Detection Of Brain Disorders using Clustering based Techniques- Expectation Maximization
Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.4, No. 2)Publication Date: 2015-02-28
Authors : Amruta Gadekar; Ravi Patki;
Page : 230-235
Keywords : Clustering Technique; Interation pattens; Interation K-Means; Expectation Maximization;
Abstract
Brain is a central as well as an important part of a human body. The Brain activities are very complicated and difficult to understand. Many psychiatric disorders related to the brain are difficult to detect or identify. Functional magnetic resonance imaging or fMRI is a technique which is responsible for measuring a brain activity. The basic signal of fMRI depends upon the blood-oxygen-level-dependent (BOLD) effect which helps to study human brain functions. The purpose of Clustering Technique is to understand the complex interaction patterns among brain regions as well as identify brain disorders. To detect clusters of objects with similar interaction patterns we proposed a partitioning clustering algorithm that is Expectation Maximization (EM) algorithm. The Expectation Maximization (EM) algorithm is Gaussian Mixtures which begins with an initial guess to the cluster centers, and iteratively refines them an efficient algorithm for partitioning clustering.
Other Latest Articles
- Comparative Study of Secured Routing Protocols in Wireless Ad hoc Networks: A Survey?
- Automated Toll Cash Collection System for Road Transportation?
- The Relevance of Analytical CRM and Knowledge Management in an Organisation: A Data Mining Structure?
- Adaptive Median Filtering with Modified BDND Algorithm for the Removal of High-Density Impulse and Random Noise?
- A REVIEW ON IMAGE COMPRESSION TECHNIQUES
Last modified: 2015-02-25 22:01:03