ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
We present a set of visualization methods for the analysis of multivariate data recorded from the measurement of the performance of athletes during training. We use a modified training device to measure the force, acceleration, displacement, and speed of the athlete's feet and arms while performing a certain training exercise. We are interested in visually measuring and comparing the performance over several training sessions of the same and/or different athletes. For this, we adapt and extend several visualization methods for multivariate data. First, we use an enhanced signal plot and statistics plot to visualize the regularity of repetitions within a given exercise. Second, we use a novel texture-based signal plot to eliminate signal noise and emphasize the average repetitive pattern of the exercise. Finally, we use a signal clustering technique, visualized with a matrix plot, to detect similar exercises over long periods of time. We demonstrate our approaches with actual data from training sessions of several athletes.