Identification of the elbow motion kinematic parameters by means of artificial neural networks technology

The research objective is to study elbow flexion kinematic parameters using the artificial neural networks (ANN). Parameters of the surface electromyogram (sEMG) are used as ANN inputs. The ANN output is kinematic parameters of motion: direction, angular displacement, and angular velocity. The study has involved DSTU students and staff (11 people without pathologies of the musculoskeletal system). The sEMG signals taken from the biceps of each trial subject during no-load elbow bending are registered. During the experiment, shoulder and elbow joints are fixed by the passive exoskeleton. The feature vector for the neural network is formed using methods of the spectral and statistical analysis. The statistical analysis in the time domain includes the determination of the following parameters: dispersion of sEMG amplitude values, arithmetic mean value and mean-square value of sEMG absolute amplitudes, sEMG signal zero crossing rates. In the frequency domain, sEMG signal spectral analysis is performed by Fast Fourier Transform method. The power spectrum and the mean frequency of the power spectrum are determined. Best results of determining the kinematic parameters are obtained when using the mean frequency of the power spectrum and the total integrated sEMG signal power as inputs to the ANN. The ANN is trained by the method of the direct signal propagation and the back propagation of error. The results obtained can be used in the development of the bioelectric control systems for the mechatronic devices.

пассивный экзоскелет, параметры движения локтя, электромиографический сигнал, статистический анализ, спектральный анализ, искусственная нейронная сеть, Matlab, Simulink, passive exoskeleton, elbow motion parameters, electromyographic signal, statistical analysis, spectral analysis, artificial neural network, Matlab, Simulink

1. Safin, D., et al. Sovremennye sistemy upravleniya protezami. Konstruktsii elektrodov i usiliteley biosignalov. [Modern Prosthetic Devices Control Systems. Electrodes and Biosignals Amplifiers Structure.] Electronics: Science, Technology, Business. 2009, no. 4. Available at: http://www.electronics.ru/journal/article/219 (accessed: 26.11.14) (in Russian).

2. Chrapka, Ph. EMG Controlled Hand Prosthesis: EMG Classification System. Electrical and Biomedical Engineering Design Project (4BI6). Department of Electrical and Computer Engineering. Available at: http://digitalcommons.mcmaster.ca/cgi/viewcontent.cgi?article=1034&context=ee4bi6 (accessed: 26.11.14).

3. Khokhar, Z.-O., Xiao, Z.-G., Menon, C. Surface EMG pattern recognition for real-time control of a wrist exoskeleton. Biomedical Engineering Online. Available at: http://www.biomedical-engineering-online.com/content/9/1/41 (accessed: 26.11.14).

4. Shenoy, P., et al. Online Electromyographic Control of a Robotic Prosthesis. Transactions on biomedical engineering, 2008, vol. 55, no. 3, pp. 1128–1135. Available at: http://homes.cs.washington.edu/~rao/emg-08.pdf (accessed: 26.11.14).

5. Heloyse, U.-K., et al. The Relationship between Electromyography and Muscle Force. Available at: http://cdn.intechopen.com/pdfs-wm/25852.pdf (accessed: 26.11.14).

6. Rangayan, R.M. Analiz biomeditsinskikh signalov. Prakticheskiy podkhod. [Analysis of biomedical signals. Practical approach.] Moscow: Fizmatlit, 2007, 440 p. (in Russian).

7. De Luca, C.-J. The use of surface electromyography in biomechanics. Journal of Applied Biomechanics, 1997, no. 13 (2), pp. 135–163.

8. Uchiyama, T., Bessho, T., Akazawa, K. Static torque-angle relation of human elbow joint estimated with artificial neural network technique. Journal of Biomechanics, 1998, no. 31, pp. 545–554.

9. Tugengold, A.K., et al. Itogi i perspektivy razvitiya issledovaniy v oblasti intellektual'nogo upravleniya mekhatronnymi tekhnologicheskimi sistemami. [Mechatronics technological systems intellectual management prospects and results.] Vestnik of DSTU, 2010, no. 5, pp. 48–67 (in Russian).

10. Bonilla, F., et al. Analiz signala EMG dvuglavoy myshtsy plecha v srede LabVIEW. [Analysis of the EMG signal of the biceps with LabVIEW.] Innovatsii, ekologiya i resursosberegayushchie tekhnologii (INERT-2014) : tr. XI mezhdunar. nauch.-tekhn. foruma. [Innovation, ecology and energy saving technologies (INERT-2014): Proc. XI Int. Sci.-Tech. Forum.] Rostov-on-Don, 2014, pp. 1394–1401 (in Russian).

11. Bonilla, F., et al. Vliyanie kinematicheskikh parametrov dvizheniya loktya na elektromiograficheskiy signal dvuglavoy myshtsy plecha. [Effect of kinematic parameters of elbow motion on biceps electromyographic signal.] Vestnik of DSTU, 2014, no. 4, pp. 48–67 (in Russian).

12. Arango, J.-C.-A., Nieto, D.-C., Giraldo, J.-C. Abordaje físico-matemático del gesto articular. EFDeportes.com.2012, no. 171. Available at http://www.efdeportes.com/efd171/abordaje-fisico-matematico-del-gesto-articular.htm (accessed: 02.12.14).

13. Konrad, P. The ABC of EMG. A Practical Introduction to Kinesiological Electromyography. Version 1.4, March 2006. Noraxon INC. Available at https://hermanwallace.com/download/The_ABC_of_EMG_by_Peter_Konrad.pdf (accessed: 02.12.14).

14. Tkach, D., Huang, H., Kuiken, T.-A. Study of stability of time-domain features for electromyographic pattern recognition. Journal of Neuroengineering and Rehabilitation, 2010, no. 7, p. 21. Available at: http://www.jneuroengrehab.com/content/7/1/21/ (accessed: 26.11.14).