Welcome to Evently

Lorem ipsum proin gravida nibh vel veali quetean sollic lorem quis bibendum nibh vel velit.

Evently

Simply enter your keyword and we will help you find what you need.

What are you looking for?

Dr. Rezzy Eko Caraka

Dr. Rezzy Eko Caraka

The National Research and Innovation Agency (BRIN), Indonesia
Ulsan National Institute of Science and Technology (UNIST) Korea.

SELECTING FEATURE SELECTION OF VOXEL TEMPORAL BRAIN CONNECTIVITY USING VARIOUS MACHINE LEARNING

Biography

REZZY EKO CARAKA, Ph.D. His research interests include, but are not limited to, data science, statistics, Large-Scale Optimization, Fast Computing, Disaster Risk, and machine learning in theory, practice, and application to Sustainable Development Goals (SDGs). He received numerous awards, including the best paper conference and an excellent research award on a national and international scale. He also serves on the Editorial Board of many reputable and impactful journals. At the same, He acts as a Faculty member, Researcher, and Senior Research Fellow in different institutions.

  • September 2020 – December 2020. Post-Doctoral Researcher, Department of Statistics,Seoul National University, South Korea.
  • January 2021-December 2021. Senior Research Fellow, Department of Nuclear Medicine,Seoul National University Hospital (SNU-H), South Korea.
  • April 2021-presents. Faculty Member, Faculty of Economics and Business, University of Indonesia, Indonesia
  • January 2022-April 2022. Assistant Research Professor, Department of Statistics, SeoulNational University, Indonesia
  • February 2022-presents. Researcher, Research Center for Data and Information Sciences,Research Organization for Electronics and Informatics, National Research and InnovationAgency (BRIN), Indonesia
  • February 2022-present. Adjunct Faculty Member, Department of Statistics, Universitas Padjadjaran, Indonesia
  • May 2022-present. Senior Research Fellow, Ulsan National Institute of Science and Technology (UNIST), South Korea.

Abstract

Brain imaging uses various techniques for direct and indirect imaging of the brain’s structure, function/pharmacology. Brain imaging is divided into two categories: structural imaging, which deals with the brain’s structure, and the diagnosis (large scale) of intracranial diseases (such as tumors) and injuries. In this case are Computerized Axial Tomography (CAT or CT), Structural Magnetic Resonance Imaging (sMRI or MRI), Magnetic Resonance Spectroscopy (MRS), and Diffusion Tensor Imaging (DTI). In this research, I use ten well-known machine learning classification types for neuropsychiatric diseases, including attention deficit hyperactivity disorder (ADHD), with 5937 voxels among patients. The voxel data is investigated only for ten subjects containing time series of 5937 voxels (1200 time points) but not the correlation matrix itself. The NII file containing the voxel information refers to the Brainnetome Center, Institute of Automation, Chinese Academy of Sciences (https://atlas.brainnetome.org). Brain mask image of reduced size (31*37*31) for removing background voxels and 4D data matrix (X*Y* Z*time) in every 180 subjects. For removing background voxels, I use the brain mask image size (31*37*31) to multiply this brain mask and the original data.