Skip to main content

Elbow angle generation during activities of daily living using a submovement prediction model


The present study aimed to develop a realistic model for the generation of human activities of daily living (ADL) movements. The angular profiles of the elbow joint during functional ADL tasks such as eating and drinking were generated by a submovement-based closed-loop model. First, the ADL movements recorded from three human participants were broken down into logical phases, and each phase was decomposed into submovement components. Three separate artificial neural networks were trained to learn the submovement parameters and were then incorporated into a closed-loop model with error correction ability. The model was able to predict angular trajectories of human ADL movements with target access rate = 100%, VAF = 98.9%, and NRMSE = 4.7% relative to the actual trajectories. In addition, the model can be used to provide the desired target for practical trajectory planning in rehabilitation systems such as functional electrical stimulation, robot therapy, brain-computer interface, and prosthetic devices.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8



Activities of daily living


Artificial neural network


Brain–computer interface


Correlation coefficient


Functional electrical stimulation


Normalized RMSE


Root mean square error


Standard deviation




Variance accounted for


  1. Ackery A, Tator C, Krassioukov A (2004) A global perspective on spinal cord injury epidemiology. J Neurotrauma 21(10):1355–1370.

    Article  PubMed  Google Scholar 

  2. Akhtar A, Hargrove LJ, Bretl T (2012) Prediction of distal arm joint angles from EMG and shoulder orientation for prosthesis control. In: 2012 Annual international conference of the IEEE engineering in medicine and biology society. IEEE, pp 4160–4163

  3. Akoglu H (2018) User’s guide to correlation coefficients. Turk J Emerg Med 18(3):91–93.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Ashegh Toosi M (2011) Synergy based anticipation of elbow joint angle using kinematic and EMG data of upper limb. Amirkabir University of Technology, Tehran

    Google Scholar 

  5. Chen LL, Lee D, Fukushima K, Fukushima J (2012) Submovement composition of head movement. PLoS ONE 7(11):4–7.

    CAS  Article  Google Scholar 

  6. Crago PE, Memberg WD, Usey MK, Keith MW, Kirsch RF, Chapman GJ et al (1998) An elbow extension neuroprosthesis for individuals with tetraplegia. IEEE Trans Rehabil Eng.

    Article  PubMed  Google Scholar 

  7. Dipietro L, Krebs HI, Fasoli SE, Volpe BT, Hogan N (2009) Submovement changes characterize generalization of motor recovery after stroke. Cortex 45(3):318–324.

    Article  PubMed  Google Scholar 

  8. Eraifej J, Clark W, France B, Desando S, Moore D (2017) Effectiveness of upper limb functional electrical stimulation after stroke for the improvement of activities of daily living and motor function: a systematic review and meta-analysis. Syst Rev 6(1):1–21.

    Article  Google Scholar 

  9. Farokhzadi M, Maleki A, Fallah A, Rashidi S (2017) Online estimation of elbow joint angle using upper arm acceleration: a movement partitioning approach. J Biomed Phys Eng 7(3):305–314

    CAS  PubMed  PubMed Central  Google Scholar 

  10. Fishbach A, Roy SA, Bastianen C, Miller LE, Houk JC (2005) Kinematic properties of on-line error corrections in the monkey. Exp Brain Res 164(4):442–457.

    Article  PubMed  Google Scholar 

  11. Fishbach A, Roy S, Bastianen C, Miller LE, Houk JC (2006) Deciding when and how to correct a movement: discrete submovements as a decision making process. Exp Brain Res 177(1):45–63.

    Article  PubMed  Google Scholar 

  12. Flash T, Hogan N (1985) The coordination of arm movements: an experimentally confirmed mathematical model. J Neurosci 5(7):1688–1703.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  13. Friedman J, Finkbeiner M (2010) Temporal dynamics of masked congruence priming: evidence from reaching trajectories. In: ASCS09: Proceedings of the 9th conference of the Australasian society for cognitive science. pp 98–105.

  14. Friedman J, Brown S, Finkbeiner M (2013) Linking cognitive and reaching trajectories via intermittent movement control. J Math Psychol 57(3–4):140–151.

    Article  Google Scholar 

  15. Frisoli A, Loconsole C, Bartalucci R, Bergamasco M (2013) A new bounded jerk on-line trajectory planning for mimicking human movements in robot-aided neurorehabilitation. Robot Auton Syst 61(4):404–415.

    Article  Google Scholar 

  16. Grafton ST, Tunik E (2011) Human basal ganglia and the dynamic control of force during on-line corrections. J Neurosci 31(5):1600–1605.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  17. Guidali M, Büchel M, Klamroth V, Nef T, Riener R (2009) Trajectory planning in ADL tasks for an exoskeletal arm rehabilitation robot. In: European conference on technically assisted rehabilitation (TAR). Deutsche Gesellschaft für Biomedizinische Technik, Berlin, pp 20–24.

  18. Henderson A, Korner-Bitensky N, Levin M (2007) Virtual reality in stroke rehabilitation: a systematic review of its effectiveness for upper limb motor recovery. Top Stroke Rehabil 14(2):52–61.

    Article  PubMed  Google Scholar 

  19. Hogan N, Sternad D (2013) Dynamic primitives in the control of locomotion. Front Comput Neurosci.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Iuppariello L (2015) Modelling and performance assessment of human reaching movements for disease classification. Università degli Studi di Napoli Federico II, Napoli

    Google Scholar 

  21. Krebs HI, Aisen ML, Volpe BT, Hogan N (1999) Quantization of continuous arm movements in humans with brain injury. Proc Natl Acad Sci USA 96(8):4645–4649.

    CAS  Article  PubMed  Google Scholar 

  22. Ku HH, Ryu JH, Bae HS, Jeong C, Lee SE (2019) Modeling a long-term effect of rice straw incorporation on SOC content and grain yield in rice field. Arch Agron Soil Sci 65(14):1941–1954.

    CAS  Article  Google Scholar 

  23. Liao JY, Kirsch RF (2014) Characterizing and predicting submovements during human three-dimensional arm reaches. PLoS ONE.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Liu MM, Herzog W, Savelberg HHCM (1999) Dynamic muscle force predictions from EMG: an artificial neural network approach. J Electromyogr Kinesiol 9(6):391–400.

    CAS  Article  PubMed  Google Scholar 

  25. Marchal-Crespo L, Reinkensmeyer DJ (2009) Review of control strategies for robotic movement training after neurologic injury. J Neuroeng Rehabil 6:20.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Meng Q, Shao H, Wang L, Yu H (2019) Task-based trajectory planning for an exoskeleton upper limb rehabilitation robot. In: International conference on man-machine-environment system engineering. Springer, Singapore, pp. 141–149.

  27. Murphy MA, Sunnerhagen KS, Johnels B, Willén C (2006) Three-dimensional kinematic motion analysis of a daily activity drinking from a glass: a pilot study. J Neuroeng Rehabil 3(1):18.

    Article  PubMed Central  Google Scholar 

  28. Naghibi SS, Maleki A, Fallah A, Ghassemi F (2017) A modified method of submovement decomposition based on velocity profile and endpoint position. In: 24th Iranian conference of biomedical engineering (ICBME). IEEE, Tehran, pp 1–4.

  29. Plamondon R, Alimi AM, Yergeau P, Leclerc F (1993) Modelling velocity profiles of rapid movements: a comparative study. Biol Cyber 69(2):119–128.

  30. Raghavan VS, Albrecht J, Irwin D (2011) Finding a “Kneedle” in a haystack: detecting knee points in system behavior. In: 31st International conference on distributed computing systems workshops. pp 166–171.

  31. Ramírez-García A, Leija L, Muñoz R (2010) Active upper limb prosthesis based on natural movement trajectories. Prosthet Orthot Int 34(1):58–72.

    Article  PubMed  Google Scholar 

  32. Rohrer BR (2002) Evolution of movement smoothness and submovement patterns in persons with stroke. Massachusetts Institute of Technology, Cambridge

    Google Scholar 

  33. Rohrer B, Hogan N (2006) Avoiding spurious submovement decompositions II: a scattershot algorithm. Biol Cybern 94(5):409–414.

    Article  PubMed  Google Scholar 

  34. Ruparel R, Johnson MJ (2008) A task-oriented, trajectory planner: could it train stroke survivors to move normally on ADLs? In: 2008 2nd IEEE RAS & EMBS International conference on biomedical robotics and biomechatronics. IEEE, pp 813–818.

  35. Sinclair J, John Taylor P, Jane Hobbs S (2013) Digital filtering of three-dimensional lower extremity kinematics: an assessment. J Hum Kinet 39(1):25–36.

    Article  PubMed  PubMed Central  Google Scholar 

  36. Triwiyanto T, Wahyunggoro O, Nugroho HA, Herianto H (2018) Estimation of elbow joint angle based on electromyography using the sign-slope change feature and Kalman filtering. IOP Conf Ser Mater Sci Eng 384(1):012014.

    Article  Google Scholar 

  37. WHO (2018) Stroke, cerebrovascular accident. Retrieved May 19, 2019 from

  38. Wisneski KJ, Johnson MJ (2007) Trajectory planning for functional wrist movements in an ADL-oriented, robot-assisted therapy environment. In: Proceedings 2007 IEEE international conference on robotics and automation. IEEE, pp 3365–3370.

  39. Woodworth RS (1899) The accuracy of voluntary movements. Psychol Rev 3:1–114

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Ali Fallah.

Additional information

Publisher's Note

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

Communicated by Peter J. Thomas.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Naghibi, S.S., Fallah, A., Maleki, A. et al. Elbow angle generation during activities of daily living using a submovement prediction model. Biol Cybern 114, 389–402 (2020).

Download citation


  • Submovement
  • Activities of daily living
  • Elbow angle
  • Closed-loop model
  • Artificial neural network
  • Movement generation