TY - JOUR
T1 - Skill level classification in basketball free-throws using a single inertial sensor
AU - Guo, X.
AU - Brown, Ellyn
AU - Chan, P. P. K.
AU - Chan, R. H. M.
AU - Cheung, Roy T. H.
PY - 2023/5
Y1 - 2023/5
N2 - Wearable sensors are an emerging technology, with growing evidence supporting their application in sport performance enhancement. This study utilized data collected from a tri-axial inertial sensor on the wrist of ten recreational and eight professional basketball players while they performed free-throws, to classify their skill levels. We employed a fully connected convolutional neural network (CNN) for the classification task, using 64% of the data for training, 16% for validation, and the remaining 20% for testing the model’s performance. In the case of considering a single parameter from the inertial sensor, the most accurate individual components were upward acceleration (AX), with an accuracy of 82% (sensitivity = 0.79; specificity = 0.84), forward acceleration (AZ), with an accuracy of 80% (sensitivity = 0.78; specificity = 0.83), and wrist angular velocity in the sagittal plane (GY), with an accuracy of 77% (sensitivity = 0.73; specificity = 0.79). The highest accuracy of the classification was achieved when these CNN inputs utilized a stack-up matrix of these three axes, resulting in an accuracy of 88% (sensitivity = 0.87, specificity = 0.90). Applying the CNN to data from a single wearable sensor successfully classified basketball players as recreational or professional with an accuracy of up to 88%. This study represents a step towards the development of a biofeedback device to improve free-throw shooting technique.
AB - Wearable sensors are an emerging technology, with growing evidence supporting their application in sport performance enhancement. This study utilized data collected from a tri-axial inertial sensor on the wrist of ten recreational and eight professional basketball players while they performed free-throws, to classify their skill levels. We employed a fully connected convolutional neural network (CNN) for the classification task, using 64% of the data for training, 16% for validation, and the remaining 20% for testing the model’s performance. In the case of considering a single parameter from the inertial sensor, the most accurate individual components were upward acceleration (AX), with an accuracy of 82% (sensitivity = 0.79; specificity = 0.84), forward acceleration (AZ), with an accuracy of 80% (sensitivity = 0.78; specificity = 0.83), and wrist angular velocity in the sagittal plane (GY), with an accuracy of 77% (sensitivity = 0.73; specificity = 0.79). The highest accuracy of the classification was achieved when these CNN inputs utilized a stack-up matrix of these three axes, resulting in an accuracy of 88% (sensitivity = 0.87, specificity = 0.90). Applying the CNN to data from a single wearable sensor successfully classified basketball players as recreational or professional with an accuracy of up to 88%. This study represents a step towards the development of a biofeedback device to improve free-throw shooting technique.
UR - https://hdl.handle.net/1959.7/uws:77943
U2 - 10.3390/app13095401
DO - 10.3390/app13095401
M3 - Article
SN - 2076-3417
VL - 13
JO - Applied Sciences
JF - Applied Sciences
IS - 9
M1 - 5401
ER -