Gutenberg Gait Database, a ground reaction force database of level overground walking in healthy individuals

Synergy in motion: Exploring the similarity and variability of muscle synergy patterns in healthy individuals

BACKGROUND

Recent studies suggest that muscle synergy patterns can be a guide for diagnosis and rehabilitation.

RESEARCH QUESTION

Does human's lower limb synergy pattern significantly change with changes in walking speed? Are there large differences in synergy patterns among different healthy individuals?

METHODS

22 healthy subjects from an open-source datasets were included. Non-negative matrix factorization was applied to identify the module composition of surface electromyography(sEMG) data, and the similarity index was adopted to quantify the overall similarity between synergy patterns.

RESULTS

Results demonstrated that healthy individuals have their own intrinsic muscle recruitment and coordination characteristics for locomotion at various speeds, additionally, their synergy patterns exhibit predictability under speed variations.

SIGNIFICANCE

This study develop reference synergy patterns for the lower limbs across 28 different walking speeds. The developed synergy patterns and the above findings may guide the study of gait synergy in rehabilitation and assistance.

The effect of time normalization and biomechanical signal processing techniques of ground reaction force curves on deep-learning model performance

Time-series data are common in biomechanical studies. These data often undergo pre-processing steps such as time normalization or filtering prior to use in further analyses, including deep-learning classification. In this context, it remains unclear how these preprocessing steps affect deep-learning model performance. Thus, the aim of this study is to assess the effect of time-normalization and filtering on the performance of deep-learning classification models. We also investigated the effect of amplitude scaling. Using a public dataset (Gutenburg Gait Database, a ground reaction force database of level overground walking at self-selected walking speed involving 350 healthy individuals), we trained convolutional neural network (CNN) and long short-term memory (LSTM) models to predict binary sex (male, female) using three-dimensional ground-reaction forces to which we applied different processing approaches: zero padding, interpolation to 100% of signal, filtering, and scaling (min-max, body mass). The results show that transformations resulted in differences in model performances. Highest performance was obtained using unfiltered data, zero-padding, and min-max amplitude scaling (F1-score of 91 and 87% for CNN and LSTM, respectively). Not filtering data and using min-max scaling generally improve performance for both model architectures. For interpolation, results are not consistent across model architectures. This study suggests that processing steps must be considered in applications where deep-learning classification performance is relevant.

Quantifying walking speeds in relation to ankle biomechanics on a real-time interactive gait platform: a musculoskeletal modeling approach in healthy adults

Background: Given the inherent variability in walking speeds encountered in day-to-day activities, understanding the corresponding alterations in ankle biomechanics would provide valuable clinical insights. Therefore, the objective of this study was to examine the influence of different walking speeds on biomechanical parameters, utilizing gait analysis and musculoskeletal modelling. Methods: Twenty healthy volunteers without any lower limb medical history were included in this study. Treadmill-assisted gait-analysis with walking speeds of 0.8 m/s and 1.1 m/s was performed using the Gait Real-time Analysis Interactive Lab (GRAIL®). Collected kinematic data and ground reaction forces were processed via the AnyBody® modeling system to determine ankle kinetics and muscle forces of the lower leg. Data were statistically analyzed using statistical parametric mapping to reveal both spatiotemporal and magnitude significant differences. Results: Significant differences were found for both magnitude and spatiotemporal curves between 0.8 m/s and 1.1 m/s for the ankle flexion (p < 0.001), subtalar force (p < 0.001), ankle joint reaction force and muscles forces of the M. gastrocnemius, M. soleus and M. peroneus longus (α = 0.05). No significant spatiotemporal differences were found between 0.8 m/s and 1.1 m/s for the M. tibialis anterior and posterior. Discussion: A significant impact on ankle joint kinematics and kinetics was observed when comparing walking speeds of 0.8 m/s and 1.1 m/s. The findings of this study underscore the influence of walking speed on the biomechanics of the ankle. Such insights may provide a biomechanical rationale for several therapeutic and preventative strategies for ankle conditions.

Enhancing biomechanical machine learning with limited data: generating realistic synthetic posture data using generative artificial intelligence

Objective: Biomechanical Machine Learning (ML) models, particularly deep-learning models, demonstrate the best performance when trained using extensive datasets. However, biomechanical data are frequently limited due to diverse challenges. Effective methods for augmenting data in developing ML models, specifically in the human posture domain, are scarce. Therefore, this study explored the feasibility of leveraging generative artificial intelligence (AI) to produce realistic synthetic posture data by utilizing three-dimensional posture data. Methods: Data were collected from 338 subjects through surface topography. A Variational Autoencoder (VAE) architecture was employed to generate and evaluate synthetic posture data, examining its distinguishability from real data by domain experts, ML classifiers, and Statistical Parametric Mapping (SPM). The benefits of incorporating augmented posture data into the learning process were exemplified by a deep autoencoder (AE) for automated feature representation. Results: Our findings highlight the challenge of differentiating synthetic data from real data for both experts and ML classifiers, underscoring the quality of synthetic data. This observation was also confirmed by SPM. By integrating synthetic data into AE training, the reconstruction error can be reduced compared to using only real data samples. Moreover, this study demonstrates the potential for reduced latent dimensions, while maintaining a reconstruction accuracy comparable to AEs trained exclusively on real data samples. Conclusion: This study emphasizes the prospects of harnessing generative AI to enhance ML tasks in the biomechanics domain.

Inertial measurement unit sensor-based gait analysis in adults and older adults: A cross-sectional study

BACKGROUND

Gait assessment has been used in a wide range of clinical applications, and gait velocity is also a leading predictor of disease and physical functional aspects in older adults.

RESEARCH QUESTION

The study aim to examine the changes in IMU-based gait parameters according to age in healthy adults aged 50 and older, to analyze differences between aging patients.

METHODS

A total of 296 healthy adults (65.32 ± 6.74 yrs; 83.10 % female) were recruited. Gait assessment was performed using an IMU sensor-based gait analysis system, and 3D motion information of hip and knee joints was obtained using magnetic sensors. The basic characteristics of the study sample were stratified by age category, and the baseline characteristics between the groups were compared using analysis of variance (ANOVA). Pearson's correlation analysis was used to analyze the relationship between age as the dependent variable and several measures of gait parameters and joint angles as independent variables.

RESULTS

The results of this study found that there were significant differences in gait velocity and both terminal double support in the three groups according to age, and statistically significant differences in the three groups in hip joint angle and knee joints angle. In addition, it was found that the gait velocity and knee/hip joint angle changed with age, and the gait velocity and knee/hip joint angle were also different in the elderly and adult groups.

CONCLUSIONS

We found changes in gait parameters and joint angles according to age in healthy adults and older adults and confirmed the difference in gait velocity and joint angles between adults and older adults.

Modeling biological individuality using machine learning: A study on human gait

Human gait is a complex and unique biological process that can offer valuable insights into an individual's health and well-being. In this work, we leverage a machine learning-based approach to model individual gait signatures and identify factors contributing to inter-individual variability in gait patterns. We provide a comprehensive analysis of gait individuality by (1) demonstrating the uniqueness of gait signatures in a large-scale dataset and (2) highlighting the gait characteristics that are most distinctive to each individual. We utilized the data from three publicly available datasets comprising 5368 bilateral ground reaction force recordings during level overground walking from 671 distinct healthy individuals. Our results show that individuals can be identified with a prediction accuracy of 99.3% by using the bilateral signals of all three ground reaction force components, with only 10 out of 1342 recordings in our test data being misclassified. This indicates that the combination of bilateral ground reaction force signals with all three components provides a more comprehensive and accurate representation of an individual's gait signature. The highest accuracy was achieved by (linear) Support Vector Machines (99.3%), followed by Random Forests (98.7%), Convolutional Neural Networks (95.8%), and Decision Trees (82.8%). The proposed approach provides a powerful tool to better understand biological individuality and has potential applications in personalized healthcare, clinical diagnosis, and therapeutic interventions.

Deep Metric Learning for Scalable Gait-Based Person Re-Identification Using Force Platform Data

Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platform-based re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or removed from the database. We formulated force platform-based re-ID as a deep metric learning (DML) task, whereby a deep neural network learns a feature representation that can be compared between inputs using a distance metric. The force platform dataset used in this study is one of the largest and the most comprehensive of its kind, containing 193 IDs with significant variations in clothing, footwear, walking speed, and time between trials. Several DML model architectures were evaluated in a challenging setting where none of the IDs were seen during training (i.e., zero-shot re-ID) and there was only one prior sample per ID to compare with each query sample. The best architecture was 85% accurate in this setting, though an analysis of changes in walking speed and footwear between measurement instances revealed that accuracy was 28% higher on same-speed, same-footwear comparisons, compared to cross-speed, cross-footwear comparisons. These results demonstrate the potential of DML algorithms for zero-shot re-ID using force platform data, and highlight challenging cases.

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.

A Multi-Modal Gait Database of Natural Everyday-Walk in an Urban Environment

Human gait data have traditionally been recorded in controlled laboratory environments focusing on single aspects in isolation. In contrast, the database presented here provides recordings of everyday walk scenarios in a natural urban environment, including synchronized IMU-, FSR-, and gaze data. Twenty healthy participants (five females, fifteen males, between 18 and 69 years old, 178.5 ± 7.64 cm, 72.9 ± 8.7 kg) wore a full-body Lycra suit with 17 IMU sensors, insoles with eight pressure sensing cells per foot, and a mobile eye tracker. They completed three different walk courses, where each trial consisted of several minutes of walking, including a variety of common elements such as ramps, stairs, and pavements. The data is annotated in detail to enable machine-learning-based analysis and prediction. We anticipate the data set to provide a foundation for research that considers natural everyday walk scenarios with transitional motions and the interaction between gait and gaze during walking.

Always Pay Attention to Which Model of Motor Learning You Are Using

This critical review considers the epistemological and historical background of the theoretical construct of motor learning for a more differentiated understanding. More than simply reflecting critically on the models that are used to solve problems-whether they are applied in therapy, physical education, or training practice-this review seeks to respond constructively to the recent discussion caused by the replication crisis in life sciences. To this end, an in-depth review of contemporary motor learning approaches is provided, with a pragmatism-oriented clarification of the researcher's intentions on fundamentals (what?), subjects (for whom?), time intervals (when?), and purpose (for what?). The complexity in which the processes of movement acquisition, learning, and refinement take place removes their predictable and linear character and therefore, from an applied point of view, invites a great deal of caution when trying to make generalization claims. Particularly when we attempt to understand and study these phenomena in unpredictable and dynamic contexts, it is recommended that scientists and practitioners seek to better understand the central role that the individual and their situatedness plays in the system. In this way, we will be closer to making a meaningful and authentic contribution to the advancement of knowledge, and not merely for the sake of renaming inventions.