Name
Abstract | ||
|---|---|---|
Analysis and classification of Electroencephalography (EEG) Data are still a big challenge. This kind if data is very sensitive and complex. EEG data plays a big role not only in medicine. The EEG data can be used as control commands of an external device, e.g. wheelchair, prosthesis, and many others. To do this, we need to establish models which can correctly classify captured EEG data. This paper presents a model based on Butterworth IIR filter, Fast Fourier transform (FFT), Singular Value Decomposition (SVD) and Decision Tree (DT) as a classifier. It can classify finger flexions - with accuracy up to 92.241% for three fingers - thumb, index, and middle. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1007/978-3-319-60834-1_7 | AECIA |
Keywords | DocType | Volume |
EEG,Finger flexion,Decision Tree,Fast Fourier transform,Singular Value Decomposition | Conference | 565 |
ISSN | Citations | PageRank |
2194-5357 | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Michal Prilepok | 1 | 32 | 6.45 |
| Ibrahim Salem Jahan | 2 | 0 | 0.34 |
| Václav Snasel | 3 | 1261 | 210.53 |