Skip to main content
SpringerLink
Log in

A Class Incremental Extreme Learning Machine for Activity Recognition

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Automatic activity recognition is an important problem in cognitive systems. Mobile phone-based activity recognition is an attractive research topic because it is unobtrusive. There are many activity recognition models that can infer a user’s activity from sensor data. However, most of them lack class incremental learning abilities. That is, the trained models can only recognize activities that were included in the training phase, and new activities cannot be added in a follow-up phase. We propose a class incremental extreme learning machine (CIELM). It (1) builds an activity recognition model from labeled samples using an extreme learning machine algorithm without iterations; (2) adds new output nodes that correspond to new activities; and (3) only requires labeled samples of new activities and not previously used training data. We have tested the method using activity data. Our results demonstrated that the CIELM algorithm is stable and can achieve a similar recognition accuracy to the batch learning method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. UCI Machine Learning Repository, http://archive.ics.uci.edu/ml/.

  2. Source codes and some references for ELM can be found at www.ntu.edu.sg/home/egbhuang.

References

  1. Taylor JG. Cognitive computation. Cogn Comput. 2009;1(1):4–16.

    Article  Google Scholar 

  2. Cambria E, Hussain A. Sentic computing: techniques, tools, and applications. Springerbriefs in cognitive computation. Dordrecht: springer; 2012.

    Book  Google Scholar 

  3. Wöllmer M, Eyben F, Graves A, Schuller B, Rigoll G. Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework. Cogn Comput. 2010;2(3):180–90.

    Article  Google Scholar 

  4. Mital P, Smith T, Hill R, Henderson J. Clustering of gaze during dynamic scene viewing is predicted by motion. Cogn Comput. 2011;3(1):5–24.

    Article  Google Scholar 

  5. Wang QF, Cambria E, Liu CL, Hussain A. Common sense knowledge for handwritten Chinese recognition. Cogn Comput. 2013;5(2):234–42.

    Article  Google Scholar 

  6. Roggen D, Magnenat S, Waibel M, Troster G. Designing and sharing activity-recognition systems across platforms. IEEE Robot Autom Mag. 2011;18:83–95.

    Google Scholar 

  7. Chen YQ, Chen ZY, Liu JF, Hu Derek H, Yang Q. Surrounding context and episode awareness using dynamic Bluetooth data. Pittsburgh, PA: UbiComp; 2012. p. 629–630.

  8. Chen ZY, Chen YQ, Wang SQ, Liu JF, Gao XY, Campbell AT. Inferring social contextual behavior from Bluetooth traces. Zurich, Switzerland: UbiComp; 2013. p. 267–270.

  9. Brajdic A, Harle R. Walk detection and step counting on unconstrained smartphones. In: UbiComp’1; 2013. p. 225–234.

  10. Chen ZY, Lin M, Chen FL, Lane ND, Cardone G, Wang R, Li TX, Chen YQ, Choudhury T, Campbell AT. Unobtrusive sleep monitoring using smartphones. In: PervasiveHealth’ 2013, p. 145–152.

  11. Lane ND, Xu Y, Lu H, Hu SH, Choudhury T, Campbell AT. Enabling large-scale human activity inference on smartphones using community similarity. Networks (CSN). UbiComp; 2011, p. 355–364.

  12. Lane ND, Xu Y, Lu H, Eisenmany SB, Choudhury T, Campbell AT. Cooperative communities (CoCo): exploiting social networks for large-scale modeling of human behavior. IEEE Pervasive Mag. 2011;10(4):45–53.

    Article  Google Scholar 

  13. Chen S, Lach J, Amft O, Altini M, Penders J. Unsupervised activity clustering to estimate energy expenditure with a single body sensor. In: BSN’13; 2013.

  14. Stanford V. Wearable computing goes live in industry. IEEE Pervasive Comput Mag. 2002;1(4):14–9.

    Article  Google Scholar 

  15. Nachman L, Baxi A, Bhattacharya S, Darera V, Deshpande P, Kodalapura N, Mageshkumar V, Rath S, Shahabdeen J, Acharya R. Jog falls: a pervasive healthcare platform for diabetes management. In: Proceedings of the pervasive; 2010. p. 94–111.

  16. Ravi N, Dandekar N, Mysore P, Littman ML. Activity recognition from accelerometer data. In: Proceedings of AAAI, 2005. pp. 1541–1546.

  17. Ward Jamie A, Lukowicz Paul, Gellersen Hans W. Performance metrics for activity recognition. ACM Trans Intell Syst Technol 2011;2(1). doi:10.1145/1889681.1889687.

  18. Chen YQ, Qi J, Sun Z, Ning Q. Mining user goals for indoor location based services with low energy and high qos. Comput Intell. 2010;26(3):318–36.

    Article  Google Scholar 

  19. Chen YQ, Zhao ZT, Wang SQ, Chen ZY. Extreme learning machine based device displacement free activity recognition model. Soft Comput. 2012;16(9):1617–25.

    Article  Google Scholar 

  20. Zhao ZT, Chen YQ, Liu JF, Shen ZQ, Liu MJ. Cross-people mobile-phone based activity recognition. In: Proceedings of the international joint conference on artificial intelligence(IJCAI2011); 2011. Barcelona, Spain, July 16–22.

  21. Huang GB, Saratchandran P, Sundararajan N. An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks. IEEE Trans Syst Man Cybern B Cybern. 2004;34(6):2284–92.

    Article  PubMed  Google Scholar 

  22. Carpenter GA, Grossberg S, Rosen D. Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw. 1991;4:759–71.

    Article  Google Scholar 

  23. Platt J. A resource-allocating network for function interpolation. Neural Comput. 1991;3:213–25.

    Article  Google Scholar 

  24. Liang NY, Huang GB, Saratchandran P, Sundararajan N. A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw. 2006;17:1411–23.

    Article  PubMed  Google Scholar 

  25. Bao L, Intille S. Activity recognition from user annotated acceleration data. In: Proceedings of the 2nd international conference on pervasive computing; 2004. pp. 1–17.

  26. Figo D, Diniz PC, Ferreira DR, Cardoso JMP. Preprocessing techniques for context recognition from accelerometer data. Pers Ubiquit Comput. 2010;14:645–62.

    Article  Google Scholar 

  27. Chen ZY, Zhao ZT, Wang SQ, Shen ZQ, Chen YQ. Online sequential ELM based transfer learning for transportation mode recognition. In: The 6th IEEE international conference on cybernetics and intelligent systems (CIS 2013); 2013. Manila, Philippines.

Download references

Acknowledgments

This work was supported in part by the Natural Science Foundation of China (61070110, 90820303), Beijing Natural Science Foundation (4112056, 4144085), Open Project of Beijing Key Laboratory of Mobile Computing and Pervasive Device, National Science and Technology Major Project (2012ZX07205-005), and Scientific and Technological Project of He’nan Province (No. 132102310258).

Author information

Authors and Affiliations

  1. Zhengzhou Institute of Aeronautical Industry Management, Zhengzhou, 450015, China

    Zhongtang Zhao

  2. Pervasive Computing Center, Institute of Computing Technology, CAS, Beijing, 100190, China

    Zhongtang Zhao, Zhenyu Chen, Yiqiang Chen & Shuangquan Wang

  3. Institute of Software, CAS, Beijing, 100190, China

    Hongan Wang

Authors
  1. Zhongtang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhenyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yiqiang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuangquan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hongan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhongtang Zhao.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhao, Z., Chen, Z., Chen, Y. et al. A Class Incremental Extreme Learning Machine for Activity Recognition. Cogn Comput 6, 423–431 (2014). https://doi.org/10.1007/s12559-014-9259-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-014-9259-y

Keywords

Search

Navigation