Please use this identifier to cite or link to this item:
https://doi.org/10.1109/EMBC.2013.6610156
DC Field | Value | |
---|---|---|
dc.title | A tensorial approach to access cognitive workload related to mental arithmetic from EEG functional connectivity estimates | |
dc.contributor.author | Dimitriadis, S.I. | |
dc.contributor.author | Sun, Y. | |
dc.contributor.author | Kwok, K. | |
dc.contributor.author | Laskaris, N.A. | |
dc.contributor.author | Bezerianos, A. | |
dc.date.accessioned | 2014-11-28T01:53:16Z | |
dc.date.available | 2014-11-28T01:53:16Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Dimitriadis, S.I., Sun, Y., Kwok, K., Laskaris, N.A., Bezerianos, A. (2013). A tensorial approach to access cognitive workload related to mental arithmetic from EEG functional connectivity estimates. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS : 2940-2943. ScholarBank@NUS Repository. https://doi.org/10.1109/EMBC.2013.6610156 | |
dc.identifier.isbn | 9781457702167 | |
dc.identifier.issn | 1557170X | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/111529 | |
dc.description.abstract | The association of functional connectivity patterns with particular cognitive tasks has long been a topic of interest in neuroscience, e.g., studies of functional connectivity have demonstrated its potential use for decoding various brain states. However, the high-dimensionality of the pairwise functional connectivity limits its usefulness in some real-time applications. In the present study, the methodology of tensor subspace analysis (TSA) is used to reduce the initial high-dimensionality of the pairwise coupling in the original functional connectivity network to a space of condensed descriptive power, which would significantly decrease the computational cost and facilitate the differentiation of brain states. We assess the feasibility of the proposed method on EEG recordings when the subject was performing mental arithmetic task which differ only in the difficulty level (easy: 1-digit addition v.s. 3-digit additions). Two different cortical connective networks were detected, and by comparing the functional connectivity networks in different work states, it was found that the task-difficulty is best reflected in the connectivity structure of sub-graphs extending over parietooccipital sites. Incorporating this data-driven information within original TSA methodology, we succeeded in predicting the difficulty level from connectivity patterns in an efficient way that can be implemented so as to work in real-time. © 2013 IEEE. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/EMBC.2013.6610156 | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | LIFE SCIENCES INSTITUTE | |
dc.description.doi | 10.1109/EMBC.2013.6610156 | |
dc.description.sourcetitle | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS | |
dc.description.page | 2940-2943 | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.