Keywords : Classification

Medical Image Classification Using Different Machine Learning Algorithms

Sami H. Ismael; Shahab W. Kareem; Firas H. Almukhtar

AL-Rafidain Journal of Computer Sciences and Mathematics, 2020, Volume 14, Issue 1, Pages 135-147
DOI: 10.33899/csmj.2020.164682

The different types of white blood cells equips us an important data for diagnosing and identifying of many diseases. The automation of this task can save time and avoid errors in the identification process. In this paper, we explore whether using shape features of nucleus is sufficient to classify white blood cells or not. According to this, an automatic system is implemented that is able to identify and analyze White Blood Cells (WBCs) into five categories (Basophil, Eosinophil, Lymphocyte, Monocyte, and Neutrophil). Four steps are required for such a system; the first step represents the segmentation of the cell images and the second step involves the scanning of each segmented image to prepare its dataset. Extracting the shapes and textures from scanned image are performed in the third step. Finally, different machine learning algorithms such as (K* classifier, Additive Regression, Bagging, Input Mapped Classifier, or Decision Table) is separately applied to the extracted (shapes and textures) to obtain the results. Each algorithm results are compared to select the best one according to different criteria’s.

Predicting Bank Loan Risks Using Machine Learning Algorithms

Maan Y. Alsaleem; Safwan O. Hasoon

AL-Rafidain Journal of Computer Sciences and Mathematics, 2020, Volume 14, Issue 1, Pages 149-158
DOI: 10.33899/csmj.2020.164686

Bank loans play a crucial role in the development of banks investment business. Nowadays, there are many risk-related issues associated with bank loans. With the advent of computerization systems, banks have become able to register borrowers' data according their criteria. In fact, there is a tremendous amount of borrowers’ data, which makes the process of load management a challenging task. Many studies have utilized data mining algorithms for the purpose of loans classification in terms of repayment or when the loans are not based on customers’ financial history. This kind of algorithms can help banks in making grant decisions for their customers. In this paper, the performance of machine learning algorithms has been compared for the purpose of classifying bank loan risks using the standard criteria and then choosing (Multilayer Perceptron) as it has given best accuracy compared to RandomForest, BayesNet, NaiveBayes and DTJ48 algorithms.

A Proposed Method for Feature Selection using a Binary Particle Swarm Optimization Algorithm and Mutual Information Technique

Mustafa Ayham Abed Alhafedh; Omar Saber Qasim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2019, Volume 13, Issue 2, Pages 49-60
DOI: 10.33899/csmj.2020.163520

Feature selection is one of the most important issues in improving the data classification process. It greatly influences the accuracy of the classification. There are many evolutionary algorithms used for this purpose, such as the Particle Swarm Optimization (PSO) in discrete space through the Binary PSO concept. The BPSO optimization algorithm derives its mechanism from the default PSO algorithm but in discrete space. In this research, a hybrid approach was proposed between the BPSO algorithm and Mutual Information (MI) to obtain subsets of features through two basic phases: the first is to use the BPSO algorithm to determine the features affecting the data classification process by relying on an objective function. In the second phase, the MI method is used to reduce the number of features identified by the BPSO method. The results of the proposed algorithm have demonstrated efficiency and effectiveness by obtaining higher classification accuracy and using fewer features than default methods.

An Analytical Mathematical Study of Artificial Neural Network Algorithms in the Suitability of a Model for Medical Diagnosis

Omar Saber Qasim; Israa Rustum Mohammed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2013, Volume 10, Issue 1, Pages 183-194
DOI: 10.33899/csmj.2013.163451

In this research discuss the concept of appropriate form, by examining mathematical behavior for three models represent neural networks are (GRNN, BPNN, PNN), were applied two types of medical data are (osteoporosis and weaknesses auditory) and different in the way of classification and spaces Input and output, and show through the application of these data and suitability models with neural networks in terms of the Domain and Range the network (PNN) is the best in the diagnosis of audio data through average MSE, and network (GRNN) is better diagnose bone crisp data (which are more complex) and the network (BPNN) is the most generalization, especially when test data are large compared with the training data.

Arabic Word Recognition Using Wavelet Neural Network

Yousra F. Al-Irhaim; Enaam Ghanim Saeed

AL-Rafidain Journal of Computer Sciences and Mathematics, 2010, Volume 7, Issue 3, Pages 81-90
DOI: 10.33899/csmj.2010.163913

In this paper, a system is presented for word recognition using  Arabic word signals. The aim of the paper is to improve the recognition rate by finding out good feature  parameters  based on discrete wavelet transform. We have used Daubechies  wavelet  for the experiment.  The back propagation neural network is used for classification. Test results showing the effectiveness of the proposed system are presented in this paper, A recognition accuracy of 77%.