Analysis of Cotton Fibre Properties: A Data Mining Approach

被引：14

作者：

Chakraborty S. ^{[1
]}

Agarwal S. ^{[1
]}

Dandge S.S. ^{[2
]}

机构：

[1] Department of Production Engineering, Jadavpur University, Kolkata, West Bengal

[2] Mechnaical Engineering Department, Government Polytechnic, Murtizapur, Maharashtra

来源：

Journal of The Institution of Engineers (India): Series E | 2018年 / 99卷 / 02期

关键词：

Cluster analysis; Cotton fibre; Data mining; Decision tree; Dendogram; Spinnability;

D O I：

10.1007/s40034-018-0125-4

中图分类号：

学科分类号：

摘要：

The quality of cotton fibre is often characterized by its various physical properties, like bundle strength, elongation at break, fineness, mean length, maturity ratio, short fibre content, neps etc. As cotton is a natural fibre, all of its properties are always subjected to variation, thereby, influencing the characteristics of the final yarn. In this paper, these cotton fibre properties are analyzed in details using various tools of data mining. Decision tree is at first developed so as to identify the most predominant property affecting the spinnability of cotton fibres. It is also adopted to study the effects of different cotton fibre properties on yarn tenacity and unevenness. The developed dendograms help in identifying pairs or groups of cotton fibres having almost similar properties. On the other hand, cluster analysis acts as a visual decision aid in segregating the considered cotton fibres into different groups having maximum intraclass similarity and minimum interclass similarity to determine the constituent fibres in the final blend. These data mining techniques can also be implemented to study the physical characteristics of other natural fibres. © 2018, The Institution of Engineers (India).

引用

页码：163 / 176

页数：13

共 33 条

[1]

Cai Y., Cui X., Rodgers J., Thibodeaux D., Martin V., Watson M., Pang S.-S., A comparative study of the effects of cotton fiber length parameters on modeling yarn properties, Text. Res. J., 83, 9, pp. 961-970, (2013)

[2]

Dias S., Vasconcelos R., Santos M., Amorim T., Amaral L., Knowledge discovery in textile field—analysis of a cotton fibre properties database, Data Mining III, pp. 215-223, (2002)

[3]

Majumdar A., Majumdar P.K., Sarkar B., Application of an adaptive neuro-fuzzy system for the prediction of cotton yarn strength from HVI fibre properties, J. Text. Inst., 96, 1, pp. 55-60, (2005)

[4]

Hsu C.-H., Wang M.-J.J., Using decision tree-based data mining to establish a sizing system for the manufacture of garments, Int. J. Adv. Manuf. Technol., 26, pp. 669-674, (2005)

[5]

Nurwaha D., Wang X.H., Prediction of rotor spun yarn strength from cotton fiber properties using adaptive neuro-fuzzy inference system method, Fibers Polym., 11, 1, pp. 97-100, (2010)

[6]

Tyagi S.K., Sharma B.K., Data mining tools and techniques to manage the textile quality control data for strategic decision making, Int. J. Comput. Appl., 13, 4, pp. 26-29, (2011)

[7]

Faridi M.S., Mustafa T., Usability of data warehousing and data mining for interactive decision making in textile sector, Global J. Comput. Sci. Technol., 12, 7, pp. 1-4, (2012)

[8]

Ghosh A., Majumdar A., Das S., A technique of cotton bale laydown using clustering algorithm, Fibers Polym., 13, 6, pp. 809-813, (2012)

[9]

Ochola J.R., Mwasiagi J.I., Modelling the influence of cotton fibre properties on ring spun yarn strength using Monte Carlo techniques, Res. Rev. Polym., 3, 3, pp. 84-88, (2012)

[10]

Banerjee D., Ghosh A., Das S., Yarn strength modelling using genetic fuzzy expert system, J. Inst. Eng. (India) Ser. E, 93, 2, pp. 83-90, (2013)

← 1 2 3 4 →