Workout Type Recognition and Repetition Counting with CNNs from 3D Acceleration Sensed on the Chest

  • Kacper Skawinski
  • Ferran Montraveta Roca
  • Rainhard Dieter FindlingEmail author
  • Stephan Sigg
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11506)


Sports and workout activities have become important parts of modern life. Nowadays, many people track characteristics about their sport activities with their mobile devices, which feature inertial measurement unit (IMU) sensors. In this paper we present a methodology to detect and recognize workout, as well as to count repetitions done in a recognized type of workout, from a single 3D accelerometer worn at the chest. We consider four different types of workout (pushups, situps, squats and jumping jacks). Our technical approach to workout type recognition and repetition counting is based on machine learning with a convolutional neural network. Our evaluation utilizes data of 10 subjects, which wear a Movesense sensors on their chest during their workout. We thereby find that workouts are recognized correctly on average 89.9% of the time, and the workout repetition counting yields an average detection accuracy of 97.9% over all types of workout.


Acceleration Activity recognition CNN Deep learning Movesense Neural Networks Workout Sensors 


  1. 1. Human body figure (2019).
  2. 2.
    Attal, F., Mohammed, S., Dedabrishvili, M., Chamroukhi, F., Oukhellou, L., Amirat, Y.: Physical human activity recognition using wearable sensors. MDPI Sens. 15, 31314–31338 (2015)CrossRefGoogle Scholar
  3. 3.
    Bayat, A., Pomplun, M., Tran, D.A.: A study on human activity recognition using accelerometer data from smartphone. In: The 11th International Conference on Mobile Systems and Pervasive Computing, pp. 1–8 (2014)CrossRefGoogle Scholar
  4. 4.
    Bergman, C., Oksanen, J.: Conflation of openstreetmap and mobile sports tracking data for automatic bicycle routing. Trans. GIS 20(6), 848–868 (2016)CrossRefGoogle Scholar
  5. 5.
    Crema, C., Depari, A., Flammini, A., Sisinni, E., Haslwanter, T., Salzmann, S.: IMU-based solution for automatic detection and classification of exercises in the fitness scenario. In: 2017 IEEE Sensors Applications Symposium (SAS), pp. 1–6, March 2017.
  6. 6.
    Jahangiri, A., Rakha, H.A.: Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. Strat. Manag. J. 16(5), 2406–2417 (2015)Google Scholar
  7. 7.
    Javed, T., Awan, M.A., Hussain, T.: Recognition of arm & elbow exercises using smartphone’s accelerometer. NFC-IEFR J. Eng. Sci. Res. 5, 1–6 (2017)Google Scholar
  8. 8.
    Liang, X., Wang, G.: A convolutional neural network for transportation mode detection based on smartphone platform. Strat. Manag. J. 18(7), 338–342 (2017)Google Scholar
  9. 9.
    Manzoni, V., et al.: Transportation mode identification and real-time CO2 emission estimation using smartphones. Technical report, Massachusetts Inst. Technol., Cambridge, MA, USA (2010)Google Scholar
  10. 10.
    Morris, D., Saponas, T.S., Guillory, A., Kelner, I.: RecoFit: using a wearable sensor to find, recognize, and count repetitive exercises. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 3225–3234. ACM (2014)Google Scholar
  11. 11.
    Movesense: Movesense sensor description (2019).
  12. 12.
    Patel, S., Park, H., Bonato, P., Chan, L., Rodgers, M.: A review of wearable sensors and systems with application in rehabilitation. JNER 9, 21 (2012)CrossRefGoogle Scholar
  13. 13.
    Weka: Waikato environment for knowledge engineering. New Zealand Computer Science Research Students Conference, University of Waikato, Hamilton, New Zealand, pp. 57–64 (1995)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Communications and NetworkingAalto UniversityEspooFinland

Personalised recommendations