Performance Analysis of Multiclass Support Vector Machine Classification for Diagnosis of Coronary Heart Diseases

Automatic diagnosis of coronary heart disease helps the doctor to support in decision making a diagnosis. Coronary heart disease have some types or levels. Referring to the UCI Repository dataset, it divided into 4 types or levels that are labeled numbers 1-4 (low, medium, high and serious). The diagnosis models can be analyzed with multiclass classification approach. One of multiclass classification approach used, one of which is a support vector machine (SVM). The SVM use due to strong performance of SVM in binary classification. This research study multiclass performance classification support vector machine to diagnose the type or level of coronary heart disease. Coronary heart disease patient data taken from the UCI Repository. Stages in this study is preprocessing, which consist of, to normalizing the data, divide the data into data training and testing. The next stage of multiclass classification and performance analysis. This study uses multiclass SVM algorithm, namely: Binary Tree Support Vector Machine (BTSVM), One-Against-One (OAO), One-Against-All (OAA), Decision Direct Acyclic Graph (DDAG) and Exhaustive Output Error Correction Code (ECOC). Performance parameter used is recall, precision, F-measure and Overall accuracy.

Identification and Counting White Blood Cells and Red Blood Cells using Image Processing Case Study of Leukemia

Leukemia is diagnosed with complete blood counts which is by calculating all blood cells and compare the number of white blood cells (White Blood Cells / WBC) and red blood cells (Red Blood Cells / RBC). Information obtained from a complete blood count, has become a cornerstone in the hematology laboratory for diagnostic purposes and monitoring of hematological disorders. However, the traditional procedure for counting blood cells manually requires effort and a long time, therefore this method is one of the most expensive routine tests in laboratory hematology clinic. Solution for such kind of time consuming task and necessity of data tracability can be found in image processing techniques based on blood cell morphology . This study aims to identify Acute Lymphocytic Leukemia (ALL) and Acute Myeloid Leukemia type M3 (AML M3) using Fuzzy Rule Based System based on morphology of white blood cells. Characteristic parameters witch extractedare WBC Area, Nucleus and Granule Ratio of white blood cells. Image processing algorithms such as thresholding, Canny edge detection and color identification filters are used.Then for identification of ALL, AML M3 and Healthy cells used Fuzzy Rule Based System with Sugeno method. In the testing process used 104 images out of which 29 ALL - Positive, 50 AML M3 - Positive and 25 Healthy cells. Test results showed 83.65 % accuracy .