Analysis of human ambulation as a chaotic time-series: with nonlinear dynamics tools.

The aim of the present study is to investigate the complexity and stability of human ambulation and the implications on robotic prostheses control systems. Fourteen healthy individuals participate in two experiments, the first group run at three different speeds. The second group ascended and descended stairs of a five-level building block at a self-selected speed. All participants completed the experiment with seven inertial measurement units wrapped around the lower body segments and waist. The data were analyzed to determine the fractal dimension, spectral entropy, and the Lyapunov exponent (LyE). Two methods were used to calculate the long-term LyE, first LyE calculated using the full size of data sets. And the embedding dimensions were calculated using Average Mutual Information (AMI) and the False Nearest Neighbor (FNN) algorithm was used to find the time delay. Besides, a second approach was developed to find long-term LyE where the time delay was based on the average period of the gait cycle using adaptive event-based window. The average values of spectral entropy are 0.538 and 0.575 for stairs ambulation and running, respectively. The degree of uncertainty and complexity increases with the ambulation speed. The short term LyEs for tibia orientation have the minimum range of variation when it comes to stairs ascent and descent. Using two-way analysis of variance we demonstrated the effect of the ambulation speed and type of ambulation on spectral entropy. Moreover, it was shown that the fractal dimension only changed significantly with ambulation speed.

Using Video Technology and AI within Parkinson's Disease Free-Living Fall Risk Assessment.

Falls are a major concern for people with Parkinson's disease (PwPD), but accurately assessing real-world fall risk beyond the clinic is challenging. Contemporary technologies could enable the capture of objective and high-resolution data to better inform fall risk through measurement of everyday factors (e.g., obstacles) that contribute to falls. Wearable inertial measurement units (IMUs) capture objective high-resolution walking/gait data in all environments but are limited by not providing absolute clarity on contextual information (i.e., obstacles) that could greatly influence how gait is interpreted. Video-based data could compliment IMU-based data for a comprehensive free-living fall risk assessment. The objective of this study was twofold. First, pilot work was conducted to propose a novel artificial intelligence (AI) algorithm for use with wearable video-based eye-tracking glasses to compliment IMU gait data in order to better inform free-living fall risk in PwPD. The suggested approach (based on a fine-tuned You Only Look Once version 8 (YOLOv8) object detection algorithm) can accurately detect and contextualize objects (mAP50 = 0.81) in the environment while also providing insights into where the PwPD is looking, which could better inform fall risk. Second, we investigated the perceptions of PwPD via a focus group discussion regarding the adoption of video technologies and AI during their everyday lives to better inform their own fall risk. This second aspect of the study is important as, traditionally, there may be clinical and patient apprehension due to ethical and privacy concerns on the use of wearable cameras to capture real-world video. Thematic content analysis was used to analyse transcripts and develop core themes and categories. Here, PwPD agreed on ergonomically designed wearable video-based glasses as an optimal mode of video data capture, ensuring discreteness and negating any public stigma on the use of research-style equipment. PwPD also emphasized the need for control in AI-assisted data processing to uphold privacy, which could overcome concerns with the adoption of video to better inform IMU-based gait and free-living fall risk. Contemporary technologies (wearable video glasses and AI) can provide a holistic approach to fall risk that PwPD recognise as helpful and safe to use.

Predicting Knee Joint Contact Force Peaks During Gait Using a Video Camera or Wearable Sensors.

PURPOSE: Estimating loading of the knee joint may be helpful in managing degenerative joint diseases. Contemporary methods to estimate loading involve calculating knee joint contact forces using musculoskeletal modeling and simulation from motion capture (MOCAP) data, which must be collected in a specialized environment and analyzed by a trained expert. To make the estimation of knee joint loading more accessible, simple input predictors should be used for predicting knee joint loading using artificial neural networks. METHODS: We trained feedforward artificial neural networks (ANNs) to predict knee joint loading peaks from the mass, height, age, sex, walking speed, and knee flexion angle (KFA) of subjects using their existing MOCAP data. We also collected an independent MOCAP dataset while recording walking with a video camera (VC) and inertial measurement units (IMUs). We quantified the prediction accuracy of the ANNs using walking speed and KFA estimates from (1) MOCAP data, (2) VC data, and (3) IMU data separately (i.e., we quantified three sets of prediction accuracy metrics). RESULTS: Using portable modalities, we achieved prediction accuracies between 0.13 and 0.37 root mean square error normalized to the mean of the musculoskeletal analysis-based reference values. The correlation between the predicted and reference loading peaks varied between 0.65 and 0.91. This was comparable to the prediction accuracies obtained when obtaining predictors from motion capture data. DISCUSSION: The prediction results show that both VCs and IMUs can be used to estimate predictors that can be used in estimating knee joint loading outside the motion laboratory. Future studies should investigate the usability of the methods in an out-of-laboratory setting.

Mechanical Deviations in Stride Characteristics During Running in the Severe Intensity Domain Are Associated With a Decline in Muscle Oxygenation.

We explored the impact of running in the severe intensity domain on running mechanics and muscle oxygenation in competitive runners by investigating the relationship between mechanical deviations from typical stride characteristics and muscle oxygen saturation (SmO2) in the quadriceps muscle. Sixteen youth competitive runners performed an 8-min exhaustive running test on an outdoor track. Running mechanics were continuously monitored using inertial measurement units. Rectus femoris SmO2 and total hemoglobin (a measure of blood volume) were continuously monitored by near-infrared spectroscopy. One-class support vector machine (OCSVM) modeling was employed for subject-specific analysis of the kinematic data. Statistical analysis included principal component analysis, ANOVA, and correlation analysis. Mechanical deviations from typical stride characteristics increased as the running test progressed. Specifically, the percentage of outliers in the OCSVM model rose gradually from 2.2 ± 0.8% at the start to 43.6 ± 28.2% at the end (p < 0.001, mean ± SD throughout). SmO2 dropped from 74.3 ± 8.4% at baseline to 10.1 ± 6.8% at the end (p < 0.001). A moderate negative correlation (r = -0.61, p = 0.013) was found between the average SmO2 and the percentage of outlier strides during the last 15% of the run. During high-intensity running, alterations in running biomechanics may occur, linked to decreased quadriceps muscle oxygenation. These parameters highlight the potential of using running kinematics and muscle oxygenation in training to optimize performance and reduce injury risks. Our research contributes to understanding biomechanical and physiological responses to endurance running and emphasizes the importance of individualized monitoring.

Kinematics-Based Predictions of External Loads during Handcycling.

The increased risk of cardiovascular disease in people with spinal cord injuries motivates work to identify exercise options that improve health outcomes without causing risk of musculoskeletal injury. Handcycling is an exercise mode that may be beneficial for wheelchair users, but further work is needed to establish appropriate guidelines and requires assessment of the external loads. The goal of this research was to predict the six-degree-of-freedom external loads during handcycling from data similar to those which can be measured from inertial measurement units (segment accelerations and velocities) using machine learning. Five neural network models and two ensemble models were compared against a statistical model. A temporal convolutional network (TCN) yielded the best predictions. Predictions of forces and moments in-plane with the crank were the most accurate (r = 0.95-0.97). The TCN model could predict external loads during activities of different intensities, making it viable for different exercise protocols. The ability to predict the loads associated with forward propulsion using wearable-type data enables the development of informed exercise guidelines.

Algorithm Validation for Quantifying ActiGraph™ Physical Activity Metrics in Individuals with Chronic Low Back Pain and Healthy Controls.

Assessing physical activity is important in the treatment of chronic conditions, including chronic low back pain (cLBP). ActiGraph™, a widely used physical activity monitor, collects raw acceleration data, and processes these data through proprietary algorithms to produce physical activity measures. The purpose of this study was to replicate ActiGraph™ algorithms in MATLAB and test the validity of this method with both healthy controls and participants with cLBP. MATLAB code was developed to replicate ActiGraph™'s activity counts and step counts algorithms, to sum the activity counts into counts per minute (CPM), and categorize each minute into activity intensity cut points. A free-living validation was performed where 24 individuals, 12 cLBP and 12 healthy, wore an ActiGraph™ GT9X on their non-dominant hip for up to seven days. The raw acceleration data were processed in both ActiLife™ (v6), ActiGraph™'s data analysis software platform, and through MATLAB (2022a). Percent errors between methods for all 24 participants, as well as separated by cLBP and healthy, were all less than 2%. ActiGraph™ algorithms were replicated and validated for both populations, based on minimal error differences between ActiLife™ and MATLAB, allowing researchers to analyze data from any accelerometer in a manner comparable to ActiLife™.

Validation of inertial measurement units based on waveform similarity assessment against a photogrammetry system for gait kinematic analysis.

When assessing gait analysis outcomes for clinical use, it is indispensable to use an accurate system ensuring a minimal measurement error. Inertial Measurement Units (IMUs) are a versatile motion capture system to evaluate gait kinematics during out-of-lab activities and technology-assisted rehabilitation therapies. However, IMUs are susceptible to distortions, offset and drifting. Therefore, it is important to have a validated instrumentation and recording protocol to ensure the reliability of the measurements, to differentiate therapy effects from system-induced errors. A protocol was carried out to validate the accuracy of gait kinematic assessment with IMUs based on the similarity of the waveform of concurrent signals captured by this system and by a photogrammetry reference system. A gait database of 32 healthy subjects was registered synchronously with both devices. The validation process involved two steps: 1) a preliminary similarity assessment using the Pearson correlation coefficient, and 2) a similarity assessment in terms of correlation, displacement and gain by estimating the offset between signals, the difference between the registered range of motion (∆ROM), the root mean square error (RMSE) and the interprotocol coefficient of multiple correlation (CMCP). Besides, the CMCP was recomputed after removing the offset between signals (CMCPoff). The correlation was strong (r > 0.75) for both limbs for hip flexion/extension, hip adduction/abduction, knee flexion/extension and ankle dorsal/plantar flexion. These joint movements were studied in the second part of the analysis. The ∆ROM values obtained were smaller than 6°, being negligible relative to the minimally clinically important difference (MCID) estimated for unaffected limbs, and the RMSE values were under 10°. The offset for hips and ankles in the sagittal plane reached -9° and -8°, respectively, whereas hips adduction/abduction and knees flexion/extension were around 1°. According to the CMCP, the kinematic pattern of hip flexion/extension (CMCP > 0.90) and adduction/abduction (CMCP > 0.75), knee flexion/extension (CMCP > 0.95) and ankle dorsi/plantar flexion (CMCP > 0.90) were equivalent when captured by each system synchronously. However, after offset correction, only hip flexion/extension (CMCPoff = 1), hip adduction/abduction (CMCPoff > 0.85) and knee flexion/extension (CMCPoff > 0.95) satisfied the conditions to be considered similar.

Tai Chi Movement Recognition and Precise Intervention for the Elderly Based on Inertial Measurement Units and Temporal Convolutional Neural Networks.

(1) Background: The objective of this study was to recognize tai chi movements using inertial measurement units (IMUs) and temporal convolutional neural networks (TCNs) and to provide precise interventions for elderly people. (2) Methods: This study consisted of two parts: firstly, 70 skilled tai chi practitioners were used for movement recognition; secondly, 60 elderly males were used for an intervention study. IMU data were collected from skilled tai chi practitioners performing Bafa Wubu, and TCN models were constructed and trained to classify these movements. Elderly participants were divided into a precision intervention group and a standard intervention group, with the former receiving weekly real-time IMU feedback. Outcomes measured included balance, grip strength, quality of life, and depression. (3) Results: The TCN model demonstrated high accuracy in identifying tai chi movements, with percentages ranging from 82.6% to 94.4%. After eight weeks of intervention, both groups showed significant improvements in grip strength, quality of life, and depression. However, only the precision intervention group showed a significant increase in balance and higher post-intervention scores compared to the standard intervention group. (4) Conclusions: This study successfully employed IMU and TCN to identify Tai Chi movements and provide targeted feedback to older participants. Real-time IMU feedback can enhance health outcome indicators in elderly males.

Risk Factors Associated with Musculoskeletal Injuries within the Crew of the Leopard 2 A6 Main Battle Tank Using Inertial Movement Unit Sensors: A Pilot Study.

This study aims to assess the musculoskeletal risk of military personnel on a Leopard 2 A6 main battle tank crew and to identify associated factors for future prevention and mitigation strategies. A sample of 57 Portuguese military personnel, who are or were part of the Leopard 2 A6 main battle tank crew, answered a questionnaire on their perception of task performance, considering muscle demands, comfort, posture, movements, and associated symptoms. A subsample of four soldiers from the Armoured Squadron of the Portuguese Mechanized Brigade were assessed using an inertial measurement unit system and underwent a whole-body kinematic analysis coupled with a Rapid Entire Body Assessment during a simulated two-hour mission. The results indicate that soldiers accurately perceive their roles within the crew and that, overall, there is a high risk of musculoskeletal injuries in all tasks. However, tasks directly related to the crew's primary duties carry consistently high risk when considering the time spent on their tasks. This study highlights the need for targeted preventive measures to reduce the incidence and severity of injuries among the crew of the Leopard 2 A6 main battle tank.

IMU Data-Driven and PCA-Based Approach to Establish Quantifiable and Practically Applicable Measures for V2 Technique Elements in Cross-Country Skiing.

Quantifying movement coordination in cross-country (XC) skiing, specifically the technique with its elemental forms, is challenging. Particularly, this applies when trying to establish a bidirectional transfer between scientific theory and practical experts' knowledge as expressed, for example, in ski instruction curricula. The objective of this study was to translate 14 curricula-informed distinct elements of the V2 ski-skating technique (horizontal and vertical posture, lateral tilt, head position, upper body rotation, arm swing, shoulder abduction, elbow flexion, hand and leg distance, plantar flexion, ski set-down, leg push-off, and gliding phase) into plausible, valid and applicable measures to make the technique training process more quantifiable and scientifically grounded. Inertial measurement unit (IMU) data of 10 highly experienced XC skiers who demonstrated the technique elements by two extreme forms each (e.g., anterior versus posterior positioning for the horizontal posture) were recorded. Element-specific principal component analyses (PCAs)-driven by the variance produced by the technique extremes-resulted in movement components that express quantifiable measures of the underlying technique elements. Ten measures were found to be sensitive in distinguishing between the inputted extreme variations using statistical parametric mapping (SPM), whereas for four elements the SPM did not detect differences (lateral tilt, plantar flexion, ski set-down, and leg push-off). Applicability of the established technique measures was determined based on quantifying individual techniques through them. The study introduces a novel approach to quantitatively assess V2 ski-skating technique, which might help to enhance technique feedback and bridge the communication gap that often exists between practitioners and scientists.

A Novel IMU-Based System for Work-Related Musculoskeletal Disorders Risk Assessment.

This study introduces a novel wearable Inertial Measurement Unit (IMU)-based system for an objective and comprehensive assessment of Work-Related Musculoskeletal Disorders (WMSDs), thus enhancing workplace safety. The system integrates wearable technology with a user-friendly interface, providing magnetometer-free orientation estimation, joint angle measurements, and WMSDs risk evaluation. Tested in a cable manufacturing facility, the system was evaluated with ten female employees. The evaluation involved work cycle identification, inter-subject comparisons, and benchmarking against standard WMSD risk assessments like RULA, REBA, Strain Index, and Rodgers Muscle Fatigue Analysis. The evaluation demonstrated uniform joint patterns across participants (ICC=0.72±0.23) and revealed a higher occurrence of postures warranting further investigation, which is not easily detected by traditional methods such as RULA. The experimental results showed that the proposed system's risk assessments closely aligned with the established methods and enabled detailed and targeted risk assessments, pinpointing specific bodily areas for immediate ergonomic interventions. This approach not only enhances the detection of ergonomic risks but also supports the development of personalized intervention strategies, addressing common workplace issues such as tendinitis, low back pain, and carpal tunnel syndrome. The outcomes highlight the system's sensitivity and specificity in identifying ergonomic hazards. Future efforts should focus on broader validation and exploring the relative influence of various WMSDs risk factors to refine risk assessment and intervention strategies for improved applicability in occupational health.

Using Inertial Measurement Units to Examine Selected Joint Kinematics in a Road Cycling Sprint: A Series of Single Cases.

Sprinting plays a significant role in determining the results of road cycling races worldwide. However, currently, there is a lack of systematic research into the kinematics of sprint cycling, especially in an outdoor, environmentally valid setting. This study aimed to describe selected joint kinematics during a cycling sprint outdoors. Three participants were recorded sprinting over 60 meters in both standing and seated sprinting positions on an outdoor course with a baseline condition of seated cycling at 20 km/h. The participants were recorded using array-based inertial measurement units to collect joint excursions of the upper and lower limbs including the trunk. A high-rate GPS unit was used to record velocity during each recorded condition. Kinematic data were analyzed in a similar fashion to running gait, where multiple pedal strokes were identified, delineated, and averaged to form a representative (average ± SD) waveform. Participants maintained stable kinematics in most joints studied during the baseline condition, but variations in ranges of movement were recorded during seated and standing sprinting. Discernable patterns started to emerge for several kinematic profiles during standing sprinting. Alternate sprinting strategies emerged between participants and bilateral asymmetries were also recorded in the individuals tested. This approach to studying road cycling holds substantial potential for researchers wishing to explore this sport.

Spatiotemporal Gait Analysis of Patients with Spinocerebellar Ataxia Types 3 and 10 Using Inertial Measurement Units: A Comparative Study.

Given the high morbidity related to the progression of gait deficits in spinocerebellar ataxias (SCA), there is a growing interest in identifying biomarkers that can guide early diagnosis and rehabilitation. Spatiotemporal parameter (STP) gait analysis using inertial measurement units (IMUs) has been increasingly studied in this context. This study evaluated STP profiles in SCA types 3 and 10, compared them to controls, and correlated them with clinical scales. IMU portable sensors were used to measure STPs under four gait conditions: self-selected pace (SSP), fast pace (FP), fast pace checking-boxes (FPCB), and fast pace with serial seven subtractions (FPS7). Compared to healthy subjects, both SCA groups had higher values for step time, variability, and swing time, with lower values for gait speed, cadence, and step length. We also found a reduction in speed gain capacity in both SCA groups compared to controls and an increase in speed dual-task cost in the SCA10 group. However, there were no significant differences between the SCA groups. Swing time, mean speed, and step length were correlated with disease severity, risk of falling and functionality in both clinical groups. In the SCA3 group, fear of falling was correlated with cadence. In the SCA10 group, results of the Montreal cognitive assessment test were correlated with step time, mean speed, and step length. These results show that individuals with SCA3 and SCA10 present a highly variable, short-stepped, slow gait pattern compared to healthy subjects, and their gait quality worsened with a fast pace and dual-task involvement.

Acute effect of dry needling on trunk kinematics and balance of patients with non-specific low back pain.

BACKGROUND: Limited knowledge exists about the effectiveness of dry needling (DN) concerning the torso kinematics in patients with non-specific low back pain (NS-LBP). Acute effects of DN in NS-LBP patients from a functional perspective were investigated. METHODS: Sixteen NS-LBP patients and 11 healthy individuals (HG) were examined. NS-LBP patients received a single session of DN at the lumbar region. Baseline and immediate post-treatment measurements during flexion-extension and lateral bending of the trunk were conducted for the NS-LBP patients. HG were measured only at baseline to be used as a reference of NS-LBP patients' initial condition. Algometry was applied in NS-LBP patients. Centre of pressure, range of motion of the trunk and its' derivatives were obtained. FINDINGS: HG performed significantly faster, smoother and with greater mobility in the performed tasks compared to the pre intervention measurements of the NS-LBP patients. For the NS-LBP patients, significant greater angular velocity in frontal plane and significant lower jerk in the sagittal plane were demonstrated post intervention. DN alleviated pain tolerance significantly at the L5 level. Regarding the effectiveness of the DN upon spine kinematics, their derivatives were more sensitive. INTERPRETATION: It appeared that the pathological type of torso movement was acutely affected by DN. NS-LBP patients showcased smoother movement immediately after the intervention and better control as imprinted in the higher derivative of motion although range of motion did not improve. This quantitative variable may not be subjected to acute effects of DN but rather need additional time and training to be improved.

Erratum: Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations.

[This corrects the article DOI: 10.3389/fbioe.2024.1285845.].

The Validity and Reliability of a Real-Time Biofeedback System for Lumbopelvic Control Training in Baseball Players.

BACKGROUND: This study validates real-time biofeedback for lumbopelvic control training in baseball. The lumbopelvic region is crucial for generating kinetic energy in pitching. Real-time biofeedback enhances training effectiveness and reduces injury risk. The validity and reliability of this system were examined. PURPOSE: This study was to investigate the validity and reliability of the real-time biofeedback system for lumbopelvic control training. METHODS: Twelve baseball players participated in this study, with data collected in two sessions separated by a week. All participants needed to do the lateral slide exercise and single-leg squat exercise in each session. Pelvic angles detected by the real-time biofeedback system were compared to the three-dimensional motion capture system (VICON) during training sessions. Additionally, pelvic angles measured by the biofeedback system were compared between the two training sessions. RESULTS: The real-time biofeedback system exhibited moderate to strong correlations with VICON in both exercises: lateral slide exercise (r = 0.66-0.88, p < 0.05) and single-leg squat exercise (r = 0.70-0.85, p < 0.05). Good to excellent reliability was observed between the first and second sessions for both exercises: lateral slide exercise (ICC = 0.76-0.97) and single-leg squat exercise (ICC = 0.79-0.90). CONCLUSIONS: The real-time biofeedback system for lumbopelvic control training, accurately providing the correct pelvic angle during training, could enhance training effectiveness.

3D gait analysis in children using wearable sensors: feasibility of predicting joint kinematics and kinetics with personalized machine learning models and inertial measurement units.

Introduction: Children's walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models' performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models' performance, 3) Finding the optimal number of IMUs required for accurate predictions. Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates' data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target's ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet. Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent. Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.

Beyond gait speed: exploring the added value of Inertial Measurement Unit-based measurements of gait in the estimation of the walking ability in daily life.

BACKGROUND: Gait speed is often used to estimate the walking ability in daily life in people after stroke. While measuring gait with inertial measurement units (IMUs) during clinical assessment yields additional information, it remains unclear if this information can improve the estimation of the walking ability in daily life beyond gait speed. OBJECTIVE: We evaluated the additive value of IMU-based gait features over a simple gait-speed measurement in the estimation of walking ability in people after stroke. METHODS: Longitudinal data during clinical stroke rehabilitation were collected. The assessment consisted of two parts and was administered every three weeks. In the first part, participants walked for two minutes (2MWT) on a fourteen-meter path with three IMUs attached to low back and feet, from which multiple gait features, including gait speed, were calculated. The dimensionality of the corresponding gait features was reduced with a principal component analysis. In the second part, gait was measured for two consecutive days using one ankle-mounted IMU. Next, three measures of walking ability in daily life were calculated, including the number of steps per day, and the average and maximal gait speed. A gait-speed-only Linear Mixed Model was used to estimate the association between gait speed and each of the three measures of walking ability. Next, the principal components (PC), derived from the 2MWT, were added to the gait-speed-only model to evaluate if they were confounders or effect modifiers. RESULTS: Eighty-one participants were measured during rehabilitation, resulting in 198 2MWTs and 135 corresponding walking-performance measurements. 106 Gait features were reduced to nine PCs with 85.1% explained variance. The linear mixed models demonstrated that gait speed was weakly associated with the average and maximum gait speed in daily life and moderately associated with the number of steps per day. The PCs did not considerably improve the outcomes in comparison to the gait speed only models. CONCLUSIONS: Gait in people after stroke assessed in a clinical setting with IMUs differs from their walking ability in daily life. More research is needed to determine whether these discrepancies also occur in non-laboratory settings, and to identify additional non-gait factors that influence walking ability in daily life.

Pattern analysis using lower body human walking data to identify the gaitprint.

All people have a fingerprint that is unique to them and persistent throughout life. Similarly, we propose that people have a gaitprint, a persistent walking pattern that contains unique information about an individual. To provide evidence of a unique gaitprint, we aimed to identify individuals based on basic spatiotemporal variables. 81 adults were recruited to walk overground on an indoor track at their own pace for four minutes wearing inertial measurement units. A total of 18 trials per participant were completed between two days, one week apart. Four methods of pattern analysis, a) Euclidean distance, b) cosine similarity, c) random forest, and d) support vector machine, were applied to our basic spatiotemporal variables such as step and stride lengths to accurately identify people. Our best accuracy (98.63%) was achieved by random forest, followed by support vector machine (98.40%), and the top 10 most similar trials from cosine similarity (98.40%). Our results clearly demonstrate a persistent walking pattern with sufficient information about the individual to make them identifiable, suggesting the existence of a gaitprint.

Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations.

Portable measurement systems using inertial sensors enable motion capture outside the lab, facilitating longitudinal and large-scale studies in natural environments. However, estimating 3D kinematics and kinetics from inertial data for a comprehensive biomechanical movement analysis is still challenging. Machine learning models or stepwise approaches performing Kalman filtering, inverse kinematics, and inverse dynamics can lead to inconsistencies between kinematics and kinetics. We investigated the reconstruction of 3D kinematics and kinetics of arbitrary running motions from inertial sensor data using optimal control simulations of full-body musculoskeletal models. To evaluate the feasibility of the proposed method, we used marker tracking simulations created from optical motion capture data as a reference and for computing virtual inertial data such that the desired solution was known exactly. We generated the inertial tracking simulations by formulating optimal control problems that tracked virtual acceleration and angular velocity while minimizing effort without requiring a task constraint or an initial state. To evaluate the proposed approach, we reconstructed three trials each of straight running, curved running, and a v-cut of 10 participants. We compared the estimated inertial signals and biomechanical variables of the marker and inertial tracking simulations. The inertial data was tracked closely, resulting in low mean root mean squared deviations for pelvis translation (≤20.2 mm), angles (≤1.8 deg), ground reaction forces (≤1.1 BW%), joint moments (≤0.1 BWBH%), and muscle forces (≤5.4 BW%) and high mean coefficients of multiple correlation for all biomechanical variables (≥0.99). Accordingly, our results showed that optimal control simulations tracking 3D inertial data could reconstruct the kinematics and kinetics of individual trials of all running motions. The simulations led to mutually and dynamically consistent kinematics and kinetics, which allows researching causal chains, for example, to analyze anterior cruciate ligament injury prevention. Our work proved the feasibility of the approach using virtual inertial data. When using the approach in the future with measured data, the sensor location and alignment on the segment must be estimated, and soft-tissue artifacts are potential error sources. Nevertheless, we demonstrated that optimal control simulation tracking inertial data is highly promising for estimating 3D kinematics and kinetics for a comprehensive biomechanical analysis.