Time Coherent Full-Body Poses Estimated Using Only Five Inertial Sensors: Deep versus Shallow Learning.

Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: "What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?". We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of a deep learning approach (~7 cm). However, the jerk errors are smaller using the deep learning approach, which can be the effect of explicit recurrent modelling. Furthermore, it is shown that the delay using a shallow learning approach (72 ms) is smaller than that of a deep learning approach (117 ms).

Estimation of Vertical Ground Reaction Forces and Sagittal Knee Kinematics During Running Using Three Inertial Sensors.

Analysis of running mechanics has traditionally been limited to a gait laboratory using either force plates or an instrumented treadmill in combination with a full-body optical motion capture system. With the introduction of inertial motion capture systems, it becomes possible to measure kinematics in any environment. However, kinetic information could not be provided with such technology. Furthermore, numerous body-worn sensors are required for a full-body motion analysis. The aim of this study is to examine the validity of a method to estimate sagittal knee joint angles and vertical ground reaction forces during running using an ambulatory minimal body-worn sensor setup. Two concatenated artificial neural networks were trained (using data from eight healthy subjects) to estimate the kinematics and kinetics of the runners. The first artificial neural network maps the information (orientation and acceleration) of three inertial sensors (placed at the lower legs and pelvis) to lower-body joint angles. The estimated joint angles in combination with measured vertical accelerations are input to a second artificial neural network that estimates vertical ground reaction forces. To validate our approach, estimated joint angles were compared to both inertial and optical references, while kinetic output was compared to measured vertical ground reaction forces from an instrumented treadmill. Performance was evaluated using two scenarios: training and evaluating on a single subject and training on multiple subjects and evaluating on a different subject. The estimated kinematics and kinetics of most subjects show excellent agreement (ρ>0.99) with the reference, for single subject training. Knee flexion/extension angles are estimated with a mean RMSE <5°. Ground reaction forces are estimated with a mean RMSE < 0.27 BW. Additionaly, peak vertical ground reaction force, loading rate and maximal knee flexion during stance were compared, however, no significant differences were found. With multiple subject training the accuracy of estimating discrete and continuous outcomes decreases, however, good agreement (ρ > 0.9) is still achieved for seven of the eight different evaluated subjects. The performance of multiple subject learning depends on the diversity in the training dataset, as differences in accuracy were found for the different evaluated subjects.

Estimation of Full-Body Poses Using Only Five Inertial Sensors: An Eager or Lazy Learning Approach?

Human movement analysis has become easier with the wide availability of motion capture systems. Inertial sensing has made it possible to capture human motion without external infrastructure, therefore allowing measurements in any environment. As high-quality motion capture data is available in large quantities, this creates possibilities to further simplify hardware setups, by use of data-driven methods to decrease the number of body-worn sensors. In this work, we contribute to this field by analyzing the capabilities of using either artificial neural networks (eager learning) or nearest neighbor search (lazy learning) for such a problem. Sparse orientation features, resulting from sensor fusion of only five inertial measurement units with magnetometers, are mapped to full-body poses. Both eager and lazy learning algorithms are shown to be capable of constructing this mapping. The full-body output poses are visually plausible with an average joint position error of approximately 7 cm, and average joint angle error of 7 ∘ . Additionally, the effects of magnetic disturbances typical in orientation tracking on the estimation of full-body poses was also investigated, where nearest neighbor search showed better performance for such disturbances.

Body-Sensor-Network-Based Kinematic Characterization and Comparative Outlook of UPDRS Scoring in Leg Agility, Sit-to-Stand, and Gait Tasks in Parkinson's Disease.

Recently, we have proposed a body-sensor-network-based approach, composed of a few body-worn wireless inertial nodes, for automatic assignment of Unified Parkinson's Disease Rating Scale (UPDRS) scores in the following tasks: Leg agility (LA), Sit-to-Stand (S2S), and Gait (G). Unlike our previous works and the majority of the published studies, where UPDRS tasks were the sole focus, in this paper, we carry out a comparative investigation of the LA, S2S, and G tasks. In particular, after providing an accurate description of the features identified for the kinematic characterization of the three tasks, we comment on the correlation between the most relevant kinematic parameters and the UPDRS scoring. We analyzed the performance achieved by the automatic UPDRS scoring system and compared the estimated UPDRS evaluation with the one performed by neurologists, showing that the proposed system compares favorably with typical interrater variability. We then investigated the correlations between the UPDRS scores assigned to the various tasks by both the neurologists and the automatic system. The results, based on a limited number of subjects with Parkinson's disease (PD) (34 patients, 47 clinical trials), show poor-to-moderate correlations between the UPDRS scores of different tasks, highlighting that the patients' motor performance may vary significantly from one task to another, since different tasks relate to different aspects of the disease. An aggregate UPDRS score is also considered as a concise parameter, which can provide additional information on the overall level of the motor impairments of a Parkinson's patient. Finally, we discuss a possible implementation of a practical e-health application for the remote monitoring of PD patients.

Automatic UPDRS Evaluation in the Sit-to-Stand Task of Parkinsonians: Kinematic Analysis and Comparative Outlook on the Leg Agility Task.

In this study, we first characterize the sit-to-stand (S2S) task, which contributes to the evaluation of the degree of severity of the Parkinson's disease (PD), through kinematic features, which are then linked to the Unified Parkinson's disease rating scale (UPDRS) scores. We propose to use a single body-worn wireless inertial node placed on the chest of a patient. The experimental investigation is carried out considering 24 PD patients, comparing the obtained results directly with the kinematic characterization of the leg agility (LA) task performed by the same set of patients. We show that i) the S2S and LA tasks are rather unrelated and ii) the UPDRS distributions (for both S2S and LA tasks) across the patients have a direct impact on the observed system performance.