Athletes’ movement biomechanics are of high interest to predict injury risk. However, using a standard optical measurement set-up with cameras and force plates influences the athlete’s performance. Alternative systems such as commercial IMU systems are still jeopardised by measurement discrepancies in the analysis of joint angles. Therefore, this study aims to estimate hip, knee and ankle joint angles from simulated IMU data during the execution and depart contact of a maximum effort 90° cutting manoeuvre using a feed-forward neural network. Simulated accelerations and angular rates of the feet, shanks, thighs and pelvis as input data. The correlation coefficient between the measured and predicted data indicates strong correlations. Hence, the proposed method can be used to predict motion kinematics during a fast change of direction.
New Investigator Award
Mundt, Marion; David, Sina; Koeppe, Arnd; Bamer, Franz; Potthast, Wolfgang; and Markert, Bernd
"JOINT ANGLE ESTIMATION DURING FAST CUTTING MANOEUVRES USING ARTIFICIAL NEURAL NETWORKS,"
ISBS Proceedings Archive: Vol. 37
, Article 23.
Available at: https://commons.nmu.edu/isbs/vol37/iss1/23