论文信息 - Self-Organizing Maps for the Analysis of Complex Movement Patterns

Self-Organizing Maps for the Analysis of Complex Movement Patterns

We apply the Self-Organizing-Map-algorithm (SOM) as a central processing step in a new scheme for the characterisation of movement patterns of athletes. Due to its non-linear dimension reduction capabilities, the SOM outperforms a direct processing of the data as well as preprocessing using principal component analysis. Our results open the way to an objective assessment of movement patterns, with possible applications in the sport sciences as well as in medicine.

Wolfgang I. Schöllhorn | Hans-Ulrich Bauer | H. Bauer | W. Schöllhorn

[1] Ralf Der,et al. A Novel Approach to Measure the Topology Preservation of Feature Maps , 1994 .

[2] H. Haken. Principles of brain functioning , 1995 .

[3] S H Holzreiter,et al. Assessment of gait patterns using neural networks. , 1993, Journal of biomechanics.

[4] Helge J. Ritter,et al. Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[5] James C. Bezdek,et al. An index of topological preservation for feature extraction , 1995, Pattern Recognit..

[6] Klaus Pawelzik,et al. Quantifying the neighborhood preservation of self-organizing feature maps , 1992, IEEE Trans. Neural Networks.