Journal
JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS
Volume 9, Issue 9, Pages 1865-1870Publisher
AMER SCIENTIFIC PUBLISHERS
DOI: 10.1166/jmihi.2019.2807
Keywords
Radial Basis Function; Neural Network; Multitask Learning; EEG Data
Funding
- National Natural Science Foundation of China [61702225, 61772241]
- Natural Science Foundation of Jiangsu Province [BK20160187]
- 2018 Six Talent Peaks Project of Jiangsu Province [XYDXX-127]
- Science and Technology demonstration project of social development of Wuxi [WX18IVJN002]
- Youth Foundation of the Commission of Health and Family Planning of Wuxi [Q201654]
- Jiangsu Committee of Health [H2018071]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available