Explore the vast range of titles available.

Automatic fault detection is a major challenge in many sports. In race walking, judges visually detect faults according to the rules. Hence, automatic fault detection systems will help a training of race walking without experts’ visual judgement. Some studies have attempted to use sensors and machine learning to automatically detect faults. However, there are problems associated with sensor attachments and equipment such as a high-speed camera, which conflict with the visual judgement of judges, and the interpretability of the fault detection models. In this study, we proposed an automatic fault detection system for non-contact measurement. We used pose estimation and machine learning models trained based on the judgements of multiple qualified judges to realize fair fault judgement. We verified them using smartphone videos of normal race walking and walking with intentional faults in several athletes including the medalist of the Tokyo Olympics. The results show that the proposed system detected faults with an average accuracy of over 90%. We also revealed that the machine learning model detects faults according to the rules. In addition, the intentional faulty walking movement of the medalist was different from that of other walkers. This finding informs realization of a more general fault detection model.

The validity of results in race walking is often questioned due to subjective decisions in the detection of faults. This study aims to compare machine-learning algorithms fed with data gathered from inertial sensors placed on lower-limb segments to define the best-performing classifiers for the automatic detection of illegal steps. Eight race walkers were enrolled and linear accelerations and angular velocities related to pelvis, thighs, shanks, and feet were acquired by seven inertial sensors. The experimental protocol consisted of two repetitions of three laps of 250 m, one performed with regular race walking, one with loss-of-contact faults, and one with knee-bent faults. The performance of 108 classifiers was evaluated in terms of accuracy, recall, precision, F1-score, and goodness index. Generally, linear accelerations revealed themselves as more characteristic with respect to the angular velocities. Among classifiers, those based on the support vector machine (SVM) were the most accurate. In particular, the quadratic SVM fed with shank linear accelerations was the best-performing classifier, with an F1-score and a goodness index equal to 0.89 and 0.11, respectively. The results open the possibility of using a wearable device for automatic detection of faults in race walking competition.

This paper presents IART, a novel inertial wearable system for automatic detection of infringements and analysis of sports performance in race walking. IART algorithms are developed from raw inertial measurements collected by a single sensor located at the bottom of the vertebral column (L5–S1). Two novel parameters are developed to estimate infringements: loss of ground contact time and loss of ground contact step classification; three classic parameters are indeed used to estimate performance: step length ratio, step cadence, and smoothness. From these parameters, five biomechanical indices customized for elite athletes are derived. The experimental protocol consists of four repetitions of a straight path of 300 m on a long-paved road, performed by nine elite athletes. Over a total of 1620 steps (54 sequences of 30 steps each), the average accuracy of correct detection of loss of ground contact events is equal to 99%, whereas the correct classification of the infringement is equal to 87% for each step sequence, with a 92% of acceptable classifications. A great emphasis is dedicated on the user-centered development of IART: an intuitive radar chart representation is indeed developed to provide practical usability and interpretation of IART indices from the athletes, coaches, and referees perspectives. The results of IART, in terms of accuracy of its indices and usability from end-users, are encouraging for its usage as tool to support athletes and coaches in training and referees in real competitions.

Due to subjectivity in refereeing, the results of race walking are often questioned. To overcome this limitation, artificial-intelligence-based technologies have demonstrated their potential. The paper aims at presenting WARNING, an inertial-based wearable sensor integrated with a support vector machine algorithm to automatically identify race-walking faults. Two WARNING sensors were used to gather the 3D linear acceleration related to the shanks of ten expert race-walkers. Participants were asked to perform a race circuit following three race-walking conditions: legal, illegal with loss-of-contact and illegal with knee-bent. Thirteen machine learning algorithms, belonging to the decision tree, support vector machine and k-nearest neighbor categories, were evaluated. An inter-athlete training procedure was applied. Algorithm performance was evaluated in terms of overall accuracy, F1 score and G-index, as well as by computing the prediction speed. The quadratic support vector was confirmed to be the best-performing classifier, achieving an accuracy above 90% with a prediction speed of 29,000 observations/s when considering data from both shanks. A significant reduction of the performance was assessed when considering only one lower limb side. The outcomes allow us to affirm the potential of WARNING to be used as a referee assistant in race-walking competitions and during training sessions.

Introduction. Race-walking is a sport that mimics normal walking and running. Previous studies on sports science mainly focused on the cardiovascular and musculoskeletal systems. However, there is still a lack of research on the central nervous system, especially the real-time changes in brain network characteristics during race-walking exercise. This study aimed to use a network perspective to investigate the effects of different exercise intensities on brain functional connectivity. Materials and Methods. A total of 16 right-handed healthy young athletes were recruited as participants in this study. The cerebral cortex concentration of oxyhemoglobin was measured by functional near-infrared spectroscopy in the bilateral prefrontal cortex (PFC), the motor cortex (MC) and occipital cortex (OC) during resting and race-walking states. Three specific periods as time windows corresponding to different exercise intensities were divided from the race-walking time of participants, including initial, intermediate and sprint stages. The brain activation and functional connectivity (FC) were calculated to describe the 0.01-0.1 Hz frequency-specific cortical activities. Results. Compared to the resting state, FC changes mainly exist between MC and OC in the initial stage, while PFC was involved in FC changes in the intermediate stage, and FC changes in the sprint stage were widely present in PFC, MC and OC. In addition, from the initial-development to the sprint stage, the significant changes in FC were displayed in PFC and MC. Conclusions. This brain functional connectivity-based study confirmed that hemodynamic changes at different exercise intensities reflected different brain network-specific characteristics. During race-walking exercise, more extensive brain activation might increase information processing speed. Increased exercise intensity could facilitate the integration of neural signals such as proprioception, motor control and motor planning, which may be an important factor for athletes to maintain sustained motor coordination and activity control at high intensity. This study was beneficial to understanding the neural mechanisms of brain networks under different exercise intensities.

The conventional race walking technique adheres to competition rules by excluding a noticeable flight phase visible to the human eye. However, race walkers often exhibit a slight flight phase, sparking an ongoing debate: Is the flight phase permissible? Is it acceptable if the referee fails to detect it? Is the flight phase an inherent part of the race walking technique that cannot be eliminated? The objective of this study was to examine the characteristics of the flight phase in race walking at different speeds. Additionally, the study aimed to compare the performance of individuals in the 20-km distance with the average TOP10 male results from three Olympic games, as well as Y. Suzuki's world record. All participants completed three race walking trials on a level treadmill, with the trials conducted in a randomized order. The walking kinematics were observed using the Optojump Next optical system. Our study revealed that race walkers were able to maintain flight time duration below the threshold of 0.04 s, which is the upper limit undetectable by the human eye, at their competition velocity. However, the impact on flight time varied at higher velocities. Double support steps were rare, occurring less than 2% of the time during race walking at competition velocity. Our findings highlight the importance of keeping the flight phase within specified threshold levels to ensure compliance with competition rules. Further research and potential implementation of electronic control systems may enforce these rules and provide valuable insights for athletes, coaches, and spectators.

The aim of the study was to assess the influence of year-long training of race walkers on physiological cost and total energy center of mass (CoM). The assessment performed was based on indicating the differences between the resulting energy cost in a group of elite race walkers walking at technical, threshold, and racing speeds calculated by physiological and biomechanical methods before beginning and after finishing a year-long training cycle. The study involved 12 competitive race walkers who had achieved champion or international champion level. Their aerobic endurance was determined by means of a direct method, applying an incremental exercise test on the treadmill. The gait of the participants was recorded using the 3D Vicon analysis system. Changes in mechanical energy amounted to the value of the total external work of the muscles needed to accelerate and lift the center of mass during a normalized gait cycle. The highest influence on the total external work increase for increasing speeds of gait in both examinations was attributed to the changes in the kinetic energy resulting from the center of mass movement. A statistically significant decrease of the mean value of total external work for racing speed was observed in the second examination (p < 0.001). An approx. 8% decrease (NS) of EE energy cost, standardized by body mass and distance covered, was found between the first and second examinations. The energy cost and total external work were significantly differentiated by the walkers’ gait speeds (p < 0.05–0.001). The energy cost significantly differed from the total external work at p < 0.001.

This study presents a three-dimensional finite element (FE) analysis of the human foot bone structure under mid-stance loading during race walking. A subject-specific biomodel comprising 26 bones and over 40 ligaments was reconstructed from computed tomography (CT) data using Materialise Mimics Research 21.0 and 3-Matic Research 13.0, and subsequently analyzed in ANSYS Workbench 2024 R1. The model included explicit cortical, trabecular, and ligamentous volumes, each assigned linear-elastic, isotropic material properties based on biomechanical literature data. Boundary conditions simulated the mid-stance phase of race walking, applying a distributed plantar pressure of 0.25 MPa over the metatarsal and phalangeal regions. Numerical simulations yielded maximum total displacements of 0.00018 mm, maximum von Mises stresses of 0.171 MPa, and maximum strains of 2.5 × 10−5, all remaining well within the elastic range of bone tissue. The results confirm the model’s numerical stability, geometric fidelity, and capacity to represent physiologically realistic loading responses. The developed framework demonstrates the potential of high-resolution, image-based finite element modelling for investigating stress–strain patterns of the foot during athletic gait, and establishes a reproducible reference for future analyses involving pathological gait, orthotic optimisation, and musculoskeletal load assessment in sports biomechanics.

Walking plays an important role in human daily life. Many previous studies suggested that long-term walking training can modulate brain functions. However, due to the use of measuring techniques such as fMRI and PET, which are highly motion-sensitive, it is difficult to record individual brain activities during the movement. This pilot study used functional near-infrared spectroscopy (fNIRS) to measure the hemodynamic responses in the frontal-parietal cortex of four elite race walkers (experimental group, EG) and twenty college students (control group, CG) during tasks involving action observation, motor imagery, and motor execution. The results showed that activation levels of the pars triangularis of the inferior frontal gyrus (IFG), dorsolateral prefrontal cortex (DLPFC), premotor and supplementary motor cortex (PMC and SMC), and primary somatosensory cortex (S1) in the EG were significantly lower than in the CG during motor execution and observation tasks. And primary motor cortex (M1) of EG in motor execution task was significantly lower than its in CG. During the motor imagery task, activation intensities of the DLPFC, PMC and SMC, and M1 in the EG were significantly higher than in the CG. These findings suggested that the results of motor execution and observation tasks might support the brain efficiency hypothesis, and the related brain regions strengthened the efficiency of neural function, but the results in motor imagery tasks could be attributed to the internal forward model of elite race walkers, which showed a trend opposed to the brain efficiency hypothesis. Additionally, the activation intensities of the pars triangularis and PMC and SMC decreased with the passage of time in the motor execution and imagery tasks, whereas during the action observation task, no significant differences in these regions were found. This reflected differences of the internal processing among the tasks.

At the current stage of sports development, technical training within the long-term improvement system for race walking athletes should involve clearly defined model characteristics of their technical actions. The integration of advanced modeling technologies, such as artificial neural networks, allows for the creation of effective anc high-quality models that represent athletes' technical actions. Objective: To improve the technical preparation o track-and-field athletes specializing in race walking by identifying model characteristics of technical actions within a long-term preparation framework. Materials and Methods: Neural network modeling of the technical actions of athletes specializing in race walking was performed based on data from biomechanical analyses of competitive exercise techniques. This data was collected via video recordings during the 2014-2021 Ukrainian Race Walking Championships, as well as at the Association of Balkan Athletic Federations Championships and the international \"Evening Ivano-Frankivsk\" Cup, organized in conjunction with Ukraine's national championships. The studies included male athletes from various age groups competing at distances of 3 km, 10 km, and 20 km. In total, 98 analyses were conducted: 31 at 3 km, 36 at 10 km, and 31 at 20 km. Results. A total of 26 biomechanical indices of athletes' techniques were analyzed. Correlation analysis identified 14 key biomechanical characteristics that significantly influence performance outcomes within the long-term development system. Using these characteristics, along with indices of body length and mass, neural network models were developed to simulate and predict athletic performance. Conclusions. Artificial neural networks enabled the creation of models for race-walking technical actions that support high-level performance in young athletes aged 13-15 years (3 km distance), boys aged 16-19 years (10 km distance), and elite athletes aged 20 years and older (20 km distance).