Predicting ground reaction forces in running using micro-sensors and neural networks |
| |
Authors: | D C Billing C R Nagarajah J P Hayes J Baker |
| |
Institution: | (1) Defence Scientist in Health and Human Performance Human Protection and Performance Division, Defence Science and Technology Organisation, 506 Lorimer St, 3207 Fishermans Bend, Vic;(2) Swinburne University of Technology, Hawthorn, Melbourne, Australia;(3) Cooperative Research Centre for microTechnology, Hawthorn, Melbourne, Australia;(4) Australian Institute of Sport, Belconnen, Canberra, Australia |
| |
Abstract: | Measurement of ground reaction force (GRF) in running provides a direct indication of the loads to which the body is subjected
at each foot-ground contact, and can provide an objective explanation for performance outcomes. Traditionally, the collection
of three orthogonal component GRF data in running requires an athlete to complete a series of return loops along a laboratory
based runway, within which a force platform is embedded, in order to collect data from a discrete footfall. The major disadvantages
associated with this GRF data collection methodology include the inability to assess multiple consecutive foot contacts and
the fact that measurements are typically confined to the laboratory. The objective of this research was to investigate the
potential for wearable instrumentation to be employed, in conjunction with artificial neural network (ANN) and multiple linear
regression (MLR) models, for the estimation of GRF in middle distance running. A modular wearable data acquisition system
was developed to acquire in-shoe force (ISF) data. Matched data sets from wearable instrumentation (source data) and force
plate (target data) records were collected from elite middle-distance runners under controlled laboratory conditions for the
purposes of ANN and MLR model development (MD) and model validation (MV).
In terms of statistical measures of prediction accuracy the MLR model was found to provide a superior level of accuracy for
the prediction of the vertical and medio-lateral components of GRF and alternatively, the ANN model provided the most accurate
predictions of the anterior-posterior component of GRF. The prediction accuracy of each component of GRF was found to be governed
by the inherent signal variability, in which case the vertical and anterior-posterior components were more reliable and subsequently
predicted significantly more accurately than the medio-lateral component.
The emerging capability for obtaining continuous GRF records from wearable instrumentation has the potential to permit unprecedented
quantification of training stress and competition demands in running. |
| |
Keywords: | artificial neural network ground reaction force multiple linear regression running |
本文献已被 SpringerLink 等数据库收录! |
|