized Model Driven mathematical approach

Cited by 9 publications

References 15 publications

The Critical Modulatory Role of Spiny Stellate Cells in Seizure Onset Based on Dynamic Analysis of a Neural Mass Model

The Critical Modulatory Role of Spiny Stellate Cells in Seizure Onset Based on Dynamic Analysis of a Neural Mass Model

The critical modulatory role of spiny stellate cells in seizure onset based on dynamic analysis of a neural mass model

Ensemble Modelling for Predicting the Relation between Bio-psychosocial Signals and Seizures using the Gradient Boosting Method

Contact Info

Product

Resources

About