Search Results (210)

This paper presents the design and implementation of a vision-based score detection system tailored for smart IoT basketball applications. The proposed architecture leverages a compact, low-cost device comprising a high-resolution overhead camera and a Raspberry Pi 5 microprocessor equipped with a hardware accelerator for real-time object detection. The detection pipeline integrates convolutional neural networks (YOLO-based) and custom preprocessing techniques to localize the basketball hoop and track the ball trajectory. A scoring event is confirmed when the ball enters the defined scoring zone with downward motion over multiple frames, effectively reducing false positives caused by occlusions, multiple balls, or irregular shot directions. The system is part of a scalable IoT analytics platform known as Koško, which provides real-time statistics, leaderboards, and user engagement tools through a web-based interface. Field tests were conducted using data collected from various public and school courts across Niš, Serbia, resulting in a robust and adaptable solution for automated basketball score monitoring in both indoor and outdoor environments. The methodology supports edge computing, multilingual deployment, and integration with smart coaching and analytics systems. Full article

This study examined child outcomes for five minimally verbal (or non-speaking) autistic preschoolers who participated in cascading coaching programs in which naturalistic developmental behavioral intervention (NDBI) techniques were taught to graduate student clinicians and Hispanic caregivers (three who primarily spoke English, and two who spoke Spanish). While prior studies reported on adult participant outcomes, this study analyzed child multimodal communication outcomes, using multiple baselines/probes single case experimental designs across contexts. Neurodiversity-affirming and culturally responsive principles were embedded within the intervention procedures. Following the introduction of a coached NDBI, all five children (three who received the intervention in English and two who received the intervention in Spanish) demonstrated increased use of (a) the total targeted communicative responses and (b) the targeted unprompted communicative responses, across both student clinician-led and caregiver-led play sessions. The Tau-U effect size measures revealed large-to-very large effects across all of the variables. Overall, higher rates of communication responses were observed during student clinician-led sessions than in caregiver-led sessions. Additionally, behavioral coding of the multimodal response forms (e.g., gestures, aided augmentative and alternative communication, signs, vocal words) using the Communication Matrix revealed that the children used a variety of response topographies during the intervention sessions beyond their preferred communication mode (e.g., signs for three participants). Four of the five children used symbolic communication forms consistently across both caregiver and student clinician-led sessions. Importantly, adults’ reinforcement of pre-symbolic or less advanced communication forms during the intervention did not inhibit the use of more advanced forms. Full article

Background/Objectives: Passing is the most frequent and impactful action in soccer. It requires players to control the ball and pass accurately with either foot, make quick decisions, and scan the field while under pressure. Using a recently developed series of passing tests that vary in complexity and scanning demands, we examined how a player’s choice of technique when controlling and passing the ball, along with their ability to scan effectively, influenced passing performance. Methods: Forty-five elite U12 and U13 players from a Brazilian academy completed three passing tests involving directional turns across 120°, 180°, and 360°. Each pass was video-coded based on foot orientation (back or front foot), foot dominance (dominant or nondominant), and pass direction (toward the dominant or nondominant side). The study tested whether (i) the most common technique used varied with pass direction due to a preference for the dominant foot, (ii) performance varied across foot techniques, and (iii) scanning prior to ball reception enhanced outcomes. Results: Players preferred techniques that used their dominant foot, such as controlling and passing with their back foot (back–back) when turning to the dominant side (58% in 120° and 57% in 180° tests) and controlling with their back foot and passing with the front (back–front) for the nondominant side (66% and 55%; χ² = 292.96 and 312.87, p < 0.001). However, using the dominant foot sometimes led to slower, less efficient actions. In the 120° test, back–front was the fastest technique (+1.11 passes/min vs. back–back), while front–back was the slowest (−4.20 passes/min, p < 0.001). In the 360° test, scanning improved turn accuracy (from 51% to 73%) and performance, resulting in 4.20 more passes/min, fewer control errors (11% vs. 31%), and fewer target misses (3% vs. 10%; all p < 0.001). Conclusions: These findings highlight the value of effective scanning and foot technique under varied conditions, and offers coaches a practical tool for player analysis, feedback, and development. Full article

Background/Objective: Understanding the training effect in high-level running is important for performance optimization and injury prevention. This includes awareness of how different running surface types (e.g., hard versus soft) may modify biomechanics. Recent studies have demonstrated that deep learning algorithms, such as convolutional neural networks (CNNs), can accurately classify human activity collected via body-worn sensors. To date, no study has assessed optimal signal type, sensor location, and model architecture to classify running surfaces. This study aimed to determine which combination of signal type, sensor location, and CNN architecture would yield the highest accuracy in classifying grass and asphalt surfaces using inertial measurement unit (IMU) sensors. Methods: Running data were collected from forty participants (27.4 years + 7.8 SD, 10.5 ± 7.3 SD years of running) with a full-body IMU system (head, sternum, pelvis, upper legs, lower legs, feet, and arms) on grass and asphalt outdoor surfaces. Performance (accuracy) for signal type (acceleration and angular velocity), sensor configuration (full body, lower body, pelvis, and feet), and CNN model architecture was tested for this specific task. Moreover, the effect of preprocessing steps (separating into running cycles and amplitude normalization) and two different data splitting protocols (leave-n-subject-out and subject-dependent split) was evaluated. Results: In general, acceleration signals improved classification results compared to angular velocity (3.8%). Moreover, the foot sensor configuration had the best performance-to-number of sensor ratio (95.5% accuracy). Finally, separating trials into gait cycles and not normalizing the raw signals improved accuracy by approximately 28%. Conclusion: This analysis sheds light on the important parameters to consider when developing machine learning classifiers in the human activity recognition field. A surface classification tool could provide useful quantitative feedback to athletes and coaches in terms of running technique effort on varied terrain surfaces, improve training personalization, prevent injuries, and improve performance. Full article

Background: Uchi-mata is one of the most frequently used throwing techniques in judo, yet little is known about the kinematic factors distinguishing specialists from non-specialists. This study compared lower-limb kinematics during uchi-mata across its three phases in elite judokas. Methods: Forty athletes (12 female, 28 male; 24.5 ± 5.9 years) were classified as specialists (n = 20) or non-specialists (n = 20). Photogrammetry assessed hip, knee, and foot displacement, velocity, acceleration, and timing during the Approach, Turning, and Throw phases. Analyses were performed using mixed-effects models with group, phase, and sex as fixed effects, plus exploratory multivariate tests (p < 0.05). Results: Specialists executed faster movements in the Approach (p = 0.036, d = 0.69) and Throw phases (p = 0.010, d = 0.85), showed greater hip displacement during Approach (p = 0.008, d = 0.89), and achieved superior knee and foot displacement in Throw (p = 0.005 and p = 0.003). Final positioning also differed, with specialists displaying higher knee (98.5 ± 14.5 vs. 86.3 ± 17.8 cm, p ≤ 0.001) and foot (121.0 ± 19.7 vs. 104.4 ± 27.4 cm, p = 0.034) heights, but lower hip position (61.9 ± 4.2 vs. 75.6 ± 7.5 cm, p = 0.021). Sex showed no significant effects or interactions, indicating that these group differences were consistent across male and female athletes. Conclusions: Uchi-mata specialists demonstrated superior displacement and velocity control, particularly in the Approach and Throw phases, reflecting greater neuromuscular coordination and efficiency. These findings provide practical markers for coaches and athletes to guide training focused on mobility, strength, and technical drills that enhance hip, knee, and foot displacement, supporting the optimization of uchi-mata performance in elite judo. Full article

Musculoskeletal injuries are a growing concern among adolescent athletes, with significant physical and psychological consequences. This integrative literature review aimed to analyze the risk factors associated with musculoskeletal injuries in adolescents engaged in sports and to explore the role of nursing interventions in their prevention. A systematic search was conducted across four databases and one gray literature source, including studies published between 2014 and 2024. Three descriptive studies were included, with evidence levels ranging from 3 to 4, according to the Joanna Briggs Institute classification. The main findings highlight that risk factors for musculoskeletal injuries include excessive training loads, inadequate sports technique, lack of professional supervision, improper use of equipment, and failure to recognize early signs of discomfort. Preventive nursing interventions were shown to be effective, particularly those focused on health education, proprioceptive training, and continuous monitoring. Multidisciplinary collaboration between nurses, coaches, and other health professionals emerged as a key strategy in creating safe sporting environments. Despite limitations such as the scarcity of studies on nursing-specific interventions in diverse sports contexts, this review supports the potential of structured, evidence-based nursing actions to reduce musculoskeletal injuries incidence, promote safer sports practices, and enhance adolescent athletes’ health outcomes. Full article

A cascading coaching model was used to teach bilingual speech-language pathology (SLP) graduate student clinicians and Spanish-speaking caregivers to implement naturalistic developmental behavioral intervention (NDBI) techniques with autistic preschoolers. Two triads (each consisting of a graduate student clinician, a minimally vocal child diagnosed with autism, and a caregiver) participated in the study. Following the cascading approach, a lead instructor (with limited Spanish conversational skills) coached bilingual student clinicians (in English) to apply culturally adapted NDBI with child participants. Following additional instruction in coaching, student clinicians coached caregivers in Spanish. Effects were evaluated using a multiple methods approach consisting of multiple probes across participants single case experimental design and a qualitative analysis of semi-structured interviews with adult participants. All adult participants increased their use of targeted NDBI skills including elicitation techniques (creating communication temptations, using wait time, and prompting) and response techniques (reinforcing children’s communication with natural consequences and providing a contextually relevant vocal model), demonstrating large to very large effect sizes. Although qualitative findings indicated areas for improvement (e.g., additional Spanish supports for clinicians), thematic analysis revealed additional benefits in terms of positive changes across adult learning, behavior, and perspectives; child communication; and child-caregiver relationships. Full article

The significance of children’s mathematical competence during the early years is well established; however, the methods for developing such competencies remain less understood. Specifically, there is a need to identify what constitutes high-quality educational environments and effective instruction. Both the study and promotion of high-quality educational environments and teaching, through coaching and other professional development initiatives, necessitate the use of observational instruments that are reliable, efficient, and valid, including content, internal, external, and consequential validity. Moreover, domain-specific measures are essential, as general quality measures often fail to adequately assess curriculum content, scope, or sequence, and they do not reliably predict improvements in children’s learning outcomes. This study employed innovative analytical techniques to evaluate the scoring and interpretation of an existing domain-specific observational measure: the Classroom Observation of Early Mathematics Environment and Teaching (COEMET). We applied non-linear modeling approaches (i.e., Random Forest [RF] and Generalized Additive Models [GAMs]) to investigate and provide a comprehensive overview of the relationships between COEMET’s measures—at both the scale and item levels—of teachers’ practices and children’s mathematical competencies. The study first employed the RF machine learning method to identify the most important COEMET items for prediction, followed by the use of GAMs to depict the non-linear relationships between COEMET predictors and the outcome variable. The analysis revealed that certain teaching practices, as indicated by the COEMET items, exhibited non-linear and even non-monotonic associations with children’s mathematical competencies. Full article

Biomechanical analyses of technique are essential for performance improvement in athletic jumps, but scarce evidence exists for adolescent athletes in the literature. The purpose of this study was to examine the sex differences in the high jump biomechanics of U18 athletes. Twenty-one women (15.2 ± 1.0 yrs) and twenty-one men (15.2 ± 1.2 yrs) Greek U18 high jumpers were recorded in regional competitions using two cameras (sampling frequency: 60 fps). The kinematic parameters of the last step, the take-off, and the crossbar clearance were calculated using 3D-DLT analysis. The independent samples t-test was used to detect significant (p < 0.05) differences between groups. Results revealed that men had significantly (p < 0.05) better performance, with larger last step angle and length, body center of mass (BCM) height at the final touchdown and take-off, approach and vertical BCM take-off velocity, touchdown lateral inclination of the take-off leg, and swing leg knee angle at take-off. Women had significantly (p < 0.05) higher vertical BCM velocity at touchdown. No differences (p > 0.05) were observed for take-off angle, the support leg knee angle, the inclination of the torso at touchdown, or the vertical BCM displacement during the take-off phase. The anthropometric and physical conditioning differences between sexes contributed to the findings of the study. Coaches should consider the age and sex differences of adolescent athletes when designing training programs to optimize high jump performance. Full article

Caregiver coaching is an essential component of caregiver-mediated interventions for young autistic children. Previous research evaluating usual practice in early intervention (EI) has found that EI providers often do not use caregiver coaching. Increasing the use of caregiver coaching strategies is critical to improving the outcomes of EI. We used a community-partnered process to develop a toolkit of implementation strategies to improve the use of caregiver coaching in EI. This study presents findings from a preliminary evaluation of the toolkit using a non-concurrent multiple-baseline design across groups of providers and caregiver–child dyads. The results indicate that providers’ caregiver coaching fidelity improved following the introduction of the toolkit. Caregivers demonstrated moderate growth in their use of supportive parenting techniques. All providers rated the toolkit as acceptable, appropriate, and feasible. The findings suggest that a toolkit of implementation strategies tailored to support the needs of community-based providers shows promise for improving caregiver coaching in EI. Full article

Aim: This scoping review examines the application of artificial intelligence (AI) in sports biomechanics, with a focus on enhancing performance and preventing injuries. The review addresses key research questions, including primary AI methods, their effectiveness in improving athletic performance, their potential for injury prediction, sport-specific applications, strategies for translating knowledge, ethical considerations, and remaining research gaps. Following the PRISMA-ScR guidelines, a comprehensive literature search was conducted across five databases (PubMed/MEDLINE, Web of Science, IEEE Xplore, Scopus, and SPORTDiscus), encompassing studies published between January 2015 and December 2024. After screening 3248 articles, 73 studies met the inclusion criteria (Cohen’s kappa = 0.84). Data were collected on AI techniques, biomechanical parameters, performance metrics, and implementation details. Results revealed a shift from traditional statistical models to advanced machine learning methods. Based on moderate-quality evidence from 12 studies, convolutional neural networks reached 94% agreement with international experts in technique assessment. Computer vision demonstrated accuracy within 15 mm compared to marker-based systems (6 studies, moderate quality). AI-driven training plans showed 25% accuracy improvements (4 studies, limited evidence). Random forest models predicted hamstring injuries with 85% accuracy (3 studies, moderate quality). Learning management systems enhanced knowledge transfer, raising coaches’ understanding by 45% and athlete adherence by 3.4 times. Implementing integrated AI systems resulted in a 23% reduction in reinjury rates. However, significant challenges remain, including standardizing data, improving model interpretability, validating models in real-world settings, and integrating them into coaching routines. In summary, incorporating AI into sports biomechanics marks a groundbreaking advancement, providing analytical capabilities that surpass traditional techniques. Future research should focus on creating explainable AI, applying rigorous validation methods, handling data ethically, and ensuring equitable access to promote the widespread and responsible use of AI across all levels of competitive sports. Full article

Background: Hamstring strain injuries (HSIs) are among the most common and recurrent injuries in sports involving high-speed running. While eccentric training has demonstrated efficacy in reducing HSI risk, the role of sprint training as a preventive strategy remains underexplored and often misinterpreted as solely a risk factor. Methods: This review aimed to systematically map the available evidence on the role of sprint training in hamstring injury prevention, identifying mechanisms, outcomes, and potential synergies with other strategies. This scoping review was conducted following the Joanna Briggs Institute’s methodology and reported in accordance with PRISMA-ScR guidelines. Seven databases (PubMed, Scopus, Web of Science, Cochrane CENTRAL, SPORTDiscus, CINAHL, and PEDro) were searched up to October 2024. Studies were included if they involved adult athletes and examined the effects of sprint training, ≥80–90% maximal sprint speed (MSS), on hamstring injury prevention, muscle architecture, or functional outcomes. All databases were searched from inception to 15 October 2024, and the screening and data-charting process was completed on 30 April 2025. Results: Twelve studies met the inclusion criteria. Sprint exposure, when combined with eccentric strengthening and biomechanical optimisation, led to injury reductions ranging from 56% to 94%. Eccentric interventions produced fascicle length increases of up to 20% and strength gains of 15–20%. Improvements in sprint technique and neuromuscular control were also reported. Biomechanical risk factors, including pelvic tilt and hip extension deficits, were linked to increased HSI risk. The most common eccentric protocols included Nordic Hamstring Exercises (NHE), Razor Curls, and hip-dominant exercises, typically performed 1–2 times per week for 4 to 8 weeks. Conclusions: High-speed sprint training, when properly programmed and integrated into comprehensive preventive strategies, may enhance tissue resilience and reduce HSI risk. Combining sprint exposure with eccentric strengthening and technical coaching appears to be more effective than isolated interventions alone. Practically, these results support the systematic inclusion of progressive high-intensity sprint exposure in routine hamstring-injury-prevention programmes for field-sport athletes. Full article

Increased forearm activity may reflect greater steering input or control effort, which, if optimised, could reduce cornering time and thereby improve lap performance. This proof-of-concept case study aimed to quantify forearm muscle activity during two test sessions, with data-driven driver feedback in between sessions to inform steering technique. One ex-professional European karting driver was recruited for this study. A 20 Hz GPS was mounted on the kart, and two electromyography sensors were attached to the left and right flexor digitorum superficialis. In session one, the driver completed 19 laps; EMG data from the fastest lap (51.99 s) were analysed and used to provide feedback. In session two, the driver completed 20 laps, achieving a best time of 51.60 s. EMG analysis revealed greater left forearm activity during left-hand corners in session one, shifting to greater right forearm activity during right-hand corners in session two. The 0.39 s improvement in lap time suggests that EMG-informed feedback may influence steering technique and enhance performance. These findings highlight the potential of integrating EMG analysis into driver coaching, particularly in training and qualifying contexts. Full article

Background and Objective: Match analysis plays a vital role in forming the scientific foundation of training and guiding strategic decision-making in wrestling. By objectively evaluating athletes’ technical and tactical performances, coaches and athletes can optimize preparation and in-match strategies. This study aimed to analyze the technical and tactical characteristics of medal matches in Greco-Roman (GR), Freestyle (FS), and Women’s Wrestling (WW) at the 2024 European Wrestling Championships. Methods: A total of 54 elite-level matches (18 from each style), held in Bucharest between 12 and 18 February, 2024, were retrospectively analyzed. Three expert observers evaluated the matches using video footage from the United World Wrestling (UWW) archive. Descriptive statistics were performed using SPSS 25.0. Results: Across 301 recorded actions, 2-point techniques (52.16%) and 1-point techniques (43.85%) were dominant; only 3.99% were 4-point actions. GR primarily utilized body lock and gut wrench; FS favored single-leg attacks and leg lace. In WW, the scores were obtained from techniques applied in the par terre position with a high frequency (60.8%). Most victories in all styles occurred by points rather than technical superiority or falls. Conclusion: The findings reveal a strategic preference for low-risk, controlled techniques in high-level matches. These insights can inform evidence-based training and match preparation for future championships. Full article

Background: This study aimed to develop a method to analyze the kinetic and kinematic characteristics of the traditional karate Gyaku Tsuki (reverse punch), focusing on the activation sequence of lower and upper extremities and trunk muscles during execution. Methods: An elite male (N = 1) karate athlete (in kata) performed 20 Gyaku Tsuki punches while equipped with 16 wireless surface EMG sensors integrated with 3-axis accelerometers. The five punches with the highest forearm acceleration were selected for analysis. EMG, accelerometer, and synchronized video data were recorded and processed. Results: A novel visualization technique was developed to represent muscle activation over time, distinguishing a spectrum of 0–25–50–75–100% activation levels. Muscle activation times for arm, leg, and trunk muscles ranged from −0.31 to −0.11 s relative to punch execution, indicating rapid, coordinated muscle engagement. Conclusions: This method enables detailed analysis of muscle activation patterns in karate punches. It offers valuable insights for biomechanics researchers and practical applications for coaches aiming to enhance performance and prevent injuries through better understanding of movement dynamics. Full article