Using Data Mining Techniques to Establish Standard Sizing System for Sudanese Army Officers Poshirt

Abstract

The purpose of this research was to use data mining techniques in establishing standard sizing system for Sudanese army officers garment especially (Poshirt) based on an anthropometric body measurements variables SUD and to compare it with Sur Military Clothing Factory in Sudan (SUR),USA, and EUR national sizing charts. The data set collected for 841 army officers and for each individual 13 anthropometric variables was involved. In this work data mining methods (WEKA and SPSS) were used for clustering and establishing sizing system. The K-means algorithm was implemented to determine the final cluster classification. Cluster analysis using chest and waist as a control anthropometric variables revealed a new established sizing system SUD which consists of eight distinct clusters namely; XS, S, M, L, XL, XXL, XXXL and XXXXL. Size codes and upper and lower size limits are generated. The new proposed sizing system SUD profile was compared with profile of SUR, USA, and EUR national standards sizing charts. The results revealed that the proposed sizing system SUD followed approximately the same profile as the three others sizing systems but there was slight differences between the new established systems SUD and the USA and EUR national standard size charts