Name
Abstract | ||
|---|---|---|
Epileptic seizure EEG signals are both similar and different because of the differences between regions or countries and races, which forces us to consider the use of multitask learning strategies when processing these types of data. A neural network model with a multitask learning mechanism is proposed in this article, and its learning algorithm is based on the classical radial basis function neural network (RBF-NN), which is used to diagnose epileptic EEG signals. The proposed novel multitask RBF-NN (MT-RBF-NN) can extract similarity information and difference information between different tasks from different EEG data recognition tasks and optimize the parameters of the classification model to improve recognition performance. According to the final experimental results, the proposed MT-RBF NN has better recognition performance than the previous single-task learning classification model and has better robustness and generalization performance. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1166/jmihi.2019.2807 | JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS |
Keywords | DocType | Volume |
Radial Basis Function,Neural Network,Multitask Learning,EEG Data | Journal | 9 |
Issue | ISSN | Citations |
9 | 2156-7018 | 1 |
PageRank | References | Authors |
0.35 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yizhang Jiang | 1 | 2 | 3.73 |
| Jing Xue | 2 | 10 | 3.14 |
| Rong Wang | 3 | 3 | 1.41 |
| Kaijian Xia | 4 | 1 | 1.36 |
| Xiaoqing Gu | 5 | 6 | 3.47 |
| Jiaqi Zhu | 6 | 7 | 7.26 |
| Li Liu | 7 | 1 | 1.36 |
| Pengjiang Qian | 8 | 133 | 11.25 |