An Evaluation of User Movement Data

  • Janelle Mason
  • Christopher Kelley
  • Bisoye Olaleye
  • Albert Esterline
  • Kaushik Roy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10868)


In this paper, an empirical evaluation of different classification techniques is conducted on user movement data. The datasets used here for experiments are composed of accelerometer data collected from various devices, including smartphones and smart watches. The user movement data was processed and fed into five traditional machine learning algorithms. The classification performances were then compared with a deep learning technique, the Long Short Term Memory-Recurrent Neural Network (LSTM-RNN). LSTM-RNN achieved its highest accuracy at 89% as opposed to 97% from a traditional machine learning algorithm, specifically, K-Nearest Neighbors (k-NN), on wrist-worn accelerometer data.


User movement Behavioral biometrics Deep learning Long short term memory-recurrent neural network Accelerometer data 


  1. 1.
    Mahfouz, A., Mahmoud, T., Eldin, A.: A survey on behavioral biometric authentication on smartphones. J. Inf. Secur. Appl. 37, 28–37 (2017). Scholar
  2. 2.
    Poushter, J.: Smartphone ownership and internet usage continues to climb in emerging economies. In: Pew Research Center Global Attitudes & Trends (2016). Accessed 29 Sept 2016
  3. 3.
    Arias, B.A.: An analysis of user movement classification. Master’s project. North Carolina Agricultural & Technical State University (2016)Google Scholar
  4. 4.
    Lichman, M.: UCI machine learning repository activity recognition from single chest-mounted accelerometer dataset. Accessed 30 Nov 2017
  5. 5.
    Bruno B., Mastrogiovanni, F., Sgorbissa, A., Vernazza, T., Zaccaria, R.: Human motion modelling and recognition: a computational approach. In: 2012 IEEE International Conference Automation Science and Engineering (CASE), 20 August 2012Google Scholar
  6. 6.
    Katz, S., Chinn, A., Cordrey, L.J., et al.: Multidisciplinary studies of illness in aged persons: a new classification of functional status in activities of daily living. J. Chronic Dis. 9(1), 55–62 (1959). Scholar
  7. 7.
    Lichman, M.: UCI machine learning repository dataset for ADL recognition with Wrist-worn Accelerometer Data Set (2013). Accessed 26 Nov 2017
  8. 8.
    Lichman, M.: UCI machine learning repository smartphone-based recognition of human activities and postural transitions data set (2013). Accessed 25 Nov 2017
  9. 9.
    Lichman, M.: UCI machine learning repository localization data for person activity data set (2013). Accessed 25 Nov 2017
  10. 10.
    Hallström, E.: Using the LSTM API in TensorFlow (3/7) (2016). Accessed 29 Nov 2017
  11. 11.
    Reyes-Ortiz, J.L., Ghio, A., Anguita, D., Parra, X., Cabestany, J., Catalá, A.: Human activity and motion disorder recognition: towards smarter interactive cognitive environments. Paper presented at the 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 24–26 April 2013 (2013)Google Scholar
  12. 12.
    Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In: Bravo, J., Hervás, R., Rodríguez, M. (eds.) IWAAL 2012. LNCS, vol. 7657, pp. 216–223. Springer, Heidelberg (2012). Scholar
  13. 13.
    Google (n.d.): TensorFlow. Accessed 25 Nov 2017

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Janelle Mason
    • 1
  • Christopher Kelley
    • 1
  • Bisoye Olaleye
    • 1
  • Albert Esterline
    • 1
  • Kaushik Roy
    • 1
  1. 1.North Carolina Agricultural and Technical State UniversityGreensboroUSA

Personalised recommendations