ith the emergence of data science and wearable body sensors, sports analytics is becoming very important study field where sports scientists and coaches are able to track player activities and performance for early injury prevention. Electronic Performance Tracking Systems (EPTS) equipped with inertial sensors and GPS have been widely used for this purpose. The real challenge is to understand the data and translate it into meaningful information; visualizing relevant results for coaches’ or sports scientists. Activity distance, speed and time can be measured using GPS data. These parameters are suffered from slow sample rate and high error tolerance which are not sufficient for predicting injury or reducing stress or fatigue. Workload estimation using inertial measurement unit (IMU) has been used for training and monitoring purposes. However, sports scientists need a closer look at the behavior of the data to identify the cause, and hence, able to prevent injury. This paper presents an algorithm for estimating the acceleration/deceleration at every change of direction and visualizing athlete’s movement for the entire session based on IMU and GPS data. The visualization results from our on-field athlete’s data have shown that the proposed algorithm can provide much more useful information for sport analytics purposes than the workload. ith the emergence of data science and wearable body sensors, sports analytics is becoming very important study field where sports scientists and coaches are able to track player activities and performance for early injury prevention. Electronic Performance Tracking Systems (EPTS) equipped with inertial sensors and GPS have been widely used for this purpose. The real challenge is to understand the data and translate it into meaningful information; visualizing relevant results for coaches’ or sports scientists. Activity distance, speed and time can be measured using GPS data. These parameters are suffered from slow sample rate and high error tolerance which are not sufficient for predicting injury or reducing stress or fatigue. Workload estimation using inertial measurement unit (IMU) has been used for training and monitoring purposes. However, sports scientists need a closer look at the behavior of the data to identify the cause, and hence, able to prevent injury. This paper presents an algorithm for estimating the acceleration/deceleration at every change of direction and visualizing athlete’s movement for the entire session based on IMU and GPS data. The visualization results from our on-field athlete’s data have shown that the proposed algorithm can provide much more useful information for sport analytics purposes than the workload. W

Wearable body sensors, Inertial sensors, Accelerometer, GPS, PlayerLoad, Sports analytics, Athlete performance tracking