WoS İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/394

Browse

Filters

20182

Settings

Publisher: search.filters.publisher.European Signal Processing Conference, EUSIPCOSubject: search.filters.subject.Signal Processing

Search Results

Now showing 1 - 2 of 2
  • Conference Object
    Citation - WoS: 7
    Citation - Scopus: 12
    Use of Topological Data Analysis in Motor Intention Based Brain-Computer Interfaces
    (European Signal Processing Conference, EUSIPCO, 2018-09) Altindis, Fatih; Yilmaz, Bulent; İçöz, Kutay; Borisenok, S.
    This study aims to investigate the use of topological data analysis in electroencephalography (EEG) based on brain-computer interface (BCI) applications. Our study focused on extracting topological features of EEG signals obtained from the motor cortex area of the brain. EEG signals from 8 subjects were used for forming data point clouds with a real-time simulation scenario and then each cloud was processed with JPlex toolbox in order to find out corresponding Betti numbers. These numbers represent the topological structure of the point data cloud related to the persistent homologies, which differ for different motor activity tasks. The estimated Betti numbers has been used as features in k-NN classifier to discriminate left or right hand motor intentions. © 2019 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - WoS: 13
    Citation - Scopus: 19
    Extracting PRNU Noise From H.264 Coded Videos
    (European Signal Processing Conference, EUSIPCO, 2018-09) Altinişik, Enes; Taşdemir, Kasím; Sencar, Hüsrev Taha
    Every device equipped with a digital camera has a unique identity. This phenomenon is essentially due to a systematic noise component of an imaging sensor, known as photo-response non-uniformity (PRNU) noise. An imaging sensor inadvertently introduces this noise pattern to all media captured by that imaging sensor. The procedure for extracting PRNU noise has been well studied in the context of photographic images, however, its extension to video has so far been neglected. In this work, considering H.264 coding standard, we describe a procedure to extract sensor fingerprint from non-stabilized videos. The crux of our method is to remove a filtering procedure applied at the decoder to reduce blockiness and to use macroblocks selectively when estimating PRNU noise pattern. Results show that our method has a potential to improve matching performance significantly. © 2019 Elsevier B.V., All rights reserved.