"JOURNAL OF RADIO ELECTRONICS"  N 1, 2012

contents             full texthtml,   pdf   

The problem of pattern recognition for the Parkinson's disease diagnosis based on electroencephalography data

 

F. N. Grigoryev, N. A. Kuznetsov

Kotelínikov Institute of Radio-engineering and Electronics of RAS

 Received January 26, 2012

 

Abstarct. The vector of estimates of normalized correlation sequence for signal O2-A2 EEG patient was defined for the diagnosis of Parkinson's disease. The linear decision rule - a hyperplane separating the sets of vectors corresponding to the patients and healthy individuals was created. The simulation of disease diagnosis in the real data was made.

Keywords: diagnosis, Parkinsonís disease, estimate, normalized correlation sequence, linear decision rule, decomposable hyperplane.