Open AccessBlood group detection using ML classifier
Author(s) -
Suresh Dannana,
D Y Vara Prasad
Publication year - 2022
Publication title -
international journal of health sciences (ijhs) (en línea)
Language(s) - English
Resource type - Journals
eISSN - 2550-6978
pISSN - 2550-696X
DOI - 10.53730/ijhs.v6ns1.5830
Subject(s) - support vector machine , artificial intelligence , human blood , blood grouping , computer science , pattern recognition (psychology) , blood type (non human) , medicine , blood typing , immunology , abo blood group system , physiology
Determining blood types is very important during emergency situations before giving a blood transfusion. Currently, tests that are performed manually by technicians can lead to human error. As the tests are performed manually, if an inappropriate blood group is detected it can result in the death of an individual. Blood type determination in a short time and without human error is very essential. Many methods are employed which aims at determining the type of blood. The first method developed is determination of blood type using fiber optics. In this method, optical signals are fed into blood sample depending upon the optical variations of different blood groups the corresponding blood group is detected. But, this method fails to find the Rh (positive and negative) type of blood group. The second method employed is classification of blood type by microscopic images. Initially image processing is performed by histogram equalization, and then corresponding blood group is analyzed by Quantification Techniques. In this Technique, the major disadvantage lies in the inaccurate detection of agglutination. In order to avoid these disadvantages a new method Blood group detection using an ML classifier, Support Vector Machine (SVM) is proposed.