Abstract:Running is a widely practiced activity but shows a high incidence of knee injuries, especially Patellofemoral Pain Syndrome (PFPS) and Iliotibial Band Syndrome (ITBS). Identifying gait patterns linked to these injuries can improve clinical decision-making, which requires precise systems capable of capturing and analyzing temporal kinematic data. This study uses optical motion capture systems to enhance detection of injury-related running patterns. We analyze a public dataset of 839 treadmill recordings from healthy and injured runners to evaluate how effectively these systems capture dynamic parameters relevant to injury classification. The focus is on the stance phase, using joint and segment angle time series and discrete point values. Three classification tasks are addressed: healthy vs. injured, healthy vs. PFPS, and healthy vs. ITBS. We examine different feature spaces, from traditional point-based metrics to full stance-phase time series and hybrid representations. Multiple models are tested, including classical algorithms (K-Nearest Neighbors, Gaussian Processes, Decision Trees) and deep learning architectures (CNNs, LSTMs). Performance is evaluated with accuracy, precision, recall, and F1-score. Explainability tools such as Shapley values, saliency maps, and Grad-CAM are used to interpret model behavior. Results show that combining time series with point values substantially improves detection. Deep learning models outperform classical ones, with CNNs achieving the highest accuracy: 77.9% for PFPS, 73.8% for ITBS, and 71.43% for the combined injury class. These findings highlight the potential of motion capture systems coupled with advanced machine learning to identify knee injury-related running patterns.
Abstract:The location of the center of rotation (COR) of joints is a key parameter in multiple applications of human motion analysis. The aim of this work was to propose a novel real-time estimator of the center of fixed joints using an inertial measurement unit (IMU). Since the distance to this center commonly varies during the joint motion due to soft tissue artifacts (STA), our approach is aimed at adapting to these small variations when the COR is fixed. Our proposal, called ArVEd, to the best of our knowledge, is the first real-time estimator of the IMU-joint center vector based on one IMU. Previous works are off-line and require a complete measurement batch to be solved and most of them are not tested on the real scenario. The algorithm is based on an Extended Kalman Filter (EKF) that provides an adaptive vector to STA motion variations at each time instant, without requiring a pre-processing stage to reduce the level of noise. ArVEd has been tested through different experiments, including synthetic and real data. The synthetic data are obtained from a simulated spherical pendulum whose COR is fixed, considering both a constant and a variable IMU-joint vector, that simulates translational IMU motions due to STA. The results prove that ArVEd is adapted to obtain a vector per sample with an accuracy of 6.8$\pm$3.9 on the synthetic data, that means an error lower than 3.5% of the simulated IMU-joint vector. Its accuracy is also tested on the real scenario estimating the COR of the hip of 5 volunteers using as reference the results from an optical system. In this case, ArVEd gets an average error of 9.5% of the real vector value. In all the experiments, ArVEd outperforms the published results of the reference algorithms.
Abstract:This document introduces the PHYTMO database, which contains data from physical therapies recorded with inertial sensors, including information from an optical reference system. PHYTMO includes the recording of 30 volunteers, aged between 20 and 70 years old. A total amount of 6 exercises and 3 gait variations were recorded. The volunteers performed two series with a minimum of 8 repetitions in each one. PHYTMO includes magneto-inertial data, together with a highly accurate location and orientation in the 3D space provided by the optical system. The files were stored in CSV format to ensure its usability. The aim of this dataset is the availability of data for two main purposes: the analysis of techniques for the identification and evaluation of exercises using inertial sensors and the validation of inertial sensor-based algorithms for human motion monitoring. Furthermore, the database stores enough data to apply Machine Learning-based algorithms. The participants' age range is large enough to establish age-based metrics for the exercises evaluation or the study of differences in motions between different groups.
Abstract:Home-based physical therapies are effective if the prescribed exercises are correctly executed and patients adhere to these routines. This is specially important for older adults who can easily forget the guidelines from therapists. Inertial Measurement Units (IMUs) are commonly used for tracking exercise execution giving information of patients' motion data. In this work, we propose the use of Machine Learning techniques to recognize which exercise is being carried out and to assess if the recognized exercise is properly executed by using data from four IMUs placed on the person limbs. To the best of our knowledge, both tasks have never been addressed together as a unique complex task before. However, their combination is needed for the complete characterization of the performance of physical therapies. We evaluate the performance of six machine learning classifiers in three contexts: recognition and evaluation in a single classifier, recognition of correct exercises, excluding the wrongly performed exercises, and a two-stage approach that first recognizes the exercise and then evaluates it. We apply our proposal to a set of 8 exercises of the upper-and lower-limbs designed for maintaining elderly people health status. To do so, the motion of volunteers were monitored with 4 IMUs. We obtain accuracies of 88.4 \% and the 91.4 \% in the two initial scenarios. In the third one, the recognition provides an accuracy of 96.2 \%, whereas the exercise evaluation varies between 93.6 \% and 100.0 \%. This work proves the feasibility of IMUs for a complete monitoring of physical therapies in which we can get information of which exercise is being performed and its quality, as a basis for designing virtual coaches.