Online human movement classification using wrist-worn wireless sensors

Abstract

The monitoring and analysis of human motion can provide valuable information for various applications. This work gives a comprehensive overview about existing methods, and a prototype system is also presented, capable of detecting different human arm and body movements using wrist-mounted wireless sensors. The wireless units are equipped with three tri-axial sensors, an accelerometer, a gyroscope, and a magnetometer. Data acquisition was done for multiple activities with the help of the used prototype system. A new online classification algorithm was developed, which enables easy implementation on the used hardware. To explore the optimal configuration, multiple datasets were tested using different feature extraction approaches, sampling frequencies, processing window widths, and used sensor combinations. The applied datasets were constructed using data collected with the help of multiple subjects. Results show that nearly 100% recognition rate can be achieved on training data, while almost 90% can be reached on validation data, which were not utilized during the training of the classifiers. This shows high correlation in the movements of different persons, since the training and validation datasets were constructed of data from different subjects.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. Aiello F, Bellifemine FL, Fortino G, Galzarano S, Gravina R (2011) An agent-based signal processing in-node environment for real-time human activity monitoring based on wireless body sensor networks. Eng Appl Artif Intell 24:1147–1161. doi: 10.1016/j.engappai.2011.06.007

    Article  Google Scholar 

  2. Alemdar H, Ersoy C (2010) Wireless sensor networks for healthcare: A survey. Comput Netw 54:2688–2710. doi: 10.1016/j.comnet.2010.05.003

    Article  Google Scholar 

  3. Altun K, Barshan B, Tuncel O (2010) Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recognit 43:3605–3620. doi: 10.1016/j.patcog.2010.04.019

    Article  MATH  Google Scholar 

  4. Attal F, Dedabrishvili M, Mohammed S, Chamroukhi F, Oukhellou L, Amirat Y (2015) Physical human activity recognition using wearable sensors. Sens 15:31314–31338. doi: 10.3390/s151229858

    Article  Google Scholar 

  5. Bao L, Intille S (2004) Activity recognition from user-annotated acceleration data. Lect Notes Comput Sci 3001:1–17. doi: 10.1007/978-3-540-24646-6_1

    Article  Google Scholar 

  6. Chernbumroong S, Cang S, Yu H (2014) A practical multi-sensor activity recognition system for home-based care. Decis Support Syst 66:61–70. doi: 10.1016/j.dss.2014.06.005

    Article  Google Scholar 

  7. Cohn G, Gupta S, Lee TJ, Morris D, Smith J, Reynolds M, Tan D, Patel S (2012) An ultra-low-power human body motion sensor using static electric field sensing. In: Proceedings of the ACM Conference on Ubiquitous Computing (UbiComp), pp 99–102

  8. Cornacchia M, Ozcan K, Zheng Y, Velipasalar S (2017) A survey on activity detection and classification using wearable sensors. IEEE Sens J 17:386–403. doi: 10.1109/JSEN.2016.2628346

    Article  Google Scholar 

  9. Field M, Stirling D, Pan Z, Ros M, Naghdy F (2015) Recognizing human motions through mixture modeling of inertial data. Pattern Recognit 48:2394–2406. doi: 10.1016/j.patcog.2015.03.004

    Article  Google Scholar 

  10. Fuentes D, Gonzalez-Abril L, Angulo C, Ortega JA (2012) Online motion recognition using an accelerometer in a mobile device. Expert Syst Appl 39:2461–2465. doi: 10.1016/j.eswa.2011.08.098

    Article  Google Scholar 

  11. Ghasemzadeh H, Ostadabbas S, Guenterberg E, Pantelopoulos A (2013) Wireless medical-embedded systems: A review of signal-processing techniques for classification. IEEE Sens J 13:423–437. doi: 10.1109/JSEN.2012.2222572

    Article  Google Scholar 

  12. Gonzalez S, Sedano J, Villar J, Corchado E, Herrero A, Baruque B (2015) Features and models for human activity recognition. Neurocomputing 167:52–60. 10.1016/j.neucom.2015.01.082

    Article  Google Scholar 

  13. Gravina R, Alinia P, Ghasemzadeh H, Fortino G (2017) Multi-sensor fusion in body sensor networks: State-of-the-art and research challenges. Inf Fusion 35:68–80. doi: 10.1016/j.inffus.2016.09.005

    Article  Google Scholar 

  14. Gu Q, Li Z, Han J (2011) Linear discriminant dimensionality reduction. Lect Notes Comput Sci 6911:549–564. doi: 10.1007/978-3-642-23780-5_45

    Article  Google Scholar 

  15. Guo Y, He W, Gao C (2012) Human activity recognition by fusing multiple sensor nodes in the wearable sensor systems. J Mech Med Biol. doi: 10.1142/S0219519412500844

    Google Scholar 

  16. Korpela J, Maekawa T, Eberle J, Chakraborty D, Aberer K (2016) Tree-structured classifier for acceleration-based activity and gesture recognition on smartwatches. In: IEEE International Conference on Pervasive Computing and Communications Workshops

  17. Lee Y-S, Cho S-B (2016) Layered hidden Markov models to recognize activity with built-in sensors on Android smartphone. Pattern Anal Applic 19:1181–1193. doi: 10.1007/s10044-016-0549-8

    MathSciNet  Article  Google Scholar 

  18. Lee MW, Khan AM, Kim TS (2011) A single tri-axial accelerometer-based real-time personal life log system capable of human activity recognition and exercise information generation. Pers Ubiquitous Comput 15:887–898. doi: 10.1007/s00779-011-0403-3

    Article  Google Scholar 

  19. Li C, Lin M, Yang L, Ding C (2014) Integrating the enriched feature with machine learning algorithms for human movement and fall detection. J Supercomput 67:854–865. doi: 10.1007/s11227-013-1056-y

    Article  Google Scholar 

  20. Maekawa T, Kishino Y, Sakurai Y, Suyama T (2013) Activity recognition with hand-worn magnetic sensors. Pers Ubiquitous Comput 17:1085–1094. doi: 10.1007/s00779-012-0556-8

    Article  Google Scholar 

  21. Martin H, Bernardos A, Iglesias J, Casar J (2013) Activity logging using lightweight classification techniques in mobile devices. Pers Ubiquitous Comput 17:675–695. doi: 10.1007/s00779-012-0515-4

    Article  Google Scholar 

  22. Martinez A, Kak A (2001) PCA versus LDA. IEEE Trans Pattern Anal Mach Intell 23:228–233. doi: 10.1109/34.908974

    Article  Google Scholar 

  23. Mitchell T (1997) Machine learning. McGraw-Hill, New York

    Google Scholar 

  24. Phinyomark A, Phukpattaranont P, Limsakul C (2012) Feature reduction and selection for EMG signal classification. Expert Syst Appl 39:7420–7431. doi: 10.1016/j.eswa.2012.01.102

    Article  Google Scholar 

  25. Preece S, Goulermas JY, Kenney L, Howard D (2009) A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans Biomed Eng 56:871–879. doi: 10.1109/TBME.2008.2006190

    Article  Google Scholar 

  26. Sarcevic P, Pletl S, Kincses Z (2014) Evolutionary algorithm based 9DOF sensor board calibration. In: IEEE International Symposium on Intelligent Systems and Informatics (SISY), pp 187–192

  27. Sarcevic P, Kincses Z, Pletl S (2015a) Comparison of different classifiers in movement recognition using WSN-based wrist-mounted sensors. IEEE Sensors Applications Symposium (SAS), pp 1–6

  28. Sarcevic P, Schaffer L, Kincses Z, Pletl S (2015b) Hierarchical-distributed approach to movement classification using wrist-mounted wireless inertial and magnetic sensors. Infocommunications J 7:33–41

    Google Scholar 

  29. Suarez I, Jahn A, Anderson C, David K (2015) Improved activity recognition by using enriched acceleration data. In: Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), pp 1011–1015

  30. Ugolotti R, Sassi F, Mordonini M, Cagnoni S (2013) Multi-sensor system for detection and classification of human activities. J Ambient Intell Human Comput 4:27–41. doi: 10.1007/s12652-011-0065-z

    Article  Google Scholar 

  31. Varkey JP, Pompili D, Walls T (2012) Human motion recognition using a wireless sensor-based wearable system. Pers Ubiquitous Comput 16:897–910. doi: 10.1007/s00779-011-0455-4

    Article  Google Scholar 

  32. Yang A, Jafari R, Sastry S, Bajcsy R (2009) Distributed recognition of human actions using wearable motion sensor networks. J Ambient Intell Smart Environ 1:103–115. doi: 10.3233/AIS-2009-0016

    Google Scholar 

  33. Zhu C, Sheng W (2011) Motion- and location-based online human daily activity recognition. Pervasive Mob Comput 7:256–269. doi: 10.1016/j.pmcj.2010.11.004

    Article  Google Scholar 

Download references

Acknowledgements

The publication is supported by the European Union and co-funded by the European Social Fund. Project title: “Telemedicine-focused research activities on the field of Mathematics, Informatics and Medical sciences” Project number: TÁMOP-4.2.2.A-11/1/KONV-2012-0073.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Peter Sarcevic.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sarcevic, P., Kincses, Z. & Pletl, S. Online human movement classification using wrist-worn wireless sensors. J Ambient Intell Human Comput 10, 89–106 (2019). https://doi.org/10.1007/s12652-017-0606-1

Download citation

Keywords

  • Activity recognition
  • Wearable sensors
  • Feature extraction
  • Time-domain analysis
  • Dimension reduction