2019 International Joint Conference on Neural Networks (IJCNN) 2019
DOI: 10.1109/ijcnn.2019.8852362
|View full text |Cite
|
Sign up to set email alerts
|

EEG-Based Motor Imagery Classification with Deep Multi-Task Learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
14
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
3
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 24 publications
(14 citation statements)
references
References 23 publications
0
14
0
Order By: Relevance
“…Thus, it can yield fast learning speed and increase data efficiency for related or downstream tasks. For example, Song et al proposed an EEG classification method based on multi-task DL [11], as shown in Fig. 4.…”
Section: Discriminator Classifiermentioning
confidence: 99%
See 1 more Smart Citation
“…Thus, it can yield fast learning speed and increase data efficiency for related or downstream tasks. For example, Song et al proposed an EEG classification method based on multi-task DL [11], as shown in Fig. 4.…”
Section: Discriminator Classifiermentioning
confidence: 99%
“…However, EEG classification performance deteriorates as the number of available training samples diminishes, emphasizing the need for robust DL models under more typical small sample size scenarios [10]. Transfer learning [8], multi-task learning [11] and multi-modal learning [12] have been recently proposed to address small-sample data concerns. DL models have usually assumed that the categories of the test EEG signals have been seen during training.…”
Section: Introductionmentioning
confidence: 99%
“…To confirm the effectiveness and accuracy of the proposed method, we first conducted intra-subject classification using BCIIV2a and compared the accuracy of our method with that given by state-of-the-art DL-based methods [EEGNet (Lawhern et al, 2018), DeepCNN (Schirrmeister et al, 2017), M3DCNN (Zhao et al, 2019), LTICNN (Sakhavi et al, 2018), DMTLCNN (Song et al, 2019), MCCNN (Amin et al, 2019), WTL (Azab et al, 2019)]; traditional FBCSP (Ang et al, 2012) was used as a baseline method to recognize MI EEG data, and an SVM was used as the classifier. Table 4 lists the accuracy of the various methods for each subject and the corresponding average accuracy for the BCIIV2a dataset.…”
Section: Quantitative Evaluation Of Bciiv2a For Intra-subject Classifmentioning
confidence: 99%
“…Azab et al (2019) proposed a novel weighted transfer learning approach that improves the accuracy of MI classification in BCI systems. Song et al (2019) improved the classification performance with limited EEG data by combining the representation module, classification module, and reconstruction module into an end-to-end framework. Sakhavi et al (2018) introduced a new data representation using a spatial-temporal DL model architecture that is designed to learn temporal information from the original input signals.…”
Section: Introductionmentioning
confidence: 99%
“…Brain-computer-interface(BCI) technology has drawn much attention globally due to its significant meaning and extensive applications [1]. It enables their users to interact with the machine through the brain signals [2], such as the task of converting the psychological imagination of motion into a command [3], which can be utilized to help people with disabilities as a rehabilitation device [4] and could be considered the only way for people with motor disabilities to communicate [5].…”
Section: Introductionmentioning
confidence: 99%