Figure 2
Classification outcome using logistic regression. The horizontal axis denotes the number of time frames to define time-varying motion data X, and the vertical axis denotes the classification accuracy in cross-validation. The green and blue dotted lines denote the classification accuracy averaged across all subjects using the motion data on the first and second days, respectively. The red solid line and the shaded area indicate the mean and standard error of the classification accuracy for all subjects and two days, respectively. We used joint angles with 17 time frames to determine the motion sequence data X for the analysis throughout this paper because the mean classification accuracy was the best for the logistic regression with 17 time frames.
