الفهرس 
Table of contentsOnly 14 pages are availabe for public view
 |  | from | 114 |  |  |
| | | from | 114 | | |
Abstract
In recent years, there are great research interests in using the Electroencephalogram (EEG) signal in biometric applications. The strength of EEG signal as a biometric comes from its major fraud prevention capability. However, EEG signals are so sensitive and many factors affect its usage as a biometric; two of these factors (that we concentrate on in this thesis) are (i) the number of channels (optimized to single channel), and (ii) the required duration for acquiring signal (optimized to one minute). The main contribution of the work we present here is that we propose two approaches. The first approach called Single-channel Single Minute (SCSM) approach. This approach is able to recognize subjects using only second recording from single channel of EEG. The second scheme is called .Deep learning Single-channel single Minute (DL-SCSM). In this case, We utilized the Long Short Term Memory (LSTM) which is often better in handling temporal information as a result of the forget gate that can control which information to save and update or discard. Different comparisons have been performed on common used classifications such as KNN, DT, SVM, NB, and RF. Set of performance measuring techniques have been applied such as TPR, FPR, Precision, Recall, and F-measure.