Name
Abstract | ||
|---|---|---|
In the field of brain computer interface (BCI), effective classification of motor imagery (MI) tasks is an important issue. Deep learning (DL) has attracted lots of attention and has been widely used in a great deal of areas such as speech recognition, object detection, and natural language processing (NLP). However, the use of deep learning approaches in BCI fields is remaining relatively lacking. In this paper, we introduce a method, combined the one-dimensional convolutional neural network (1D CNN) with long short-term memory (LSTM) to classify MI tasks, a novel deep learning network is formed. CNN and LSTM are used to extract the time representation of MI tasks. Performance of the put forward method has been estimated in the BCI competition IV dataset 2a. The outcomes demonstrate that our proposed method is capable of enhancing the classification accuracy compared to state of art approaches. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CISP-BMEI48845.2019.8965653 | 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) |
Keywords | DocType | ISBN |
BCI,motor imagery,deep learning,convolutional neural networks | Conference | 978-1-7281-4853-3 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Peijun Lu | 1 | 0 | 0.34 |
| Ning Gao | 2 | 0 | 0.34 |
| Zhao-Hua Lu | 3 | 66 | 12.54 |
| Jingjing Yang | 4 | 0 | 3.04 |
| Ou Bai | 5 | 50 | 14.24 |
| Qi Li | 6 | 410 | 78.59 |