Multi-Feature Fusion Approach for Epileptic Seizure Detection From EEG Signals

Radman, Moein; Moradi, Milad; Chaibakhsh, Ali; Kordestani, Mojtaba; Saif, Mehrdad

doi:10.1109/jsen.2020.3026032

Cited by 64 publications

(16 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 2020 ) and multi-feature fusion (Radman et al. 2020 ) methods. Our proposed method differs from those works by focusing on hierarchical attention-based 1-D CNN for appropriate learning and classification.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism

Chirasani

Manikandan

2022

Soft Comput

View full text Add to dashboard Cite

Electroencephalogram (EEG) is a common diagnostic tool for measuring the seizure activity of the brain. There are many deep learning techniques introduced to analyze EEG. These methods show phenomenal results, although they are limited to computational complexity. Our objective was to develop a novel algorithm that gives maximum classification accuracy with a minor computational complexity. In this view, we have introduced a novel convolutional architecture with an integration of a hierarchical attention mechanism. The model comprises three parts: Feature extraction layer, which uses to extract the convoluted feature map; hierarchical attention layer, which is used to obtain weighted hierarchical feature map; classification layer, which uses weighted features for classification of healthy and seizure subjects. The proposed model can extract significant information from the EEG signal to classify seizure subjects, and it is compared with a few existing deep convolutional algorithms through experimentation. The experimental outcomes show that the proposed model has higher accuracy with less computational time.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism

Chirasani

Manikandan

2022

Soft Comput

View full text Add to dashboard Cite

show abstract

“…where k,i is the feature value of the i − th feature of the k − th negative class sample, and p is the feature dimension. e larger the F value, the stronger the discrimination of the corresponding features [21]. e traditional F-score method sorts the features according to the Fisher score and then selects the top K features for subsequent classification.…”

Section: Hybrid Feature Selection Methodmentioning

confidence: 99%

Motor Imagery EEG Decoding Based on New Spatial-Frequency Feature and Hybrid Feature Selection Method

Tang

Zhao

Zhang

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Feature extraction and selection are important parts of motor imagery electroencephalogram (EEG) decoding and have always been the focus and difficulty of brain-computer interface (BCI) system research. In order to improve the accuracy of EEG decoding and reduce model training time, new feature extraction and selection methods are proposed in this paper. First, a new spatial-frequency feature extraction method is proposed. The original EEG signal is preprocessed, and then the common spatial pattern (CSP) is used for spatial filtering and dimensionality reduction. Finally, the filter bank method is used to decompose the spatially filtered signals into multiple frequency subbands, and the logarithmic band power feature of each frequency subband is extracted. Second, to select the subject-specific spatial-frequency features, a hybrid feature selection method based on the Fisher score and support vector machine (SVM) is proposed. The Fisher score of each feature is calculated, then a series of threshold parameters are set to generate different feature subsets, and finally, SVM and cross-validation are used to select the optimal feature subset. The effectiveness of the proposed method is validated using two sets of publicly available BCI competition data and a set of self-collected data. The total average accuracy of the three data sets achieved by the proposed method is 82.39%, which is 2.99% higher than the CSP method. The experimental results show that the proposed method has a better classification effect than the existing methods, and at the same time, feature extraction and feature selection time also have greater advantages.

show abstract

“…Radman et al [15] present a novel fusion system-based DSET algorithm for ESD in brain disorders. First, different characteristics in temporal-spectral, temporal, and spectral fields are extracted from the EEG signal.…”

Section: Literature Reviewmentioning

confidence: 99%

An automated deep learning enabled brain signal classification for epileptic seizure detection on complex measurement systems

et al. 2022

View full text Add to dashboard Cite

Multi-Feature Fusion Approach for Epileptic Seizure Detection From EEG Signals

Cited by 64 publications

References 54 publications

RETRACTED ARTICLE: A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism

RETRACTED ARTICLE: A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism

Motor Imagery EEG Decoding Based on New Spatial-Frequency Feature and Hybrid Feature Selection Method

An automated deep learning enabled brain signal classification for epileptic seizure detection on complex measurement systems

Contact Info

Product

Resources

About