Key result
A 2D-CNN scalogram-based approach successfully distinguished attention and meditation mental states using EEG signals with an average classification accuracy of 87.48%.
Why the study?
EEG-based BCI systems developed for controlling devices via mental states can benefit individuals with neurological disorders, motivating algorithms to detect and distinguish attention and meditation states.
Does a 2D-CNN Scalogram based approach accurately classify attention and meditation mental states using EEG signals?
Does a 2D-CNN Scalogram based approach accurately classify attention and meditation mental states using EEG signals?
A 2D-CNN Scalogram based approach can classify attention and meditation mental states from EEG signals with 87.48% accuracy, which may be useful for brain-computer interface systems.
May support BCI development for mental-state monitoring; hypothesis-generating and requires prospective validation before clinical adoption.
EEG-based BCI system developed for controlling a device via mental states can be extremely beneficial to people suffering from neurological disorders. The objective of this paper is to present an algorithm for detecting and distinguishing the attention and meditation states of the human brain. This paper introduces a 2D-CNN Scalogram based approach to classify the mental tasks viz attention and meditation. First, this study focuses on the signals originating in the human brain in attentive and meditative states acquired using scalp EEG electrodes. Second, EEG-based 1D signals have been converted into 2D images (scalograms) because the information between time and frequency coefficients in 1D data is generally missing. Then, these images have been resized in grayscale format. And, thus obtained feature images have been fed as input to 2D CNN for classification. The proposed method successfully distinguishes the attention and meditation mental states performed by the volunteers with an average classification accuracy of 87.48%.
No takes yet. Share an insight, caveat, or question.
Chaudhary et al. (2022) studied Attention and meditation mental states. 2D-CNN Scalogram based approach was evaluated on Classification accuracy of attention and meditation mental states. A 2D-CNN scalogram-based approach successfully distinguished attention and meditation mental states using EEG signals with an average classification accuracy of 87.48%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: