Researcher:
Öztekin, İlke

Profile Picture
ORCID

Job Title

Faculty Member

First Name

İlke

Last Name

Öztekin

Name

Name Variants

Öztekin, İlke

Email Address

Birth Date

Filters

2011 - 201828

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.a7742cc6-7684-4c0f-a1ed-4444332110d8

Search Results

Now showing 1 - 10 of 28
  • Placeholder
    PublicationMetadata only
    Learning deep temporal representations for fMRI brain decoding
    (Springer International Publishing Ag, 2015) Firat, Orhan; Aksan, Emre; Fatos T. Yarman; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    Functional magnetic resonance imaging (fMRI) produces low number of samples in high dimensional vector spaces which is hardly adequate for brain decoding tasks. In this study, we propose a combination of autoencoding and temporal convolutional neural network architecture which aims to reduce the feature dimensionality along with improved classification performance. The proposed network learns temporal representations of voxel intensities at each layer of the network by leveraging unlabeled fMRI data with regularized autoencoders. Learned temporal representations capture the temporal regularities of the fMRI data and are observed to be an expressive bank of activation patterns. Then a temporal convolutional neural network with spatial pooling layers reduces the dimensionality of the learned representations. By employing the proposed method, raw input fMRI data is mapped to a low-dimensional feature space where the final classification is conducted. In addition, a simple decorrelated representation approach is proposed for tuning the model hyper-parameters. The proposed method is tested on a ten class recognition memory experiment with nine subjects. Results support the efficiency and potential of the proposed model, compared to the baseline multi-voxel pattern analysis techniques.
  • Placeholder
    PublicationMetadata only
    An information theoretic approach to classify cognitive states using fMRI
    (Institute of Electrical and Electronics Engineers (IEEE), 2013) Onal, Itir; Ozay, Mete; Firat, Orhan; Vural, Fatos T. Yarman; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    In this study, an information theoretic approach is proposed to model brain connectivity during a cognitive processing task, measured by functional Magnetic Resonance Imaging (fMRI). For this purpose, a local mesh of varying size is formed around each voxel. The arc weights of each mesh are estimated using a linear regression model by minimizing the squared error. Then, the optimal mesh size for each sample, that represents the information distribution in the brain, is estimated by minimizing various information criteria which employ the mean square error of linear regression model. The estimated mesh size shows the degree of locality or degree of connectivity of the voxels for the underlying cognitive process. The samples are generated during an fMRI experiment employing item recognition (IR) and judgment of recency (JOR) tasks. For each sample, estimated arc weights of the local mesh with optimal size are used to classify whether it belongs to IR or JOR tasks. Results indicate that the suggested connectivity model with optimal mesh size for each sample represent the information distribution in the brain better than the state-of-the art methods.
  • Placeholder
    PublicationMetadata only
    Retrieval dynamics of the strength based mirror effect in recognition memory
    (Academic Press Inc Elsevier Science, 2014) N/A; Department of Psychology; Özhan, Aslı Kılıç; Öztekin, İlke; Researcher; Faculty Member; Department of Psychology; N/A; College of Social Sciences and Humanities; N/A; N/A
    The strength based mirror effect (SBME) refers to an increase in hit rates (HR) and a decrease in false alarm rates (FAR) for the test lists that follow a strongly encoded study list. Earlier investigation of accuracy and reaction time distributions by fitting the diffusion model indicated a mirror effect in the drift rate parameter, which was interpreted as an indication of more conservative responses due to a shift in the drift criterion. Additionally, the starting point for the evidence accumulation was found to be more liberal for the strong test lists. In order to further investigate this paradoxical effect of list strength on these two kinds of bias estimated from the diffusion model, we employed the response-deadline procedure which provided a direct assessment of response bias early in retrieval, prior to evidence accumulation. Results from the retrieval functions indicated more liberal response bias in the list strength paradigm with both pure- and mixed-strength study lists. On the contrary, the SBME was observed at the asymptotic accuracy, suggesting that the conservative response bias might be observed later in retrieval when memory evidence has fully accumulated. In addition, comparison of the SBME across pure and mixed lists revealed that the SBME was most prominent in the pure-list paradigm, suggesting that both the differentiation and criterion shift accounts jointly explain the SBME in recognition memory.
  • Placeholder
    PublicationMetadata only
    Working memory capacity and controlled serial memory search
    (Elsevier, 2016) N/A; Department of Psychology; Mızrak, Eda; Öztekin, İlke; PhD Student; Faculty Member; Department of Psychology; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; N/A
    The speed-accuracy trade-off (SAT) procedure was used to investigate the relationship between working memory capacity (WMC) and the dynamics of temporal order memory retrieval. High- and low-span participants (HSs, LSs) studied sequentially presented five-item lists, followed by two probes from the study list. Participants indicated the more recent probe. Overall, accuracy was higher for HSs compared to LSs. Crucially, in contrast to previous investigations that observed no impact of WMC on speed of access to item information in memory (e.g., Oztekin & McElree, 2010), recovery of temporal order memory was slower for LSs. While accessing an item's representation in memory can be direct, recovery of relational information such as temporal order information requires a more controlled serial memory search. Collectively, these data indicate that WMC effects are particularly prominent during high demands of cognitive control, such as serial search operations necessary to access temporal order information from memory. (C) 2016 Elsevier B.V. All rights reserved.
  • Placeholder
    PublicationMetadata only
    Estimating brain connectivity for pattern analysis
    (IEEE Computer Society, 2014) Onal, Itir; Aksan, Emre; Velioglu, Burak; Firat, Orhan; Ozay, Mete; Vural, Fatos T. Yarman; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    In this study, the degree of connectivity for each voxel, which is the unit element of functional Magnetic Resonance Imaging (fMRI) data, with its neighboring voxels is estimated. The neighborhood system is defined by spatial connectivity metrics and a local mesh of variable size is formed around each voxel using spatial neighborhood. Then, the mesh arc weights, called Mesh Arc Descriptors (MAD), are used to represent each voxel rather than its own intensity value measured by functional Magnetic Resonance Images (fMRI). Finally, the optimal mesh size of each voxel is estimated using various information theoretic criteria. fMRI measurements are obtained during a memory encoding and retrieval experiment performed on a subject who is exposed to the stimuli from 10 semantic categories. Using the Mesh Arc Descriptors (MAD) having the variable mesh sizes, a k-NN classifier is trained. The classification performances reflect that the suggested variable-size Mesh Arc Descriptors represent the cognitive states better than the classical multi-voxel pattern representation and fixed-size Mesh Arc Descriptors. Moreover, it is observed that the degree of connectivities in the brain greatly varies for each voxel. / Bu çalışmada, fonksiyonel Manyetik Rezonans Görüntüleme (fMRG) verisinin temel elemanı olan vokselin komşu voksellerle olan bağlanırlık derecesi kestirilmiştir. Komşuluk sistemi uzamsal bağlanırlık metrikleri ile tanımlanır ve her voksel etrafında uzamsal komşuluk kullanılarak değişken boyutlu yerel örgü oluşturulur. Daha sonra, her voksel kendi yoğunluk değeri yerine Örgü Yay Betimleyicileri olarak adlandırılan örgü yay ağırlıkları ile ifade edilir. Sonuç olarak, her vokselin ideal örgü boyutu, çeşitli bilgi teoretik kriterler kullanılarak kestirilir. fMRG ölçümleri 10 anlamsal kategori içeren uyarılara maruz bırakılan bir katılımcıya uygulanan beyne bilgi kaydı ve beyinden bilgi geri getirme deneyi sırasında edinilmiştir. Değişken örgü boyutuna sahip Örgü Yay Betimleyicileri kullanilarak bir k-en yakın komşu sınıflandırıcısı egitilmiştir. Sınıflandırma performansı gösterir ki, önerilen degişken boyutlu Örgü Yay Betimleyicileri, bilişsel süreçleri klasik çoklu-voksel örüntü betimleyicilerinden ve sabit boyutlu Örgü Yay Betimleyicileri’nden daha iyi ifade eder. Ek olarak, baglanırlık derecesinin beyinde oldukça değişken olduğu gözlemlenmiştir.
  • Placeholder
    PublicationMetadata only
    Large scale functional connectivity for brain decoding
    (Acta Press, 2014) Firat, Orhan; Onal, Itir; Aksan, Emre; Velioglu, Burak; Yarman Vural, Fatos T.; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    Functional Magnetic Resonance Imaging (fMRI) data consists of time series for each voxel recorded during a cognitive task. In order to extract useful information from this noisy and redundant data, techniques are proposed to select the voxels that are relevant to the underlying cognitive task. We propose a simple and efficient algorithm for decoding the brain states by modelling the correlation patterns between the voxel time series. For each stimulus during the experiment, a separate functional connectivity matrix is computed in voxel level. The elements in connectivity matrices are then filtered out by making use of a minimum spanning tree formed using a global connectivity matrix for the entire experiment in order to reduce dimensionality. For a recognition memory experiment with nine subjects, functional connectivity matrices are computed for encoding and retrieval phases. The class labels of the retrieval samples are predicted within a k-nearest neighbour space constructed by the traversed entries in the functional connectivity matrices for encoding samples. The proposed method is also adapted to large scale functional connectivity tasks by making use of graphics boards. Classification performance in ten categories is comparable and even better compared to both classical and enhanced methods of multi-voxel pattern analysis techniques.
  • Placeholder
    PublicationMetadata only
    Mesh learning for object classification using fMRI measurements
    (Institute of Electrical and Electronics Engineers (IEEE), 2013) Ekmekci, Omer; Firat, Orhan; Ozay, Mete; Vural, Fatos T. Yarman; Oztekin, Uygar; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    Machine learning algorithms have been widely used as reliable methods for modeling and classifying cognitive processes using functional Magnetic Resonance Imaging (fMRI) data. In this study, we aim to classify fMRI measurements recorded during an object recognition experiment. Previous studies focus on Multi Voxel Pattern Analysis (MVPA) which feeds a set of active voxels in a concatenated vector form to a machine learning algorithm to train and classify the cognitive processes. In most of the MVPA methods, after an image preprocessing step, the voxel intensity values are fed to a classifier to train and recognize the underlying cognitive process. Sometimes, the fMRI data is further processed for de-noising or feature selection where techniques, such as Generalized Linear Model (GLM), Independent Component Analysis (ICA) or Principal Component Analysis are employed. Although these techniques are proved to be useful in MVPA, they do not model the spatial connectivity among the voxels. In this study, we attempt to represent the local relations among the voxel intensity values by forming a mesh network around each voxel to model the relationship of a voxel and its surroundings. The degree of connectivity of a voxel to its surroundings is represented by the arc weights of each mesh. The arc weights, which are estimated by a linear regression model, are fed to a classifier to discriminate the brain states during an object recognition task. This approach, called Mesh Learning, provides a powerful tool to analyze various cognitive states using fMRI data. Compared to traditional studies which focus either merely on multi-voxel pattern vectors or their reduced-dimension versions, the suggested Mesh Learning provides a better representation of object recognition task. Various machine learning algorithms are tested to compare the suggested Mesh Learning to the state-of-the art MVPA techniques. The performance of the Mesh Learning is shown to be higher than that of the available MVPA techniques.
  • Placeholder
    PublicationMetadata only
    Cognitive process representation with minimum spanning tree of local meshes
    (Institute of Electrical and Electronics Engineers (IEEE), 2013) Firat, Orhan; Özay, Mete; Önal, Itir; Yarman Vural, Fatoş T.; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    In this study, we propose a new graphical model, namely Cognitive Process Graph (CPG) for classifying cognitive processes. In CPG, first local meshes are formed around each voxel. Second, the relationships between a voxel and its neighbors in a local mesh, which are estimated by using a linear regression model, are used to form the edges among the voxels (graph nodes) in the CPG. Then, a minimum spanning tree (MST) of the CPG which spans all the voxels in the region of interest is computed. The arc weights of the MST are used to represent the underlying cognitive processes. Finally, the arc weights computed over the path of the MST called MST-Features (MST-F) are used to train a statistical learning machine. The proposed method is tested on a recognition memory experiment, including data pertaining to encoding and retrieval of words belonging to ten different semantic categories. Two popular classifiers, namely kNearest Neighbor (k-NN) and Support Vector Machine (SVM), are trained in order to predict the semantic category of the item being retrieved, based on activation patterns during encoding. The proposed method reduces the curse of dimensionality problem that is caused by very large dimension of the feature space of the fMRI measurements, compared to number of instances. The classification performance is also superior to the classical multi-voxel pattern analysis (MVPA) methods for the underlying cognitive process. / Bu çalışmada, bilişsel süreçlerin sınıflandırılması maksadıyla, Bilişsel Süreç Çizgesi (BSÇ) adı verilen yeni bir grafiksel model önerilmektedir. Önerilen BSÇ’de öncelikle, her voksel etrafında bir yerel örgü kurulmaktadır. İkinci olarak, doğrusal bağlanım modeli kullanılarak hesaplanan yerel örgüdeki vokseller ile komşularının ilişkileri, BSÇ’yi oluşturan vokseller (çizge düğümleri) arasındaki kenarları oluşturmak için kullanılmıştır. Ardından, oluşturulan BSÇ’nin minimum yayılan ağacı (MYA) ilgi bölgesindeki tüm vokselleri kapsayacak şekilde hesaplanmıştır. MYA üzerinde bulunan kenar ağırlıkları bilişsel süreci betimlemekte kullanılmıştır. Son olarak, hesaplanan kenar ağırlıklarından MYA üzerinde bulunanlar istatistiksel bir öğrenme makinasını eğitmekte kullanılmıştır. Kullanılan bu kenar ağırlıkları MYA-Öznitelikleri (MYA-Ö) olarak adlandırılmıştır. Önerilen yaklaşım, belleğe bilgi kaydı ve geri getirme işlemleri için 10 sınıflı bilgi tipinden oluşan bir kelime tanıma çalışması verisi üzerinde test edilmiştir. Bellekten geri getirmeyi farklı kategorideki sınıflar için ayırt edebilmek maksadıyla yaygın olarak kullanılan iki sınıflandırıcı eğitilmiştir. Bu sınfılandırıcılar k-En Yakın Komşu (k-EK) ve Destek Vektör Makinası (DVM) olup, belleğe bilgi kaydı esnasındaki aktifleşme örüntüsü kullanılarak eğitilmişlerdir. Önerilen yaklaşım, örnek sayısıyla karşılaştırıldığında oldukça yüksek boyutta olan fMRG ölçümlerinin boyutluluk sorununu azaltmakla beraber bilişsel süreç sınıflandırma başarımı klasik Çoklu Voksel Örüntü Çözümleme (Multi Voxel Pattern Analysis-MVPA) yöntemlerinden daha yüksektir.
  • Placeholder
    PublicationMetadata only
    Yerel örgülerin minimum yayılan ağaçları ile bilişsel süreç betimleme
    (IEEE, 2013) Firat, Orhan; Ozay, Mete; Onal, Itir; Vural, Fatos T. Yarman; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    In this study, we propose a new graphical model, namely Cognitive Process Graph (CPG) for classifying cognitive processes. In CPG, first local meshes are formed around each voxel. Second, the relationships between a voxel and its neighbors in a local mesh, which are estimated by using a linear regression model, are used to form the edges among the voxels (graph nodes) in the CPG. Then, a minimum spanning tree (MST) of the CPG which spans all the voxels in the region of interest is computed. The arc weights of the MST are used to represent the underlying cognitive processes. Finally, the arc weights computed over the path of the MST called MST-Features (MST-F) are used to train a statistical learning machine. The proposed method is tested on a recognition memory experiment, including data pertaining to encoding and retrieval of words belonging to ten different semantic categories. Two popular classifiers, namely kNearest Neighbor (k-NN) and Support Vector Machine (SVM), are trained in order to predict the semantic category of the item being retrieved, based on activation patterns during encoding. The proposed method reduces the curse of dimensionality problem that is caused by very large dimension of the feature space of the fMRI measurements, compared to number of instances. The classification performance is also superior to the classical multi-voxel pattern analysis (MVPA) methods for the underlying cognitive process. Keywords — fMRI; mesh learning; minimum spanning tree; pattern recognition. / Bu çalışmada, bilişsel süreçlerin sınıflandırılması maksadıyla, Bilişsel Süreç Çizgesi (BSÇ) adı verilen yeni bir grafiksel model önerilmektedir. Önerilen BSÇ’de öncelikle, her voksel etrafında bir yerel örgü kurulmaktadır. İkinci olarak, doğrusal bağlanım modeli kullanılarak hesaplanan yerel örgüdeki vokseller ile komşularının ilişkileri, BSÇ’yi oluşturan vokseller (çizge düğümleri) arasındaki kenarları oluşturmak için kullanılmıştır. Ardından, oluşturulan BSÇ’nin minimum yayılan ağacı (MYA) ilgi bölgesindeki tüm vokselleri kapsayacak şekilde hesaplanmıştır. MYA üzerinde bulunan kenar ağırlıkları bilişsel süreci betimlemekte kullanılmıştır. Son olarak, hesaplanan kenar ağırlıklarından MYA üzerinde bulunanlar istatistiksel bir öğrenme makinasını eğitmekte kullanılmıştır. Kullanılan bu kenar ağırlıkları MYA-Öznitelikleri (MYA-Ö) olarak adlandırılmıştır. Önerilen yaklaşım, belleğe bilgi kaydı ve geri getirme işlemleri için 10 sınıflı bilgi tipinden oluşan bir kelime tanıma çalışması verisi üzerinde test edilmiştir. Bellekten geri getirmeyi farklı kategorideki sınıflar için ayırt edebilmek maksadıyla yaygın olarak kullanılan iki sınıflandırıcı eğitilmiştir. Bu sınfılandırıcılar k-En Yakın Komşu (k-EK) ve Destek Vektör Makinası (DVM) olup, belleğe bilgi kaydı esnasındaki aktifleşme örüntüsü kullanılarak eğitilmişlerdir. Önerilen yaklaşım, örnek sayısıyla karşılaştırıldığında oldukça yüksek boyutta olan fMRG ölçümlerinin boyutluluk sorununu azaltmakla beraber bilişsel süreç sınıflandırma başarımı klasik Çoklu Voksel Örüntü Çözümleme (Multi Voxel Pattern Analysis-MVPA) yöntemlerinden daha yüksektir.
  • Placeholder
    PublicationMetadata only
    Deep learning for brain decoding
    (Institute of Electrical and Electronics Engineers (IEEE), 2014) Firat, Orhan; Vural, Fatos T. Yarman; Department of Psychology; Öztekin, İlke; Faculty Member; Department of Psychology; College of Social Sciences and Humanities; N/A
    Learning low dimensional embedding spaces (manifolds) for efficient feature representation is crucial for complex and high dimensional input spaces. Functional magnetic resonance imaging (fMRI) produces high dimensional input data and with a less then ideal number of labeled samples for a classification task. In this study, we explore deep learning methods for fMRI classification tasks in order to reduce dimensions of feature space, along with improving classification performance for brain decoding. We employ sparse autoencoders for unsupervised feature learning, leveraging unlabeled fMRI data to learn efficient, non-linear representations as the building blocks of a deep learning architecture by stacking them. Proposed method is tested on a memory encoding/retrieval experiment with ten classes. The results support the efficiency compared to the baseline multi-voxel pattern analysis techniques.