Developing a new suit sizing system using data optimization techniques

Abstract

Purpose -The purpose of this paper is to develop a new suit sizing system based on up-dated data, using data mining techniques, to improve the final quality and reduce the waste of fabric. This paper aims to investigate the effect of data reduction on the final fitness of the sizing chart. Design/methodology/approach -Principal component analysis is applied to reduce the sizing variables, non-hierarchical clustering approach is used to segment the heterogeneous population to more homogeneous one, and the aggregate loss of fitness is used to evaluate the resulted sizing chart. Findings -The results show that, when principal component analysis reduces the ten sizing variables to two main components, the final fitness for the resulted sizing chart is the best. These two main components are height and circumference. The hierarchical clustering approach could effectively group all body type to seven clusters. The resulted sizing chart could be used as a reference for suit manufacturers. Practical implications -Due to wide differences in race, nutrition and climate, people who live in different countries have their own body size; also, most of current sizing systems are out-dated, so there is an urgent need to develop a new sizing system. Due to the growing rate of globalization, the final results will be useful for those companies wanting to connect to global business chains. Originality/value -This work introduces the first suit sizing systems, based on data mining, for Iranian males, that has more fitness in comparison to the current sizing chart. The effect of the number of principal components on the final fitness of a sizing system is introduced as an innovative way, to avoid losing useful data during data reduction process with principal component analysis.

Development of a Military Uniform Size System Using Hybrid Support Vector Clustering with a Genetic Algorithm

“…The approach of Bagherzadeh et al [19] consists of three phases: factor analysis, two-step cluster analysis, and decision tree analysis. Esfandarani and Shahrabi [20] used principal component analysis to cut sizing variables to partition a heterogeneous population into a homogeneous community such that the resulting size chart is estimated by the aggregate loss of the fitness method. Xia and Istook [21] considered the sizing system creation process including natural log-transformation, principle component analysis, multivariate linear regression, size range determination, and measurements calculation.…”

Data mining and machine learning in textile industry

“…It helps us better understand the characteristics of data because fewer groups are more easily interpreted. Several studies have focused on the application of the clustering process in the textile industry with the aid of algorithms named K-means, [54][55][56][57][58] Fuzzy C-means, 59 and Hierarchical. 60,61 K-means is an easily implemented algorithm that divides the given dataset into k clusters by determining the centroids of each cluster.…”

“…For example, identification of user and usage profiles to innovate, create, and improve textile products and services 10,40 For example, predictive data analysis to understand user requirements in order to be able to design better textile products 46,47,56,57 • Recognition and classification of textile defects for quality control For example, fabric defects 6,8,38,51 (i.e., yarn, woven, knitted, dyeing defects), embroidery defects, 53 and garment defects 50,70 (i.e., cutting, sewing, and accessories defects)…”

“…Garment fitting problems in the textile industry are instances of clustering problems and were tackled via PCA and K-means algorithms 56,57 for size charts with higher fitting. Esfandarani and Shahbari 56 proposed a suit sizing system by segmenting the heterogeneous population to a more homogenous one, and the aggregate loss of fitness is used to evaluate the resultant sizing.…”

“…• Analyzing the records of financial transactions in the textile sector for better decision making 20 • Using DM as a preprocessing step before performing the essential textile study 52 • Text mining to extract interesting patterns and perform textile knowledge extraction from the unstructured textile documents that are obtained from different sources • Clustering the items in textile data to describe the current situation more clearly and to plan different activities for different groups [55][56][57][58][59][60][61][62][63][64][65][66] • Usage of process mining in the context of workflow management and to improve the processes in the textile sector 16,18 Challenges of DMTI Even though DM is a helpful tool based on the above indicated advantages, there are also challenges that could be eliminated. Challenges of DMTI can be classified into four main titles: data preparation, complex nature of textile data, task/algorithms, and postprocessing.…”