Indirect Estimation of Vertical Ground Reaction Force from a Body-Mounted INS/GPS Using Machine Learning

Towards an accurate rolling resistance: Estimating intra-cycle load distribution between front and rear wheels during wheelchair propulsion from inertial sensors

Accurate assessment of rolling resistance is important for wheelchair propulsion analyses. However, the commonly used drag and deceleration tests are reported to underestimate rolling resistance up to 6% due to the (neglected) influence of trunk motion. The first aim of this study was to investigate the accuracy of using trunk and wheelchair kinematics to predict the intra-cyclical load distribution, more particularly front wheel loading, during hand-rim wheelchair propulsion. Secondly, the study compared the accuracy of rolling resistance determined from the predicted load distribution with the accuracy of drag test-based rolling resistance. Twenty-five able-bodied participants performed hand-rim wheelchair propulsion on a large motor-driven treadmill. During the treadmill sessions, front wheel load was assessed with load pins to determine the load distribution between the front and rear wheels. Accordingly, a machine learning model was trained to predict front wheel load from kinematic data. Based on two inertial sensors (attached to the trunk and wheelchair) and the machine learning model, front wheel load was predicted with a mean absolute error (MAE) of 3.8% (or 1.8 kg). Rolling resistance determined from the predicted load distribution (MAE: 0.9%, mean error (ME): 0.1%) was more accurate than drag test-based rolling resistance (MAE: 2.5%, ME: -1.3%).

Estimation of Kinetics Using IMUs to Monitor and Aid in Clinical Decision-Making during ACL Rehabilitation: A Systematic Review

After an ACL injury, rehabilitation consists of multiple phases, and progress between these phases is guided by subjective visual assessments of activities such as running, hopping, jump landing, etc. Estimation of objective kinetic measures like knee joint moments and GRF during assessment can help physiotherapists gain insights on knee loading and tailor rehabilitation protocols. Conventional methods deployed to estimate kinetics require complex, expensive systems and are limited to laboratory settings. Alternatively, multiple algorithms have been proposed in the literature to estimate kinetics from kinematics measured using only IMUs. However, the knowledge about their accuracy and generalizability for patient populations is still limited. Therefore, this article aims to identify the available algorithms for the estimation of kinetic parameters using kinematics measured only from IMUs and to evaluate their applicability in ACL rehabilitation through a comprehensive systematic review. The papers identified through the search were categorized based on the modelling techniques and kinetic parameters of interest, and subsequently compared based on the accuracies achieved and applicability for ACL patients during rehabilitation. IMUs have exhibited potential in estimating kinetic parameters with good accuracy, particularly for sagittal movements in healthy cohorts. However, several shortcomings were identified and future directions for improvement have been proposed, including extension of proposed algorithms to accommodate multiplanar movements and validation of the proposed techniques in diverse patient populations and in particular the ACL population.

Acceleration-Based Estimation of Vertical Ground Reaction Forces during Running: A Comparison of Methods across Running Speeds, Surfaces, and Foot Strike Patterns

Twenty-seven methods of estimating vertical ground reaction force first peak, loading rate, second peak, average, and/or time series from a single wearable accelerometer worn on the shank or approximate center of mass during running were compared. Force estimation errors were quantified for 74 participants across different running surfaces, speeds, and foot strike angles and biases, repeatability coefficients, and limits of agreement were modeled with linear mixed effects to quantify the accuracy, reliability, and precision. Several methods accurately and reliably estimated the first peak and loading rate, however, none could do so precisely (the limits of agreement exceeded ±65% of target values). Thus, we do not recommend first peak or loading rate estimation from accelerometers with the methods currently available. In contrast, the second peak, average, and time series could all be estimated accurately, reliably, and precisely with several different methods. Of these, we recommend the 'Pogson' methods due to their accuracy, reliability, and precision as well as their stability across surfaces, speeds, and foot strike angles.

Limiting the Use of Electromyography and Ground Reaction Force Data Changes the Magnitude and Ranking of Modelled Anterior Cruciate Ligament Forces

Neuromusculoskeletal models often require three-dimensional (3D) body motions, ground reaction forces (GRF), and electromyography (EMG) as input data. Acquiring these data in real-world settings is challenging, with barriers such as the cost of instruments, setup time, and operator skills to correctly acquire and interpret data. This study investigated the consequences of limiting EMG and GRF data on modelled anterior cruciate ligament (ACL) forces during a drop–land–jump task in late-/post-pubertal females. We compared ACL forces generated by a reference model (i.e., EMG-informed neural mode combined with 3D GRF) to those generated by an EMG-informed with only vertical GRF, static optimisation with 3D GRF, and static optimisation with only vertical GRF. Results indicated ACL force magnitude during landing (when ACL injury typically occurs) was significantly overestimated if only vertical GRF were used for either EMG-informed or static optimisation neural modes. If 3D GRF were used in combination with static optimisation, ACL force was marginally overestimated compared to the reference model. None of the alternative models maintained rank order of ACL loading magnitudes generated by the reference model. Finally, we observed substantial variability across the study sample in response to limiting EMG and GRF data, indicating need for methods incorporating subject-specific measures of muscle activation patterns and external loading when modelling ACL loading during dynamic motor tasks.

Using Raw Accelerometer Data to Predict High-Impact Mechanical Loading

The purpose of this study was to develop peak ground reaction force (pGRF) and peak loading rate (pLR) prediction equations for high-impact activities in adult subjects with a broad range of body masses, from normal weight to severe obesity. A total of 78 participants (27 males; 82.4 ± 20.6 kg) completed a series of trials involving jumps of different types and heights on force plates while wearing accelerometers at the ankle, lower back, and hip. Regression equations were developed to predict pGRF and pLR from accelerometry data. Leave-one-out cross-validation was used to calculate prediction accuracy and Bland-Altman plots. Body mass was a predictor in all models, along with peak acceleration in the pGRF models and peak acceleration rate in the pLR models. The equations to predict pGRF had a coefficient of determination (R²) of at least 0.83, and a mean absolute percentage error (MAPE) below 14.5%, while the R² for the pLR prediction equations was at least 0.87 and the highest MAPE was 24.7%. Jumping pGRF can be accurately predicted through accelerometry data, enabling the continuous assessment of mechanical loading in clinical settings. The pLR prediction equations yielded a lower accuracy when compared to the pGRF equations.

Surrogate Modelling for Oxygen Uptake Prediction Using LSTM Neural Network

Oxygen uptake (V˙O2) is an important metric in any exercise test including walking and running. It can be measured using portable spirometers or metabolic analyzers. Those devices are, however, not suitable for constant use by consumers due to their costs, difficulty of operation and their intervening in the physical integrity of their users. Therefore, it is important to develop approaches for the indirect estimation of V˙O2-based measurements of motion parameters, heart rate data and application-specific measurements from consumer-grade sensors. Typically, these approaches are based on linear regression models or neural networks. This study investigates how motion data contribute to V˙O2 estimation accuracy during unconstrained running and walking. The results suggest that a long short term memory (LSTM) neural network can predict oxygen consumption with an accuracy of 2.49 mL/min/kg (95% limits of agreement) based only on speed, speed change, cadence and vertical oscillation measurements from an inertial navigation system combined with a Global Positioning System (INS/GPS) device developed by our group, worn on the torso. Combining motion data and heart rate data can significantly improve the V˙O2 estimation resulting in approximately 1.7-1.9 times smaller prediction errors than using only motion or heart rate data.

Inertial Sensor Location for Ground Reaction Force and Gait Event Detection Using Reservoir Computing in Gait

Inertial measurement units (IMUs) have shown promising outcomes for estimating gait event detection (GED) and ground reaction force (GRF). This study aims to determine the best sensor location for GED and GRF prediction in gait using data from IMUs for healthy and medial knee osteoarthritis (MKOA) individuals. In this study, 27 healthy and 18 MKOA individuals participated. Participants walked at different speeds on an instrumented treadmill. Five synchronized IMUs (Physilog®, 200 Hz) were placed on the lower limb (top of the shoe, heel, above medial malleolus, middle and front of tibia, and on medial of shank close to knee joint). To predict GRF and GED, an artificial neural network known as reservoir computing was trained using combinations of acceleration signals retrieved from each IMU. For GRF prediction, the best sensor location was top of the shoe for 72.2% and 41.7% of individuals in the healthy and MKOA populations, respectively, based on the minimum value of the mean absolute error (MAE). For GED, the minimum MAE value for both groups was for middle and front of tibia, then top of the shoe. This study demonstrates that top of the shoe is the best sensor location for GED and GRF prediction.

Real-world measurements of ground reaction forces of normal gait of young adults wearing various footwear

For years, researchers have been recognizing patterns in gait for purposes of medical diagnostics, rehabilitation, and biometrics. A method for observing gait is to measure ground reaction forces (GRFs) between the foot and solid plate with tension sensors. The presented dataset consists of 13,702 measurements of bipedal GRFs of one step of normal gait of 324 students wearing shoes of various types. Each measurement includes raw digital signals of two force plates. A signal comprises stance-related samples but also preceding and following ones, in which one can observe noise, interferences, and artifacts caused by imperfections of devices and walkway. Such real-world time series can be used to study methods for detecting foot-strike and foot-off events, and for coping with artifacts. For user convenience, processed data are also available, which describe only the stance phase of gait and form ready-to-use patterns suitable for experiments in GRF-based recognition of persons and footwear, and for generating synthetic GRF waveforms. The dataset is accompanied by Matlab and Python programs for organizing and validating data.

Predicting Vertical Ground Reaction Forces in Running from the Sound of Footsteps

From the point of view of measurement, footstep sounds represent a simple, wearable and inexpensive sensing opportunity to assess running biomechanical parameters. Therefore, the aim of this study was to investigate whether the sounds of footsteps can be used to predict the vertical ground reaction force profiles during running. Thirty-seven recreational runners performed overground running, and their sounds of footsteps were recorded from four microphones, while the vertical ground reaction force was recorded using a force plate. We generated nine different combinations of microphone data, ranging from individual recordings up to all four microphones combined. We trained machine learning models using these microphone combinations and predicted the ground reaction force profiles by a leave-one-out approach on the subject level. There were no significant differences in the prediction accuracy between the different microphone combinations (p < 0.05). Moreover, the machine learning model was able to predict the ground reaction force profiles with a mean Pearson correlation coefficient of 0.99 (range 0.79−0.999), mean relative root-mean-square error of 9.96% (range 2−23%) and mean accuracy to define rearfoot or forefoot strike of 77%. Our results demonstrate the feasibility of using the sounds of footsteps in combination with machine learning algorithms based on Fourier transforms to predict the ground reaction force curves. The results are encouraging in terms of the opportunity to create wearable technology to assess the ground reaction force profiles for runners in the interests of injury prevention and performance optimization.

Predicting vertical ground reaction forces from 3D accelerometry using reservoir computers leads to accurate gait event detection

Accelerometers are low-cost measurement devices that can readily be used outside the lab. However, determining isolated gait events from accelerometer signals, especially foot-off events during running, is an open problem. We outline a two-step approach where machine learning serves to predict vertical ground reaction forces from accelerometer signals, followed by force-based event detection. We collected shank accelerometer signals and ground reaction forces from 21 adults during comfortable walking and running on an instrumented treadmill. We trained one common reservoir computer using segmented data using both walking and running data. Despite being trained on just a small number of strides, this reservoir computer predicted vertical ground reaction forces in continuous gait with high quality. The subsequent foot contact and foot off event detection proved highly accurate when compared to the gold standard based on co-registered ground reaction forces. Our proof-of-concept illustrates the capacity of combining accelerometry with machine learning for detecting isolated gait events irrespective of mode of locomotion.

Detecting mechanical breakpoints during treadmill-based graded exercise test: Relationships to ventilatory thresholds

BACKGROUND

While changes in cardiorespiratory variables during graded exercise tests (GXTs) are well described, less is known about running mechanical alterations.

PURPOSE

We determined mechanical breakpoints during GXT and compared their temporal location with thresholds in ventilation.

METHODS

Thirty-one recreational male runners completed continuous GXT on an instrumented treadmill, starting at 2.5 m.s^-1 with velocity increases of + 0.14 m.s^-1 every 30 s. Subsequently, the first and second ventilatory thresholds (VT1 and VT2) were determined from expired gases. Spatio-temporal and antero-posterior force variables, and spring-mass model characteristics were averaged for each stage. Mechanical breakpoints were detected using a linear fit process that partitioned the timeseries into two regions and minimised the error sum of squares. All measurements were normalised to % GXT duration for subsequent comparisons.

RESULTS

Fifteen out of 16 mechanical variables (all except leg stiffness) displayed breakpoints occurring between 61.9% and 82.3% of GXT duration; these occurred significantly later than VT1 (46.9 ± 6.4% of GXT duration, p < 0.05). Mechanical breakpoints for eight variables (step frequency, aerial time, step length, peak push-off force, braking impulse, peak vertical force, maximal downward vertical displacement and leg compression) occurred at a time point not different to VT2 (75.3 ± 6.2% of GXT duration; all p > 0.05). Relationships between mechanical breakpoints and either VT1 or VT2 were weak (all r < 0.25).

CONCLUSION

During treadmill GXT, breakpoints can be detected for the vast majority of mechanical variables (except leg stiffness), yet these are not related with ventilatory thresholds.