Decision Rule Prediction for Assessment of Rotor Spun Cotton Yarn Strength Using Rough Set

ABSTRACT

Being an agro-based natural product, cotton always poses vagueness in the parameters. Hence, formulation of decision rules for prediction of cotton yarn quality from the imprecise cotton fiber properties is an intricate problem. Yarn tenacity is considered an imperative quality parameter in the cotton textile industry. Modelling of yarn tenacity has remained as the cynosure of research for textile engineers. In recent years, rough set theory has evolved as one of the most important techniques used for handling imprecise data. One of the cardinal uses of rough set theory is its application to rule generation. Our approach focuses on the elimination of the redundant data set in order to generate effective decision rules which retain the accuracy of the original data set. In this work rough set theory is employed to generate decision rules to predict yarn tenacity from six input parameters. The validation results prove that the generated 45 decision rules accurately predicted 14 out of 16 unknown test data. Thus, in the present competitive market, this model is potent for getting recognition from the textile industry.

摘要

棉花是一种以农业为基础的天然产品，其参数总是模糊不清. 因此，根据不精确的棉纤维特性来制定预测棉纱质量的决策规则是一个复杂的问题. 纱线韧性被认为是棉纺织工业中一个必不可少的质量参数. 纱线强力建模一直是纺织工程师研究的重点. 近年来，粗糙集理论已发展成为处理不精确数据的最重要技术之一. 粗糙集理论的主要用途之一是将其应用于规则生成. 我们的方法侧重于消除冗余数据集，以生成有效的决策规则，保持原始数据集的准确性. 在这项工作中，粗集理论被用来生成决策规则，从六个输入参数预测纱线强力. 验证结果证明，生成的45条决策规则准确预测了16个未知测试数据中的14个. 因此，在当前竞争激烈的市场中，这种模式有可能获得纺织行业的认可.

KEYWORDS:

• Cotton
• decision rule
• rough set
• tenacity
• yarn

关键词:

• 棉
• 决策规则
• 粗糙集
• 韧性
• 纱线

Highlights

• In recent years, rough set theory has evolved as one of the most important techniques used for handling imprecise data. One of the cardinal uses of rough set theory is its application for rule generation. Our approach focuses on the elimination of the redundant data set in order to generate the effective decision rule which retain the accuracy of the original data set.

• Being an agro-based natural product, cotton always poses vagueness in the parameters. This work dealt with the impreciseness present in cotton using rough set theory.

• The different operations of rough set, viz., discretization, upper approximation, lower approximation and reduct are performed on 92 datasets in step-by-step and eventually only 24 reducted datasets are obtained. The 45 decision rules are generated from the reducted dataset.

• The proposed rough set model focuses on the yarn tenacity prediction from six cotton fiber properties. The validation results prove that the generated 45 decision rules accurately predicted 14 out of 16 unknown test data.

• Now-a-days, with the advent of modern computational system, data storage and processing of huge data has become very simple. Thus, the model has huge potential for industrial acceptability for prediction of yarn properties.

Acknowledgment

The authors would like to thank Government College of Engineering & Textile Technology Berhampore, India for providing necessary infrastructural support required to complete this work successfully. With the submission of this manuscript I would like to inform that the type of submitted manuscript is an ‘Original Research Article’. I would like to undertake that the above mentioned manuscript has not been published elsewhere, accepted for publication elsewhere or under editorial review for publication elsewhere; and that my Institute’s Government College of Engineering & Textile Technology, Berhampore, India, representative is fully aware of this submission.

Disclosure statement

No potential conflict of interest was reported by the author(s).