Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2018
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.17329209 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901643682906112 |
|---|---|
| author | Pakgohar, Amirpouya |
| author_facet | Pakgohar, Amirpouya |
| contents | <p>The person identification by Electroencephalographic (EEG) signals has attracted the</p> <p>researchers’ great attention in recent years and lots of investigations have been</p> <p>developed. An identification system seeks to identify a person in a database. The</p> <p>advantage of using EEG signals for person identification is the difficulty in generating</p> <p>artificial signals for imposters. But more works need to be done to use EEG based</p> <p>biometric in real-life and this thesis is one of them.</p> <p>In this project we classify the EEG signals for person identification using AdaBoost</p> <p>algorithm. Adaptive boosting (AdaBoost) is a machine learning technique for pattern</p> <p>classification in which the performance of the weak learners such as k-Nearest</p> <p>Neighbour (k-NN) can be enhanced effectively by using the results of these weak</p> <p>classifiers.</p> <p>We also represent a new way for classification by combining multi-tasks and electrodes</p> <p>as data for each person. So with this new method we have more datasets for everyone.</p> <p>The results of classifications are impressive (100%) with methods for feature selection</p> <p>such as Principal Component Analysis (PCA) and for feature extraction like wavelet</p> <p>transform (WT) and Butterworth filter.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17329209 |
| institution | Zenodo |
| language | |
| publishDate | 2018 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | EEG based Person Identification Using AdaBoost Algorithm Pakgohar, Amirpouya Pattern recognition Signal processing Machine learning <p>The person identification by Electroencephalographic (EEG) signals has attracted the</p> <p>researchers’ great attention in recent years and lots of investigations have been</p> <p>developed. An identification system seeks to identify a person in a database. The</p> <p>advantage of using EEG signals for person identification is the difficulty in generating</p> <p>artificial signals for imposters. But more works need to be done to use EEG based</p> <p>biometric in real-life and this thesis is one of them.</p> <p>In this project we classify the EEG signals for person identification using AdaBoost</p> <p>algorithm. Adaptive boosting (AdaBoost) is a machine learning technique for pattern</p> <p>classification in which the performance of the weak learners such as k-Nearest</p> <p>Neighbour (k-NN) can be enhanced effectively by using the results of these weak</p> <p>classifiers.</p> <p>We also represent a new way for classification by combining multi-tasks and electrodes</p> <p>as data for each person. So with this new method we have more datasets for everyone.</p> <p>The results of classifications are impressive (100%) with methods for feature selection</p> <p>such as Principal Component Analysis (PCA) and for feature extraction like wavelet</p> <p>transform (WT) and Butterworth filter.</p> |
| title | EEG based Person Identification Using AdaBoost Algorithm |
| topic | Pattern recognition Signal processing Machine learning |
| url | https://doi.org/10.5281/zenodo.17329209 |