Realising transfer learning through convolutional neural network and support vector machine for mental task classification

Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Electronics letters Ročník 56; číslo 25; s. 1375 - 1378
Hlavní autoři:	Singh, D, Singh, S
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	The Institution of Engineering and Technology 10.12.2020
Témata:	BCI brainwaves brain‐computer interface applications brain‐computer interfaces classification accuracy conventional machine learning approaches convolutional neural nets convolutional neural network‐based approach data availability data scarcity diverse feature extraction EEG signal EEG‐based classification electroencephalogram electroencephalography false‐positive rates feature extraction learning (artificial intelligence) medical signal processing mental task classification model misclassification ratio model selection optimal network pre‐trained network Resnet18 Resnet50 signal classification Special Issue: Current Trends in Cognitive Science and Brain Computing Research and Applications support vector machine support vector machines training data transfer learning model Vgg16 Vgg19 brain-computer interfaces misclassification ratio Resnet50 classification accuracy diverse feature extraction brain-computer interface applications mental task classification model data scarcity optimal network feature extraction pre-trained network data availability training data conventional machine learning approaches learning (artificial intelligence) EEG-based classification electroencephalography brainwaves support vector machines model selection BCI false-positive rates EEG signal transfer learning model electroencephalogram signal classification medical signal processing Vgg19 support vector machine Resnet18 Vgg16 convolutional neural nets convolutional neural network-based approach
ISSN:	0013-5194, 1350-911X, 1350-911X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high false-positive rates are the challenges that need immediate attention. Therefore, in this Letter, the authors present a mental task classification model based on the notion of transfer learning that addresses the issue of data scarcity, model selection and misclassification ratio. In the framework, the proposed model uses pre-trained network for the extraction of diverse feature and classify using support vector machine. The authors employed four pre-trained networks to identify the optimal network for the proposed framework: Vgg16, Vgg19, Resnet18 and Resnet50. The highest classification accuracy of 86.85% (using Resnet50) was achieved using transfer learning. Comparison results showed that convolutional neural network-based approach outperformed conventional machine learning approaches and hence it can be concluded that the EEG-based classification of the mental task using transfer learning model could be used in developing a superior model despite the limited data availability.
ISSN:	0013-5194 1350-911X 1350-911X
DOI:	10.1049/el.2020.2632