A review on transfer learning in EEG signal analysis

Wan, Zitong; Yang, Rui; Huang, Mengjie; Zeng, Nianyin; Liu, Xiaohui

doi:10.1016/j.neucom.2020.09.017

Cited by 319 publications

(149 citation statements)

References 132 publications

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…In EEG analysis based on Deep Learning, for enhancing the classifier performance, transfer learning is a common approach to adjust a pre-trained neural network model equipped with the label probability vector

, aiming to provide a close domain distance measurement

, lower than a given value

, between the paired domains to approximate the source

to the target

[ 24 ], as follows:

…”

Section: Materials and Methodsmentioning

confidence: 99%

“…However, collecting extensive data is time-consuming and mentally exhausting during a prolonged recording session, deteriorating the measurement quality. To overcome this lack of subject-specific data, transfer learning-based approaches are increasingly integrated into MI systems using pre-existing information from other subjects (source domain) to facilitate the calibration for a new subject (target domain) through a set of shared features among individuals under the assumption of a unique data acquisition paradigm [ 22 , 23 , 24 ]. Therefore, to have the advantages of transfer learning in EEG signal analysis, strategies for individual difference matching and data requirement reduction are needed to fine-tune the model for the target subject [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Collazos-Huertas

Velásquez-Martínez

Perez-Nastar

et al. 2021

Sensors

View full text Add to dashboard Cite

Motor imagery (MI) promotes motor learning and encourages brain–computer interface systems that entail electroencephalogram (EEG) decoding. However, a long period of training is required to master brain rhythms’ self-regulation, resulting in users with MI inefficiency. We introduce a parameter-based approach of cross-subject transfer-learning to improve the performances of poor-performing individuals in MI-based BCI systems, pooling data from labeled EEG measurements and psychological questionnaires via kernel-embedding. To this end, a Deep and Wide neural network for MI classification is implemented to pre-train the network from the source domain. Then, the parameter layers are transferred to initialize the target network within a fine-tuning procedure to recompute the Multilayer Perceptron-based accuracy. To perform data-fusion combining categorical features with the real-valued features, we implement stepwise kernel-matching via Gaussian-embedding. Finally, the paired source–target sets are selected for evaluation purposes according to the inefficiency-based clustering by subjects to consider their influence on BCI motor skills, exploring two choosing strategies of the best-performing subjects (source space): single-subject and multiple-subjects. Validation results achieved for discriminant MI tasks demonstrate that the introduced Deep and Wide neural network presents competitive performance of accuracy even after the inclusion of questionnaire data.

show abstract

, aiming to provide a close domain distance measurement

, lower than a given value

, between the paired domains to approximate the source

to the target

[ 24 ], as follows:

…”

Section: Materials and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Collazos-Huertas

Velásquez-Martínez

Perez-Nastar

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Several behavioral and psychological states, such as attention, stress, anxiety, and/or sleep quality may contribute to the above EEG non-stationarity. Effectively alleviating non-stationarity is still an open challenge [ 65 – 67 ], and, therefore, the ERP-marker’s robustness has to be elucidated over repeated measurements interspaced in the chronic pharmacological plans. Lastly, we mainly addressed the ERP signatures’ feasibility to reflect the ICD adverse effect in patients with PD.…”

Section: Limitationsmentioning

confidence: 99%

Objective assessment of impulse control disorder in patients with Parkinson’s disease using a low-cost LEGO-like EEG headset: a feasibility study

Lin

Liang

Chen

et al. 2021

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background Patients with Parkinson’s disease (PD) can develop impulse control disorders (ICDs) while undergoing a pharmacological treatment for motor control dysfunctions with a dopamine agonist (DA). Conventional clinical interviews or questionnaires can be biased and may not accurately diagnose at the early stage. A wearable electroencephalogram (EEG)-sensing headset paired with an examination procedure can be a potential user-friendly method to explore ICD-related signatures that can detect its early signs and progression by reflecting brain activity. Methods A stereotypical Go/NoGo test that targets impulse inhibition was performed on 59 individuals, including healthy controls, patients with PD, and patients with PD diagnosed by ICDs. We conducted two Go/NoGo sessions before and after the DA-pharmacological treatment for the PD and ICD groups. A low-cost LEGO-like EEG headset was used to record concurrent EEG signals. Then, we used the event-related potential (ERP) analytical framework to explore ICD-related EEG abnormalities after DA treatment. Results After the DA treatment, only the ICD-diagnosed PD patients made more behavioral errors and tended to exhibit the deterioration for the NoGo N2 and P3 peak amplitudes at fronto-central electrodes in contrast to the HC and PD groups. Particularly, the extent of the diminished NoGo-N2 amplitude was prone to be modulated by the ICD scores at Fz with marginal statistical significance (r = − 0.34, p = 0.07). Conclusions The low-cost LEGO-like EEG headset successfully captured ERP waveforms and objectively assessed ICD in patients with PD undergoing DA treatment. This objective neuro-evidence could provide complementary information to conventional clinical scales used to diagnose ICD adverse effects.

show abstract

“…In transfer learning, a domain refers to a data set and its probability distribution. Particularly, the domain containing prior knowledge is called source domain, and the domain containing unknown knowledge is called target domain [39]. e aim of transfer learning is to learn the target task with the help of the knowledge of source task, such as features, parameters, and labels.…”

Section: Transfer Learningmentioning

confidence: 99%

Deep Transfer Learning-Based Fault Diagnosis for Gearbox under Complex Working Conditions

Wan

Yang

Huang

2020

Shock and Vibration

Self Cite

View full text Add to dashboard Cite

In the large amount of available data, information insensitive to faults in historical data interferes in gear fault feature extraction. Furthermore, as most of the fault diagnosis models are learned from offline data collected under single/fixed working condition only, this may cause unsatisfactory performance for complex working conditions (including multiple and unknown working conditions) if not properly dealt with. This paper proposes a transfer learning-based fault diagnosis method of gear faults to reduce the negative effects of the abovementioned problems. In the proposed method, a cohesion evaluation method is applied to select sensitive features to the task with a transfer learning-based sparse autoencoder to transfer the knowledge learnt under single working condition to complex working conditions. The experimental results on wind turbine drivetrain diagnostics simulator show that the proposed method is effective in complex working conditions and the achieved results are better than those of traditional algorithms.

show abstract

A review on transfer learning in EEG signal analysis

Cited by 319 publications

References 132 publications

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

Objective assessment of impulse control disorder in patients with Parkinson’s disease using a low-cost LEGO-like EEG headset: a feasibility study

Deep Transfer Learning-Based Fault Diagnosis for Gearbox under Complex Working Conditions

Contact Info

Product

Resources

About