Exceptional events classification in warehousing based on an integrated clustering method for a dataset with mixed-valued attributes. Issue 11 (2nd November 2018)

• Record Type: Journal Article
• Authors: Li, Nailiang; Zhang, Chang; Xie, Weixing; Li, Yupeng
• Is Part Of: International journal of computer integrated manufacturing. Volume 31:Issue 11(2018)
• Page Start: 1078
• Page End: 1096
• Publication Date: 2018-11-02
• Subjects: Warehousing -- exceptional events -- clustering -- mixed-valued attributes -- initial clustering centres; Computer integrated manufacturing systems -- Periodicals; 670.427
• DOI: 10.1080/0951192X.2018.1509129
• Languages: English
• ISSNs: 0951-192X

Abstract

ABSTRACT: As an essential component of a supply chain, warehousing with a high operational management level can significantly enhance the efficiency of manufacturing. Practically, there are many exceptional events (EEs) that impede agile operation in warehousing, and disparate handling processes should be established according to the characteristics of the EEs. In this context, a classification methodology for the EEs based on a generalised criterion with mixed-valued attributes is presented in this study. The approaches for determining the initial clustering centres for a dataset with mixed-valued attributes are illustrated in accordance with the distribution regularities of values of numerical and categorical attributes. Subsequently, two algorithms without randomisation of the initial clustering centres are successively generated: one is a basic iterative algorithm and the other is an algorithm that can optimise the number of clusters automatically. The classification of EEs in warehousing by utilising the proposed algorithm is established as a case study in the storage department of an electric tool enterprise. Finally, the applicability of the proposed algorithm is evaluated by comparing with k -prototypes and the original algorithm, and a processing flow is proposed for EEs in warehousing based on the final clustering results.