Fatos Tunay Yarman Vural - Academia.edu (original) (raw)

Papers by Fatos Tunay Yarman Vural

Frontiers in Neuroinformatics

In this study, we suggest an information-theoretic brain model, assuming that the fMRI recordings... more In this study, we suggest an information-theoretic brain model, assuming that the fMRI recordings of a subject, who performs a cognitive task, are the observable signals, generated by the anatomical regions, each of which can be represented as an information source. Based upon this assumption, we define two versions of Shannon entropy, namely, dynamic and static entropy to analyze the information content of anatomical regions during a cognitive state. We also propose two network models by estimating dynamic and static Kullback-Leibler (K-L) divergences to investigate the interactions across the anatomical regions.

arXiv (Cornell University), Dec 23, 2014

Functional magnetic resonance imaging produces high dimensional data, with a less then ideal numb... more Functional magnetic resonance imaging produces high dimensional data, with a less then ideal number of labelled samples for brain decoding tasks (predicting brain states). In this study, we propose a new deep temporal convolutional neural network architecture with spatial pooling for brain decoding which aims to reduce dimensionality of feature space along with improved classification performance. Temporal representations (filters) for each layer of the convolutional model are learned by leveraging unlabelled fMRI data in an unsupervised fashion with regularized autoencoders. Learned temporal representations in multiple levels capture the regularities in the temporal domain and are observed to be a rich bank of activation patterns which also exhibit similarities to the actual hemodynamic responses. Further, spatial pooling layers in the convolutional architecture reduce the dimensionality without losing excessive information. By employing the proposed temporal convolutional architecture with spatial pooling, raw input fMRI data is mapped to a non-linear, highly-expressive and low-dimensional feature space where the final classification is conducted. In addition, we propose a simple heuristic approach for hyper-parameter tuning when no validation data is available. Proposed method is tested on a ten class recognition memory experiment with nine subjects. The results support the efficiency and potential of the proposed model, compared to the baseline multi-voxel pattern analysis techniques.

Stacked Generalization is a classification technique which aims to increase the performance of in... more Stacked Generalization is a classification technique which aims to increase the performance of individual classifiers by combining them under a hierarchical architecture. In many applications, this technique, performs better than other classification schemas under some circumstances. However, in some applications, the performance of the technique goes astray, for the reasons that are not well-known. Even though it is used in several application domains up to now, it is not clear under which circumstances Stacked Generalization technique increases the performance. In this work, the states of the performance of Stacked Generalization technique is analyzed in terms of the performance parameters of the individual classifiers under the architecture. This work shows that the individual classifiers should learn the training set sharing the members of the set among themselves for the success of the Stacked Generalization architecture.

arXiv (Cornell University), Feb 23, 2014

We propose a statistical learning model for classifying cognitive processes based on distributed ... more We propose a statistical learning model for classifying cognitive processes based on distributed patterns of neural activation in the brain, acquired via functional magnetic resonance imaging (fMRI). In the proposed learning method, local meshes are formed around each voxel. The distance between voxels in the mesh is determined by using a functional neighbourhood concept. In order to define the functional neighbourhood, the similarities between the time series recorded for voxels are measured and functional connectivity matrices are constructed. Then, the local mesh for each voxel is formed by including the functionally closest neighbouring voxels in the mesh. The relationship between the voxels within a mesh is estimated by using a linear regression model. These relationship vectors, called Functional Connectivity aware Local Relational Features (FC-LRF) are then used to train a statistical learning machine. The proposed method was 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 neighbour (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 classification performance of the Functional Mesh Learning model, which range in 62% − 71% is superior to the classical multi-voxel pattern analysis (MVPA) methods, which range in 40% − 48%, for ten semantic categories.

2022 30th Signal Processing and Communications Applications Conference (SIU)

2020 25th International Conference on Pattern Recognition (ICPR)

Representing brain activities by networks is very crucial to understand various cognitive states.... more Representing brain activities by networks is very crucial to understand various cognitive states. This study proposes a novel method to estimate static and dynamic brain networks using Kulback-Leibler divergence. The suggested brain networks are based on the probability distributions of voxel intensity values measured by functional Magnetic Resonance Images (fMRI) recorded while the subjects perform a predefined cognitive task, called complex problem solving. We investigate the validity of the estimated brain networks by modeling and analyzing the different phases of complex problem solving process of human brain, namely planning and execution phases. The suggested computational network model is tested by a classification schema using Support Vector Machines. We observe that the network models can successfully discriminate the planning and execution phases of complex problem solving process with more than 90% accuracy, when the estimated dynamic networks, extracted from the fMRI data, are classified by Support Vector Machines.

Signal, Image and Video Processing, 2022

In this study, we introduce a measure for machine perception, inspired by the concept of Just Not... more In this study, we introduce a measure for machine perception, inspired by the concept of Just Noticeable Difference (JND) of human perception. Based on this measure, we suggest an adversarial image generation algorithm, which iteratively distorts an image by an additive noise until the machine learning model detects the change in the image by outputting a false label. The amount of noise added to the original image is defined as the gradient of the cost function of the machine learning model. This cost function explicitly minimizes the amount of perturbation applied on the input image and it is regularized by bounded range and total variation functions to assure perceptual similarity of the adversarial image to the input. We evaluate the adversarial images generated by our algorithm both qualitatively and quantitatively on CIFAR10, ImageNet, and MS COCO datasets. Our experiments on image classification and object detection tasks show that adversarial images generated by our method are both more successful in deceiving the recognition/detection model and less perturbed compared to the images generated by the state-of-the-art methods.

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019

In this paper, we aim to measure the information content of brain anatomic regions using the func... more In this paper, we aim to measure the information content of brain anatomic regions using the functional magnetic resonance images (fMRI) recorded during a complex problem solving (CPS) task. We, also, analyze the brain regions, activated in different phases of the problem solving process. Previous studies have widely used machine learning approaches to examine the active anatomic regions for cognitive states of human subjects based on their fMRI data. This study proposes an information theoretic method for analyzing the activity in anatomic regions. Briefly, we define and estimate two types of Shannon entropy, namely, static and dynamic entropy, to understand how complex problem solving processes lead to changes in information content of anatomic regions. We investigate the relationship between the problem-solving task phases and the Shannon entropy measures suggested in this study, for the underlying brain activity during a Tower of London (TOL) problem solving process. We observe that the dynamic entropy fluctuations in brain regions during the CPS task provides a measure for the information content of the main phases of complex problem solving, namely planning and execution. We, also, observe that static entropy measures of anatomic regions are consistent with the experimental findings of neuroscience. The preliminary results show strong promise in using the suggested static and dynamic entropy as a measure for characterizing the brain states related to the problem solving process. This capability would be useful in revealing the hidden cognitive states of subjects performing a specific cognitive task.

2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), 2018

Tower of London (TOL) is a classic problem solving task to study high-level cognitive processes. ... more Tower of London (TOL) is a classic problem solving task to study high-level cognitive processes. In this paper, using the TOL experiment, we aim to investigate the activation and relations of anatomic regions during the planning and execution phases of the problem solving task. We propose a dynamic sparse network representation estimated from the fMRI brain volumes at all time instances. This representation, called Dynamic Mesh Network, enables us to analyze the network properties of the brain under planning and execution stages of a TOL problem. Results indicate that activation during the planing phase is relatively higher than during the execution phase in most of the anatomic regions. Also, the connectivity between the anatomic regions is denser and stronger during the planing phase, compared to the execution phase.

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

Lecture Notes in Computer Science, 2018

In this study, we propose a novel brain parcellation algorithm, called BrainParcel. BrainParcel d... more In this study, we propose a novel brain parcellation algorithm, called BrainParcel. BrainParcel defines a set of supervoxels by partitioning a voxel level brain graph into a number of subgraphs, which are assumed to represent “homogeneous” brain regions with respect to a predefined criteria. Aforementioned brain graph is constructed by a set of local meshes, called mesh networks. Then, the supervoxels are obtained using a graph partitioning algorithm. The supervoxels form partitions of brain as an alternative to anatomical regions (AAL). Compared to AAL, supervoxels gather functionally and spatially close voxels. This study shows that BrainParcel can achieve higher accuracies in cognitive state classification compared to AAL. It has a better representation power compared to similar brain segmentation methods, reported the literature.

2018 26th Signal Processing and Communications Applications Conference (SIU), 2018

Brain decoding aims to predict cognitive states of the brain during a mental process. In order to... more Brain decoding aims to predict cognitive states of the brain during a mental process. In order to analyze the active brain regions and decode cognitive subtasks of complex problem solving, we use the data collected from subjects scanned while playing Tower of London (TOL) game. TOL is a problem solving task consisting of two major subtasks, namely, planning and execution. We propose a pipeline of 3 steps for a subtask decoding in this problem solving experiment. The first step of the pipeline is voxel selection and regrouping the selected voxels to their related AAL brain region so that we can obtain informative voxels and resolve curse of dimensionality of the data. Second step is temporal interpolation of the time series to increase the number of brain slice. Then, pseudo-random noise addition is applied to these time series for the purpose of generalization of learning methods. It is observed that this step increases the representation power of the fMRI data for TOL experiment. Lastly, we employ k-means clustering and linear support vector machines (SVM) to observe the effects of above-mentioned steps. We observe that there is gradual increases of the decoding performances on both supervised and unsupervised methods after each of the steps.

2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), 2016

One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI)... more One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI) is the very high dimension of feature space which consists of thousands of voxels in sequence of brain volumes, recorded during a cognitive stimulus. In this study, we propose a new architecture, called Sparse Temporal Mesh Model (STMM), which reduces the dimension of the feature space by combining the voxel selection methods with the mesh learning method. We, first, select the “most discriminative” voxels using the state-of-the-art feature selection methods, namely, Recursive Feature Elimination (RFE), one way Analysis of Variance (ANOVA) and Mutual Information (MI). After we select the most informative voxels, we form a star mesh around each selected voxel with their functional neighbors. Then, we estimate the mesh arc weights, which represent the relationship among the voxels within a neighborhood. We further prune the estimated arc weights using ANOVA to get rid of redundant relationships among the voxels. By doing so, we obtain a sparse representation of information in the brain to discriminate cognitive states. Finally, we train k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers by the feature vectors of sparse mesh arc weights. We test STMM architecture on a visual object recognition experiment. Our results show that forming meshes around the selected voxels leads to a substantial increase in the classification accuracy, compared to forming meshes around all the voxels in the brain. Furthermore, pruning the mesh arc weights by ANOVA solves the dimensionality curse problem and leads to a slight increase in the classification performance. We also discover that, the resulting network of sparse temporal meshes are quite similar in all three voxel selection methods, namely, RFE, ANOVA or MI.

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

In this study, we propose an ensemble learning architecture called "Cognitive Learner",... more In this study, we propose an ensemble learning architecture called "Cognitive Learner", for classification of cognitive states from functional magnetic resonance imaging (fMRI). Proposed architecture consists of a two-layer hierarchy. In the first layer, called voxel layer, we model the connectivity among the voxel time series to represent the detailed information about the experiment. In the second layer, we cluster the voxel time series by using functional similarity measure, to partition the brain volume into homogeneous regions, called super-voxels. Each super-voxel is represented by the average voxel time series that resides in that region. The cognitive states are represented independently in two layers. A set of star meshes are established around each voxel in the first layer and around each super-voxel, in the second layer. The arc weights of the meshes at each layer are estimated by regularized Ridge regression model among the voxels/super-voxels. Mesh arc weights, estimated at voxel and super-voxel levels are used to train independent classifiers. The outputs of two classifiers are ensembled under a stacked generalization architecture. Experiments are carried out to classify the cognitive states in an emotion dataset. Our model achieves 4% higher accuracy on the average compared to state of the art brain decoding models, such as voxel selection methods.

Frontiers in Neuroinformatics, 2021

Complex problem solving is a high level cognitive task of the human brain, which has been studied... more Complex problem solving is a high level cognitive task of the human brain, which has been studied over the last decade. Tower of London (TOL) is a game that has been widely used to study complex problem solving. In this paper, we aim to explore the underlying cognitive network structure among anatomical regions of complex problem solving and its subtasks, namely planning and execution. A new computational model for estimating a brain network at each time instant of fMRI recordings is proposed. The suggested method models the brain network as an Artificial Neural Network, where the weights correspond to the relationships among the brain anatomic regions. The first step of the model is preprocessing that manages to decrease the spatial redundancy while increasing the temporal resolution of the fMRI recordings. Then, dynamic brain networks are estimated using the preprocessed fMRI signal to train the Artificial Neural Network. The properties of the estimated brain networks are studied ...

2020 IEEE International Conference on Image Processing (ICIP), 2020

One way of designing a robust machine learning algorithm is to generate authentic adversarial ima... more One way of designing a robust machine learning algorithm is to generate authentic adversarial images which can trick the algorithms as much as possible. In this study, we propose a new method to generate adversarial images which are very similar to true images, yet, these images are discriminated from the original ones and are assigned into another category by the model. The proposed method is based on a popular concept of experimental psychology, called, Just Noticeable Difference. We define Just Noticeable Difference for a machine learning model and generate a least perceptible difference for adversarial images which can trick a model. The suggested model iteratively distorts a true image by gradient descent method until the machine learning algorithm outputs a false label. Deep Neural Networks are trained for object detection and classification tasks. The cost function includes regularization terms to generate just noticeably different adversarial images which can be detected by the model. The adversarial images generated in this study looks more natural compared to the output of state of the art adversarial image generators.

Brain imaging and behavior, Jan 15, 2018

In this work, we propose a novel framework to encode the local connectivity patterns of brain, us... more In this work, we propose a novel framework to encode the local connectivity patterns of brain, using Fisher vectors (FV), vector of locally aggregated descriptors (VLAD) and bag-of-words (BoW) methods. We first obtain local descriptors, called mesh arc descriptors (MADs) from fMRI data, by forming local meshes around anatomical regions, and estimating their relationship within a neighborhood. Then, we extract a dictionary of relationships, called brain connectivity dictionary by fitting a generative Gaussian mixture model (GMM) to a set of MADs, and selecting codewords at the mean of each component of the mixture. Codewords represent connectivity patterns among anatomical regions. We also encode MADs by VLAD and BoW methods using k-Means clustering. We classify cognitive tasks using the Human Connectome Project (HCP) task fMRI dataset and cognitive states using the Emotional Memory Retrieval (EMR). We train support vector machines (SVMs) using the encoded MADs. Results demonstrate t...

Brain imaging and behavior, Jan 4, 2017

Human brain is supposed to process information in multiple frequency bands. Therefore, we can ext... more Human brain is supposed to process information in multiple frequency bands. Therefore, we can extract diverse information from functional Magnetic Resonance Imaging (fMRI) data by processing it at multiple resolutions. We propose a framework, called Hierarchical Multi-resolution Mesh Networks (HMMNs), which establishes a set of brain networks at multiple resolutions of fMRI signal to represent the underlying cognitive process. Our framework, first, decomposes the fMRI signal into various frequency subbands using wavelet transform. Then, a brain network is formed at each subband by ensembling a set of local meshes. Arc weights of each local mesh are estimated by ridge regression. Finally, adjacency matrices of mesh networks obtained at different subbands are used to train classifiers in an ensemble learning architecture, called fuzzy stacked generalization (FSG). Our decoding performances on Human Connectome Project task-fMRI dataset reflect that HMMNs can successfully discriminate t...