Anemia Detection Through Conjunctiva on Eyes Using Principal Component Analysis Method and K-Nearest Neighbor

Abstract

Anemia is a condition where red blood cells and hemoglobin in a person's body are below normal values. Most anemia are characterized by some symptoms such as the conjunctiva of the eyes becoming pale, weakened endurance, and decreased physical labor. To carry out the detection of anemia is usually done by invasive means or taking a sample of a person's blood using a syringe on the fingertips of the hand. In addition to the invasive way, the detection of anemia can also be done in a non-invasive way or without taking a pair of blood using a syringe on the fingertips of the hand. In this paper, the detection of anemia is carried out non-invasively through the conjunctiva of the eye using the Principal Component Analysis (PCA) method and the K-Nearest Neighbor (K-NN) method. The results obtained based on the best parameters with an image size of $256\times 128$ pixels, PCA percentage parameters of 40%, cityblock distance, with a value of $\mathrm{K}=9$ systems resulted in an accuracy of 87.5% with a computing time of 1,317 seconds using 60 training data and 40 test data.