This study proposes a reinforcement learning-based adaptive running motion simulation for a unilateral transtibial amputee with the flexibility of a leaf-spring-type sports prosthesis using hybrid-link system. The design and selection of sports prostheses often rely on trial and error. A comprehensive whole-body dynamics analysis that considers the interaction between human motion and prosthetic deformation could provide valuable insights for user-specific design and selection. The hybrid-link system facilitates whole-body dynamics analysis by incorporating the Piece-wise Constant Strain model to represent the flexible deformation of the prosthesis. Based on this system, the simulation methodology generates whole-body dynamic motions of a unilateral transtibial amputee through a reinforcement learning-based approach, which combines imitation learning from motion capture data with accurate prosthetic dynamics computation. We simulated running motions under different virtual prosthetic stiffness conditions and analyzed the metabolic cost of transport obtained from the simulations, suggesting that variations in stiffness influence running performance. Our findings demonstrate the potential of this approach for simulation and analysis under virtual conditions that differ from real conditions.
Safety education is important for young athletes because it reduces injuries and serves as a stepping stone to becoming a professional athlete. Mandatory safety education and legislation for sports players are being discussed, but no progress has been made thus far. Therefore, this study investigated how young Korean athletes’ participation in sports safety education is related to sports injuries, sports safety awareness, and sports activity habits. We sourced all the data of 3262 professional athletes aged 13 to 18 years from the 2019 Sports Safety Accident Survey. We analyzed the data using SPSS for Windows (version 23.0; IBM Corp., Armonk, NY). Frequency analysis, chi-square analysis, and multivariate logistic regression were performed. The results revealed that the more athletes participate in safety education, the less likely they are to have sports injuries and the more likely they are to develop safety awareness and beneficial activity habits such as managing accidents. Additionally, those who participate in safety education are more likely to carry enough water to stay hydrated during exercise than those who do not. Overall, the results suggest that safety education should be emphasized for athletes from a young age, as it helps prevent injuries and improve performance. A governance-based safety education system must be established so young athletes can participate in safety education. Furthermore, safety education must be regular and sports-specific.
In recent years, radiology has become a key factor in sports clinical decision-making, primarily due to two parallel trends: the need for timely imaging in elite sports and the increase in recreational and weekend exercise-related injuries among individuals who adopt a healthy lifestyle, often in outdoor settings and without structured physical preparation [...]
Introduction: Authors of numerous publications released over the past several decades have emphasized the increasing importance and significance of different forms of non-formal learning, including extra-curricular and out-of-school activities that are expected to respond to the needs and expectations of pupils, and to promote development of their interests. This paper attempts to examine the currently available offer of complementary classes for primary school pupils and to describe the most frequently pursued ones.
Research Aim: The purpose of the study was to learn about activities in which learners engage during their leisure time and to describe the extra-curricular and out-of-school activities addressed to primary school pupils. The study was intended to respond to the question of what extra-curricular and out-of-school activities have been organised and what the level of pupil attendance is.
Method: Diagnostic survey wasthe applied research design. It was addressed to primary school pupils attending grades 6 to 8and was administered online. Our analyses included 868 questionnaires correctly completed by young respondents from four Polish provinces.
Results: The study revealed two more or less equally numbered groups of pupils: active pupils, engaging in different non-compulsory activities and significant number of pupils not using any form of organised non-formal activities. Different types of activities extending the school curriculum as well as sports classes were the prevailing types of activities.
Conclusions: The goal should be to make extra-curricular and out-of-school activities more varied to make them refer to formal education to a much smaller extent, and to reveal more areas of human activity.
Massive irreparable rotator cuff tears are difficult to restore when the tendon quality is poor, and the tendon retraction prevents complete repair. In such cases, tendon allograft bridging can restore continuity but cannot replicate the native tendon–bone interface. In this study, we evaluated an Achilles-tendon–bone block allograft (BTA) for anatomic tendon–bone interface reconstruction in a rabbit model of chronic massive rotator cuff tear. Thirty-six rabbits underwent bilateral infraspinatus tendon detachment, followed by repair after 3 weeks using direct suture (DS), tendon allograft without bone block (TA), or BTA. At 8 and 16 weeks, we assessed the magnetic-resonance-imaging-based tendon maturation (signal-to-noise quotient (SNQ)), micro-computed-tomography-based bone volume fraction (BV/TV) and histology, immunohistochemistry (COL I, II, X), and biomechanical-testing-based healing. The BTA group showed superior tendon continuity, significantly lower SNQ, and higher BV/TV than the DS and TA groups (p < 0.05) at both timepoints. The histological examination demonstrated denser collagen fibers, greater fibrocartilage formation, and complete bone–bone fusion in BTA. The immunohistochemical assessment revealed higher COL II and COL X expression, indicating advanced fibrocartilage maturation and mineralization. At 16 weeks, the BTA group achieved the highest ultimate load to failure (113.45 ± 14.45 N) and stiffness (19.65 ± 3.41 N/mm) values, exceeding those of the TA and DS groups (p < 0.05). These results indicate that the Achilles-tendon–bone block allograft bridge effectively reconstructs the layered tendon–bone interface, promotes osteointegration and fibrocartilage regeneration, and enhances biomechanical strength, all of which support its potential as a translational option for functional enthesis reconstruction in massive rotator cuff tear repair.
Luiz Augusto Brusaca, Nidhi Gupta, David M. Hallman
et al.
Abstract Background Physical behaviours over a 24-hour period are important for health. However, we do not know if interventions using a “24-hour time-use approach” are more effective in improving 24-hour time-use behaviours than the traditional “reduce sitting at work approach”. Thus, the aim of our non-randomised controlled study was to investigate this in a high-risk group of overweight and obese Brazilian office workers. Methods Forty-five office workers were allocated to three non-randomised controlled groups; “Reduce sitting at work” (n = 15) receiving an intervention focused on reducing sitting time at work; the “24-hour” (n = 15) receiving an intervention aiming to reduce sitting at work as well as promoting behavioural changes around 24 hours (e.g., sedentary lifestyle, benefits of physical activity, and healthy sleep hygiene); or “control” (n = 15) without any intervention. Daily time spent in physical behaviours (sitting, standing, active, and in bed) was monitored for 7 days using a thigh-worn accelerometer at baseline, and at the 3- and 6-month follow-ups. Intervention effects were analysed using linear mixed models, adjusted for baseline values, age, and sex, with a compositional data analysis approach. Results At baseline, the demographic characteristics and 24-hour physical behaviours of the groups were similar. No significant intervention effect was observed between the intervention groups for the overall 24-hour composition, except for time-in-bed, which decreased for Reduce sitting at work compared to 24-hour group from baseline to the 6-month follow-up (p-value = 0.02). Compared to the control group, both intervention approaches resulted in less time spent sitting, more time standing, and less time-in-bed from baseline to the 3-month follow-up, but these effects were not sustained at the 6-month follow-up. Notably, domain-specific (i.e., work and leisure) analysis revealed that most changes in the overall 24-hour composition occurred due to changes in behaviours during working hours. Conclusions Among Brazilian overweight and obese office workers, the “24-hour time-use approach” may not lead to better improvements in overall 24-hour composition of physical behaviours compared to the traditional “reduce sitting at work approach”.
The use of Large Language Models (LLMs) in recent years has also given rise to the development of Multimodal LLMs (MLLMs). These new MLLMs allow us to process images, videos and even audio alongside textual inputs. In this project, we aim to assess the effectiveness of MLLMs in analysing sports videos, focusing mainly on tennis videos. Despite research done on tennis analysis, there remains a gap in models that are able to understand and identify the sequence of events in a tennis rally, which would be useful in other fields of sports analytics. As such, we will mainly assess the MLLMs on their ability to fill this gap - to classify tennis actions, as well as their ability to identify these actions in a sequence of tennis actions in a rally. We further looked into ways we can improve the MLLMs' performance, including different training methods and even using them together with other traditional models.
In this paper, we present a novel architecture for interactive segmentation in winter sports contexts. The field of interactive segmentation deals with the prediction of high-quality segmentation masks by informing the network about the objects position with the help of user guidance. In our case the guidance consists of click prompts. For this task, we first present a baseline architecture which is specifically geared towards quickly responding after each click. Afterwards, we motivate and describe a number of architectural modifications which improve the performance when tasked with segmenting winter sports equipment on the WSESeg dataset. With regards to the average NoC@85 metric on the WSESeg classes, we outperform SAM and HQ-SAM by 2.336 and 7.946 clicks, respectively. When applied to the HQSeg-44k dataset, our system delivers state-of-the-art results with a NoC@90 of 6.00 and NoC@95 of 9.89. In addition to that, we test our model on a novel dataset containing masks for humans during skiing.
Nico Krull, Lukas Schulthess, Michele Magno
et al.
Biomechanical data acquisition in sports demands sub-millisecond synchronization across distributed body-worn sensor nodes. This study evaluates and characterizes the Enhanced ShockBurst (ESB) protocol from Nordic Semiconductor under controlled laboratory conditions for wireless, low-latency command broadcasting, enabling fast event updates in multi-node systems. Through systematic profiling of protocol parameters, including cyclic-redundancy-check modes, bitrate, transmission modes, and payload handling, we achieve a mean Device-to-Device (D2D) latency of 504.99 +- 96.89 us and a network-to-network core latency of 311.78 +- 96.90 us using a one-byte payload with retransmission optimization. This performance significantly outperforms Bluetooth Low Energy (BLE), which is constrained by a 7.5 ms connection interval, by providing deterministic, sub-millisecond synchronization suitable for high-frequency (500 Hz to 1000 Hz) biosignals. These results position ESB as a viable solution for time-critical, multi-node wearable systems in sports, enabling precise event alignment and reliable high-speed data fusion for advanced athlete monitoring and feedback applications.
Automated sports skill assessment requires capturing fundamental movement patterns that distinguish expert from novice performance, yet current video sampling methods disrupt the temporal continuity essential for proficiency evaluation. To this end, we introduce Proficiency-Aware Temporal Sampling (PATS), a novel sampling strategy that preserves complete fundamental movements within continuous temporal segments for multi-view skill assessment. PATS adaptively segments videos to ensure each analyzed portion contains full execution of critical performance components, repeating this process across multiple segments to maximize information coverage while maintaining temporal coherence. Evaluated on the EgoExo4D benchmark with SkillFormer, PATS surpasses the state-of-the-art accuracy across all viewing configurations (+0.65% to +3.05%) and delivers substantial gains in challenging domains (+26.22% bouldering, +2.39% music, +1.13% basketball). Systematic analysis reveals that PATS successfully adapts to diverse activity characteristics-from high-frequency sampling for dynamic sports to fine-grained segmentation for sequential skills-demonstrating its effectiveness as an adaptive approach to temporal sampling that advances automated skill assessment for real-world applications. Visit our project page at https://edowhite.github.io/PATS
Over the past four decades, cheerleading has evolved from a sideline activity at major sporting events into a professional, competitive sport with growing global popularity. Evaluating tumbling elements in cheerleading relies on both objective measures and subjective judgments, such as difficulty and execution quality. However, the complexity of tumbling - encompassing team synchronicity, ground interactions, choreography, and artistic expression - makes objective assessment challenging. Artificial intelligence (AI) has revolutionized various scientific fields and industries through precise data-driven analyses, yet their application in acrobatic sports remains limited despite significant potential for enhancing performance evaluation and coaching. This study investigates the feasibility of using an AI-based approach with data from a single inertial measurement unit to accurately identify and objectively assess tumbling elements in standard cheerleading routines. A sample of 16 participants (13 females, 3 males) from a Division I collegiate cheerleading team wore a single inertial measurement unit at the dorsal pelvis. Over a 4-week seasonal preparation period, 1102 tumbling elements were recorded during regular practice sessions. Using triaxial accelerations and rotational speeds, various ML algorithms were employed to classify and evaluate the execution of tumbling manoeuvres. Results indicate that certain machine learning models can effectively identify different tumbling elements despite inter-individual variability and data noise, achieving high accuracy. These findings demonstrate the significant potential for integrating AI-driven assessments into cheerleading and other acrobatic sports, providing objective metrics that complement traditional judging methods.
The rapid growth of big data and advancements in computational techniques have significantly transformed sports analytics. However, the diverse range of data sources -- including structured statistics, semi-structured formats like sensor data, and unstructured media such as written articles, audio, and video -- creates substantial challenges in extracting actionable insights. These various formats, often referred to as multimodal data, require integration to fully leverage their potential. Conventional systems, which typically prioritize structured data, face limitations when processing and combining these diverse content types, reducing their effectiveness in real-time sports analysis. To address these challenges, recent research highlights the importance of multimodal data integration for capturing the complexity of real-world sports environments. Building on this foundation, this paper introduces GridMind, a multi-agent framework that unifies structured, semi-structured, and unstructured data through Retrieval-Augmented Generation (RAG) and large language models (LLMs) to facilitate natural language querying of NFL data. This approach aligns with the evolving field of multimodal representation learning, where unified models are increasingly essential for real-time, cross-modal interactions. GridMind's distributed architecture includes specialized agents that autonomously manage each stage of a prompt -- from interpretation and data retrieval to response synthesis. This modular design enables flexible, scalable handling of multimodal data, allowing users to pose complex, context-rich questions and receive comprehensive, intuitive responses via a conversational interface.
Human action video recognition has recently attracted more attention in applications such as video security and sports posture correction. Popular solutions, including graph convolutional networks (GCNs) that model the human skeleton as a spatiotemporal graph, have proven very effective. GCNs-based methods with stacked blocks usually utilize top-layer semantics for classification/annotation purposes. Although the global features learned through the procedure are suitable for the general classification, they have difficulty capturing fine-grained action change across adjacent frames -- decisive factors in sports actions. In this paper, we propose a novel ``Cross-block Fine-grained Semantic Cascade (CFSC)'' module to overcome this challenge. In summary, the proposed CFSC progressively integrates shallow visual knowledge into high-level blocks to allow networks to focus on action details. In particular, the CFSC module utilizes the GCN feature maps produced at different levels, as well as aggregated features from proceeding levels to consolidate fine-grained features. In addition, a dedicated temporal convolution is applied at each level to learn short-term temporal features, which will be carried over from shallow to deep layers to maximize the leverage of low-level details. This cross-block feature aggregation methodology, capable of mitigating the loss of fine-grained information, has resulted in improved performance. Last, FD-7, a new action recognition dataset for fencing sports, was collected and will be made publicly available. Experimental results and empirical analysis on public benchmarks (FSD-10) and self-collected (FD-7) demonstrate the advantage of our CFSC module on learning discriminative patterns for action classification over others.
This study investigates the effectiveness of Large Language Models (LLMs) in processing semi-structured data from PDF documents into structured formats, specifically examining their application in updating the Finnish Sports Clubs Database. Through action research methodology, we developed and evaluated an AI-assisted approach utilizing OpenAI's GPT-4 and Anthropic's Claude 3 Opus models to process data from 72 sports federation membership reports. The system achieved a 90% success rate in automated processing, successfully handling 65 of 72 files without errors and converting over 7,900 rows of data. While the initial development time was comparable to traditional manual processing (three months), the implemented system shows potential for reducing future processing time by approximately 90%. Key challenges included handling multilingual content, processing multi-page datasets, and managing extraneous information. The findings suggest that while LLMs demonstrate significant potential for automating semi-structured data processing tasks, optimal results are achieved through a hybrid approach combining AI automation with selective human oversight. This research contributes to the growing body of literature on practical LLM applications in organizational data management and provides insights into the transformation of traditional data processing workflows.
Customer segmentation is a fundamental process to develop effective marketing strategies, personalize customer experience and boost their retention and loyalty. This problem has been widely addressed in the scientific literature, yet no definitive solution for every case is available. A specific case study characterized by several individualizing features is thoroughly analyzed and discussed in this paper. Because of the case properties a robust and innovative approach to both data handling and analytical processes is required. The study led to a sound proposal for customer segmentation. The highlights of the proposal include a convenient data partition to decompose the problem, an adaptive distance function definition and its optimization through genetic algorithms. These comprehensive data handling strategies not only enhance the dataset reliability for segmentation analysis but also support the operational efficiency and marketing strategies of sports centers, ultimately improving the customer experience.
Over the last decade, there has been a significant increase in the development of mobile applications to deliver various services in sports, including psychological skills training (PST) for athletes. While there are numerous PST-related apps available, little attention has been given to their objective quality. This study aimed to assess the current offerings of PST apps in sports, rate their quality, and provide recommendations for future app development. A scoping review of PST-related apps available on the Apple App Store was conducted, resulting in the retention of 19 apps. The apps used different media types to develop the PST. Of the 19 apps, videos were used by 8 (42%), audios by 7 (37%), articles by 3 (16%), assessment by 4 (21%), ebook by 1 (5%), and both cognitive tasks and personalized journals by 2 (10%). Overall, the app quality measured through the Mobile App Rating Scale (MARS) failed to meet acceptable standards, with a mean rating of 2.78 and only 6 of the apps receiving a score that met the acceptable standards. The findings highlight the need for improvement in the development of PST apps to enhance their quality and usability.