The Gaitprint: Identifying Individuals by Their Running Style

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.

A new method proposed for realizing human gait pattern recognition: Inspirations for the application of sports and clinical gait analysis

BACKGROUND

Finding the best subset of gait features among biomechanical variables is considered very important because of its ability to identify relevant sports and clinical gait pattern differences to be explored under specific study conditions. This study proposes a new method of metaheuristic optimization-based selection of optimal gait features, and then investigates how much contribution the selected gait features can achieve in gait pattern recognition.

METHODS

Firstly, 800 group gait datasets performed feature extraction to initially eliminate redundant variables. Then, the metaheuristic optimization algorithm model was performed to select the optimal gait feature, and four classification algorithm models were used to recognize the selected gait feature. Meanwhile, the accuracy results were compared with two widely used feature selection methods and previous studies to verify the validity of the new method. Finally, the final selected features were used to reconstruct the data waveform to interpret the biomechanical meaning of the gait feature.

RESULTS

The new method finalized 10 optimal gait features (6 ankle-related and 4-related knee features) based on the extracted 36 gait features (85 % variable explanation) by feature extraction. The accuracy in gait pattern recognition among the optimal gait features selected by the new method (99.81 % ± 0.53 %) was significantly higher than that of the feature-based sorting of effect size (94.69 % ± 2.68 %), the sequential forward selection (95.59 % ± 2.38 %), and the results of previous study. The interval between reconstructed waveform-high and reconstructed waveform-low curves based on the selected feature was larger during the whole stance phase.

SIGNIFICANCE

The selected gait feature based on the proposed new method (metaheuristic optimization-based selection) has a great contribution to gait pattern recognition. Sports and clinical gait pattern recognition can benefit from population-based metaheuristic optimization techniques. The metaheuristic optimization algorithms are expected to provide a practical and elegant solution for sports and clinical biomechanical feature selection with better economy and accuracy.

NONAN GaitPrint: An IMU gait database of healthy young adults

An ongoing thrust of research focused on human gait pertains to identifying individuals based on gait patterns. However, no existing gait database supports modeling efforts to assess gait patterns unique to individuals. Hence, we introduce the Nonlinear Analysis Core (NONAN) GaitPrint database containing whole body kinematics and foot placement during self-paced overground walking on a 200-meter looping indoor track. Noraxon Ultium MotionTM inertial measurement unit (IMU) sensors sampled the motion of 35 healthy young adults (19-35 years old; 18 men and 17 women; mean ± 1 s.d. age: 24.6 ± 2.7 years; height: 1.73 ± 0.78 m; body mass: 72.44 ± 15.04 kg) over 18 4-min trials across two days. Continuous variables include acceleration, velocity, position, and the acceleration, velocity, position, orientation, and rotational velocity of each corresponding body segment, and the angle of each respective joint. The discrete variables include an exhaustive set of gait parameters derived from the spatiotemporal dynamics of foot placement. We technically validate our data using continuous relative phase, Lyapunov exponent, and Hurst exponent-nonlinear metrics quantifying different aspects of healthy human gait.

Discovering the sluggishness of triathlon running - using the attractor method to quantify the impact of the bike-run transition

Running in a triathlon, a so-called brick run, is uniquely influenced by accumulated load from its preceding disciplines. Crucially, however, and irrespective of race type, the demands of a triathlon always exceed the sum of its parts. Triathletes of all levels commonly report subjectively perceived incoordination within the initial stages of the cycle run transition (T2). Although minimizing it, and its influence on running kinematics, can positively impact running and overall triathlon performance, the mechanisms behind the T2 effect remain unclear. In the present study, we assessed the influence of the pre-load exercise mode focusing on the biomechanical perspective. To analyze inertial sensor-based raw data from both legs, the so-called Attractor Method was applied. The latter represents a sensitive approach, allowing to quantify subtle changes of cyclic motions to uncover the transient effect, a potentially detrimental transient phase at the beginning of a run. The purpose was to analyze the impact of a pre-load on the biomechanics of a brick run during a simulated Olympic Distance triathlon (without the swimming section). Therefore, we assessed the influence of pre-load exercise mode on running pattern (δM) and precision (δD), and on the length of the transient effect (t_T) within a 10 km field-based run in 22 well-trained triathletes. We found that δD, but not δM, differed significantly between an isolated run (I_Run) and when it was preceded by a 40 km cycle (T_Run) or an energetically matched run (R_Run). The average distance ran until overcoming the transient phase (t_T) was 679 m for T_Run, 450 m for R_Run, and 29 4 m for I_Run. The results demonstrated that especially the first kilometer of a triathlon run is prone to an uncoordinated running sensation, which is also commonly reported by athletes. That is, i) the T2 effect appeared more linked to variability in running style than to running style per se ii) run t_T distance was influenced by preceding exercise load mode, being greater for a T_Run than for the R_Run condition, and iii) the Attractor Method seemed to be a potentially promising method of sensitively monitoring T2 adaptation under ecologically valid conditions.

Prominent Fatigue but No Motor Fatigability in Non-Hospitalized Patients With Post-COVID-Syndrome

Objectives

Fatigue is a frequent and often disabling symptom in patients with post-COVID syndrome. To better understand and evaluate the symptom of motor fatigue in the context of the post-COVID syndrome, we conducted treadmill walking tests to detect the phenomenon of motor fatigability or to evaluate whether evidence of organic lesions of the motor system could be found, similar to patients with multiple sclerosis.

Method

Twenty-nine non-hospitalized patients with post-COVID syndrome completed the Fatigue Scale for Motor and Cognitive Function (FSMC) questionnaire to determine the trait component of subjective fatigue before they were tested on a treadmill walking at a moderate speed for up to 60 min or until exhaustion. During the walking test oxygen uptake, ventilation and acceleration data of both feet were collected. To determine motor performance fatigability, the Fatigue Index Kliniken Schmieder (FKS) was calculated using the attractor method.

Results

The average walking duration was 42.7 ± 18.6 min with 15 subjects stopping the walking test prematurely. The FSMC score revealed a severe cognitive (37.6 ± 8.2) and motor (37.1 ± 7.8) fatigue averaged over all subjects but only two subjects showed an FKS above the normal range (>4), representing performance fatigability. There was no significant correlation between subjective fatigue (FSMC) and FKS as well as walking time. Absolute values of oxygen uptake and ventilation were in the normal range reported in literature (r = 0.9, p < 0.05), although eight subjects did not produce a steady-state behavior.

Conclusion

Almost all patients with post-COVID syndrome and subjectively severe motor fatigue, did not show motor fatigability nor severe metabolic anomalies. This is argued against organic, permanent damage to the motor system, as is often seen in MS. Many of the patients were - to our and their own surprise - motorically more exertable than expected.

Systematic reduction of leg muscle activity throughout a standard assessment of running footwear

PURPOSE

This study aimed to investigate whether there is a systematic change of leg muscle activity, as quantified by surface electromyography (EMG), throughout a standard running footwear assessment protocol at a predetermined running speed.

METHODS

Thirty-one physically active adults (15 females and 16 males) completed 5 testing rounds consisting of overground running trials at a speed of 3.5 m/s. The level of muscle activity from 6 major leg muscles was recorded using surface EMG. The variables assessed were the EMG total intensity as a function of time and the cumulative EMG overall intensity. Systematic effects of the chronological testing round (independent variable) on the normalized EMG overall intensity (dependent variable) were examined using Friedman analysis of variates and post hoc pairwise Wilcoxon signed-rank tests (α = 0.05).

RESULTS

There was a systematic reduction in overall EMG intensity for all 6 muscles over the time course of the running protocol (p < 0.001) until the fourth testing round when EMG intensities reached a steady state. The one exception was the biceps femoris muscle, which showed a significant reduction of EMG intensity during the stance phase (p < 0.001) but not the swing phase (p = 0.16).

CONCLUSION

While running at a predetermined speed, the neuromuscular system undergoes an adaptation process characterized by a progressive reduction in the activity level of major leg muscles. This process may represent an optimization strategy of the neuromuscular system towards a more energetically efficient running style. Future running protocols should include a familiarization period of at least 7 min or 600 strides of running at the predetermined speed.

Isolating the Unique and Generic Movement Characteristics of Highly Trained Runners

Human movement patterns were shown to be as unique to individuals as their fingerprints. However, some movement characteristics are more important than other characteristics for machine learning algorithms to distinguish between individuals. Here, we explored the idea that movement patterns contain unique characteristics that differentiate between individuals and generic characteristics that do not differentiate between individuals. Layer-wise relevance propagation was applied to an artificial neural network that was trained to recognize 20 male triathletes based on their respective movement patterns to derive characteristics of high/low importance for human recognition. The similarity between movement patterns that were defined exclusively through characteristics of high/low importance was then evaluated for all participants in a pairwise fashion. We found that movement patterns of triathletes overlapped minimally when they were defined by variables that were very important for a neural network to distinguish between individuals. The movement patterns overlapped substantially when defined through less important characteristics. We concluded that the unique movement characteristics of elite runners were predominantly sagittal plane movements of the spine and lower extremities during mid-stance and mid-swing, while the generic movement characteristics were sagittal plane movements of the spine during early and late stance.

Individuality decoded by running patterns: Movement characteristics that determine the uniqueness of human running

Human gait is as unique to an individual as is their fingerprint. It remains unknown, however, what gait characteristics differentiate well between individuals that could define the uniqueness of human gait. The purpose of this work was to determine the gait characteristics that were most relevant for a neural network to identify individuals based on their running patterns. An artificial neural network was trained to recognize kinetic and kinematic movement trajectories of overground running from 50 healthy novice runners (males and females). Using layer-wise relevance propagation, the contribution of each variable to the classification result of the neural network was determined. It was found that gait characteristics of the coronal and transverse plane as well as medio-lateral ground reaction forces provided more information for subject identification than gait characteristics of the sagittal plane and ground reaction forces in vertical or anterior-posterior direction. Additionally, gait characteristics during the early stance were more relevant for gait recognition than those of the mid and late stance phase. It was concluded that the uniqueness of human gait is predominantly encoded in movements of the coronal and transverse plane during early stance.

Transient Effect at the Onset of Human Running

While training and competing as a runner, athletes often sense an unsteady feeling during the first meters on the road. This sensation, termed as transient effect, disappears after a short period as the runners approach their individual running rhythm. The foundation of this work focuses on the detection and quantification of this phenomenon. Thirty athletes ran two sessions over 60 min on a treadmill at moderate speed. Three-dimensional acceleration data were collected using two MEMS sensors attached to the lower limbs. By using the attractor method and Fourier transforms, the transient effect was isolated from noise and further components of human cyclic motion. A substantial transient effect was detected in 81% of all measured runs. On average, the transient effect lasted 5.25 min with a range of less than one minute to a maximum of 31 min. A link to performance data such as running level, experience and weekly training hours could not be found. The presented work provides the methodological basis to detect and quantify the transient effect at moderate running speeds. The acquisition of further physical or metabolic performance data could provide more detailed information about the impact of the transient effect on athletic performance.