Using Multi-Agent Systems Technique for Developing an Autonomous Model Used to Analyze Work-Stress Data

  • Anusua Ghosh
  • Jeffery W. Tweedale
  • Andrew Nafalski
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 234)


This chapter presents a semi-autonomous data collection and analysis application that facilitates the measurement of indivudal stress (or any other metric) within the workplace. This novel approach uses a hybridized autonomous Multi-Agent System (MAS) framework that has been tailored to analyze work-related stress for individuals submitting the on-line survey in real-time. Psychologists continue to report that work-stress affects people from all profession. This model allows them to remotely measure the level of stress within the workplace, against national norms, that can help employers identify and address or prevent stress by influencing changes to the working environment. The system has been presented at conferences, then tested both within the workplace and remotely as an on-line kiosk. Intelligent Multi-Agent Decision Analyser (IMADA) is the core component of the model and each agent represents independent capabilities in their own right. The MAS provides the interaction and communication between each agent in order to accomplish the desired desired goal (individual bench-marked responses). IMADA replaces the existing manual processes and reduces the significant effort required to access employees. It also automates the collection, analysis and management of the survey data (which was typically achieved by professionals through questions during long phone interviews).


Artificial Intelligence Intelligent Agent Multi-Agent System  Neural Network Fuzzy Logic 



This research work is supported by the Australian Research Council Linkage Grant LP 100100449. The authors would like to thank my Prof. Maureen Dollard, Director, Centre for Applied Psychological Research for her support and encouragement and also would like to thank research assistant Wayan Firdaus Mahamoody for his assistance and co-operation in developing the StressCaf Website.


  1. 1.
    Dollard, M.F., Taylor, A.: Cohort Profile: The Australian Workplace Barometer AWB. Prentice Hall, Upper Saddle River (2010)Google Scholar
  2. 2.
    McCarthy, J.: Program with common sense. In: Mechanisation of Thought Processes, Proceedings of the Symposium of the National Physics Laboratory, pp. 77–84. London, Her Majesty’s Stationery Office (1959)Google Scholar
  3. 3.
    McCarthy, J.: From here to human-level AI. AIJ 171(18), 1174–1182 (2007)Google Scholar
  4. 4.
    Nilission, N.J.: The Quest for Artificial Intelligence: A History of Ideas and Achievements. Cambridge University Press, Stanford University (2009)Google Scholar
  5. 5.
    Abbot, L., Siskovic., Intelligent Agents in Computer and Network Managements. Teachnet, University of Texas (2011)Google Scholar
  6. 6.
    Mills, F., Stufflebeam, R.: Introduction to Intelligent Agents. Ants NASA, Intelligent agent (2005)Google Scholar
  7. 7.
    Wooldridge, M., Jennings, N.: Intelligent agents: theory and practice. Knowl. Eng. Rev. 10(2), 115–152 (1995)CrossRefGoogle Scholar
  8. 8.
    Wooldridge, M., Jennings, N.R.: Agent theories, architectures, and languages: a survey. In: Wooldridge, M., Jennings, N.R. (eds.) Intelligent Agents, pp. 261–276, Springer, Heidelberg (1995)Google Scholar
  9. 9.
    Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. 3rd edn. Prentice Hall, Inc., Englewood Cliffs (2010)Google Scholar
  10. 10.
    Tweedale, J., Jain, L.C.: Embedded automation in human-agent environment, Adaptation, Learning and Optimization, vol. 10. Springer, Berlin (2011)Google Scholar
  11. 11.
    McArthur, S.D.J., Davidson, E.M.: Concepts and Approaches in Multi-Agent Systems for Power Applications. Intelligent Systems Application to Power Systems (2005)Google Scholar
  12. 12.
    Nakano, K., Yamaguchi, D., Katayama, F., Takahashi, M.: The Medical Diagnosis Support System with Intelligent Multi Agent Techniques by Performance Differential Difference. In: Fifth International Workshop on Computational intelligence and Applications, IEEE SMC Hiroshima Chapter, pp. 10–12, Hiroshima University, Japan, Nov 2009Google Scholar
  13. 13.
    Tweedale, J., Ichalkaranje, N., Sioutis, C., Jarvis, B., Consoli, A., Phillips-Wren, G.: Innovations in multi-agent systems. J. Netw. Comput. Appl. 30(3), 1089–1115 (2007)Google Scholar
  14. 14.
    Tweedale, J.W.: Autonomous agent teaming providing enhanced communication components. Phd Thesis, University of South Australia, Australia (2009)Google Scholar
  15. 15.
    Mangina, E.: Intelligent agent-based monitoring platform for applications in engineering. Int. J. Comput. Sci. Appl. 2(1), 38–48 (2005)Google Scholar
  16. 16.
    Jung, I., Thapa, D., Wang, G.N.: Intelligent Agent based Graphic User Interface (GUI) for e-physician. World Academy of Science, Engineering and Technology, vol. 36 (2007)Google Scholar
  17. 17.
    Agah, A., Tanie, K.: Intelligent graphical user interface design utilizing multiple fuzzy agents. Interact. Comput. 12, 529–542 (2000)CrossRefGoogle Scholar
  18. 18.
    Zdrenghea, V., Man, D.O., Tosa-Abrudan, M.: Fuzzy Clustering in an Intelligent Agent for Diagnosis Establishment. Studia Universita, Babes-bolyai, Informatica, vol. 55, issue 2 (2010)Google Scholar
  19. 19.
    Moreno, A.: Medical Applications of Multi-Agent Systems. Computer Medical Applications, vol. 3, 2002Google Scholar
  20. 20.
    Warren, M., Walter P.: A logical calculus of ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, vol. 5, pp. 115–133 (1943)Google Scholar
  21. 21.
    Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organisation in the brain. Psychology Review, vol. 65, pp. 42–99 (1958)Google Scholar
  22. 22.
    Rumelhart, D., Hilton, G., Williams, R.: Learning representations by backpropogation errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  23. 23.
    Patterson, D.W.: Artificial Neural Networks Theory and Applications. Prentice Hall International pp. 247–264 (1996)Google Scholar
  24. 24.
    Rojas, R.: Neural networks-A systematic introduction. University of Pennsylvania Law Review, 154(3), chaps 2–6 (1996)Google Scholar
  25. 25.
    Werbos, P.J.: Beyond regression: new tools for prediction and analysis in the behavior science. PhD. Thesis, Harvard University, Cambridge, pp. 99–154 (1974)Google Scholar
  26. 26.
    Parker, D.: Learning Logic, Tecnical report Tr-47, Center for Computational Research in Economics and Management Science, MIT, Cambridge, pp. 99–154 (1985)Google Scholar
  27. 27.
    Rumelhart, D.E., McClelland, J.L., and the PDP Research Group. Parallel Distributed Processing (PDP): Exploration in the Micro-structure of Cognition, vol. 1, The MIT Press, Cambridge, pp. (76, 77, 154, 155, 219, 329) (1986)Google Scholar
  28. 28.
    Tweedale, J.: Fuzzy control loop in an autonomous landing system for unmanned air vehicles. In: IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–8. IEEE Press, Barcelona (2012)Google Scholar
  29. 29.
    Zadeh, L.A.: Fuzzy sets. Inform and Control 8, 338–353 (1965)Google Scholar
  30. 30.
    Jang, J.S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing. A computational approach to learning and machine intelligence, Mathlab Curriculum Series (1997)Google Scholar
  31. 31.
    Zang, Z., Zang, C.: Agent-Based Hybrid Intelligent Systems. LANI 2938, pp. 3–11, Springer, Berlin (2004)Google Scholar
  32. 32.
    Ghosh, A., Nafalski, A., Tweedale, J., Dollard, M.: Hybridized technique to analyse workstress related data via the StressCaf, ICCESSE 2012: International Conference on Computer, Electrical, and Systems Sciences, and Engineering. Bali, Indonesia, Oct 24–25, (2012)Google Scholar
  33. 33.
    Ghosh, A., Nafalski, A., Tweedale, J., Dollard, M.: Using hybridized techniques to develop an online workplace risk assessment tool. J. Inform. Control Meas. Econ. Environ. Prot. 4b, 42–45 (2012)Google Scholar
  34. 34.
    Ghosh, A., Tweedale, J., Nafalski, A., Dollard, M.: Multi-agent based system for analysing stress using the Stresscafe. Advances in Knowledge-Based and Intelligent Information and Engineering Systems, Amsterdam, vol. 243, pp. 1656–1665 (Sep 2012)Google Scholar
  35. 35.
    Taylor, A., Gill, T.: Eleonora. Population Research and Outcome Studies, University of Adelaide, Adelaide, Australia, Dall Grande (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Anusua Ghosh
    • 1
  • Jeffery W. Tweedale
    • 1
    • 2
  • Andrew Nafalski
    • 1
  1. 1.School of Electrical and Information EngineeringUniversity of South AustraliaAdelaideAustralia
  2. 2.Aerospace DivisionDefence Science and Technology OrganizationAdelaideAustralia

Personalised recommendations