VolleyJump 2.0: A Computational Approach to Analysis and Classification of Volleyball Jumps Based on Multiple Inertial Devices

Technological resources have become indispensable in professional sports activities due to the critical level of competitiveness of athletes required in tournaments. One of the main aspects that characterize a volleyball athlete's success is his performance in the jumps performed during a match. This physical action is performed several times by the athlete to attack or prevent the success of an opposing team's attack. Wearable computing has become common in sports training, just as there are approaches that use sensors attached to the athletes' body to study and quantify the jump's movement. However, these marketable portable devices tend to be used as activity trackers that provide simple recommendations, such as the number of steps, heart rate, distance traveled, and amount of calories lost. Besides, real-time monitoring and evaluation solutions to provide personalized feedback and decisions are expensive and not viable for athletes without sponsorship. For this reason, this work presents VolleyJump 2.0, a computational approach to classify volleyball athletes jumps using techniques of extraction and selection of features from digital signals provided by inertial sensors. The performance results of the data set are also presented, in a promising way, in some machine learning models developed to predict volleyball jumps. Recent studies dealing with this topic show that classification models have good results for distinguishing jumps using a device that contains an accelerometer and gyroscope sensor. In this study, we proposed using prototypes of electronic devices of inertial sensors attached to the wrist and waist of the user. These sensors emit digital signals via WiFi connection, which will be processed to extract features and, from there, create a data-set of jump activity. With this, it will be possible to analyze the selection of characteristics and measure the performance of these variables using some classification models.