Skip to main content
SpringerLink
Log in

Determining the most relevant frequency bands in motion identification by accelerometer sensors

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Sensors embedded in wearable technologies and smartphones provide a massive amount of data that has huge potential to be exploited in human motion identification/authentication systems. The accelerometer is one of the most common sensors that hold significant information about human actions. Acceleration signals show distinctive characteristics in time and frequency domains. In this study, public dataset consisting of eighteen diverse human activities is analyzed in wavelet subband space, and the resulting features are employed for classification by the Randomized Neural Network (RNN). The goal of this research is to determine the unique and dominant characteristics of each physical activity. This study proposes a methodology that combines RNN and wavelet-subband features to improve the achievement of human action recognition systems. The contribution resides in enlarging the application of human action recognition systems by employing robust classification and feature extraction techniques utilizing subband wavelet space, which has not been applied in the literature before, to the best of our knowledge. The results indicate to have a high potential to be exploited in applications of human-activity-based identification/authentication and remote health monitoring systems. The proposed method achieves an accuracy rate of over 95% for each movement by determining proper subbands of wavelet spaces.

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
Fig. 9

Similar content being viewed by others

References

  1. Abidi MH, Alkhalefah H, Moiduddin K, Alazab M, Mohammed MK, Ameen W, Gadekallu TR (2021) Optimal 5G network slicing using machine learning and deep learning concepts. Comput Stand Interfaces 76:103518

    Article  Google Scholar 

  2. Altun K, Barshan B, Tunçel O (2010) Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recogn 43(10):3605–3620

    Article  Google Scholar 

  3. Atallah L, Lo B, King R, Yang GZ (2010) Sensor placement for activity detection using wearable accelerometers. In 2010 International Conference on Body Sensor Networks. IEEE, pp 24-29

  4. Bayat A, Pomplun M, Tran DA (2014) A study on human activity recognition using accelerometer data from smartphones. Procedia Comput Sci 34:450–457

    Article  Google Scholar 

  5. Bidargaddi N, Klingbeil L, Sarela A, Boyle J, Cheung V, Yelland C, ... Gray L (2007) Wavelet based approach for posture transition estimation using a waist worn accelerometer. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp 1884-1887. https://doi.org/10.1109/IEMBS.2007.4352683

  6. Bouchrika I (2018) A survey of using biometrics for smart visual surveillance: Gait recognition. Surveillance in Action. Springer, Cham, pp 3–23

    Chapter  Google Scholar 

  7. Brajdic A, Harle R (2013), September Walk detection and step counting on unconstrained smartphones. In: Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing. ACM, pp 225-234

  8. Cuppens K, Karsmakers P, Van de Vel A, Bonroy B, Milosevic M, Luca S, Vanrumste B (2013) Accelerometry-based home monitoring for detection of nocturnal hyper motor seizures based on novelty detection. IEEE J Biomed Health Inform 18(3):1026–1033

    Article  Google Scholar 

  9. Dargie W (2009) Analysis of time and frequency domain features of accelerometer measurements. In 2009 Proceedings of 18th International Conference on Computer Communications and Networks. IEEE, pp 1-6

  10. Dua D, Graff C (2019) UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine. http://archive.ics.uci.edu/ml 07 January, 2021.

  11. Ejupi A, Brodie M, Lord SR, Annegarn J, Redmond SJ, Delbaere K (2016) Wavelet-based sit-to-stand detection and assessment of fall risk in older people using a wearable pendant device. IEEE Trans Biomed Eng 64(7):1602–1607. https://doi.org/10.1109/TBME.2016.2614230

    Article  Google Scholar 

  12. Ertuğrul ÖF, Tağluk ME (2017) A fast feature selection approach based on extreme learning machine and coefficient of variation. Turk J Electr Eng Comput Sci 25(4):3409–3342

    Article  Google Scholar 

  13. Heng X, Wang Z, Wang J (2016) Human activity recognition based on transformed accelerometer data from a mobile phone. Int J Commun Syst 29(13):1981–1991

    Article  Google Scholar 

  14. Hoang T, Nguyen TD, Luong C, Do S, Choi D (2013) Adaptive cross-device gait recognition using a mobile accelerometer. JIPS 9(2):333

    Google Scholar 

  15. Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70 (1–3):489-501

  16. Huang GB, Zhu QY, Siew CK. Extreme learning machine: a new learning scheme of feedforward neural networks. In: IEEE 2004 Neural Networks Conference; 25–29 July 2004; Budapest, Hungary. New York, NY, USA: IEEE, pp 985-990

  17. Jain AK, Bolle R, Pankanti S (eds) (2006) Biometrics: personal identification in networked society, vol 479. Springer Science & Business Media, Berlin

  18. Kang X, Huang B, Qi G (2018) A novel walking detection and step counting algorithm using unconstrained smartphones. Sensors 18(1):297

    Article  Google Scholar 

  19. Khan AM, Lee YK, Lee SY, Kim TS (2010) Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. In 2010 5th international conference on future information technology. IEEE, pp 1-6

  20. Klassen TD, Simpson LA, Lim SB, Louie DR, Parappilly B, Sakakibara BM, Eng JJ (2016) “Stepping up” activity poststroke: ankle-positioned accelerometer can accurately record steps during slow walking. Phys Ther 96(3):355–360

    Article  Google Scholar 

  21. Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SIGKDD Explor Newsl 12(2):74–82

    Article  Google Scholar 

  22. Li M, Wang D (2017) Insights into randomized algorithms for neural networks: practical issues and common pitfalls. Inf Sci 382–383:170–178

  23. Luca S, Karsmakers P, Cuppens K, Croonenborghs T, Van de Vel A, Ceulemans B, Vanrumste B (2014) Detecting rare events using extreme value statistics applied to epileptic convulsions in children. Artif Intell Med 60(2):89–96

    Article  Google Scholar 

  24. Majala J (2017) Frequency analysis of accelerometer measurements on trains. Retrieved December 24, 2019, from Luleå Tekniska Universitet database

  25. Malekzadeh M, Clegg RG, Cavallaro A, Haddadi H (2018) Protecting sensory data against sensitive inferences. In: Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems, pp 1-6

  26. Morales J, Akopian D (2017) Physical activity recognition by smartphones, a survey. Biocybern Biomed Eng 37(3):388–400

    Article  Google Scholar 

  27. Nyan MN, Tay FEH, Seah KHW, Sitoh YY (2006) Classification of gait patterns in the time–frequency domain. J Biomech 39(14):2647–2656

    Article  Google Scholar 

  28. Ponce H, Miralles-Pechuán L, Martínez-Villaseñor M (2016) A flexible approach for human activity recognition using artificial hydrocarbon networks. Sensors 16(11):1715

    Article  Google Scholar 

  29. Ramchandran K, Vetterli M, Herley C (1996) Wavelets, sub-band coding, and best bases. Proc IEEE 84(4):541-560

  30. Ravi N, Dandekar N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data. In Aaai, vol 5, no 2005, pp 1541-1546

  31. Rogers MJ, Hrovat K, McPherson K, Moskowitz ME, Reckart T (1997) Accelerometer data analysis and presentation techniques (technical report ID 19970034695). Retrieved December 8, 2019, from NASA database

  32. Sekine M, Tamura T, Akay M, Fujimoto T, Togawa T, Fukui Y (2002) Discrimination of walking patterns using wavelet-based fractal analysis. IEEE Trans Neural Syst Rehabil Eng 10(3):188–196

    Article  Google Scholar 

  33. Su X, Tong H, Ji P (2014) Activity recognition with smartphone sensors. Tsinghua Sci Technol 19(3):235–249

    Article  Google Scholar 

  34. Tang J, Deng C, Huang GB (2015) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst 27(4):809–821

    Article  MathSciNet  Google Scholar 

  35. Tapia EM, Intille SS, Haskell W, Larson K, Wright J, King A, Friedman R (2007) Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. In: 2007 11th IEEE international symposium on wearable computers. IEEE, pp 37-40

  36. Walse KH, Dharaskar RV, Thakare VM (2016) A study of human activity recognition using AdaBoost classifiers on WISDM dataset. Inst Integr Omics Appl Biotechnol J 7(2):68–76

    Google Scholar 

  37. Wang L, Hu W, Tan T (2003) Recent developments in human motion analysis. Pattern Recogn 36(3):585–601

    Article  Google Scholar 

  38. Wang A, Chen G, Yang J, Zhao S, Chang CY (2016) A comparative study on human activity recognition using inertial sensors in a smartphone. IEEE Sens J 16(11):4566–4578

    Article  Google Scholar 

  39. Weiss GM, Yoneda K, Hayajneh T (2019) Smartphone and smartwatch-based biometrics using activities of daily living. IEEE Access 7:133190–133202

    Article  Google Scholar 

  40. Yoneda K, Weiss GM (2017) Mobile sensor-based biometrics using common daily activities. In 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON). IEEE, pp 584-590

  41. Zhang L, Suganthan PN (2016) A comprehensive evaluation of random vector functional link networks. Inf Sci 367–368:1094–1105

  42. Zhou H, Hu H (2008) Human motion tracking for rehabilitation—A survey. Biomed Signal Process Control 3(1):1–18

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Electronics Engineering, Batman University, Batman, 72000, Turkey

    Abdulkerim Öztekin, Ömer Faruk Ertuğrul, Erdoğan Aldemir & Emrullah Acar

Authors
  1. Abdulkerim Öztekin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ömer Faruk Ertuğrul
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Erdoğan Aldemir
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Emrullah Acar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abdulkerim Öztekin.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Öztekin, A., Ertuğrul, Ö.F., Aldemir, E. et al. Determining the most relevant frequency bands in motion identification by accelerometer sensors. Multimed Tools Appl 81, 11639–11663 (2022). https://doi.org/10.1007/s11042-022-12099-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12099-5

Keywords

Search

Navigation