Adapting instance weights for unsupervised domain adaptation using quadratic mutual information and subspace learning

Khan, Marium; Heisterkamp, Douglas R.

doi:10.1109/icpr.2016.7899859

Cited by 25 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on instance transfer, the majority of the literature utilized the measurement method to evaluate the similarity between data from the source and target domains. The similarity metric was then converted into the transfer weight coefficient, which was directly used to instance transfer by re-weighting the source domain data [30][31][32]. Herein, we have listed a few typical methods based on instance transfer.…”

Section: Transfer Learning Based On Instance Knowledgementioning

confidence: 99%

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

Zhang

Zheng

et al. 2020

Sensors

View full text Add to dashboard Cite

The algorithms of electroencephalography (EEG) decoding are mainly based on machine learning in current research. One of the main assumptions of machine learning is that training and test data belong to the same feature space and are subject to the same probability distribution. However, this may be violated in EEG processing. Variations across sessions/subjects result in a deviation of the feature distribution of EEG signals in the same task, which reduces the accuracy of the decoding model for mental tasks. Recently, transfer learning (TL) has shown great potential in processing EEG signals across sessions/subjects. In this work, we reviewed 80 related published studies from 2010 to 2020 about TL application for EEG decoding. Herein, we report what kind of TL methods have been used (e.g., instance knowledge, feature representation knowledge, and model parameter knowledge), describe which types of EEG paradigms have been analyzed, and summarize the datasets that have been used to evaluate performance. Moreover, we discuss the state-of-the-art and future development of TL for EEG decoding. The results show that TL can significantly improve the performance of decoding models across subjects/sessions and can reduce the calibration time of brain–computer interface (BCI) systems. This review summarizes the current practical suggestions and performance outcomes in the hope that it will provide guidance and help for EEG research in the future.

show abstract

Section: Transfer Learning Based On Instance Knowledgementioning

confidence: 99%

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

Zhang

Zheng

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…To efficiently use the similarity with the target domain, some source domain data samples are reused according to weight generation rules to carry out the transfer learning [21][22][23][24]. The instance-based weight method has rich theoretical achievements and is easily deduced and used.…”

Section: Instance-based Transfer Learningmentioning

confidence: 99%

A Review of Transfer Learning for EEG-Based Driving Fatigue Detection

Cui

Peng

Ozawa

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Driver mental state detection has been playing an increasingly significant role in safe driving for decades. Electroencephalogram (EEG)-based detection methods have already been applied to improve detection performance. However, numerous problems still have not been addressed in practical applications. Specifically, most of the existing traditional methods require a large number of training data, caused by differences in cross-subject samples and cross-time of the same subject, resulting in enormous calculations and time consumption. To overcome the above limitations, transfer learning, which applies data or knowledge from the source domain to the target domain, has been widely adopted in EEG processing. This article reviews the current state of mainstream transfer learning methods and their application based on driver mental state detection. To the best of our knowledge, this is the first comprehensive review of transfer learning methods for driving fatigue detection.

show abstract

“…Therefore, it is a more challenging task compared with the semi-supervised scenario. There are multiple UDA methods have been proposed [19], [20], [21], [22], [23], [24], [25] in recent years which achieved promising results. These methods could be grouped into three categories, which are 1) source-target divergence metric-based methods, 2) generalization extension-based methods, and 3) constant term-based methods [26].…”

Section: A Unsupervised Domain Adaptationmentioning

confidence: 99%

Semi-supervised Domain Adaptive Structure Learning

Qin¹,

Wang²,

Ma³

et al. 2021

Preprint

View full text Add to dashboard Cite

Adapting instance weights for unsupervised domain adaptation using quadratic mutual information and subspace learning

Cited by 25 publications

References 11 publications

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review

A Review of Transfer Learning for EEG-Based Driving Fatigue Detection

Semi-supervised Domain Adaptive Structure Learning

Contact Info

Product

Resources

About