Advertisement

Limited-Memory Warping LCSS for Real-Time Low-Power Pattern Recognition in Wireless Nodes

  • Daniel Roggen
  • Luis Ponce Cuspinera
  • Guilherme Pombo
  • Falah Ali
  • Long-Van Nguyen-Dinh
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8965)

Abstract

We present and evaluate a microcontroller-optimized limited-memory implementation of a Warping Longest Common Subsequence algorithm (WarpingLCSS). It permits to spot patterns within noisy sensor data in real-time in resource constrained sensor nodes. It allows variability in the sensed system dynamics through warping; it uses only integer operations; it can be applied to various sensor modalities; and it is suitable for embedded training to recognize new patterns. We illustrate the method on 3 applications from wearable sensing and activity recognition using 3 sensor modalities: spotting the QRS complex in ECG, recognizing gestures in everyday life, and analyzing beach volleyball. We implemented the system on a low-power 8-bit AVR wireless node and a 32-bit ARM Cortex M4 microcontroller. Up to 67 or 140 10-second gestures can be recognized simultaneously in real-time from a 10Hz motion sensor on the AVR and M4 using 8mW and 10mW respectively. A single gesture spotter uses as few as 135μW on the AVR. The method allows low data rate distributed in-network recognition and we show a 100 fold data rate reduction in a complex activity recognition scenario. The versatility and low complexity of the method makes it well suited as a generic pattern recognition method and could be implemented as part of sensor front-ends.

Keywords

Activity Recognition Wearable Sensing Streaming pattern spotting Distributed Recognition Machine Learning Event Processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Avci, A., Bosch, S., Marin-Perianu, M., Marin-Perianu, R., Havinga, P.: Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey. In: Proc Int. Conf. on Architecture of Computing Systems, pp. 1–10 (2010)Google Scholar
  2. 2.
    Bahrepour, M., Meratnia, N., Havinga, P.: Sensor fusion-based event detection in wireless sensor networks. In: Mobile and Ubiquitous Systems, pp. 1–8 (2009)Google Scholar
  3. 3.
    Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  4. 4.
    Benatti, S., Farella, E., Benini, L.: EMG embedded HMI for smart garments. In: Atelier of Smart Garments and Accessories Workshop at Ubicomp (2014)Google Scholar
  5. 5.
    Buscà, B., Moras, G., Peña, J., Rodríguez-Jiménez, S.: The influence of serve characteristics on performance in men’s and women’s high-standard beach volleyball. Journal of Sports Sciences 30(3), 269–276 (2012)CrossRefGoogle Scholar
  6. 6.
    Pham, C., Plötz, T., Olivier, P.: A dynamic time warping approach to real-time activity recognition for food preparation. In: de Ruyter, B., Wichert, R., Keyson, D.V., Markopoulos, P., Streitz, N., Divitini, M., Georgantas, N., Mana Gomez, A. (eds.) AmI 2010. LNCS, vol. 6439, pp. 21–30. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S., Millán, J., Roggen, D., Tröster, G.: The opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recognition Letters 34, 2033–2042 (2013)CrossRefGoogle Scholar
  8. 8.
    Chen, Z., Ranieri, J., Zhang, R., Vetterli, M.: DASS: Distributed adaptive sparse sensing. arXiv:1401.1191 (1013)Google Scholar
  9. 9.
    Fortino, G., Guerrieri, A., Bellifemine, F.L., Giannantonio, R.: SPINE2: Developing BSN applications on heterogeneous sensor nodes. In: Proc. IEEE Symposium on Industrial Embedded Systems (2009)Google Scholar
  10. 10.
    Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Transactions on Biomedical Engineering 32(3) (1985)Google Scholar
  11. 11.
    Kale, N., Lee, J., Lotfian, R., Jafari, R.: Impact of sensor misplacement on dynamic time warping based human activity recognition using wearable computers. In: Proc Wireless Health (2012)Google Scholar
  12. 12.
    Kim, S., Pakzad, S., Culler, D., Demmel, J., Fenves, G., Glaser, S., Turon, M.: Health monitoring of civil infrastructures using wireless sensor networks. In: 6th Int. Symp. on Information Processing in Sensor Networks, pp. 254–263 (2007)Google Scholar
  13. 13.
    Kunze, K., Lukowicz, P.: Dealing with sensor displacement in motion-based onbody activity recognition systems. In: Proc. 10th Int. Conf. on Ubiquitous Computing (2008)Google Scholar
  14. 14.
    Marin-Perianu, M., Lombriser, C., Amft, O., Havinga, P., Tröster, G.: Distributed activity recognition with fuzzy-enabled wireless sensor networks. In: Nikoletseas, S.E., Chlebus, B.S., Johnson, D.B., Krishnamachari, B. (eds.) DCOSS 2008. LNCS, vol. 5067, pp. 296–313. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Nguyen-Dinh, L.V., Calatroni, A., Tröster, G.: Robust online gesture recognition with crowdsourced annotations. Journal of Machine Learning Research 15, 3187–3220 (2014)zbMATHGoogle Scholar
  16. 16.
    Nguyen-Dinh, L.V., Roggen, D., Calatroni, A., Tröster, G.: Improving online gesture recognition with template matching methods in accelerometer data. In: Proc 12th Int Conf. on Intelligent Systems Design and Applications, pp. 831–836 (2012)Google Scholar
  17. 17.
    Patel, S., Park, H., Bonato, P., Chan, L., Rodgers, M.: A review of wearable sensors and systems with application in rehabilitation. Journal of NeuroEngineering and Rehabilitation 9(21) (2012)Google Scholar
  18. 18.
    Rashidi, P., Cook, D.J.: The resident in the loop: Adapting the smart home to the user. IEEE Transactions on Systems, Man, and Cybernetics Journal, Part A 39(5), 949–959 (2009)CrossRefGoogle Scholar
  19. 19.
    Roggen, D., Bächlin, M., Schumm, J., Holleczek, T., Lombriser, C., Tröster, G., Widmer, L., Majoe, D., Gutknecht, J.: An educational and research kit for activity and context recognition from on-body sensors. In: Proc. IEEE Int. Conf. on Body Sensor Networks (BSN), pp. 277–282 (2010)Google Scholar
  20. 20.
    Sagha, H., Bayati, H., del R. Millán, J.: On-line anomaly detection and resilience in classifier ensembles. Pattern Recognition Letters 34(15), 1916–1927 (2013)CrossRefGoogle Scholar
  21. 21.
    Stäger, M., Lukowicz, P., Perera, N., von Büren, T., Tröster, G., Starner, T.: SoundButton: Design of a Low Power Wearable Audio Classification System. In: Proc of the 7th International Symposium on Wearable Computers, pp. 12–17. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  22. 22.
    Vlachos, M., Hadjieleftheriou, M., Gunopulos, D., Keogh, E.: Indexing multi-dimensional time-series with support for multiple distance measures. In: Proc 9th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp. 216–225. ACM, New York (2003)Google Scholar
  23. 23.
    Wark, T., Corke, P., Sikka, P., Klingbeil, L., Guo, Y., Crossman, C., Valencia, P., Swain, D., Bishop-Hurley, G.: Transforming agriculture through pervasive wireless sensor networks. IEEE Pervasive Computing Magazine 6(2), 50–57 (2007)CrossRefGoogle Scholar
  24. 24.
    Wei, B., Yang, M., Shen, Y., Rana, R., Chou, C.T., Hu, W.: Real-time classification via sparse representation in acoustic sensor networks. In: Proc 11th ACM Conf. on Embedded Networked Sensor Systems, vol. (21) (2013)Google Scholar
  25. 25.
    Yang, A.Y., Jafari, R., Sastry, S.S., Bajcsy, R.: Distributed recognition of human actions using wearable motion sensor networks. Journal of Ambient Intelligence and Smart Environments 1, 1–13 (2009)Google Scholar
  26. 26.
    Yick, J., Mukherjee, B., Ghosal, D.: Wireless sensor network survey. Computer Networks 52(12), 2292–2330 (2008)CrossRefGoogle Scholar
  27. 27.
    Zappi, P., Farella, E., Benini, L.: Hidden markov models implementation for tangible interfaces. In: Nijholt, A., Reidsma, D., Hondorp, H. (eds.) INTETAIN 2009. LNICST, vol. 9, pp. 258–263. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  28. 28.
    Zappi, P., Roggen, D., Farella, E., Tröster, G., Benini, L.: Network-level power-performance trade-off in wearable activity recognition: a dynamic sensor selection approach. ACM Transactions on Embedded Computing Systems 11(3) (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Daniel Roggen
    • 1
  • Luis Ponce Cuspinera
    • 1
  • Guilherme Pombo
    • 1
  • Falah Ali
    • 1
  • Long-Van Nguyen-Dinh
    • 2
  1. 1.Sensor Technology Research CentreUniversity of SussexUnited Kingdom
  2. 2.Wearable Computing LaboratoryETH ZurichSwitzerland

Personalised recommendations