fMRG Verilerinde Temel Bileşenler Analizi ve Özyinemeli Boyut Eliminasyonu Kullanarak Boyut Küçültme

2015-05-19
Afrasiyabi, Arman
Yarman Vural, Fatoş Tunay
In this study, dimension reduction analysis is done on the Functional Magnetic Resonance Imagining (fMRI) data. The reduction of voxels which are the dimension in our case is the fundamental step in developing of a generalized model. To reach this goal, two different methods have been applied. In the first one Principle Component Analysis (PCA) is used to reduce the effect of curse of dimensionality. On the other hand, the method known as Recursive Feature Elimination (RFE) is used to drop the voxels with less discriminative information. RFE ranks the voxels according to their weights in the model obtained from Support Vector Machine, then eliminate the voxels with low rank. The obtained result showed the outperforming of PCA over RFE. But, due to the transformation of new space, the obtained dimensions at the output of PCA do not contain the 3D coordinate information. Therefore, RFE can useful when the selected voxels are interested such as neuroscientifical and psychology studies.

Suggestions

An Information theoretic representation of brain connectivity for cognitive state classification using functional magnetic resonance imaging
Önal, Itır; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2013)
In this study, a new method for analyzing and representing the discriminative information, distributed in functional Magnetic Resonance Imaging (fMRI) data, is proposed. For this purpose, a local mesh with varying size is formed around each voxel, called the seed voxel. The relationships among each seed voxel and its neighbors are estimated using a linear regression equation by minimizing the expectation of the squared error. This squared error coming from linear regression is used to calculate various info...
2D simulations based on the general time dependent reciprocal relation and initial experiments for LFEIT /
Karadaş, Mürsel; Gençer, Nevzat Güneri; Department of Electrical and Electronics Engineering (2014)
In this study, the new imaging modality Lorentz Field Electrical Impedance Tomography (LFEIT) is investigated. In LFEIT, the main aim is finding the conductivity distribution of different tissues. This method is based on the development of the current density distribution in the conductive medium. To develop the current density, the object is located in a static magnetic field and pressure wave due to an ultrasonic transducer develops particle movements inside the body. As a result, a velocity current distr...
Statistical disease detection with resting state functional magnetic resonance imaging
Öztürk, Ebru; İlk Dağ, Özlem; Department of Statistics (2017)
Most of the functional magnetic resonance imaging (fMRI) data are based on a particular task. The fMRI data are obtained while the subject performs a task. Yet, it's obvious that the brain is active even when the subject is not performing a task. Resting state fMRI (R-fMRI) is a comparatively new and popular technique for assessing regional interactions when a subject is not performing a task. This study focuses on classifying subjects as healthy or diseased with the diagnosis of schizophrenia by analyzing ...
A Hybrid geo-activity recommendation system using advanced feature combination and semantic activity similarity
Sattari, Masoud; Toroslu, İsmail Hakkı; Department of Computer Engineering (2013)
In this study, a new method for analyzing and representing the discriminative information, distributed in functional Magnetic Resonance Imaging (fMRI) data, is proposed. For this purpose, a local mesh with varying size is formed around each voxel, called the seed voxel. The relationships among each seed voxel and its neighbors are estimated using a linear regression equation by minimizing the expectation of the squared error. This squared error coming from linear regression is used to calculate various info...
Representation of human brain by mesh networks
Önal Ertuğrul, Itır; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2017)
In this thesis, we propose novel representations to extract discriminative information in functional Magnetic Resonance Imaging (fMRI) data for cognitive state and gender classification. First, we model the local relationship among a set of fMRI time series within a neighborhood by considering temporal information obtained from all measurements in time series. The estimated local relationships, called Mesh Arc Descriptors (MADs), are employed to represent information in fMRI data. Second, we adapt encoding ...
Citation Formats
A. Afrasiyabi and F. T. Yarman Vural, “fMRG Verilerinde Temel Bileşenler Analizi ve Özyinemeli Boyut Eliminasyonu Kullanarak Boyut Küçültme,” 2015, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/69360.