A Deep Learning Approach for Classification of Reaching Targets from EEG Images
| Autor: | Ronan Boulic, Damares Crystina Oliveira de Resende, Henrique Galvan Debarba, Schubert R. Carvalho, Ana Carolina Siravenha, Bruno Gomes, Iraquitan Cordeiro Filho, Cleidson R. B. de Souza |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Brain-Computer Interface
medicine.diagnostic_test Artificial neural network Computer science business.industry Deep learning Feature extraction Early detection EEG Imagens 02 engineering and technology Electroencephalography Virtual reality Convolutional neural network Convolution 03 medical and health sciences Deep Learning 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Computer vision Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | SIBGRAPI Carvalho, S R, Filho, I C, Resende, D O D, Siravenha, A C, Souza, C D, Debarba, H G, Gomes, B & Boulic, R 2017, A Deep Learning Approach for Classification of Reaching Targets from EEG Images . in Proceedings-30th Conference on Graphics, Patterns and Images, SIBGRAPI 2017 ., 8097310, IEEE Signal Processing Society, Proceedings-30th Conference on Graphics, Patterns and Images, SIBGRAPI 2017, pp. 178-184, 30th Conference on Graphics, Patterns and Images, SIBGRAPI 2017, Niteroi, Rio de Janeiro, Brazil, 17/10/2017 . https://doi.org/10.1109/SIBGRAPI.2017.30 |
| DOI: | 10.1109/sibgrapi.2017.30 |
| Popis: | In this paper, we propose a new approach for the classification of reaching targets before movement onset, during visually-guided reaching in 3D space. Our approach combines the discriminant power of two-dimensional Electroencephalography (EEG) signals (i.e., EEG images) built from short epochs, with the feature extraction and classification capabilities of deep learning (DL) techniques, such as the Convolutional Neural Networks (CNN). In this work, reaching motions are performed into four directions: left, right, up and down. To allow more natural reaching movements, we explore the use of Virtual Reality (VR) to build an experimental setup that allows the subject to perform self-paced reaching in 3D space while standing. Our results reported an increase both in classification performance and early detection in the majority of our experiments. To our knowledge this is the first time that EEG images and CNN are combined for the classification of reaching targets before movement onset. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|