دورية أكاديمية
Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures.
| العنوان: | Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures. |
|---|---|
| المؤلفون: | Mwata-Velu, Tat'y, Zamora, Erik, Vasquez-Gomez, Juan Irving, Ruiz-Pinales, Jose, Sossa, Humberto |
| المصدر: | Sensors (Basel) ; ISSN:1424-8220 ; Volume:24 ; Issue:12 |
| بيانات النشر: | MDPI |
| سنة النشر: | 2024 |
| المجموعة: | PubMed Central (PMC) |
| مصطلحات موضوعية: | EEGNet, brain–computer interfaces (BCIs), convolutional neural network (CNN), long short-term memory (LSTM), minimum-norm estimate (MNE), mutual information (MutIn), visual EEG classification |
| الوصف: | This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K). |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| العلاقة: | https://doi.org/10.3390/s24123968Test; https://pubmed.ncbi.nlm.nih.gov/38931751Test; https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11207572Test/ |
| DOI: | 10.3390/s24123968 |
| الإتاحة: | https://doi.org/10.3390/s24123968Test https://pubmed.ncbi.nlm.nih.gov/38931751Test https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11207572Test/ |
| رقم الانضمام: | edsbas.2B5DBAAB |
| قاعدة البيانات: | BASE |
| DOI: | 10.3390/s24123968 |
|---|