FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229049930> ?p ?o ?g. }

• W4229049930 endingPage "13" @default.
• W4229049930 startingPage "1" @default.
• W4229049930 abstract "With the rapid development of deep learning, researchers have gradually applied it to motor imagery brain computer interface (MI-BCI) and initially demonstrated its advantages over traditional machine learning. However, its application still faces many challenges, and the recognition rate of electroencephalogram (EEG) is still the bottleneck restricting the development of MI-BCI. In order to improve the accuracy of EEG classification, a DSC-ConvLSTM model based on the attention mechanism is proposed for the multi-classification of motor imagery EEG signals. To address the problem of the small sample size of well-labeled and accurate EEG data, the preprocessing uses sliding windows for data augmentation, and the average prediction loss of each sliding window is used as the final prediction loss for that trial. This not only increases the training sample size and is beneficial to train complex neural network models, but also the network no longer extracts the global features of the whole trial so as to avoid learning the difference features among trials, which can effectively eliminate the influence of individual specificity. In the aspect of feature extraction and classification, the overall network structure is designed according to the characteristics of the EEG signals in this paper. Firstly, depth separable convolution (DSC) is used to extract spatial features of EEG signals. On the one hand, this reduces the number of parameters and improves the response speed of the system. On the other hand, the network structure we designed is more conducive to extract directly the direct extraction of spatial features of EEG signals. Secondly, the internal structure of the Long Short-Term Memory (LSTM) unit is improved by using convolution and attention mechanism, and a novel bidirectional convolution LSTM (ConvLSTM) structure is proposed by comparing the effects of embedding convolution and attention mechanism in the input and different gates, respectively. In the ConvLSTM module, the convolutional structure is only introduced into the input-to-state transition, while the gates still remain the original fully connected mechanism, and the attention mechanism is introduced into the input to further improve the overall decoding performance of the model. This bidirectional ConvLSTM extracts the time-domain features of EEG signals and integrates the feature extraction capability of the CNN and the sequence processing capability of LSTM. The experimental results show that the average classification accuracy of the model reaches 73.7% and 92.6% on two datasets, BCI Competition IV Dataset 2a and High Gamma Dataset, respectively, which proves the robustness and effectiveness of the model we proposed. It can be seen that the model in this paper can deeply excavate significant EEG features from the original EEG signals, show good performance in different subjects and different datasets, and improve the influence of individual variability on the classification performance, which is of practical significance for promoting the development of brain-computer interface technology towards a practical and marketable direction." @default.
• W4229049930 created "2022-05-08" @default.
• W4229049930 creator A5008791425 @default.
• W4229049930 creator A5059144514 @default.
• W4229049930 date "2022-05-05" @default.
• W4229049930 modified "2023-09-26" @default.
• W4229049930 title "Attention-Based DSC-ConvLSTM for Multiclass Motor Imagery Classification" @default.
• W4229049930 cites W1969878365 @default.
• W4229049930 cites W2036341195 @default.
• W4229049930 cites W2081092123 @default.
• W4229049930 cites W2106006415 @default.
• W4229049930 cites W2116308679 @default.
• W4229049930 cites W2118872857 @default.
• W4229049930 cites W2119163516 @default.
• W4229049930 cites W2142280324 @default.
• W4229049930 cites W2145302786 @default.
• W4229049930 cites W2151669316 @default.
• W4229049930 cites W21769058 @default.
• W4229049930 cites W2507528282 @default.
• W4229049930 cites W2741907166 @default.
• W4229049930 cites W2894424125 @default.
• W4229049930 cites W2896120927 @default.
• W4229049930 cites W2911969890 @default.
• W4229049930 cites W2940740645 @default.
• W4229049930 cites W2986984881 @default.
• W4229049930 cites W2996722826 @default.
• W4229049930 cites W3004827935 @default.
• W4229049930 cites W3102455230 @default.
• W4229049930 doi "https://doi.org/10.1155/2022/8187009" @default.
• W4229049930 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35571721" @default.
• W4229049930 hasPublicationYear "2022" @default.
• W4229049930 type Work @default.
• W4229049930 citedByCount "1" @default.
• W4229049930 countsByYear W42290499302023 @default.
• W4229049930 crossrefType "journal-article" @default.
• W4229049930 hasAuthorship W4229049930A5008791425 @default.
• W4229049930 hasAuthorship W4229049930A5059144514 @default.
• W4229049930 hasBestOaLocation W42290499301 @default.
• W4229049930 hasConcept C102392041 @default.
• W4229049930 hasConcept C111919701 @default.
• W4229049930 hasConcept C113843644 @default.
• W4229049930 hasConcept C118552586 @default.
• W4229049930 hasConcept C119857082 @default.
• W4229049930 hasConcept C12267149 @default.
• W4229049930 hasConcept C129307140 @default.
• W4229049930 hasConcept C149635348 @default.
• W4229049930 hasConcept C153180895 @default.
• W4229049930 hasConcept C154945302 @default.
• W4229049930 hasConcept C15744967 @default.
• W4229049930 hasConcept C157915830 @default.
• W4229049930 hasConcept C173201364 @default.
• W4229049930 hasConcept C173608175 @default.
• W4229049930 hasConcept C2778751112 @default.
• W4229049930 hasConcept C2780513914 @default.
• W4229049930 hasConcept C34736171 @default.
• W4229049930 hasConcept C41008148 @default.
• W4229049930 hasConcept C50644808 @default.
• W4229049930 hasConcept C522805319 @default.
• W4229049930 hasConcept C52622490 @default.
• W4229049930 hasConcept C54808283 @default.
• W4229049930 hasConceptScore W4229049930C102392041 @default.
• W4229049930 hasConceptScore W4229049930C111919701 @default.
• W4229049930 hasConceptScore W4229049930C113843644 @default.
• W4229049930 hasConceptScore W4229049930C118552586 @default.
• W4229049930 hasConceptScore W4229049930C119857082 @default.
• W4229049930 hasConceptScore W4229049930C12267149 @default.
• W4229049930 hasConceptScore W4229049930C129307140 @default.
• W4229049930 hasConceptScore W4229049930C149635348 @default.
• W4229049930 hasConceptScore W4229049930C153180895 @default.
• W4229049930 hasConceptScore W4229049930C154945302 @default.
• W4229049930 hasConceptScore W4229049930C15744967 @default.
• W4229049930 hasConceptScore W4229049930C157915830 @default.
• W4229049930 hasConceptScore W4229049930C173201364 @default.
• W4229049930 hasConceptScore W4229049930C173608175 @default.
• W4229049930 hasConceptScore W4229049930C2778751112 @default.
• W4229049930 hasConceptScore W4229049930C2780513914 @default.
• W4229049930 hasConceptScore W4229049930C34736171 @default.
• W4229049930 hasConceptScore W4229049930C41008148 @default.
• W4229049930 hasConceptScore W4229049930C50644808 @default.
• W4229049930 hasConceptScore W4229049930C522805319 @default.
• W4229049930 hasConceptScore W4229049930C52622490 @default.
• W4229049930 hasConceptScore W4229049930C54808283 @default.
• W4229049930 hasLocation W42290499301 @default.
• W4229049930 hasLocation W42290499302 @default.
• W4229049930 hasLocation W42290499303 @default.
• W4229049930 hasOpenAccess W4229049930 @default.
• W4229049930 hasPrimaryLocation W42290499301 @default.
• W4229049930 hasRelatedWork W1486208236 @default.
• W4229049930 hasRelatedWork W2045193781 @default.
• W4229049930 hasRelatedWork W2076654769 @default.
• W4229049930 hasRelatedWork W2118502806 @default.
• W4229049930 hasRelatedWork W2126100045 @default.
• W4229049930 hasRelatedWork W2186720820 @default.
• W4229049930 hasRelatedWork W2336974148 @default.
• W4229049930 hasRelatedWork W2391959412 @default.
• W4229049930 hasRelatedWork W2584802378 @default.
• W4229049930 hasRelatedWork W2345184372 @default.
• W4229049930 hasVolume "2022" @default.

• next