Advertisement

Combining Design of Models for Smart Environments with Pattern-Based Extraction

  • Gregor Buchholz
  • Peter Forbrig
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8510)

Abstract

There are two different types of approaches for smart environments. The first group provides an infrastructure that contains mechanisms from artificial intelligence that allow to adapt to certain behavior of users and to support them by performing their tasks. These approaches work fine if the conditions in the environment are not experiencing too many changes. However, when different types of activities have to be supported and participants change a lot there is the problem of getting enough training data to recognize the users’ activities with sufficient reliability. In such cases, designing support by providing models for activities of participating users seems to be a solution. Thus, mechanisms from artificial intelligence can be supported by reducing the search space for possible actions.

Designing of activity models can be performed by employing the top-down approach through predefined generic patterns or alternatively the bottom-up mechanism by looking at traces of performed activities (scenarios). Again patterns play an important role as they allow the identification of important parts of traces that lead to parts of models. The identification of such trace sections can be done almost automatically. The mapping to parts of models however, has to be done in an interactive way. Human decisions are necessary to provide good models. Different strategies can be supported by tools in order to make decisions within the models ranging from abstract levels down to the most detailed level.

This paper will provide a discussion of the outlined approach.

Keywords

task models smart environment model generation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agrawal, R., Srikant, R.: Fast Algorithms for Mining Association Rules. In: Proc. VLDB 1994, pp. 487–499. Morgan Kaufmann (1994)Google Scholar
  2. 2.
    Chikhaoui, B., Wang, S., Pigot, H.: A Frequent Pattern Mining Approach for ADLs Recognition in Smart Environments. In: IEEE International Conference on Advanced Information Networking and Applications (AINA), pp. 248–255 (2011)Google Scholar
  3. 3.
    van Dongen, B.F., de Medeiros, A.K.A., Verbeek, H.M.W., Weijters, A.J.M.M., van der Aalst, W.M.P.: The ProM Framework: A New Era in Process Mining Tool Support. In: Ciardo, G., Darondeau, P. (eds.) ICATPN 2005. LNCS, vol. 3536, pp. 444–454. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    El-Ramly, M., Stroulia, E., Sorenson, P.: Recovering Software Requirements from System-user Interaction Traces. In: Proc. SEKE 2002, pp. 447–454. ACM Press (2002)Google Scholar
  5. 5.
    Ferilli, S., De Carolis, B., Redavid, D.: Logic-Based Incremental Process Mining in Smart Environments. In: Ali, M., Bosse, T., Hindriks, K.V., Hoogendoorn, M., Jonker, C.M., Treur, J. (eds.) IEA/AIE 2013. LNCS, vol. 7906, pp. 392–401. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  6. 6.
    Garland, A., Lesh, N.: Learning Hierarchical Task Models By Demonstration. Technical Report, Mitsubishi Electric Research Laboratories (2003)Google Scholar
  7. 7.
    Hamou-Lhadj, A., Braun, E., Amyot, D., Lethbridge, T.: Recovering Behavioral Design Models from Execution Traces. In: 9th European Conference on Software Maintenance and Reengineering, pp. 112–123. IEEE Computer Society (2005)Google Scholar
  8. 8.
    Hoßbach, B., Glombiewski, N., Morgen, A., Ritter, F., Seeger, B.: JEPC: The Java Event Processing Connectivity. Datenbank-Spektrum 13(3), 167–178 (2013)CrossRefGoogle Scholar
  9. 9.
    Krämer, J., Seeger, B.: Semantics and Implementation of Continuous Sliding Window Queries over Data Streams. ACM Trans. Database Syst., 4:1–4:49 (2009)Google Scholar
  10. 10.
    Maulsby, D.: Inductive Task Modeling for User Interface Customization. In: Proc. IUI 1997, pp. 233–236. ACM (1997)Google Scholar
  11. 11.
    Paris, C., Lu, S., Linden, K.V.: Environments for the Construction and Use of Task Models. In: The Handbook of Task Analysis for Human-Computer Interaction, pp. 467–482. Lawrence Erlbaum Associates (2004)Google Scholar
  12. 12.
    Pei, J., Han, J., Mortazavi-Asl, B., Wang, J., Pinto, H., Chen, Q., Dayal, U., Hsu, M.-C.: Mining Sequential Patterns by Pattern-Growth: The PrefixSpan Approach. IEEE Transactions on Knowledge and Data Engineering 16(11), 1424–1440 (2004)CrossRefGoogle Scholar
  13. 13.
    Seyff, N.: Exploring how to use scenarios to discover requirements. Requirements Engineering, 91–111 (2009)Google Scholar
  14. 14.
    Wang, J., Han, J.: BIDE: Efficient Mining of Frequent Closed Sequences. In: Proc. ICDE 2007, pp. 79–90. IEEE Computer Society (2007)Google Scholar
  15. 15.
    Wurdel, M., Sinnig, D., Forbrig, P.: CTML: Domain and Task Modeling for Col-laborative Environments. Journal of Universal Computer Science 14(19), 3188–3201 (2008) (Special Issue on Human-Computer Interaction)Google Scholar
  16. 16.
    Zaki, M., Wurdel, M., Forbrig, P.: Pattern Driven Task Model Refinement. In: Abraham, A., Corchado, J.M., González, S.R., De Paz Santana, J.F. (eds.) International Symposium on DCAI. AISC, vol. 91, pp. 249–256. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  17. 17.
    Zaki, M., Forbrig, P.: A methodology for generating an assistive system for smart environments based on contextual activity patterns. In: EICS 2013, London, pp. 75–80 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Gregor Buchholz
    • 1
  • Peter Forbrig
    • 1
  1. 1.Department of Computer ScienceUniversity of RostockRostockGermany

Personalised recommendations