Decision support system for safety improvement: An approach using multiple correspondence analysis, t-SNE algorithm and K-means clustering. (February 2019)

• Record Type: Journal Article
• Authors: Dhalmahapatra, Krantiraditya; Shingade, Rohan; Mahajan, Harshawardhan; Verma, Abhishek; Maiti, J.
• Is Part Of: Computers & industrial engineering. Volume 128(2019)
• Page Start: 277
• Page End: 289
• Publication Date: 2019-02
• Subjects: Safety analytics -- Near miss incidents -- R2-profile -- Perceptual mapping -- Kernel category -- Chi-square distance; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2018.12.044
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: Development of Decision support system for EOT crane safety improvement. Hybrid methodology using MCA, t-SNE algorithm and K-means clustering. A novel R 2 -profile approach to retain desired number of dimensions in MCA. Kernel category based chi-square distance for identification of sub-clusters within a cluster. Four meaningful safety rules and related safety interventions. Abstract: An attempt has been made to develop a decision support system (DSS) for safety improvement using a multi-step knowledge discovery process involving multiple correspondence analysis (MCA), t-SNE algorithm and K-means clustering. MCA is used for dimension reduction and perceptual mapping from categorical data. Usually, the first two dimensions are used for perceptual mapping if these two dimensions explain a significant percentage of variance. Otherwise, the traditional method of two dimensional mapping, leads to loss of important categorical information involved with other dimensions. Considering the above, a novel R 2 -profile approach, as an alternate to inertia based approach, is adopted to obtain the desired number of dimensions to be retained without loss of significant amount of information. t-SNE technique reduces the high dimensional data into two dimensional (2D) map, which provides the associations amongst different categories. K-means clustering grouped the 2D categories in homogenous clusters as per the similarities of the categories. A novel kernel category based chi-square distance method is proposed to identify sub-clusters within a cluster which subsequently provides useful rules for safety improvement. The methodology also provides a logical approach of dimension reduction in a form called 'funnel diagram'. Finally, the DSS is applied to analysing near miss incidents occurred in electric overhead traveling (EOT) crane operations in a steel plant. Several safety rules are identified and safety interventions are proposed.