Cross-domain EEG signal classification via geometric preserving transfer discriminative dictionary learning

Gu, Xiaoqing; Shen, Zongxuan; Qu, Jia; Ni, Tongguang

doi:10.1007/s11042-021-11244-w

Cited by 7 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a white box model meets the interpretability requirement in the field of medicine well. Consequently, we use the Takagi-Sugeno-Kang (TSK) fuzzy system as a basis to design our model in this study [3,4]. TSK fuzzy systems usually optimize parameters via three pathways: 1) by the genetic algorithm, 2) by the least square method, and 3) by back propagation (BP)-based gradient descent.…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain TSK Fuzzy System Based on Semi-Supervised Learning for Epilepsy Classification

Cheng¹,

Tao²,

Gu³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Through semi-supervised learning and knowledge inheritance, a novel Takagi-Sugeno-Kang (TSK) fuzzy system framework is proposed for epilepsy data classi cation in this study. The new method is based on the maximum mean discrepancy (MMD) method and TSK fuzzy system, as a basic model for the classi cation of epilepsy data. First, for medical data, the interpretability of TSK fuzzy systems can ensure that the prediction results are traceable and safe. Second, in view of the deviation in the data distribution between the real source domain and the target domain, MMD is used to measure the distance between di erent data distributions. The objective function is constructed according to the MMD distance, and the distribution distance of di erent datasets is minimized to nd the similar characteristics of di erent datasets. We introduce semi-supervised learning to further explore the relationship between data. Based on the MMD method, a semi-supervised learning (SSL)-MMD method is constructed by using pseudo-tags to realize the data distribution alignment of the same category. In addition, the idea of knowledge dissemination is used to learn pseudo-tags as additional data features. Finally, for epilepsy classi cation, the cross-domain TSK fuzzy system uses the cross-entropy function as the objective function and adopts the back-propagation strategy to optimize the parameters. The experimental results show that the new method can process complex epilepsy data and identify whether patients have epilepsy.

show abstract

Section: Introductionmentioning

confidence: 99%

Cross-Domain TSK Fuzzy System Based on Semi-Supervised Learning for Epilepsy Classification

Cheng¹,

Tao²,

Gu³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

Transfer Learning Based Seizure Detection: A Review

Cui

Cao

Jiang

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

A design of bat-based optimized deep learning model for EEG signal analysis

Gupta¹,

Kanungo²,

Kumar

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

Depression is one of the mental illnesses that negatively affect a person's thinking, action, and feeling. Thus the rate of depression is identified by analyzing Electroencephalogram (EEG) signals, but it has the problem of classifying depression rate because of noise. In this paper, a novel Bat-based UNET Signal Analysis (BUSA) framework is designed to organize the depression rate of patients with an EEG dataset. This technique involves preprocessing, feature selection, feature extraction, and classification. After the data training process preprocessing function was activated to remove the noise in the brain signal. Hereafter, the noiseless signal is used for the further process.Here, the fitness of the bat is upgraded in the UNET classification layer. Moreover, the brain signal's feature selection and depression rate were classified using the bat fitness that has helped to gain the desired output. Finally, performance metrics of the proposed BUSA technique are compared with other existing methods regarding the accuracy, AUC, precision, recall, and power. In that, the developed framework has attained better results to classify depression rates.

show abstract

Cross-domain EEG signal classification via geometric preserving transfer discriminative dictionary learning

Cited by 7 publications

References 36 publications

Cross-Domain TSK Fuzzy System Based on Semi-Supervised Learning for Epilepsy Classification

Cross-Domain TSK Fuzzy System Based on Semi-Supervised Learning for Epilepsy Classification

Transfer Learning Based Seizure Detection: A Review

A design of bat-based optimized deep learning model for EEG signal analysis

Contact Info

Product

Resources

About