Labor Accidents in Brazil: a Descriptive Analysis
Resumo
Labor accidents cause several misfortunes, such as inconvenience to the injured ones, loss of laborproductivity, and public spending on aid and accident compensation. This work aims to search and characterize groupsof labor accidents, granting interpretability to the obtained results, to extract information that can be relevant to publicmanagers. The method proposed in this work consists of the following steps: data pre-processing; the applicationof two hierarchical clustering algorithms, HDBSCAN * and COBWEB; the evaluation of results using the SimplifiedSilhouette. The research demonstrated the susceptibility of male workers, focused on ages between 18 and 34 years old,with labor accidents that caused injuries on the fingers, by handling machines and equipment or manual tools, followedby those activities such as fishing. Considering clusters majorly composed by female victims, those related to work incellulose, paper, and related products stand out. Moreover, fingers are the most affected part, featured for incidentscaused by the handling of chemical, biological, or hand tools.
Referências
Brito, L. L. A strategy for temporal visual analysis of labor accident data. M.S. thesis, Universidade Federal de Uberlândia, 2019. Programa de Pós-Graduação em Computação.
Campello, R. J., Moulavi, D., Zimek, A., and Sander, J. Hierarchical density estimates for data clustering, visualization, and outlier detection. ACM Transactions on Knowledge Discovery from Data (TKDD) 10 (1): 1–51, 2015.
de Trabalho Decente MPT OIT, S. Observatório digital de saúde e segurança no trabalho (MPT-OIT), 2017. Dados acessados em: 10/03/2018. Disponível online no seguinte endereço http://observatoriosst.mpt.mp.br.
Fisher, D. H. Knowledge acquisition via incremental conceptual clustering. Machine learning 2 (2): 139–172, 1987.
Hruschka, E. R., de Castro, L. N., and Campello, R. J. Evolutionary algorithms for clustering gene-expression data. In Fourth IEEE International Conference on Data Mining (ICDM’04). IEEE, pp. 403–406, 2004.
IBGE. Desemprego recua em dezembro, mas taxa media do ano e a maior desde 2012, 2018. Acesso em: 01/08/2018.
Porto, S. S. S. and Júnior, I. J. d. N. Acidentes de trabalho no hospital anchieta: Uma análise exploratória de suas características a partir da análise de agrupamentos (clusters). In Anais do Congresso Brasileiro de Custos-ABC, 2006.
Rodrigues, M. P. A strategy for visual structural data analysis of labor accident data. M.S. thesis, Universidade Federal de Uberlândia, 2019. Programa de Pós-Graduação em Computação.
Semaan, G. S. Algoritmos para o Problema de Agrupamento Automático. Ph.D. thesis, Tese de Doutorado, Instituto de Computação, Universidade Federal Fluminense, 2013.