Asian Ethnic Group Classification Model Using Data Mining
Korean J Leg Med 2017;41:32-40

Department of Applied Statistics, Yonsei University, Seoul, Korea,
Department of Forensic Medicine, Seoul National University College of Medicine, Seoul, Korea,
Institute of Forensic Science, Seoul National University College of Medicine, Seoul, Korea,
Department of Information and Statistics, Yonsei University, Wonju, Korea

E-mail: ahn2615@yonsei.ac.kr

In addition to identifying genetic differences between target populations, it is also important to determine the impact of genetic differences with regard to the respective target populations. In recent years, there has been an increasing number of cases where this approach is needed, and thus various statistical methods must be considered. In this study, genetic data from populations of Southeast and Southwest Asia were collected, and several statistical approaches were valuated on the Y-chromosome short tandem repeat data. In order to develop a more accurate and ractical lassification model, we applied gradient boosting and ensemble techniques. To infer between the outheast and Southwest Asian populations, the overall performance of the classification models as better than that of the decision trees and regression models used in the past. In conclusion, his study suggests that additional statistical approaches, such as data mining techniques, could rovide more useful interpretations for forensic analyses. These trials are expected to be the basis or further studies extending from target regions to the entire continent of Asia as well as the use f additional genes such as mitochondrial genes.

Key Words: Y-chromosomal short tandem repeats; Statistical models; Decision trees; Data mining; Ensemble model