Comparative Study Between Decision Tree, SVM and KNN to Predict Anaemic Condition

Anemia, a disease which is caused by an inadequacy of hemoglobin or red blood cells in the blood. It is very risky at the time of pregnancy, menstruation and in ICU sometimes causing death. So, it is a need of hemoglobin and detects anemia quickly. Usually, doctors examine the eye conjunctiva color and confirmed by a blood test which is painful, time-consuming and costly. In this study, a total of 104 people (54 males and 50 females) are collected with their clinical blood hemoglobin level, anemic condition and taken palpebral conjunctiva image. The images are captured with a cell phone camera of good resolution. By using the images, the percentage of the red, green and blue pixels are extracted in MATLAB, image processing method. Taking those features, the Hemoglobin level is plotted. A total of 81 data is taken for training purposes and 23 data for testing. For Anemia detection, the 81 data are trained with a used different classifier such as Linear SVM, Coarse Tree, and Cosine KNN and have been got highest accuracy of 82.61% in Decision Tree (Coarse) by testing 23 data.