Simulation of Sparse Model for Fmri Signal with Brain Activation During Hunger Regulation Process
Divya1, Saurabh Mukherjee2
1Divya*, Assistant Professor, Department of Computer Science, Banasthali Vidyapith, Rajasthan, India.
2Saurabh Mukherjee, Professor, Department of Computer Science, Banasthali Vidyapith, Rajasthan, India.
Manuscript received on January 18, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 29, 2020. | PP: 4006-4011 | Volume-9 Issue-3, February 2020. | Retrieval Number: C6420029320/2020©BEIESP | DOI: 10.35940/ijeat.C6420.029320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Functional Magnetic Resonance Imaging (fMRI), a non-invasive technique, is used for the recognition of different Cerebral Blood Flow (CBF) and Blood Oxygenated level dependent (BOLD) measures which result into the identification of various neural activities related to different physiological processes such as Hunger Regulation, Water Balancing etc. Different BOLD contrast levels (blood oxygenated and deoxygenated level) specify diversity in various state of human brain functioning subject to various tasks. The proposed model is a hybrid combination of Sparse method (Carroll et al., 2009) and Hypothalamic Hunger Regulation Model i.e. Sparse matrix for Hypothalamic BOLD Signal method (SMHB Method). SMHB method is dynamic and linear in nature. It defines the sparse parameters which act on the mapping between the fMRI signal for hunger regulation process and sparse representation of the signal segmented from the input image by which every voxel of fMRI signal in temporal domain can be expressed as a sparse signal. A sparse model provides a well define results for task based localized activity. It can be applied on a single image as well as an fMRI dataset. The implementation of SMHB method divided into different sub-modules such as Input image analysis and visualization, Linear Voxel Module and Neuro Activation Module. Our study have completed first two module with different pre-processing techniques used for image analysis and linear representation of each voxels of fMRI signal in the form of sparse parameters.
Keywords: Hunger Regulation, fMRI, BOLD, Linear Sparse Model, Sparse Matrix.