In addition, another previous study analyzed inter-session test-retest reliability of quantified YBT variables using a single lumbar inertial sensor, providing a reliable measure of balance performing across all three reach directions between tests performed in two different weeks. For example, a previous work demonstrated that inertial sensor-derived 95% ellipsoid volume (95 EV) measure could capture alterations in dynamic balance control, which were not detected by traditional reach distances alone, and distinguish pre-fatigue and post-fatigue dynamic balance control for all three reach directions. Previous studies have been focused on evaluating the validity and reliability of assessment protocols in laboratory environments. Postural control assessments have been frequently used for performance testing, injury risk screening, injury rehabilitation, and assessment of readiness to return to play. Wearable inertial sensors have been widely used in sports science and medicine postural control applications. The architecture output generates an estimation of the NRD, allowing to score the performance of the YBT. The inertial signals could be used for feeding a deep learning architecture. Evaluating the YBT automatically using a back inertial sensor facilitates its evaluation, allowing subjects to supervise their evolution without the need of attending the sport center neither the help of the physiotherapist. Although the NRD formula and setup are easy to assess, obtaining the NRD with the equipment requires the subjects to attend to the physiotherapist or sports center to perform the YBT. These IMUs provide a new opportunity to estimate the NRD directly from the sensor data and score the YBT, by developing a fully automated system. Inertial measurement units (IMUs) are now being used to capture movement quality during the reaching tasks, providing a more sensitive approach to measuring dynamic balance performance. The traditional method for scoring the YBT is the normalized reach distance (NRD), which is obtained by measuring the distance an individual can reach in each of the three directions, normalized by leg length. This test assesses performance during single-leg balance while reaching in three directions (anterior, posteromedial, and posterolateral). ![]() For example, YBT has been used for determining a person’s risk for injury or return to sport readiness. In particular, the Y Balance Test (YBT) is a test for assessing dynamic balance control, which has been widely used in clinical practice and research. This deep learning approach was compared to a previous work using dynamic time warping and k-NN algorithms, obtaining a relative MAPE reduction of 10%.ĭynamic balance refers to the ability to maintain equilibrium while performing actions that include movements of the center of mass outside of the base of support. Moreover, this work proposes specific regression systems to estimate the NRD for each direction separately, obtaining an average MAPE of 7.33 ± 0.26%. The mean absolute percentage error (MAPE) obtained was 7.88 ± 0.20%. The experimentation setup considered a 10-fold subject-wise cross-validation using training, validation, and testing subsets. This dataset allowed developing a global and robust solution for scoring the YBT in a wide range of applications. ![]() ![]() All analyses were carried out using a dataset with YBT assessments from 407 subjects, including young and middle-aged volunteers and athletes from different sports. This deep neural network includes long short-term memory (LSTM) layers to learn features from time series by modeling temporal patterns and an additional fully connected layer to estimate the NRD (normalized by the leg length). This evaluation was performed using a state-of-the-art human activity recognition system based on recurrent neural networks (RNNs). ![]() This paper evaluates several signal processing techniques to extract relevant information to feed the deep neural network. This work proposes a deep learning approach to automatically score this YBT by estimating the normalized reach distance (NRD) using a wearable sensor to register inertial signals during the movement. The Y Balance Test (YBT) is a dynamic balance assessment typically used in sports medicine.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |