Search Results (568)

Synthetic data has become an increasingly important tool for semantic segmentation, where collecting large-scale annotated datasets is often costly and impractical. Prior work has leveraged computer graphics and game engines to generate training data, but many pipelines remain limited to single modalities and constrained environments or require substantial manual setup. To address these limitations, we present a fully automated pipeline built within Unreal Engine 5 (UE5) that procedurally generates diverse, labeled environments and collects multimodal visual data for semantic segmentation tasks. Our system integrates UE5’s biome-based procedural generation framework with a spline-following drone actor capable of capturing both RGB and depth imagery, alongside pixel-perfect semantic segmentation labels. As a proof of concept, we generated a dataset consisting of 1169 samples across two visual modalities and seven semantic classes. The pipeline supports scalable expansion and rapid environment variation, enabling high-throughput synthetic data generation with minimal human intervention. To validate our approach, we trained benchmark computer vision segmentation models on the synthetic dataset and demonstrated their ability to learn meaningful semantic representations. This work highlights the potential of game-engine-based data generation to accelerate research in multimodal perception and provide reproducible, scalable benchmarks for future segmentation models. Full article

Background: This study examined the effects of high-intensity interval training with change of direction (HIITcod) and small-sided games (SSGs) on components of physical fitness in school-aged children. The aim was to provide practical insights for optimizing exercise interventions in constrained indoor environments. Methods: A randomized controlled trial was conducted during regular physical education (PE) classes in a school’s indoor sports hall. Fifty healthy boys (mean ± SD = 12.6 ± 0.6 years) were randomly assigned to a HIITcod group (n = 25) or an SSG group (n = 25). The intervention lasted eight weeks and consisted of structured training sessions designed to progressively increase intensity and training load in a child-friendly and safe environment. Individual maximal heart rate (HRmax) was determined using the 20 m shuttle run test prior to the intervention. Heart rate monitors were worn throughout all sessions to ensure exercise intensity consistently exceeded 75% of HRmax, with real-time monitoring used to adjust effort when necessary. Physical fitness outcomes, including the shuttle run test (SRT), handgrip strength (HG), 20 m sprint, standing broad jump (SBJ), Illinois agility test, and T-test, were assessed pre- and post-intervention. Results: Both groups demonstrated significant improvements over time in the SRT, SBJ, Illinois agility test, and T-test (p < 0.05). No significant group × time interactions were detected (all p > 0.05). Handgrip strength increased significantly in the HIITcod group (35.03 ± 7.19 kg to 36.80 ± 6.68 kg, p = 0.001, d = 0.25) and showed a non-significant trend in the SSG group (38.28 ± 9.09 kg to 39.23 ± 9.12 kg, p = 0.056). No significant changes were observed in 20 m sprint performance. Conclusions: Based on the study results, both HIITcod and SSGs were associated with improvements in multiple components of physical fitness in school-aged boys. These findings suggest that both training modalities may be viable options for implementation during physical education classes, particularly in limited indoor settings. The observed positive changes in fitness could indicate their potential to positively impact children’s fitness in a structured and engaging manner. Full article

Stock price forecasting remains a central challenge in financial modeling due to the non-stationarity, noise, and high dimensionality of market dynamics, as well as the growing importance of unstructured textual information. In this work, we propose a multimodal prediction framework that combines FinBERT-based financial sentiment extraction with technical and statistical indicators to forecast short-term stock price movement. Contextual sentiment signals are derived from financial news headlines using FinBERT, a domain-specific transformer model fine-tuned on annotated financial text. These signals are aggregated and fused with price- and volatility-based features, forming the input to a gradient-boosted decision tree classifier (XGBoost). To ensure interpretability, we employ SHAP (SHapley Additive exPlanations), which decomposes each prediction into additive feature attributions while satisfying game-theoretic fairness axioms. In addition, we integrate differential privacy into the training pipeline to ensure robustness against membership inference attacks and protect proprietary or client-sensitive data. Empirical evaluations across multiple S&P 500 equities from 2018–2023 demonstrate that our FinBERT-enhanced model consistently outperforms both technical-only and lexicon-based sentiment baselines in terms of AUC, F1-score, and simulated trading profitability. SHAP analysis confirms that FinBERT-derived features rank among the most influential predictors. Our findings highlight the complementary value of domain-specific NLP and privacy-preserving machine learning in financial forecasting, offering a principled, interpretable, and deployable solution for real-world quantitative finance applications. Full article

The real-time simulation of atmospheric clouds for the visualisation of outdoor scenarios has been a computer graphics research challenge since the emergence of the natural phenomena rendering field in the 1980s. In this work, we present an innovative method for real-time cumuli movement and transition based on a Recurrent Neural Network (RNN). Specifically, an LSTM, a GRU and an Elman RNN network are trained on time-series data generated by a parallel Navier–Stokes fluid solver. The training process optimizes the network to predict the velocity of cloud particles for the subsequent time step, allowing the model to act as a computationally efficient surrogate for the full physics simulation. In the experiments, we obtained natural-looking behaviour for cumuli evolution and dissipation with excellent performance by the RNN fluid algorithm compared with that of classical finite-element computational solvers. These experiments prove the suitability of our ontogenetic computational model in terms of achieving an optimum balance between natural-looking realism and performance in opposition to computationally expensive hyper-realistic fluid dynamics simulations which are usually in non-real time. Therefore, the core contributions of our research to the state of the art in cloud dynamics are the following: a progressively improved real-time step of the RNN-LSTM fluid algorithm compared to the previous literature to date by outperforming the inference times during the runtime cumuli animation in the analysed hardware, the absence of spatial grid bounds and the replacement of fluid dynamics equation solving with the RNN. As a consequence, this method is applicable in flight simulation systems, climate awareness educational tools, atmospheric simulations, nature-based video games and architectural software. Full article

This paper presents a corporate training approach that relies on cloud infrastructure and business process models to improve employee development. It introduces a cloud-based corporate hierarchy model that forms the basis for designing and implementing training materials and courses to achieve corporate strategy goals. The approach is based on business processes designed as BPMN diagrams to provide clarity of the process execution structure in the organization. The training course is also modelled using BPMN diagrams, which allows for a systematic and consistent presentation of the training content in all processes in which employees participate. The paper describes an experiment of simulated collaborative corporate training conducted during the learning process at one Bulgarian university. Within the experiment, gamification was integrated using game elements, game techniques, and competitive challenges, which stimulated the engagement of the learners and strengthened their motivation for active participation in corporate training. Full article

Physical activity (PA) integration in special education has gained recognition as a neuroeducational intervention supporting emotional and social development in students with special educational needs and disabilities (SEND), yet teacher perceptions remain underexplored. This cross-sectional study examined how Israeli special education teachers perceive physical activity’s benefits and how teaching experience and educational setting influence these perceptions. A structured questionnaire was administered to 45 female special education teachers from northern Israel. The instrument assessed perceptions of physical activity’s emotional benefits, social outcomes, and implementation practices using Likert-type scales. Teachers strongly endorsed PA as a means to foster emotional resilience and coping, with most preferring group-based activities. Mixed activities were the most preferred approach, followed by movement games. Experienced teachers reported significantly stronger perceptions of emotional benefits compared to less experienced colleagues. Secondary teachers demonstrated higher extracurricular promotion and perceived greater social benefits than elementary teachers. Despite positive attitudes, implementation barriers, including infrastructure limitations and training gaps, were evident. These findings highlight physical activity’s potential as a neuroeducational tool for fostering regulation and inclusion while revealing the need for differentiated professional development, infrastructure investment, and policy integration. Full article

Motor competence (MC) is defined as a global term that describes a person’s ability to be proficient in a wide range of motor acts. Based on this principle, we have created a training program that aims to determine the effect of 12 weeks of enriched athletics sports training with complementary motor activities on MC in children aged between 6 and 10 years old. The subjects will be divided into two groups: (i) the athletics training group (IG_A) that will participate in athletics training three times a week for 12 weeks, with 60 min sessions; and (ii) the athletics training + other activities group (IG_B) that will participate in athletics training twice a week and will have another activity training (gymnastics, handball, swimming, and motor games) for 12 weeks, with 60 min sessions. The two groups will be assessed at baseline and 12 weeks later. The KTK3+ will be used to assess MC. A between–within ANOVA-RM (2 [groups] × 2 [time points]) will be conducted. The results and conclusions of the implementation program will be presented in another study. Full article

Background/Objectives: Pediatric acquired brain injury (ABI) often results in persistent challenges that extend beyond motor impairments, affecting quality of life (QoL), social participation, and engagement in physical activity. Given the complexity and chronicity of these outcomes, there is a pressing need for multidimensional interventions grounded in the International Classification of Functioning, Disability and Health (ICF). Sport-based exercise interventions, when developmentally adapted and tailored to individual interests, may promote intrinsic motivation, peer connection, and sustainable engagement—factors especially relevant in pediatric ABI populations, who often experience reduced physical activity and social isolation. However, standardized, replicable protocols specifically tailored to this population remain scarce. This study presents the protocol for a randomized controlled trial evaluating the effects of a 16-week sport-based intervention on QoL, social participation, physical activity engagement, and motor functioning tailored for adolescents with pediatric ABI. Methods: Participants will be randomly assigned to an intervention group or a control group receiving usual care. The intervention consists of one weekly 60-minute session, led by trained professionals in adapted physical activity and pediatric neurorehabilitation. It combines sport-based motor skill training, cooperative games, and group activities specifically tailored to each child’s developmental level, motor abilities, and preferences. Outcomes will be assessed at baseline and following the 16-week intervention period, focusing on QoL, participation, physical activity engagement, and motor functioning. Discussion: This study introduces a structured, child-centered model that bridges clinical rehabilitation and community-based sport. By integrating motor and psychosocial targets through a group sport-based intervention, it aims to enhance recovery across ICF domains. Findings may inform interdisciplinary practice and support the development of sustainable strategies to promote long-term engagement and well-being in adolescents with ABI. Full article

In this paper, an Enhanced Greylag Goose Optimization Algorithm (EGGO) based on evolutionary game theory is presented to address the limitations of the traditional Greylag Goose Optimization Algorithm (GGO) in global search ability and convergence speed. By incorporating dynamic strategy adjustment from evolutionary game theory, EGGO improves global search efficiency and convergence speed. Furthermore, EGGO employs dynamic grouping, random mutation, and local search enhancement to boost efficiency and robustness. Experimental comparisons on standard test functions and the CEC 2022 benchmark suite show that EGGO outperforms other classic algorithms and variants in convergence precision and speed. Its effectiveness in practical optimization problems is also demonstrated through applications in engineering design, such as the design of tension/compression springs, gear trains, and three-bar trusses. EGGO offers a novel solution for optimization problems and provides a new theoretical foundation and research framework for swarm intelligence algorithms. Full article

Video games, especially competitive ones such as Dota 2, have gained great relevance both as entertainment and in e-sports, where predicting the outcome of games can offer significant strategic advantages. In this context, machine learning (ML) is presented as a useful tool for analysing and predicting performance in these games based on data collected before the start of the games, such as character selection information. Thus, in this work, we have developed and tested ML models, including Random Forest and Gradient Boosting, to predict the outcome of Dota 2 matches. This study is innovative in that it incorporates explainability techniques using Shapley Additive Explanations (SHAP) graphs, allowing us to understand which specific factors influence model predictions. Data extracted from the OpenDota API were preprocessed and used to train the models, evaluating them using metrics such as accuracy, precision, recall, F1-score, and cross-validated accuracy. The results indicate that predictive models, particularly Random Forest, can accurately predict game outcomes based only on pregame information, also suggesting that the explainability of machine learning techniques can be effective for analysing strategic factors in competitive video games. Full article

This study examines the influence of software agents on information-sharing behavior within security-sensitive organizations, where confidentiality and hierarchical culture often limit the flow of knowledge. While such organizations aim to collect, analyze, and disseminate information for security purposes, internal sharing dynamics are shaped by competing norms of secrecy and collaboration. To explore this tension, we developed a digital simulation game in which participants from security-sensitive organizations engaged in collaborative tasks over three rounds. In rounds two and three, software agents were introduced to interact with participants by sharing public and classified information. A total of 28 participants took part, generating 1626 text-based interactions. Findings indicate that (1) information-sharing patterns in security-sensitive contexts differ significantly from those in non-sensitive environments; (2) when software agents share classified information, participants are more likely to share sensitive data in return; (3) when participants are aware of the agents’ presence, they reduce classified sharing and increase public sharing; and (4) agents that share both public and classified information lead to decreased public and increased classified sharing. These results provide insight into the role of artificial agents in shaping communication behaviors in secure environments and inform strategies for training and design in knowledge-sensitive organizational settings. Full article

Serious games are an important tool for education and training that offers interactive and powerful experience. However, a significant challenge lays with adapting a game to meet the specific needs of each player in real-time. The present paper introduces a framework to guide the development of serious games using a phased approach. The framework introduces a level of standardization for the game elements, scenarios and data descriptions, mainly to support portability, interpretability and comprehension. This standardization is achieved through semantic annotation and it is utilized by digital twins to support self-adaptation. The proposed approach describes the game environment using ontologies and specific semantic structures, while it collects and semantically tags data during players’ interactions, including performance metrics, decision-making patterns and levels of engagement. This information is then used by a digital twin for automatically adjusting the game experience using a set of rules defined by a group of domain experts. The framework thus follows a hybrid approach, combing expert knowledge with automated adaptation actions being performed to ensure meaningful educational content delivery and flexible, real-time personalization. Real-time adaptation includes modifying the game’s level of difficulty, controlling the learning ability support and maintaining a suitable level of challenge for each player based on progress. The framework is demonstrated and evaluated using two real-word examples, the first targeting at supporting the education of children with syndromes that affect their learning abilities in close collaboration with speech therapists and the second being involved with training engineers in a poultry meat factory. Preliminary, small-scale experimentation indicated that this framework promotes personalized and dynamic user experience, with improved engagement through the adjustment of gaming elements in real-time to match each player’s unique profile, actions and achievements. Using a specially prepared questionnaire the framework was evaluated by domain experts that suggested high levels of usability and game adaptation. Comparison with similar approaches via a set of properties and features indicated the superiority of the proposed framework. Full article

Foodborne diseases remain a major global health issue, with over 250 illnesses linked to contaminated food. Effective food safety management relies on well-trained handlers; however, traditional classroom-based, passive learning often lacks engagement and efficacy, limiting awareness and hindering the development of a strong food safety culture. Gamification offers a promising alternative for vocational training, enhancing motivation and engagement through interactive, emotionally engaging learning experiences. This study aims to evaluate the user’s perception of a gamification-based training system (Food Safety Trainer, FST web app) developed and implemented for the training of food handlers in a large-scale retail company in Tuscany, Italy. A total of 249 employees completed a survey after using FST web app for their annual training. Seniority was used as the primary variable to assess differences among respondents. Although some slight variations in opinion emerged, the results indicate that the web app was generally more appreciated than traditional learning. Gamification demonstrated great potential as a tool for enhancing engagement, promoting team building, and supporting the development of a food safety culture. Future studies could extend the evaluation beyond user perception by assessing the system’s effectiveness, comparing outcomes and performance through specific indicators. Full article

The exponential growth in artificial intelligence (AI) and automation technologies is changing industries, creating a niche for a digitally competent workforce. Technical and vocational education (TVET) and training institutions are at the center of this transformational wave, with their role of equipping individuals with the competencies required for the digital era. The integration of AI and automation into the TVET curriculum and practice was explored as a game-changer for vocational education and training. AI-powered tools are used for personalized learning, intelligent tutoring systems, and virtual simulation of hands-on skills acquisition. The challenges and opportunities in using the technologies were explored to mitigate the digital divide, update instructor capabilities, and ensure inclusive access to modern training resources. Based on the results, TVET institutions can educate students, aligning with the need for Industry 4.0/5.0. Strategic frameworks for policy, curriculum design, and industry partnerships must be established to ensure that TVET continues to play a pivotal role in sustainable and equitable digital transformation. Full article

Background/Objectives: Frailty is a prevalent geriatric syndrome associated with impaired postural control and elevated fall risk. Although conventional exercise is a core strategy for frailty management, adherence remains limited. Virtual reality (VR)-based interventions have emerged as potentially engaging alternatives, but their effects on objective postural control and task-specific confidence in frail populations remain understudied. This study aimed to evaluate the effectiveness of a supervised VR training program using the Nintendo Ring Fit Plus™ on postural control, functional mobility, and balance confidence among frail community-dwelling older adults. Methods: Fifty-one adults aged ≥65 years classified as frail or prefrail were enrolled in a four-week trial. Participants were assigned to either a VR intervention group (n = 28) or control group (n = 23). Participants were non-randomly assigned based on availability and preference. Outcome measures were collected at baseline and post-intervention. Primary outcomes included center of pressure (CoP) metrics—sway area, mean velocity, and sway path. Secondary outcomes were the Timed Up and Go (TUG), Berg Balance Scale (BBS), Activities-specific Balance Confidence (ABC), and Falls Efficacy Scale–International (FES-I). Results: After adjusting for baseline values, age, and BMI, the intervention group showed significantly greater improvements than the control group across all postural control outcomes. Notably, reductions in sway area, mean velocity, and sway path were observed under both eyes-open and eyes-closed conditions, with effect sizes ranging from moderate to very large (Cohen’s d = 0.57 to 1.61). For secondary outcomes, significant between-group differences were found in functional mobility (TUG), balance performance (BBS), and balance confidence (ABC), with moderate-to-large effect sizes (Cohen’s d = 0.53 to 0.73). However, no significant improvement was observed in fear of falling (FES-I), despite a small-to-moderate effect size. Conclusions: A supervised VR program significantly enhanced postural control, mobility, and task-specific balance confidence in frail older adults. These findings support the feasibility and efficacy of VR-based training as a scalable strategy for mitigating frailty-related mobility impairments. Full article