Figure 1 | Scientific Reports

Figure 1

From: A machine-learning method isolating changes in wrist kinematics that identify age-related changes in arm movement

Figure 1

Features Selected for Classification. From features selected after the MRMR algorithm, use features that explain \(\sim\) 90% of variance. Five features selected were Total Power of (1) linear acceleration in Y-axis (\(P_{a_y}\)), (2) linear velocity in Y-axis (\(P_{v_y}\)), (3) angular velocity in Yaw-axis (\(P_{\omega _{Yaw}}\)), (4) angular velocity in Roll-axis (\(P_{\omega _{Roll}}\)) and (5) angular acceleration in Yaw-axis (\(P_{\alpha _{Yaw}}\)). The variance explained by each variable was 27%, 23%, 16%, 15% and 10% respectively.

Back to article page