One Dimensional Median Local Binary Pattern Based Feature Extraction For Classifying Epileptic EEG Signals
Journal Title: Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji - Year 2017, Vol 5, Issue 3
Abstract
Electroencephalogram is an important data source that widely used in detecting epilepsy. In this study, EEG records consisting of five markers A, B, C, D, E that obtained from the database of Epilogy of Bonn University Epileptology Department was used. The feature vectors that obtained by applying the one dimension median local binary pattern (1D-MLBP) method were classified by using k nearest neighbor (kNN) algorithm The classification performance related to 1D-MLBP method developed was evaluated as an attribute. For this classification, the performance criteria was evaluated by calculating the confusion matrix. In this study,the classification performance for the A-E data sets was found to be 100.0%, 99.00% for the A-D data sets, 98.00% for the D-E data sets, 99.50% for the E-CD data sets and 96.00% for the A-D-E data sets. It has been seen that 1D-MLBP method used in the study gives better results than many methods used in the literature.
Authors and Affiliations
Ömer Türk, Mehmet Siraç Özerdem
Keywords
Related Articles
- EP ID EP484327
- DOI -
- Views 79
- Downloads 0
Reactive Power Control of Thyristor Controlled Reactor using Neuro - Fuzzy Controller
In this study, the reactive power of thyristor controlled reactor (TCR) that is fundamental element of flexible ac transmission system devices is controlled using neuro-fuzzy controller. Adaptive neuro fuzzy inference sy...
Teorical and experimental investigation of system dynamics in a process control simulator developed with wireless control purpose
System identification is a very important process that affects the success of process control operations. For the system identification, the theoretical studies have been done by using experimental and MATLAB in the wire...
Semi Quantitative Evaluation of the Workers’ Findings About Health and Safety in Health Sector
In this study a semi-quantitative analysis was done in order to determine the views of workers who work in direct medical services related to health and safety hazards and risks in the workplace by receiving the opinions...
Development of Metal-Porous Silicon Direct Hydrogen Fuel-Cell Production Parameters
Effect of the electrochemical etching (anodization) that is one of the manufacturing process of porous silicon (PS) on the electrical parameters of metal-porous silicon direct hydrogen cell (Metal-PS-DHC) is considerably...
A Goal Programming Model for Multi-Resource Generalized Assignment Problem that Contains Agents With Different Abilities and Priorities Along With Jobs to Be Assigned to the Same Agents
Generalized Assignment Problem (GAP) is assignment of jobs to agents with capacity constraints. For Multi Resource GAP (MR-GAP), as an extension of GAP, each agent has a certain number of constrained resources. The aim o...