Transfer discriminative dictionary learning with label consistency for classification of EEG signals of epilepsy
- PDF / 1,566,019 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 68 Downloads / 199 Views
ORIGINAL RESEARCH
Transfer discriminative dictionary learning with label consistency for classification of EEG signals of epilepsy Tongguang Ni1 · Xiaoqing Gu1 · Yizhang Jiang2 Received: 7 July 2020 / Accepted: 12 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract EEG signal classification play an important role in recognition of epilepsy. Recently, dictionary learning algorithms have shown the effectiveness in this field. When designing dictionaries, due to highly non-stationary of EEG signals, and collecting signals existing in different stimulus and drug modes, training and testing scenarios may be different. Thus, the performance of classical dictionary learning algorithms is unsatisfactory. In this paper, a transfer discriminative dictionary learning with label consistency (called TDDLLC) algorithm is proposed for EEG signal classification. Since each EEG signal can be represented as a linear combination of dictionary atoms, and some atoms are dataset independent, two dictionaries are learned simultaneously in source domain (SD) and target domain (TD) respectively where the discrepancy between two dictionaries is minimized. Meanwhile, utilizing the label information of samples in SD and a small number of labeled samples in TD, these dictionaries are learned with the aim of achieving discriminative abilities. To avoid the NP-hard problem, 𝓁1-norm regularization term is used in TDDLLC, and objective function is solved by block-coordinate descent method. Extensive experiments have been performed on Bonn dataset and show the validity of the TDDLLC algorithm. Keywords Dictionary learning · Transfer learning · Label consistency · EEG signal classification · Epilepsy
1 Introduction Epilepsy is a transient brain dysfunction caused by a brain injury. One of its main characters is to have recurring seizures. Epilepsy is one of the most common diseases in the human brain and is extremely harmful to human health (Mendoza et al. 2019; Wang et al. 2018; Zhang et al. 2018a). Electroencephalogram (EEG) signals from patients with epilepsy contain a large amount of physiological and pathological information in the brain, so the intelligent identification of EEG is very important for detection of epilepsy (Hu et al. 2019; Kevric et al. 2017; Sridhar et al. 2019). Meanwhile, * Yizhang Jiang [email protected] Tongguang Ni hbxtntg‑[email protected] Xiaoqing Gu [email protected] 1
School of Information Science and Engineering, Changzhou University, Changzhou 213164, China
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
2
more and more researches are focus on the automatic recognition of EEG signals of epilepsy. The EEG epilepsy recognizer can be considered as a classifier in pattern recognition. For classical epilepsy recognition, feature extraction and classification are two core components. The goal of feature extraction is to characterize distinctive EEG patterns, and the feature representation directly affects the performance of epilepsy
Data Loading...
