Search Results (19)

In the era of digital advancement, the integration of Deep Learning (DL) algorithms is revolutionizing performance monitoring in football. Due to restrictions on monitoring devices during games to prevent unfair advantages, coaches are tasked to analyze players’ movements and performance visually. As a result, Computer Vision (CV) technology has emerged as a vital non-contact tool for performance analysis, offering numerous opportunities to enhance the clarity, accuracy, and intelligence of sports event observations. However, existing CV studies in football face critical challenges, including low-resolution imagery of distant players and balls, severe occlusion in crowded scenes, motion blur during rapid movements, and the lack of large-scale annotated datasets tailored for dynamic football scenarios. This review paper fills this gap by comprehensively analyzing advancements in CV, particularly in four key areas: player/ball detection and tracking, motion prediction, tactical analysis, and event detection in football. By exploring these areas, this review offers valuable insights for future research on using CV technology to improve sports performance. Future directions should prioritize super-resolution techniques to enhance video quality and improve small-object detection performance, collaborative efforts to build diverse and richly annotated datasets, and the integration of contextual game information (e.g., score differentials and time remaining) to improve predictive models. The in-depth analysis of current State-Of-The-Art (SOTA) CV techniques provides researchers with a detailed reference to further develop robust and intelligent CV systems in football. Full article

Technological advancements have led to widespread use of wearable devices that capture external performance metrics in team sports. Tracking systems including global positioning system (GPS) technology with inbuilt microelectromechanical systems (MEMS), instrumented mouthguards (iMGs), and video analysis provide valuable insights into the contact demands of collision sports. In collision sports, successfully “winning the contact” is positively associated with better individual and team performance, but it also comes with a high risk of injury, posing a concern for player welfare. Understanding the frequency and intensity of these contact events is important in order for coaches and practitioners to adequately prepare players for competition and can simultaneously reduce the burden on athletes. Different methods have been developed for detecting contact events, although limitations of the current methods include validity and reliability issues, varying thresholds, algorithm inconsistencies, and a lack of code- and sex-specific algorithms. In this review, we evaluate common methods for capturing contact events in team collision sports and detail a new method for assessing contact intensity through notational analysis, offering a potential alternative for capturing contact events that are currently challenging to detect through microtechnology alone. Full article

In the current digital era, the Google Play Store and the App Store are major platforms for the distribution of mobile applications and games. Billions of users regularly download mobile games and provide reviews, which serve as a valuable resource for game vendors and developers, offering insights into bug reports, feature suggestions, and documentation of existing functionalities. This study showcases an innovative application of fine-tuned RoBERTa for detecting bugs in mobile phone games, highlighting advanced classification capabilities. This approach will increase player satisfaction, lead to higher ratings, and improve brand reputation for game developers, while also reducing development costs and saving time in creating high-quality games. To achieve this goal, a new bug detection dataset was created. Initially, data were sourced from four top-rated mobile games from multiple domains on the Google Play Store and the App Store, focusing on bugs, using the Google Play API and App Store API. Subsequently, the data were categorized into two classes: binary and multi-class. The Logistic Regression, Convolutional Neural Network (CNN), and pre-trained Robustly Optimized BERT Approach (RoBERTa) algorithms were used to compare the results. We explored the strength of pre-trained RoBERTa, which demonstrated its ability to capture both semantic nuances and contextual information within textual content. The results showed that pre-trained RoBERTa significantly outperformed the baseline models (Logistic Regression), achieving superior performance with a 5.49% improvement in binary classification and an 8.24% improvement in multi-class classification, resulting in cross-validation scores of 96% and 92%, respectively. Full article

Policy space response oracles (PSRO) is an important algorithmic framework for approximating Nash equilibria in two-player zero-sum games. Enhancing policy diversity has been shown to improve the performance of PSRO in this approximation process significantly. However, existing diversity metrics are often prone to redundancy, which can hinder optimal strategy convergence. In this paper, we introduce the policy similarity measure (PSM), a novel approach that combines Gaussian and cosine similarity measures to assess policy similarity. We further incorporate the PSM into the PSRO framework as a regularization term, effectively fostering a more diverse policy population. We demonstrate the effectiveness of our method in two distinct game environments: a non-transitive mixture model and Leduc poker. The experimental results show that the PSM-augmented PSRO outperforms baseline methods in reducing exploitability by approximately 7% and exhibits greater policy diversity in visual analysis. Ablation studies further validate the benefits of combining Gaussian and cosine similarities in cultivating more diverse policy sets. This work provides a valuable method for measuring and improving the policy diversity in two-player zero-sum games. Full article

Background/Objectives: This study compared step-by-step kinematic measurements from an infrared contact mat (IR-mat) and an inertial measurement unit (IMU) system during bounding and single leg jumping for speed, while also evaluating the validity of algorithms originally developed for sprinting and running when applied to horizontal jumps. The aim was to investigate differences in contact times between the systems. Methods: Nineteen female football players (15 ± 0.5 years, 61.0 ± 5.9 kg, 1.70 ± 0.06 m) performed attempts in both jumps over 20 m with maximum speed, of which the first eight steps were analysed. Results: Significant differences were found between the systems, with the IR-mat recording longer contact times than the IMU. The IR-mat began and ended its measurements slightly earlier and later, respectively, compared to the IMU system, likely due to the IMU’s algorithm, which was developed for sprinting with forefoot contact, while more midfoot and heel landing is used during jumps. Conclusions: Both systems provide reliable measurements; however, the IR mat consistently records slightly longer contact times for horizontal jumps. While the IMU is dependable, it exhibits a consistent bias compared to the IR mat. For bounding, the IR mat begins recording 0.018 s earlier at touch down and stops 0.021 s later. For single leg jumps, it starts 0.024 s earlier and ends 0.021 s later, resulting in contact times that are, on average, 0.039–0.045 s longer. These findings provide valuable insights for coaches and researchers in selecting appropriate measurement tools, highlighting the systematic differences between IR mats and IMUs in horizontal jump analysis. Full article

Games provide an excellent testing ground for machine learning and artificial intelligence, offering diverse environments with strategic challenges and complex decision-making scenarios. This study seeks to design a self-learning artificial intelligent agent capable of playing the trick-taking stage of the popular card game Thousand, known for its complex bidding system and dynamic gameplay. Due to the game’s vast state space and strategic complexity, other artificial intelligence approaches, such as Monte Carlo Tree Search and Deep Counterfactual Regret Minimisation, are infeasible. To address these challenges, the enhanced version of the REINFORCE policy gradient algorithm is proposed. Introducing a score-related parameter $\beta$ designed to guide the learning process by prioritising valuable games, the proposed approach enhances policy updates and improves overall learning outcomes. Moreover, leveraging the off-policy experience replay, along with the importance weighting of behavioural policy, enhanced training stability and reduced model variance. The proposed algorithm was applied to the trick-taking stage of the popular game Thousand Schnapsen in a two-player setup. Four distinct neural network models were explored to evaluate the performance of the proposed approach. A custom test suite of selected deals and tournament evaluations was employed to assess effectiveness. Comparisons were made against two benchmark strategies: a random strategy agent and an alpha-beta pruning tree search with varying search depths. The proposed algorithm achieved win rates exceeding 65% against the random agent, nearly 60% against alpha-beta pruning at a search depth of 6, and 55% against alpha-beta pruning at the maximum possible depth. Full article

This paper investigates the effectiveness of centrality measures for the influence maximization problem in competitive social networks (SNs). We consider a framework, which we call “I-Game” (Influence Game), to conceptualize the adoption of competing products as a strategic game. Firms, as players, aim to maximize the adoption of their products, considering the possible rational choice of their competitors under a competitive diffusion model. They independently and simultaneously select their seeds (initial adopters) using an algorithm from a finite strategy space of algorithms. Since strategies may agree to select similar seeds, it is necessary to include an initial seed tie-breaking rule into the game model of the I-Game. We perform an empirical study in a two-player game under the competitive independent cascade model with three different seed-tie-breaking rules using four real-world SNs. The objective is to compare the performance of centrality-based strategies with some state-of-the-art algorithms used in the non-competitive influence maximization problem. The experimental results show that Nash equilibria vary according to the SN, seed-tie-breaking rules, and budgets. Moreover, they reveal that classical centrality measures outperform the most effective propagation-based algorithms in a competitive diffusion setting in three graphs. We attempt to explain these results by introducing a novel metric, the Early Influence Diffusion (EID) index, which measures the early influence diffusion of a strategy in a non-competitive setting. The EID index may be considered a valuable metric for predicting the effectiveness of a strategy in a competitive influence diffusion setting. Full article

This study presents a novel system for diagnosing and evaluating soccer performance using wearable inertial sensors integrated into players’ insoles. Designed to meet the needs of professional podiatrists and sports practitioners, the system focuses on three key soccer-related movements: passing, shooting, and changes of direction (CoDs). The system leverages low-power IMU sensors, Bluetooth Low Energy (BLE) communication, and a cloud-based architecture to enable real-time data analysis and performance feedback. Data were collected from nine professional players from the SD Huesca women’s team during controlled tests, and bespoke algorithms were developed to process kinematic data for precise event detection. Results indicate high accuracy rates for detecting ball-striking events and CoDs, with improvements in algorithm performance achieved through adaptive thresholds and ensemble neural network models. Compared to existing systems, this approach significantly reduces costs and enhances practicality by minimizing the number of sensors required while ensuring real-time evaluation capabilities. However, the study is limited by a small sample size, which restricts generalizability. Future research will aim to expand the dataset, include diverse sports, and integrate additional sensors for broader applications. This system offers a valuable tool for injury prevention, player rehabilitation, and performance optimization in professional soccer, bridging technical advancements with practical applications in sports science. Full article

Background: Monitoring player mobility in wheelchair sports is crucial for helping coaches understand activity dynamics and optimize training programs. However, the lack of data from monitoring tools, combined with a lack of standardized processing approaches and ineffective data presentation, limits their usability outside of research teams. To address these issues, this study aimed to propose a simple and efficient algorithm for identifying locomotor tasks (static, forward/backward propulsion, pivot/tight/wide rotation) during wheelchair movements, utilizing kinematic data from standard wheelchair mobility tests. Methods: Each participant’s wheelchair was equipped with inertial measurement units—two on the wheel axes and one on the frame. A total of 36 wheelchair tennis and badminton players completed at least one of three proposed tests: the star test, the figure-of-eight test, and the forward/backward test. Locomotor tasks were identified using a five-step procedure involving data reduction, symbolic approximation, and logical pattern searching. Results: This method successfully identified 99% of locomotor tasks for the star test, 95% for the figure-of-eight test, and 100% for the forward/backward test. Conclusion: The proposed method offers a valuable tool for the simple and clear identification and representation of locomotor tasks over extended periods. Future research should focus on applying this method to wheelchair court sports matches and daily life scenarios. Full article

This research investigates clutch performance in the National Basketball Association (NBA) with a focus on the final minutes of contested games. By employing advanced data science techniques, we aim to identify key factors that enhance winning probabilities during these critical moments. The study introduces the Estimation of Clutch Competency (EoCC) metric, which is a novel formula designed to evaluate players’ impact under pressure. Examining player performance statistics over twenty seasons, this research addresses a significant gap in the literature regarding the quantification of clutch moments and challenges conventional wisdom in basketball analytics. Our findings deal valuable insights into player efficiency during the final minutes and its impact on the probabilities of a positive outcome. The EoCC metric’s validation through comparison with the NBA Clutch Player of the Year voting results demonstrates its effectiveness in identifying top performers in high-pressure situations. Leveraging state-of-the-art data science techniques and algorithms, this study analyzes play data to uncover key factors contributing to a team’s success in pivotal moments. This research not only enhances the theoretical understanding of clutch dynamics but also provides practical insights for coaches, analysts, and the broader sports community. It contributes to more informed decision making in high-stakes basketball environments, advancing the field of sports analytics. Full article

This study utilized advanced data mining and machine learning to examine player injuries in the National Basketball Association (NBA) from 2000–01 to 2022–23. By analyzing a dataset of 2296 players, including sociodemographics, injury records, and financial data, this research investigated the relationships between injury types and player recovery durations, and their socioeconomic impacts. Our methodology involved data collection, engineering, and mining; the application of techniques such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN), isolation forest, and the Z score for anomaly detection; and the application of the Apriori algorithm for association rule mining. Anomaly detection revealed 189 anomalies (1.04% of cases), highlighting unusual recovery durations and factors influencing recovery beyond physical healing. Association rule mining indicated shorter recovery times for lower extremity injuries and a 95% confidence level for quick returns from “Rest” injuries, affirming the NBA’s treatment and rest policies. Additionally, economic factors were observed, with players in lower salary brackets experiencing shorter recoveries, pointing to a financial influence on recovery decisions. This study offers critical insights into sports injuries and recovery, providing valuable information for sports professionals and league administrators. This study will impact player health management and team tactics, laying the groundwork for future research on long-term injury effects and technology integration in player health monitoring. Full article

The burgeoning electric vehicle industry has become a crucial player in tackling environmental pollution and addressing oil scarcity. As these vehicles continue to advance, effective thermal management systems are essential to ensure battery safety, optimize energy utilization, and prolong vehicle lifespan. This paper presents an exhaustive review of diverse thermal management approaches at both the component and system levels, focusing on electric vehicle air conditioning systems, battery thermal management systems, and motor thermal management systems. In each subsystem, an advanced heat transfer process with phase change is recommended to dissipate the heat or directly cool the target. Moreover, the review suggested that a comprehensive integration of AC systems, battery thermal management systems, and motor thermal management systems is inevitable and is expected to maximize energy utilization efficiency. The challenges and limitations of existing thermal management systems, including system integration, control algorithms, performance balance, and cost estimation, are discussed, along with potential avenues for future research. This paper is expected to serve as a valuable reference for forthcoming research. Full article

Stock price prediction is a significant area of research in finance that has been ongoing for a long time. Several mathematical models have been utilized in this field to predict stock prices. However, recently, machine learning techniques have demonstrated remarkable performance in stock price prediction. Moreover, XAI (explainable artificial intelligence) methodologies have been developed, which are models capable of interpreting the results of machine learning algorithms. This study utilizes machine learning to predict stock prices and uses XAI methodologies to investigate the factors that influence this prediction. Specifically, we investigated the relationship between the public’s interest in artists affiliated with four K-Pop entertainment companies (HYBE, SM, JYP, and YG). We used the Naver Keyword Trend and Google Trend index data for the companies and their representative artists to measure local and global interest. Furthermore, we employed the SHAP-XGBoost model to show how the local and global interest in each artist affects the companies’ stock prices. SHAP (SHapley Additive exPlanations) and XGBoost are models that show excellent results as XAI and machine learning methodologies, respectively. We found that SM, JYP, and YG are highly correlated, whereas HYBE is a major player in the industry. YG is influenced by variables from other companies, likely owing to HYBE being a major shareholder in YG’s subsidiary music distribution company. The influence of popular artists from each company was significant in predicting the companies’ stock prices. Additionally, the foreign ownership ratio of a company’s stocks affected the importance of Google Trend and Naver Trend indexes. For example, JYP and SM had relatively high foreign ownership ratios and were influenced more by Google Trend indexes, whereas HYBE and YG were influenced more by Naver Trend indexes. Finally, the trend indexes of artists in SM and HYBE had a positive correlation with stock prices, whereas those of YG and JYP had a negative correlation. This may be due to steady promotions and album releases from SM and HYBE artists, while YG and JYP suffered from negative publicity related to their artists and executives. Overall, this study suggests that public interest in K-Pop artists can have a significant impact on the financial performance of entertainment companies. Moreover, our approach offers valuable insights into the dynamics of the stock market, which makes it a promising technique for understanding and predicting the behavior of entertainment stocks. Full article

Online purchasing has developed rapidly in recent years due to its efficiency, convenience, low cost, and product variety. This has increased the number of online multi-category e-commerce retailers that sell a variety of product categories. Due to the growth in the number of players, each company needs to optimize its own business strategy in order to compete. Customer lifetime value (CLV) is a common metric that multi-category e-commerce retailers usually consider for competition because it helps determine the most valuable customers for the retailers. However, in this paper, we introduce two additional novel factors in addition to CLV to determine which customers will bring in the highest revenue in the future: distinct product category (DPC) and trend in amount spent (TAS). Then, we propose a new framework. We utilized, for the first time in the relevant literature, a multi-output deep neural network (DNN) model to test our proposed framework while forecasting CLV, DPC, and TAS together. To make this outcome applicable in real life, we constructed customer clusters that allow the management of multi-category e-commerce companies to segment end-users based on the three variables. We compared the proposed framework (constructed with multiple outputs: CLV, DPC, and TAS) against a baseline single-output model to determine the combined effect of the multi-output model. In addition, we also compared the proposed model with multi-output Decision Tree (DT) and multi-output Random Forest (RF) algorithms on the same dataset. The results indicate that the multi-output DNN model outperforms the single-output DNN model, multi-output DT, and multi-output RF across all assessment measures, proving that the multi-output DNN model is more suitable for multi-category e-commerce retailers’ usage. Furthermore, Shapley values derived through the explainable artificial intelligence method are used to interpret the decisions of the DNN. This practice demonstrates which inputs contribute more to the outcomes (a significant novelty in interpreting the DNN model for the CLV). Full article

In the power sector, competitive strategic bidding optimization has become a major challenge. Digital plate-form provides a superior technical base as well as backing for the optimization’s execution. The state-of-the-art frameworks used for simulating strategic bidding decisions in deregulated electricity markets (EM’s) in this article are bi-level optimization and neural networks. In this research, we provide HHO-NN (Harris Hawk Optimization-Neural network), a novel algorithm based on Harris Hawk Optimization (HHO) that is capable of fast convergence when compared to previous evolutionary algorithms for automatically searching for meaningful multilayered perceptron neural networks (MPNNs) topologies for optimal bidding. This technique usually demands a considerable amount of time and computer resources. This method sets up the problem in multi-dimensional continuous state-action spaces, allowing market players to get precise information on the effect of their bidding judgments on the market clearing results, as well as implement more valuable bidding decisions by utilizing a whole action domain and accounting for non-convex operating principles. Due to the use of the MPNN, case studies show that the suggested methodology delivers a much larger profit than other state-of-the-art methods and has a better computational performance than the benchmark HHO technique. Full article