دورية أكاديمية
Deep Learning with ConvNet Predicts Imagery Tasks Through EEG
| العنوان: | Deep Learning with ConvNet Predicts Imagery Tasks Through EEG |
|---|---|
| المؤلفون: | Altan, Gökhan, Yayık, Apdullah, Kutlu, Yakup |
| المساهمون: | Mühendislik ve Doğa Bilimleri Fakültesi -- Bilgisayar Mühendisliği Bölümü, Altan, Gökhan, Kutlu, Yakup |
| بيانات النشر: | Springer |
| سنة النشر: | 2021 |
| المجموعة: | DSpace@ISTE (Iskenderun Technical University Institutional Repository) |
| مصطلحات موضوعية: | ConvNets, Deep learning, EEG, Predicting imagined hand movements, Motor Imagery, Brain Computer Interface, Visual Evoked Potentials, Computer Science, Neural networks, Convolutional neural networks, Electroencephalography, Electrophysiology, Forecasting, Learning systems, Predictive analytics, Classification performance, Computer vision applications, Different structure, Extreme learning machine, Fully connected neural network, Learning capabilities, Prediction model, Spectral feature, Learning algorithms |
| الوصف: | Deep learning with convolutional neural networks (ConvNets) has dramatically improved the learning capabilities of computer vision applications just through considering raw data without any prior feature extraction. Nowadays, there is a rising curiosity in interpreting and analyzing electroencephalography (EEG) dynamics with ConvNets. Our study focused on ConvNets of different structures, the efficiency of multiple machine learning algorithms with optimization on ConvNets, constructing for predicting imagined left and right movements on a subject-independent basis through raw EEG data. We adapted novel lower-upper triangularization based extreme learning machines (LuELM) to the ConvNet architecture. Results showed that recently advanced methods in machine learning field, i.e. adaptive moments and batch normalization together with dropout strategy, improved ConvNets predicting ability, outperforming that of conventional fully-connected neural networks with widely-used spectral features. The proposed prediction model achieved improvements in classification performances with the rates of 90.33%, 91.00%, and 89.67% for accuracy, recall, and specificity, respectively. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | application/pdf |
| اللغة: | English |
| العلاقة: | Neural Processing Letters; Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı; Web of Science - Scopus; Web of Science Core Collection - Science Citation Index Expanded; https://doi.org/10.1007/s11063-021-10533-7Test; https://hdl.handle.net/20.500.12508/1931Test; 53; 2917; 2932 |
| DOI: | 10.1007/s11063-021-10533-7 |
| الإتاحة: | https://doi.org/20.500.12508/1931Test https://doi.org/10.1007/s11063-021-10533-7Test https://hdl.handle.net/20.500.12508/1931Test |
| حقوق: | info:eu-repo/semantics/openAccess |
| رقم الانضمام: | edsbas.97E5DCFA |
| قاعدة البيانات: | BASE |
| DOI: | 10.1007/s11063-021-10533-7 |
|---|