Advertisement

Neural Computing and Applications

, Volume 28, Supplement 1, pp 65–77 | Cite as

Neural computing for walking gait pattern identification based on multi-sensor data fusion of lower limb muscles

  • Joko Triloka
  • S. M. N. Arosha SenanayakeEmail author
  • Daphne Lai
Original Article

Abstract

The use of neural computing for gait analysis widely known as computational intelligent gait analysis is addressed recently. This research work reports multilayer feed-forward neural networks for walking gait pattern identification using multi-sensor data fusion; electromyography (EMG) signals and soft tissue deformation analysis using successive frames of video sequence extracted from lower limb muscles according to each gait phase within the considered gait cycle. Neural computing framework for walking gait pattern identification consists of system hardware and intelligent system software. System hardware comprises a wireless surface EMG sensor unit and two video cameras for measuring the neuromuscular activity of lower limb muscles, and a custom-developed artificial neural network for classifying the gait patterns of subjects during walking. The system uses root mean square and soft tissue deformation parameter as the input features. Multilayer feed-forward back propagation neural networks (FFBPNNs) with different network training functions were designed, and their classification results were compared. The intelligent gait analysis system validation has been carried out for a group of healthy and injured subjects. The results demonstrated that the overall accuracy of 98 % prediction is achieved for gait patterns classification established by multi-sensor data fusion of lower limb muscles using FFBPNN with Levenberg–Marquardt training function resulting better performance over FFBPNN with other training functions.

Keywords

Electromyography Soft tissue deformation Gait patterns Multi-sensor data fusion 

Notes

Acknowledgments

The authors appreciate the suggestions provided by Owais A. Malik as well as his assistance in electromyography experiment of this work.

References

  1. 1.
    Yun J, Woo W, Ryu J (2005) User identification using user’s walking pattern over the ubiFloorII. Comput Intell Secur 3801:949–956CrossRefGoogle Scholar
  2. 2.
    Trevino R, Frye M, Chunjiang Q (2009) Development of a full body balance model using an artificial neural network approach. In: IEEE international conference on systems, man and cybernetics, 2009, SMC 2009. pp 4238–4242Google Scholar
  3. 3.
    Arosha Senanayake SMN, Triloka J, Malik OA, Iskandar M (2014) Artificial neural network based gait patterns identification using neuromuscular signals and soft tissue deformation analysis of lower limbs muscles. In: 2014 international joint conference on neural networks (IJCNN), 2014, pp 3503–3510Google Scholar
  4. 4.
    Christ P, Werner F, Rückert U, Mielebacher J (2013) Athlete identification using acceleration and electrocardiographic measurements recorded with a wireless body sensor. In: Alvarez S, Solé-Casals J, Fred A, Gamboa H (eds) Proceedings of the 6th international conference on bio-inspired systems and signal processing. International joint conference on biomedical engineering systems and technologies. SciTePress, pp 11–19Google Scholar
  5. 5.
    Ming Z, Nguyen LT, Yu B, Mengshoel OJ, Zhu J, Wu P, Zhang J (2014) Convolutional neural networks for human activity recognition using mobile sensors. In: MOBICASE, 2014, 2014 6th international conference on mobile computing, applications and services (MobiCASE) 2014, pp 197–205Google Scholar
  6. 6.
    Fridlund AJ, Cacioppo JT (1986) Guidelines for human electromyographic research. Psychophysiology 23(5):567–589CrossRefGoogle Scholar
  7. 7.
    Fukuda TY, Echeimberg JO, Pompeu JE, Lucareli PRG, Garbelotti S, Gimenes RO, Apolinario A (2010) Root mean square value of the electromyographic signal in the isometric torque of the quadriceps, hamstrings and brachial biceps muscles in female subjects. J Appl Res 10:32–39Google Scholar
  8. 8.
    Onishi H, Yagi R, Akasaka K, Momose K, Ihashi K, Handa Y (2000) Relationship between EMG signals and force in human vastus lateralis muscle using multiple bipolar wire electrodes. J Electromyogr Kinesiol 10:59–67CrossRefGoogle Scholar
  9. 9.
    Edwards L, Dixon J, Kent JR, Hodgson D, Whittaker VJ (2008) Effect of shoe heel height on vastus medialis and vastus lateralis electromyographic activity during sit to stand. J Orthop Surg Res 3:2CrossRefGoogle Scholar
  10. 10.
    Mishra AK, Srivastava A, Tewari RP, Mathur R (2012) EMG analysis of lower limb muscles for developing robotic exoskeleton orthotic device. In: International symposium on robotics and intelligent sensors (IRIS 2012), vol 1, pp 32–36Google Scholar
  11. 11.
    Carli M, Goffredo M, Schmid M, Neri A (2006) Study of muscular deformation based on surface slope estimation. In: Dougherty ER, Astola JT, Egiazarian KO, Nasrabadi NM, Rizvi SA (eds) Image processing: algorithms and systems, neural networks, and machine learning, vol 6064. Society of photo-optical instrumentation engineers (SPIE) conference series. SPIE, 200Google Scholar
  12. 12.
    Goffredo M, Carli M, Conforto S, Bibbo D, Neri A, D’Alessio T (2005) Evaluation of skin and muscular deformations in a non-rigid motion analysis. In: Proceedings of the SPIE 5746, medical imaging: physiology, function, and structure from medical images, 535Google Scholar
  13. 13.
    Schöllhorn WI (2004) Applications of artificial neural nets in clinical biomechanics. Clin Biomech 19:876–898CrossRefGoogle Scholar
  14. 14.
    Senanayake C, Senanayake SMNA (2010) Computational intelligent gait phase detection system to identify pathological gait. IEEE Trans Inf Technol Biomed 14(5):1173–1179CrossRefGoogle Scholar
  15. 15.
    Perry J (1992) Gait analysis: normal and pathological function. Delmar LearningGoogle Scholar
  16. 16.
    Chan SH, Vo DT, Nguyen TQ (2010) Subpixel motion estimation without interpolation. In: IEEE international conference on presented at acoustics speech and signal processing (ICASSP), pp 722–725Google Scholar
  17. 17.
    Munderloh M, Klomp S, Ostermann J (2010) Mesh-based decoder-side motion estimation. In: 17th IEEE international conference on presented at image processing (ICIP), 2010, Hong Kong, pp 2049–2052Google Scholar
  18. 18.
    Hermens HJ, Freriks B, Disselhorst-klug C, Rau G (2000) Development of recommendations for SEMG sensors and sensor placement procedures. J Electromyogr Kinesiol 10(5):361–374CrossRefGoogle Scholar
  19. 19.
    Ravi KVR, Palaniappan R (2006) Neural network classification of late gamma band electroencephalogram features. J Soft Comput A Fusion Found Methodol Appl 10:163–169Google Scholar
  20. 20.
    Haykin S (2000) Neural network a comprehensive foundation, 2nd edn. Prentice Hall, Upper Saddle RiverzbMATHGoogle Scholar
  21. 21.
    Hagen M, Demuth H, Beale M (1996) Neural network design. PWS Publishing, BostonGoogle Scholar
  22. 22.
    Merletti R (1999) Standards for reporting EMG data. J Electromyogr Kinesiol 9(1):3–4Google Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  1. 1.Motion Analysis Lab, Integrated Science BuildingUniversiti Brunei DarussalamGadongBrunei Darussalam

Personalised recommendations