Yazar "Aydin, Serap" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    A Case Study on Auditory Brain Activations Relative to Musical Experience by Means of EEG Complexity Levels
    (IEEE, 2018) Aydin, Serap; Guducu, Cagdas; Kutluk, Firat; Ozgoren, Adile Oniz; Ozgoren, Murat
    In this pre-work, entropy estimation methods have been firstly applied to single trial auditory oscillations mediated by tonal (non-target) and atonal (target) chords in order to show functional superior performance of musicians in auditory tasks. For this purpose, both embedding and probabilistic as well as wavelet entropy methods are compared to each other with respect to classification performance criteria in tests where two groups (5 musicians and 5 non-musicians) are classified by using 10-fold cross validated Support Vector Machine Classifiers for both target and non-target records. An embedding entropy so called Permutation Entropy provided the highest classification accuracies (99.96% for target records, 99.29% for non-target records) with respect to specified features extracted from 22 electrode locations near to auditory cortex (P7, TP7, T7, FT7, F7, AF7, AF8, F8, FT8, T8, TP8, P8, P5, CP5, C5, FC5, F5, F6, FC6, C6, CP6, P6). In conclusion, musical training enhances the neural encoding of sound and this performance can be quantified in terms of entropy values. In detail, the degree of EEG complexity increases depending on the existing of musical experience in auditory tasks.
  • Küçük Resim Yok
    Öğe
    Improving Cognitive Functions of Dyslexics using Multi-sensory Learning and EEG Neurofeedback
    (IEEE, 2018) Eroglu, Gunet; Aydin, Serap; Cetin, Mujdat; Balcisoy, Selim
    AutoTrainBrain is a neurofeedback and multisensory based mobile phone software application, designed in Sabanci University laboratory with the aim of improving the cognitive functions of dyslexic children. It reads electroencephalography (EEG) signals from 14 channels of eMotiv EPOC+ and processes these signals to provide neurofeedback to child for improving the brain signals with visual and auditory cues in real time. AutoTrainBrain software has been applied to a 14-year old dyslexic child, 10 minutes per week for 9 consecutive weeks.The EEG data has been analyzed by using the following three approaches: estimation of single-channel EEG complexity levels (entropy), spectral brain connectivity between two-channels (coherence), single channel relative Alpha band power ratio. Our experimental analysis shows that the proposed brain training system offers improvements based on the measures used in the three approaches mentioned above. This suggests such training may help increase the number of active cortical neurons and improve regional brain connectivity.
  • Küçük Resim Yok
    Öğe
    Smart Classification of Normal and Aggressive Muscle Actions
    (IEEE, 2018) Aydemir, Kemal; Aydin, Serap
    In the present study, linear, non-linear and statistical approaches so named Fourier Correlation (FC), Wavelet Correlation (WC) and Pearson Correlation (PC), respectively have been compared to each other in estimating cross-correlations between two EMG series, simultaneously collected from the same muscle groups (biceps, triceps, thighs) on symmetric limb (legs and arms). The features, which are computed for both normal and aggressive muscle actions, are computed for four electrode pairs and then these features are classified by different classifiers which are Penalized Logistic Regression (PLR), Random Forests (RF), Conditional Inference Tree (CIT) and Support Vector Machines (SVM) with 10-fold cross-validation in order to have highest calculation accuracy (CA). Experimental data including six normal and six aggressive actions of 4 young participants (3 male and 1 female with the mean age of 21.8) is provided by the data base of UCI (University of California Irvine).PC has given the highest calculation accuracy (100%) with R programming for the RF classifier. CA obtained with this classifier and correlation method can be directly suggested to detect diagnostic evaluation and neuromuscular diseases and dysfunction.