Show simple item record

dc.contributor.authorHema, Chengalvarayan Radhakrishnamurthy
dc.contributor.authorPaulraj, Murugesapandian
dc.contributor.authorSazali, Yaacob
dc.contributor.authorAbd Hamid, Adom
dc.contributor.authorRamachandran, Nagarajan
dc.date.accessioned2009-12-14T08:25:47Z
dc.date.available2009-12-14T08:25:47Z
dc.date.issued2007-11-25
dc.identifier.citationp.1153-1156en_US
dc.identifier.isbn978-1-4244-1355-3
dc.identifier.urihttp://dspace.unimap.edu.my/123456789/7418
dc.identifier.urihttp://ieeexplore.ieee.org/xpls/abs_all.jsp?=&arnumber=4658565
dc.descriptionLink to publisher's homepage at http://ieeexplore.ieee.orgen_US
dc.description.abstractBrain machine interface provides a communication channel between the human brain and an external device. Brain interfaces are studied to provide rehabilitation to patients with neurodegenerative diseases; such patients loose all communication pathways except for their sensory and cognitive functions. One of the possible rehabilitation methods for these patients is to provide a brain machine interface (BMI) for communication, using the electrical activity of the brain detected by scalp EEG electrodes. Classification of EEG signals extracted during mental tasks is a technique for designing a BMI. In this paper a BMI design using five mental task EEG signals from two subjects were studied, a combination of two tasks is studied per subject. An Elman recurrent neural network is proposed for classification of EEG signals. Principal component analysis is used for extracting features from the EEG signals. The EEG signal is classified into two tasks. Ten such task combinations are studied. Average classification accuracies varied from 75.5% to 100% with a testing error tolerance of 0.05. The classification performance of the proposed algorithm is found to be better compared to our earlier work using AR model features.en_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineering (IEEE)en_US
dc.relation.ispartofseriesProceedings of the International Conference on Intelligent and Advanced Systems (ICIAS 2007)en_US
dc.subjectBrain-computer interfacesen_US
dc.subjectElectroencephalographyen_US
dc.subjectMedical signal processingen_US
dc.subjectSignal classificationen_US
dc.subjectEEG signal classificationen_US
dc.subjectFeature extractionen_US
dc.titleBrain machine interface: classification of mental tasks using short-time PCA and recurrent neural networksen_US
dc.typeWorking Paperen_US
dc.contributor.urlhema@unimap.edu.myen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record