Determination and classification of human blood type using maching learning image processing and support vector machine (SVM) methods

The importance of blood grouping in various medical and health fields is important. Also, the problems in blood group identification and the need to use artificial intelligence methods for more accurate blood group prediction are discussed in this section. The use of machine learning algorithms, especially deep learning and support vector machines, is examined for this purpose. The use of algorithms such as SVM, deep neural networks, decision tree machines, and reinforcement learning are mentioned. Various articles in the fields of biometrics or genetics have also addressed this topic.. Support Vector Machine SVM The SVM model is a powerful algorithm for data classification that separates data by creating a decision line between categories.- In this paper, SVM is used to predict the blood group of individuals based on various features (such as age, gender, and genetic data). Choosing a suitable kernel such as linear kernel or radical basis kernel (RBF) to improve the prediction accuracy will be one of the important parts of the paper.The main methods and techniques used in the paper for blood group prediction are explained. These methods are usually divided into two categories: deep learning and support vector machine (SVM).In an operational environment, images of new blood samples are collected and preprocessed, features are extracted and fed to the SVM model to determine the blood group. By following these steps and using machine learning tools and libraries such as scikit-learn in Python, an efficient system for determining human blood type can be created using machine learning and SVM. c) Statement of the main research problem: Pre-transfusion tests are necessary for blood transfusion. Although the donor is universal, if the blood types are not similar, blood transfusion reactions can occur. Various systems have been developed to automate these tests, but none of them have the ability to perform timely analysis for emergency situations. One of the new methods used in the field of classification and diagnosis of human blood types is image processing and the use of artificial intelligence techniques, which leads to increased detection accuracy and increased detection performance. To determine ABO and Rh blood types, using existing techniques, it is necessary to use some identifiers. To evaluate the performance of this proposed system, a microarray database is used, which includes breast cancer, leukemia, and bone marrow and lymphoid cancers from the Stanford University microarray database. For this purpose, this system is based on the plate test method. It is small in size and easy to carryThe importance of blood grouping in various medical and health fields is important. Also, the problems in blood group identification and the need to use artificial intelligence methods for more accurate blood group prediction are discussed in this section. The use of machine learning algorithms, especially deep learning and support vector machines, is examined for this purpose. The use of algorithms such as SVM, deep neural networks, decision tree machines, and reinforcement learning are mentioned. Various articles in the fields of biometrics or genetics have also addressed this topic. . Support Vector Machine SVM The SVM model is a powerful algorithm for data classification that separates data by creating a decision line between categories. - In this paper, SVM is used to predict the blood group of individuals based on various features (such as age, gender, and genetic data). Choosing a suitable kernel such as linear kernel or radical basis kernel (RBF) to improve the prediction accuracy will be one of the important parts of the paper. The main methods and techniques used in the paper for blood group prediction are explained. These methods are usually divided into two categories: deep learning and support vector machine (SVM). In an operational environment, images of new blood samples are collected and preprocessed, features are extracted and fed to the SVM model to determine the blood group. By following these steps and using machine learning tools and libraries such as scikit-learn in Python, an efficient system for determining human blood type can be created using machine learning and SVM. c) Statement of the main research problem: Pre-transfusion tests are necessary for blood transfusion. Although the donor is universal, if the blood types are not similar, blood transfusion reactions can occur. Various systems have been developed to automate these tests, but none of them have the ability to perform timely analysis for emergency situations. One of the new methods used in the field of classification and diagnosis of human blood types is image processing and the use of artificial intelligence techniques, which leads to increased detection accuracy and increased detection performance. To determine ABO and Rh blood types, using existing techniques, it is necessary to use some identifiers. To evaluate the performance of this proposed system, a microarray database is used, which includes breast cancer, leukemia, and bone marrow and lymphoid cancers from the Stanford University microarray database. For this purpose, this system is based on the plate test method. It is small in size and easy to carry

کلیدواژه ها:

Blood Group Classification ، Machine Learning ، Image Processing ، Support Vector Machine SVM