Valuation of climbing activities using Multi-Scale Jensen-Shannon Neighbour Embedding

This paper presents a study carried out in a controlled environment that aims at understanding behavioural patterns in climbing activities. Multi-Scale Jensen-Shannon Neighbour Embedding [8], a recent advance in non linear dimension reduction, has been applied to recordings of movement sensors in order to help the visualization of coordination modes. Initial clustering results show a correlation with jerk, an indicator of fluency in climbing activities, but provides more details on behavioural patterns.

[1]  Sebastian O. H. Madgwick,et al.  An efficient orientation filter for inertial and inertial / magnetic sensor arrays , 2010 .

[2]  Michel Verleysen,et al.  Multi-scale similarities in stochastic neighbour embedding: Reducing dimensionality while preserving both local and global structure , 2015, Neurocomputing.

[3]  R. Bootsma,et al.  Dynamics of human postural transitions. , 2002, Journal of experimental psychology. Human perception and performance.

[4]  Michèle Basseville,et al.  Detection of abrupt changes: theory and application , 1993 .

[5]  Jonathan H. Manton,et al.  A globally convergent numerical algorithm for computing the centre of mass on compact Lie groups , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[6]  Kenth Engø-Monsen,et al.  On the BCH-formula in so(3) , 2001 .

[7]  Sebastian Madgwick,et al.  Estimation of IMU and MARG orientation using a gradient descent algorithm , 2011, 2011 IEEE International Conference on Rehabilitation Robotics.

[8]  Romain Hérault,et al.  Automatic Sensor-Based Detection and Classification of Climbing Activities , 2015, IEEE Sensors Journal.

[9]  B. Hall.  Lie Groups, Lie Algebras, and Representations: An Elementary Introduction , 2004 .

[10]  Didier Delignières,et al.  The nature of the transition between novice and skilled coordination during learning to swing. , 2007, Human movement science.

[11]  Romain Hérault,et al.  Climbing skill and complexity of climbing wall design: assessment of jerk as a novel indicator of performance fluency. , 2014, Journal of applied biomechanics.

[12]  Michel Verleysen,et al.  Type 1 and 2 mixtures of Kullback-Leibler divergences as cost functions in dimensionality reduction based on similarity preservation , 2013, Neurocomputing.

[13]  J. Kelso.  Phase transitions and critical behavior in human bimanual coordination. , 1984, The American journal of physiology.

[14]  Geoffrey E. Hinton,et al.  Stochastic Neighbor Embedding , 2002, NIPS.