Abstract—Feature Selection plays an important role in many areas especially in classification tasks. It is also an important pre-treatment for every classification process and not only decreases the computational time and cost, but selecting an appropriate variable also increases the classification accuracy. In this research, the comparison of classification performance of machine learning techniques using Principal Components Analysis (PCA) for screening the genotypes of β-Thalassemia patients will be proposed. The aim of this study is to reduce the dimensions of data before classification. According to the PCA method and classification techniques, results show that the Multi-Layer Perceptron (MLP) is the best algorithm providing that the percentage of accuracy reaches 86.61. K- Nearest Neighbors (KNN), Naive Bayes, Bayesian Networks (BNs) and Multinomial Logistic Regression require accuracy percentages of 85.83, 85.04, 85.04 and 82.68 respectively. In the future, we will search for the other feature selection techniques in order to improve the classification performance such as the hybrid method, filtering method etc.

Index Terms—β-Thalassemia, Classification Techniques, Principal Components Analysis (PCA), Feature Selection, Machine Leaning Techniques.

Dr. Somdat Srichairatanakool is Associate Professor in Biochemistry at Faculty of Medical, Chiang Mai University, Thailand. He can be contacted by E-mail: ssrichai@med.cmu.ac.th.
Dr. Napat Harnpornchai is Assistant Professor in Knowledge management at College of Arts, Media and Technology, Chiang Mai University, Thailand. He can be contacted by E-mail: napatresearch@gmail.com.
Michele Ceccarelli is Associate Professor in Computer Sciences at Faculty of Medical, Chiang Mai University, Thailand. He can be contacted by E-mail: ceccarelli@unisannio.it.

Cite: Patcharaporn Paokanta, Napat Harnpornchai, Somdat Srichairatanakool, and Michele Ceccarelli, "The Knowledge Discovery of β-Thalassemia Using Principal Components Analysis: PCA and Machine Learning Techniques," International Journal of e-Education, e-Business, e-Management and e-Learning vol. 1, no. 2, pp. 169-174, 2011.