Performance Evaluation of an IoT-Based E-Learning Testbed Using Mean Shift Clustering Approach Considering Electroencephalogram Data

  • Masafumi Yamada
  • Tetsuya Oda
  • Yi Liu
  • Keita Matsuo
  • Leonard Barolli
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 2)


Due to the opportunities provided by the Internet, people are taking advantage of e-learning courses and enormous research efforts have been dedicated to the development of e-learning systems. So far, many e-learning systems are proposed and used practically. However, in these systems the e-learning completion rate is low. One of the reasons is the low study desire and motivation. In this work, we design and implement an IoT-Based E-Learning testbed using Raspberry Pi mounted on Raspbian. We analyze the performance of mean shift clustering algorithm considering electroencephalogram data. For evaluation we considered attention value. The evaluation results show that by the mean shift clustering algorithm the learner concentration is increased.


Shift Procedure Ubiquitous Learning Shift Cluster Empirical Probability Density Function Ubiquitous Learn Environment 
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.
    K. Matsuo, L. Barolli, F. Xhafa, V. Kolici, A. Koyama, A. Durresi, R. Miho, “Implementation of an E-Learning System Using P2P, Web and Sensor Technologies”, Proc. of AINA-2009, pp. 800-807, 2009.Google Scholar
  2. 2.
    M. G. Domingo, J. A. M. Forner, “Expanding the Learning Environment: Combining Physicality and Virtuality - The Internet of Things for eLearning”, Proc. of IEEE 10th International Conference on Advanced Learning Technologies (ICALT), pp. 730-731, 2010.Google Scholar
  3. 3.
    I. Gasparini, V. Eyharabide, S. Schiaffino, M. S. Pimenta, A. Amandi, J. P. M. de Oliveira, “Improving User Profiling for a Richer Personalization: Modeling Context in E-Learning”, Intelligent and Adaptive Learning Systems: Technology Enhanced Support for Learners and Teachers, Chapter 12, pp. 182-197, 2012.Google Scholar
  4. 4.
    V. de Freitas, V. P. Marcal, I. Gasparini, M. A. Amaral, M. L. Proenca Jr., M. A. C. Brunetto, M. S. Pimenta, C. H. F. P. Ribeiro, J. V. de Lima, J. P. M. de Oliveira, “AdaptWeb: an adaptive web-based courseware”, Proc. of ICTE-2002, pp. 131-134, 2002.Google Scholar
  5. 5.
    S. Schiaffino, P. Garcia, A. Amandi, “eTeacher: Providing personalized assistance to e-learning students”, Computers & Education, Vol. 51, pp. 1744-1754, 2008.Google Scholar
  6. 6.
    A. Zanella, N. Bui, A. Castellani, L. Vangelista, “Internet of Things for Smart Cities”, IEEE Internet of Things Journal, Vol. 1, No. 1, pp. 22-32, 2014.Google Scholar
  7. 7.
    L. Atzori, A. Iera, and G. Morabito, “The internet of things: A survey”, Comput. Netw., Vol. 54, No. 15, pp. 2787-2805, 2010.Google Scholar
  8. 8.
    P. Bellavista, G. Cardone, A. Corradi, and L. Foschini, “Convergence of MANET and WSN in IoT urban scenarios”, IEEE Sens. J., Vol. 13, No. 10, pp. 3558-3567, Oct. 2013.Google Scholar
  9. 9.
    R. Obukata, T. Oda, D. Elmazi, L. Barolli, K. Matsuo, I. Woungang, “Performance Evaluation of an Ambient Intelligence Testbed for Improving Quality of Life: Evaluation Using Clustering Approach”, The 9-th International Workshop on Intelligent Informatics and Natural Inspired Computing (IINIC-2016), Fukuoka Institute of Technology, Fukuoka, Japan, July 6-8, 2016.Google Scholar
  10. 10.
    K. G. Derpanis, “Mean shift clustering”, See accessed on 14 September 2016.
  11. 11.
    O. Tuzel, F. Porikli, P. Meer, “Kernel methods for weakly supervised mean shift clustering”, IEEE 12th International Conference on Computer Vision, pp. 48-55, 2009.Google Scholar
  12. 12.
    D. Comaniciu, “Variable bandwidth density-based fusion”, In Proc. IEEE Conf. on Comp. Vis. and Pat. Recog., Madison, WI, Vol. 1, pp. 56-66, 2003.Google Scholar
  13. 13.
    D. Comaniciu and P. Meer, “Mean shift: A robust approach toward feature space analysis”, IEEE Trans. Pat. Anal. Mach. Intell., 24:603-619, 2002.Google Scholar
  14. 14.
    M. Yamada, T. Oda, K. Matsuo, L. Barolli, “Design of an IoT-Based E-Learning Testbed”, The 9-th International Symposium on Mining and Web (MAW-2016), pp. 720-724, 2016.Google Scholar
  15. 15.
    “Raspberry Pi Foundation.”,
  16. 16.
    T. Oda, A. Barolli, S. Sakamoto, L. Barolli, M. Ikeda, K. Uchida, “Implementation and Experimental Results of a WMN Testbed in Indoor Environment Considering LoS Scenario”, The 29-th IEEE International Conference on Advanced Information Networking and Applications (AINA-2015), pp. 37-42, 2015.Google Scholar
  17. 17.
    “NeuroSky to Release MindWave mobile”,
  18. 18.
    W. Salabun, “Processing and spectral analysis of the raw EEG signal from the MindWave”, Przeglad Elektrotechniczny, Vol. 90, No. 2, pp. 169-174, February 2014.Google Scholar
  19. 19.
    K. Matsuo, L. Barolli, J. Arnedo-Moreno, F. Xhafa, A. Koyama, A. Durresi, “Experimental Results and Evaluation of SmartBox Stimulation Device in a P2P E-learning System”, Proc. of NBiS-2009, pp. 37-44, 2009.Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Masafumi Yamada
    • 1
  • Tetsuya Oda
    • 2
  • Yi Liu
    • 1
  • Keita Matsuo
    • 2
  • Leonard Barolli
    • 2
  1. 1.Graduate School of EngineeringFukuoka Institute of Technology (FIT)FukuokaJapan
  2. 2.Department of Information and Communication EngineeringFukuoka Institute of Technology (FIT)FukuokaJapan

Personalised recommendations