Optimized fuzzy C-means clustering algorithm for cotton fibre quality analysis. (2021)

• Record Type: Journal Article
• Authors: Dhanapal, R.; Selvapandian, D.
• Is Part Of: Materials today. Volume 45:Part 2(2021)
• Page Start: 2082
• Page End: 2086
• Publication Date: 2021
• Subjects: Cotton quality -- Principal component analysis -- Fuzzy C means clustering -- Cuckoo search -- Map-reduce -- Agglomerative approach; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2020.09.606
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: Exact determination of cotton fibre quality is a huge help for turning factories to purchase cotton as per the least prerequisites. The nature of cotton fibre is decided on numerous elements, for example, staple length, development, finesses, neatness, tenacity, and quality, to make reference to. The essential target of the framework is to accomplish the institutionalization at various levels in the cotton production network the board in the conveyed mechanical systems condition with exact estimation and characterization procedures. The current framework is executed in information mining procedures to foresee the nature of cotton fibre and to establish the most noteworthy connection between's short fibre file and yellowness. The proposed framework incorporates a bunching strategy to group cotton quality fibre. The proposed optimized principal component analysis (OPCA), and Fuzzy C-means bunching in huge dataset. These proposed calculations are executed inside the Map-Reduce method and cuckoo searching technique is applied for reduces the time complexity it is implemented in Hadoop stage to anticipate dampness content, micronaire, extension, and group quality.