ANN for gait estimations: A review on current trends and future applications

In recent years, gait analysis through estimations has gained significant interest. Through a critical evaluation of recent gait estimations based on Artificial Neural Networks (ANNs), this paper reviews the potential of these methods. It is found that three layer Feed Forward Neural Networks (FFNNs) are widely employed in gait parameter estimations. Traditional kinetic sensors are generally expensive and requires a laboratory environment for data collection. Due to this reason, previous research mainly performed estimations of kinetic parameters from kinematic data thus eliminating the need of traditional kinetic sensors. In comparison to kinematic data, kinetic data are less complex. Moreover, the advancement of wearable kinetic foot sensors offers the advantage of data recording outside laboratory, and are comparatively cost effective. Therefore, estimating kinematics from wearable kinetic sensor data may present to be a better alternative, which has not yet been investigated, thus providing space for future research.

[1]  R. Dennis Cook,et al.  Cross-Validation of Regression Models , 1984 .

[2]  Ruth E Mayagoitia,et al.  A portable system for collecting anatomical joint angles during stair ascent: a comparison with an optical tracking device , 2009, Dynamic medicine : DM.

[3]  Jan Rueterbories,et al.  Methods for gait event detection and analysis in ambulatory systems. , 2010, Medical engineering & physics.

[4]  José M. N. Vieira,et al.  Neuro-Fuzzy Systems: A Survey , 2004 .

[5]  Yujiang Xiang,et al.  Optimization-based prediction of asymmetric human gait. , 2011, Journal of biomechanics.

[6]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  Daniel Vélez Día,et al.  Biomechanics and Motor Control of Human Movement , 2013 .

[9]  Donald Y. C. Lie,et al.  An Efficient and Robust Fall Detection System Using Wireless Gait Analysis Sensor with Artificial Neural Network (ANN) and Support Vector Machine (SVM) Algorithms , 2014 .

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[12]  M. Saleh,et al.  In defence of gait analysis. Observation and measurement in gait assessment. , 1985, The Journal of bone and joint surgery. British volume.

[13]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[14]  安藤 寛,et al.  Cross-Validation , 1952, Encyclopedia of Machine Learning and Data Mining.

[15]  Ahnryul Choi,et al.  Ground reaction forces predicted by using artificial neural network during asymmetric movements , 2013 .

[16]  Jing Zhang,et al.  A real-time topography of maximum contact pressure distribution at medial tibiofemoral knee implant during gait: Application to knee rehabilitation , 2015, Neurocomputing.

[17]  T. Wren,et al.  Reliability and Validity of Visual Assessments of Gait Using a Modified Physician Rating Scale for Crouch and Foot Contact , 2005, Journal of pediatric orthopedics.

[18]  H. Watts.  Gait laboratory analysis for preoperative decision making in spastic cerebral palsy: is it all it's cracked up to be? , 1994, Journal of pediatric orthopedics.

[19]  S. Õunpuu,et al.  Efficacy of clinical gait analysis: A systematic review. , 2011, Gait & posture.

[20]  Xiaoou Li,et al.  Haar wavelet neural networks for nonlinear system identification , 2012, 2012 IEEE International Symposium on Intelligent Control.

[21]  Marimuthu Palaniswami,et al.  Computational Intelligence in Gait Research: A Perspective on Current Applications and Future Challenges , 2009, IEEE Transactions on Information Technology in Biomedicine.

[22]  Ganapati Panda,et al.  Identification of nonlinear dynamic systems using functional link artificial neural networks , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[23]  Bruno Watier,et al.  An algorithm to decompose ground reaction forces and moments from a single force platform in walking gait. , 2014, Medical engineering & physics.

[24]  George Cybenko,et al.  Complexity Theory of Neural Networks and Classification Problems , 1990, EURASIP Workshop.

[25]  Trent M. Guess,et al.  Application of neural networks for the prediction of cartilage stress in a musculoskeletal system , 2013, Biomed. Signal Process. Control..

[26]  Ahnryul Choi,et al.  Prediction of ground reaction forces during gait based on kinematics and a neural network model. , 2013, Journal of biomechanics.

[27]  W I Schöllhorn,et al.  Applications of artificial neural nets in clinical biomechanics. , 2004, Clinical biomechanics.

[28]  Keizo Sato,et al.  Factors Affecting Minimum Foot Clearance in the Elderly Walking: A Multiple Regression Analysis , 2015 .

[29]  Gerd Hirzinger,et al.  Solving the Ill-Conditioning in Neural Network Learning , 1996, Neural Networks: Tricks of the Trade.

[30]  D. Howard,et al.  Whole body inverse dynamics over a complete gait cycle based only on measured kinematics. , 2008, Journal of biomechanics.

[31]  Ravi Kothari,et al.  Artificial Neural Networks in Remote Sensing of Hydrologic Processes , 2000 .

[32]  Xuan Zhang,et al.  Human lower extremity joint moment prediction: A wavelet neural network approach , 2014, Expert Syst. Appl..

[33]  Eckart Fleck,et al.  Frequency analysis of atrial fibrillation surface and intracardiac electrograms during pulmonary vein isolation. , 2011, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[34]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[35]  Zhongmin Jin,et al.  Gait modification and optimization using neural network-genetic algorithm approach: Application to knee rehabilitation , 2014, Expert Syst. Appl..

[36]  Geoffrey E. Hinton,et al.  How neural networks learn from experience. , 1992, Scientific American.

[37]  Richi Nayak,et al.  Artificial neural networks in biomedical engineering: a review , 2001 .

[38]  Daniel P. Ferris,et al.  Estimation of ground reaction forces and ankle moment with multiple, low-cost sensors , 2015, Journal of NeuroEngineering and Rehabilitation.

[39]  T Chau,et al.  A review of analytical techniques for gait data. Part 2: neural network and wavelet methods. , 2001, Gait & posture.

[40]  Sheldon R Simon,et al.  Quantification of human motion: gait analysis-benefits and limitations to its application to clinical problems. , 2004, Journal of biomechanics.

[41]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[42]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[43]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[44]  Stéphane Mallat,et al.  Wavelet interpolation networks , 1998, ESANN.

[45]  Zhongmin Jin,et al.  Sensitivity analysis of human lower extremity joint moments due to changes in joint kinematics. , 2015, Medical engineering & physics.

[46]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.