Workforce satisfaction level in military organization: a case study using Fuzzy logic and artificial neural networks


  • Priscila da Silva Oliveira Universidade Estácio de Sá, UNESA


Fuzzy Logic, Artificial Neural Networks, Quality of life at work.


The effective management of productive resources in organizations has become, in contemporary times, a factor of competitiveness. Decision makers seek more assertive means to manage the companies’s activities and therefore see the intellectual capital as a promising core to operate and optmize. In the context of the pursuit of excellence in management processes, this research aims to determine and analyze the degree of satisfaction of the civil work force, in a military facility located in the city of Rio de Janeiro, through the study of the perceptions of the staff concerning indicators of quality of life at work. This research aims to make tangible complex data of quality of life at work and the expectations of the employees and transmute them into output of satisfaction. Therefore, we used Fuzzy Logic to study complex data and Artificial Neural Networks, to decompose attributes in neurons, arranged in affinity groups, and their subsequent submission to the intelligent layer system: i) fuzzyfication ii) inference and iii) defuzzyffycation. It was observed that after the use of the application, the level of employee satisfaction was "regular" and it was very near the "Poor" level proposed by this modeling. Thus, lessons were learned about the motivating factors of the civil work force, as well as we obtained a starting point for the implementation of improvement actions.


Altrock, C.v: Fuzzy-Logik. Munchen, Oldenbourg, 1993.

Bailey, S. A.;Ye-Hwa C. (1998). "A Two Layer Network using OR/AND Neuron", IEEE World Congress on Computational Intelligence, 1998.

Bandemer, H.; Gottwald, S. Einführung in Fuzzy-Methoden. 4. Aufl., Akademie-Verlag, Berlin (1993)

Barreto, J. B. Introdução às Redes Neurais Artificiais. 2002. Disponível em barreto/tutoriais/Survey.pdf. Acessado em 10 de maio de 2016.

Biewer, B. Fuzzy-Methoden, Springer, Berlin (1997).

Bocklish, S. Prozeßanalyse mit unscharfen Verfahren, Akademie-Verlag, Berlin, 1987.

Buckeley, J. The multiple judge, multiple criteria ranking problem: A fuzzy set approach. Fuzzy Sets and Systems, v.13, p.25-37, 1984.

Costa, R.S et al. Os cinco passos do pensamento enxuto (LEAN THINKING). Rio de Janeiro, 2010.

Dallinghaus, K. Realisierung und Optimierung eines Neuro-Fuzzy Systems zur Erkennung rhythmischer Muster. PICS-Verlag. Osnabrück, 2005.

Demant, B. Fuzzy-Theorie oder die Faszination des Vagen. Vieweg Verlag, Braunschweig, 1993

Dubois, D.; Prade, M. Fuzzy Sets and Systems, Academie Press, New York (1980).

Fernandes, Eda Conte. (outubro/dezembro 1988). "Qualidade de vida no trabalho (QVT): A renovação das empresas para os anos 90". Revista de Administração.

Fernandes, E. Qualidade de vida no trabalho – Como medir para melhorar. Bahia: Casa da Qualidade, 1996.

Gutjahr, W et al. 2010, Multi-objective decision analysis for competence-oriented project, European Journal of Operational Research, v. 205, pp. 670- 679.

Hell M.B., (2006). “Abordagem Neurofuzzy para Modelagem de Sistemas Dinâmicos Não Lineares", Programa de Pós-graduação em Eng. Elétrica. UNICAMP, Cap. 2 p. 7-38, outubro 2006.

Hirota, K. and Pedrycz. W., (1994). “OR/AND neuron in modeling fuzzy set connectives”, IEEE Trans. Fuzzy Syst., vol. 2, pp. 151–161, 1994.

Huftle, M. Methoden der unscharfen Optimierung. 2005.

Khashman, A. Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes. Expert Systems with Applications Volume 37, Issue 9, September 2010, Pages 6233-6239

Lazzari, L. et al. Teoria de la decisón fuzzy. Ediciones Macchi, Buenos Aires, 1998.

Li, Hong Xing; Yen, V. C. Fuzzy Sets and Fuzzy Decision-making, ISBN 0-8493-8931-3, CRC Press, USA, 1995.

Lean Institute Brasil (2016). O que é Lean. Disponível em: Capturado em: 23 de julho de 2016.

Masters, Timothy. Advanced Algorithms for Neural Networks: A C++ sourcebook. John Wiley & Sons, Inc., 1995. 431 páginas.

Medeiros, A. V. de, Souza, F. E. C. e Maitelli, A. L. (2003) Implementação de um Sistema de Extração de Conhecimento de Redes Neurofuzzy In:II Workshop Técnico Científico do DIMAp Universidade Federal do Rio Grande do Norte, Rio Grande do Norte.

Mcloch, W. S. and Pitts, W. H. (1943). "A logical calculus of the ideas immanent in nervous activity", Bulletin of Mathematical Biophysics, 5, 115–133, 1943.

Oliveira Jr., H. A. Lógica Difusa – Aspectos Práticos e Aplicações. Editora Interciência, Rio de Janeiro, 1999.

Moraes, J. A. R. de e Sahb, L. M. Manufatura Enxuta. 2004. Disponível em: http:// Capturado em: 24 de julho de 2016.

Pedrycz, W; Reformat, M. and Li, K., (2006). "OR/AND Neurons and the Development of Interpretable Logic Models", IEEE Transactions Neural Network, vol. 17, maio, 2006.

Rodrigues, M. V. C. Qualidade de vida no trabalho – Evolução e Análise no nível gerencial. Rio de Janeiro: Vozes, 1994.

Scanzio, S. et al., P. Parallel implementation of Artificial Neural Network training for speech recognition. Pattern Recognition Letters. Volume 31, Issue 11, 1 August 2010, Pages 1302-1309.

Shi, Y. and Y. H. Liu, Fuzzy Potential Solutions in Multicriteria and Multiconstraints Levels Linear Programming Problems. Fuzzy Sets and Systems 60, 163–179. 1993.

Tanaka, Kazuo, An Introduction to Fuzzy Logic for Practical Applications. Ed.Springer, Nova York, 1997

Tatibana, C. Y. , Kaetsu, D. Aplicações de Redes Neurais Artificiais 2009 Disponível em Acessado em 20 de maio de 2016.

Walton, R. Quality of working life: what is it? Slow Management Review. USA: v15,n.1, p. 11-21, 1973.

Zadeh, L.A. (1965). Fuzzy Sets. Inf. & Control, 8. 338-353.

Zadeh, L.A. Similarity relations and fuzzy orderings. Inform. Sci., 3. 177-200.

Zimmermann, H.J. Unscharfe Entscheidungen und Multi-Criteria Analyse, in: Proceedings in OR, Wurzburg 1976, pp. 99-116