Classification of textile fabrics using statistical multivariate techniques
In this study, an attempt has been made to classify the textile fabrics based on the physical properties using statistical multivariate techniques like discriminant analysis and cluster analysis. Initially, the discriminant functions have been constructed for the classification of the three known categories of fabrics made up of polyster, lyocell/viscose and treated-polyster. The classification yielded hundred per cent accuracy. Each of the three different categories of fabrics has been further subjected to the K-means clustering algorithm that yielded three clusters. These clusters are subjected to discriminant analysis which again yielded a 100% correct classification, indicating that the clusters are well separated. The properties of clusters are also investigated with respect to the measurements.
Year of publication: |
2012
|
---|---|
Authors: | Kiruthika, C. ; Chandrasekaran, R. |
Published in: |
Journal of Applied Statistics. - Taylor & Francis Journals, ISSN 0266-4763. - Vol. 39.2012, 5, p. 1129-1138
|
Publisher: |
Taylor & Francis Journals |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Location on Tree Networks: P-Centre and n-Dispersion Problems
Chandrasekaran, R., (1978)
-
Prognosis Using an Isotonic Prediction Technique
Ryu, Young U., (2004)
-
Production Planning in Assembly Line Systems
Chandrasekaran, R., (1984)
- More ...