Automatic Discovery of Basic Motion Classification Rules

  • Satoshi Hori
  • Mizuho Sasaki
  • Hirokazu Taki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4252)


There is a keen demand for a method of sharing better work practices in a factory because better work practices are the key to improving productivity. We have developed a system that can measure a worker’s motion and automatically generate a manual that describes his movements. This system employs motion study as used in Industrial Engineering to identify the important steps in a job, and it has proven to be effective especially in the fields of factory machine operation and maintenance. However, work procedures often include unique basic motions. The determination of basic motions and the creation of an algorithm that can classify these basic motions are time consuming and complex tasks. Therefore we have employed the C4.5 algorithm to discover rules that classify the basic motions. Experimental results prove that our method can successfully discover rules for various work procedures.


Motion Study Basic Motion Automatic Discovery Rule Discovery Work Procedure 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barnes : Motion and Time Study. John Wiley & Sons, Inc., Chichester (1968)Google Scholar
  2. 2.
    Murphy, R.R.: Introduction to AI Robotics. MIT Press, Cambridge (2000)Google Scholar
  3. 3.
    Quinlan, J.R.: C4.5 an Induction System. Academic Press, LondonGoogle Scholar
  4. 4.
    Quinlan, J.R.: Decision Trees and Decision making. IEEE Trans. on Systems, Man and Cybernetics 20(2), 339–346 (1990)CrossRefGoogle Scholar
  5. 5.
    Hori, S., Hirose, K., Taki, H.: Acquiring After-Sales Knowledge from Human Motions. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds.) KES 2004. LNCS (LNAI), vol. 3214, pp. 188–194. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Nakata, T.: Automatic Generation of Expressive Body Movement Based on Cohen-Kestenberg Lifelike Motion Stereotypes. Journal of Advanced Computational Intelligence and Intelligent Informatics 7(2), 124–129 (2003)Google Scholar
  7. 7.
    Song, Goncalves, Perona: Unsupervised learning of human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(7), 814–827 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Satoshi Hori
    • 1
  • Mizuho Sasaki
    • 1
  • Hirokazu Taki
    • 2
  1. 1.Monotsukuri Institute of TechnologistsGyodaJapan
  2. 2.Wakayama UniversityWakayamaJapan

Personalised recommendations