Classification of mental task EEG records using Hjorth parameters [Mental Aktivitelere ilişkin EEG Kayitlarinin Hjorth Parametreleri ile Siniflandirilmasi]
Küçük Resim Yok
Tarih
2017
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of Electrical and Electronics Engineers Inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
The effects of mental activities on brain dynamics is the main field that studied for a long time, but the results of studies have not reached the desired level. The aim of present study was to classify the mental task EEG records by using Hjorth parameters. In this study, EEG signals that recorded from 9 subjects were used. EEG signals were recorded by applying a experimental paradigm which contains five stimuli related to different mental task. These stimuli are defined as condition word mental subtraction spatial navigation right hand motor imagery and feet motor imagery Wavelet packet transform was used to obtain sub-bands of EEG signals. Statistical parameters that consist of mobility, complexity and Mahalanobis distance were applied to sub-bands. Feature vectors were classified by using artificial neural network. When classification performances related to mental activities were examined, the best classification accuracy was obtained as nearly 80% for 'condition word - mental subtraction', ('spatial navigation - feet motor imagery;' and 'spatial navigation - condition word'. The lowest classification accuracy was obtained for 'mental subtraction - right hand motor imagery,', 'condition word - right hand motor imagery' and 'spatial navigation - right hand motor imagery'. The classification accuracies related to all stimuli that classifed among themselves were obtained as 77,61%. © 2017 IEEE.
Açıklama
25th Signal Processing and Communications Applications Conference, SIU 2017 -- 15 May 2017 through 18 May 2017 -- -- 128703
Anahtar Kelimeler
Hjorth Parameters, Mental Task, Waveler Packet Decomposition
Kaynak
2017 25th Signal Processing and Communications Applications Conference, SIU 2017
WoS Q Değeri
Scopus Q Değeri
N/A
