Abstract: This study investigated the impact of AI-driven video analysis on the serve performance of national university elite male tennis players, focusing on speed and accuracy optimization. Using a pre-test/post-test design, 46 participants (23 experimental, 23 control) underwent an 8-week AI-guided training intervention. The experimental group received individualized biomechanical recommendations via 2D motion analysis using OpenPose. Results showed serve speed increased from 160.0 ± 6.0 km/h to 163.0 ± 5.8 km/h (p = 0.032) and accuracy from 65.0 ± 8.0% to 72.0 ± 7.0% (p < 0.001) in the experimental group, with significant improvements in shoulder rotation, elbow velocity, racket speed, and center of mass displacement (p < 0.05). The control group showed no significant changes. Knee flexion, toss height, trunk rotation, and racket angle remained unchanged (p > 0.05). Findings suggest AI video analysis effectively enhances serve performance, particularly accuracy, with low-cost scalability, though speed gains were modest, indicating a need for longer interventions. Future research could explore 3D analysis and broader populations.

Abstract: Artificial Intelligence (AI) faces a range of mathematical challenges, such as optimization, generalization, model interpretability, and phase transitions. These issues significantly limit the application of AI in critical domains such as medicine, autonomous systems, and finance. This article examines the primary mathematical problems of AI and proposes solutions based on the universality of the Riemann zeta function. Furthermore, AI, as a major trend attracting hundreds of billions of dollars, is now tasked with addressing humanity’s most complex challenges, including nuclear fusion, turbulence, the functioning of consciousness, the creation of new materials and medicines, genetic issues, and catastrophes such as earthquakes, volcanoes, tsunamis, as well as climatic and social upheavals, ultimately aiming to elevate civilization to a galactic level. All these problems, both listed and unlisted, are interconnected by the issue of prediction and the problem of “black swans” within existing challenges. This work offers an analysis of AI’s problems and potential pathways to overcome them, which, in our view, will strengthen existing trends established by our great predecessors, which we believe will become foundational in mastering AI.

Abstract: In this paper, we address the problem of obtaining bias-free and complete finite size approximations of the solution sets (Pareto fronts) of multi-objective optimization problems (MOPs). Such approximations are, in particular, required for the fair usage of distance-based performance indicators, which are frequently used in evolutionary multi-objective optimization (EMO). If the Pareto front approximations are biased or incomplete, the use of these performance indicators can lead to misleading or false information. To address this issue, we propose the Reference Set Generator (RSG), which can, in principle, be applied to Pareto fronts of any shape and dimension. We finally demonstrate the strength of the novel approach on several benchmark problems.

Abstract: This paper formally defines blockchain-based concepts by leveraging the relational model, a framework widely used for studying database systems. We review the cryptographic building blocks and structural aspects of blockchains, provide formal definitions of key security and consensus mechanisms, and illustrate these concepts through algorithmic descriptions and relational algebra. In addition, we analyze game-theoretic phenomena such as selfish mining to highlight how strategic behaviors affect network security and performance. This multifaceted approach offers a rigorous framework for understanding and further developing blockchain technology.

Abstract: Music, movies, books, pictures, and other media can change a user's emotions, which are important factors in recommending appropriate items. As users' emotions change over time, the content they select may vary accordingly. Existing emotion-based content recommendation methods primarily recommend content based on the user's current emotional state. In this study, we propose a continuous music recommendation method that adapts to a user's changing emotions. Based on Thayer's emotion model, emotions were classified into four areas, and music and user emotion vectors were created by analyzing the relationships between valence, arousal, and each emotion using a multiple regression model. Based on the user's emotional history data, a personalized mental model (PMM) was created using a Markov chain. PMM was used to predict future emotions and generate user emotion vectors for each period. A recommendation list was created by calculating the similarity between music emotion vectors and user emotion vectors. To prove the effectiveness of the proposed method, the accuracy of the music emotion analysis, user emotion prediction, and music recommendation results were evaluated. To evaluate the experiments, the PMM and the modified mental model (MMM) were used to predict user emotions and generate recommendation lists. The accuracy of the content emotion analysis was 87.26%, and the accuracy of user emotion prediction was 86.72%, an improvement of 13.68% compared with the MMM. Additionally, the balanced accuracy of the content recommendation was 79.31%, an improvement of 26.88% compared with the MMM. The proposed method can recommend content that is suitable for users.

Abstract: The quest for effective pedagogical practices in mathematics education has increasingly highlighted the flipped classroom model. This model has been shown to be particularly successful in higher education settings within developed countries, where resources and technological infrastructure are readily available. However, its implementation in secondary education, especially in developing nations, remains a critical area of investigation. Building on our earlier research which found that students rated flipped classroom model positively, this mixed-method study explored teachers’ experiences with implementing the model for mathematics instruction at the senior secondary level. Since teachers play a pivotal role as facilitators of this pedagogical approach, their understanding and perceptions of it can significantly im-pact its effectiveness. To gather insights into teachers’ experiences, this study employed both close-ended questionnaires and semi-structured interviews. Quantitative analysis of participants’ responses to the questionnaires, including mean scores, standard de-viations and Kruskal-Wallis H tests, revealed that teachers generally gave positive evaluations of their experiences with flipped classrooms, but also pinpointed notable differences in their assessments. Qualitative findings from the thematic analysis of the interview data provided insights into the specific support systems teachers require for successful adoption of the flipped classroom model for senior secondary mathematics instruction.

Abstract: This paper presents a novel approach for three-dimensional point cloud coordinate reconstruction using a depth-first search algorithm combined with rotational convex hull gift wrapping. The proposed method searches for optimal convex hulls by maximizing both the number of faces and the sum of squared face areas. Experimental results demonstrate that our algorithm achieves superior reconstruction accuracy with an average L2 norm error reduction of 18.7% compared to traditional methods. The algorithm shows particular promise for virtual reality applications, especially for placing interactive virtual objects at corners and edges to facilitate user interaction.

Abstract: We present a novel form of scalable knowledge representation about agents in a simulated democracy, e-polis, where real users respond to social challenges associated with democratic institutions, structured as Smart Spatial Types, a new type of Smart Building that changes architectural form according to the philosophical doctrine of a visitor. At the end of the game players vote on the Smart City that results from their collective choices.Our approach uses deductive systems in an unusual way: by integrating a model of democracy with a model of a Smart City we are able to prove quality aspects of the simulated democracy in different urban and social settings, while adding ease and flexibility to the development. Second, we can infer and reason with abstract knowledge, which is a limitation of the Unity platform; third, our system enables real-time decision-making and adaptation of the game flow based on the player’s abstract state, paving the road to explainability.Scalability is achieved by maintaining a dual-layer knowledge representation mechanism for reasoning about the simulated democracy that functions in a similar way to a two-level cache. The lower layer knows about the current state of the game by continually processing a high rate of events produced by the in-built physics engine of the Unity platform, e.g., it knows of the position of a player in space, in terms of his coordinates x,y,z as well as their choices for each challenge. The higher layer knows of easily-retrievable, user-defined abstract knowledge about current and historical states, e.g., it knows of the political doctrine of a Smart Spatial Type, a player’s philosophical doctrine, and the collective philosophical doctrine of a community players with respect to current social issues.

Abstract: Inspired by principles of the decision tree test method in software engineering, this paper provides a discussion on intelligent AI test modeling chat systems, including basic concepts, quality validation, test generation and augmentation, testing scopes, approaches, and needs. The novelty of the paper lies in an intelligent AI test modeling chatbot system that is built and implemented based on an innovative 3-dimensional AI test model for AI-powered functions in intelligent mobile apps to support model-based AI function testing, test data generation, and adequate test coverage result analysis.

Abstract:

With the advancement of VR technology, the demand for highly immersive virtual environments has increased, driving VR adoption across various fields. This has led to growing interest in physics-based 3D virtual environments, where real-world physical principles are incorporated. In virtual environments, undo functionality allows users to quickly recover from unintended errors. While conventional 2D undo mechanisms remain applicable in non-physics-based 3D virtual spaces, they are less effective in realistic physics-based 3D virtual environments, where objects are influenced by physical forces such as gravity and friction, leading to unintended cascading interactions among multiple objects. To address this challenge, this study proposes Action-based Undo, a novel 3D undo mechanism, designed to effectively restore cascading interactions. A user study with 24 participants, compared three conditions: Action-based Undo, Object-based Undo (a conventional 2D-like approach), and No Undo using a domino task in a physics-based 3D virtual environment. Experimental results showed that Action-based Undo required the fewest interactions and the shortest recovery time, demonstrating superior task efficiency. Usability evaluations indicated positive user responses when a 3D undo function was available, particularly for Action-based Undo and Object-based Undo. The proposed Action-based Undo mechanism provides an effective solution for enhancing efficiency and usability in physics-based 3D virtual environments where frequent cascading interactions occur.

Abstract:

Medical large language models(LLMs) possess huge potential in improving the quality of medical services. However, the problem of factual information has become a severe challenge that urgently needs to be overcome and is hindering the development of medical LLMs. Given this situation, this paper systematically introduces the "ShanZhiXingYu", which is committed to resolving eight key factual information problems, including the reliability of all sources of factual information, the real-time update of factual information, the high quality of the complete set of unique training data, the high efficiency of the complete set of reasoning logic algorithms, the full controllability of model effect verification, the interpretability of the professional knowledge base across the entire domain, the all-dimensional precision of personalized diagnosis and treatment, and the guarantee of data security and compliance throughout the whole chain. A series of innovative solutions have comprehensively strengthened the trustworthiness, controllability and interpretability of LLMs, laid a solid foundation and provided a powerful boost for their practical applications in the medical and health field, and thus served users, medical institutions and pharmaceutical enterprises with higher quality, promoting the steady development of the medical and health industry.

Abstract: Mathematics is fundamental to Information Technology (IT), underpinning key areas such as programming, cryptography, artificial intelligence (AI), and networking. However, many IT students perceive mathematics as abstract and disconnected from computing applications, leading to low engagement and weak competency. This study proposes the ITM-RPF, a structured pedagogical model designed to enhance IT students’ perception of mathematics by integrating it with real-world computing tasks. The ITM-RPF framework consists of four phases; Perception Analysis and Diagnostic, Contextualized Integration and Applied Learning, Experiential Simulation and Performance Enhancement, and Perception Shift Evaluation and Continuous Learning. A quasi-experimental research design was used with 152 undergraduate IT students at AAMUSTED, Ghana, assessing their mathematical competency and perceptions before and after a 12-week intervention. Results show a significant improvement in mathematical competency and perception, with post-intervention data indicating higher confidence, increased engagement, and stronger alignment with industry needs. Paired samples t-tests and descriptive statistics confirm that ITM-RPF effectively bridges the gap between mathematical theory and IT applications. This study contributes to IT education by providing a structured model that fosters applied learning and reshapes students' perceptions of mathematics.

Abstract: The increasing demand for engaging UI/UX designs has highlighted the importance of color selection as a critical element influencing user engagement and aesthetics. However, existing design tools such as Figma and Adobe XD lack advanced, context-aware AI functionalities, particularly in areas like automated palette generation, real-time analytics, and beginner-friendly interfaces. These gaps hinder accessibility for novice designers and force reliance on third-party plugins, which can complicate workflows. This study introduces AI-UIX, an AI-driven system that integrates functionalities such as image-based color extraction, palette generation using additive and subtractive models, and AI-powered recommendations through third-party APIs. The system is developed using modular methodologies and evaluated through computational complexity analysis, expert validation rubrics, and user-centered metrics like ease of use and feature relevance. Results showed that AI-UIX significantly enhances design workflows by automating color selection and generating contextually relevant palettes. Expert validation indicated strong accuracy and usability, with over 90% of participants rating the system as highly effective and user-friendly. Furthermore, computational analysis demonstrated linear scalability, making the system adaptable for both novice and advanced designers. AI-UIX addresses key limitations in existing tools and provides a streamlined, intuitive interface that bridges the gap for users with limited design expertise. This innovation has the potential to transform UI/UX design processes and will be further refined based on broader user feedback to extend its capabilities.

Abstract: The pervasive influence of technology and social media has transformed con- temporary life in unprecedented ways, yet beneath the surface lies a complex web of hidden costs that affect individuals, society, and ethical norms. This paper explores these multifaceted dimensions, illuminating critical issues such as misinformation, mental health implications, and the manipulative practices employed by technology and social media companies while presenting an in-depth analysis of the underlying factors contributing to these developments and the key stakeholders involved. It emphasises the necessity to scrutinise technology design and prevailing business models to ascertain their roles and responsibilities in shaping the ethical utilisation of innovative services, addressing the ethical dilemmas arising from data usage, privacy considerations, and the influence of persuasive technologies designed to capture user attention. Additionally, the rising prevalence of mental health challenges among adolescents in the social media era, the integration of advanced technologies, and the real-world consequences of weaponised social media are examined. Ultimately, the paper offers practical strategies to manage the influence of technology and mitigate its unintended consequences.

Abstract:

This study presents a novel encryption method for RGB (Red-Green-Blue) color images that combines scrambling techniques with the logistic map equation. In this method, image scrambling serves as a reversible transformation, rendering the image unintelligible to unauthorized users and thus enhancing security against potential attacks. The proposed encryption scheme, called Bit-Plane Representation of Quantum Images (BRQI), utilizes quantum operations in conjunction with a one-dimensional chaotic system to increase encryption efficiency. The encryption algorithm operates in two phases: first, the quantum image undergoes scrambling through bit-plane manipulation, and second, the scrambled image is mixed with a key image generated using the logistic map. To assess the performance of the algorithm, simulations and analyses were conducted, evaluating parameters such as entropy (a measure of disorder) and correlation coefficients confirm the effectiveness and robustness of this algorithm in safeguarding and encoding color images. The results show that the proposed quantum color image encryption algorithm surpasses classical methods in terms of security, robustness, and computational complexity.

Abstract: This work presents a methodology for rapidly generating many multi-modal journey alternatives including cheap, fast, green, convenient and low effort alternatives to private car journeys. The proposed methodology firstly generates a Pareto set of journey profiles based on static inter-transfer zone objective criteria contribution estimates. Secondly, integrated and extended versions of existing shortest path algorithms for open and public transport networks are used to optimise paths and transfer points in a procedure guided by neural networks while using real-time transport network information. A novel hybrid k-means and Dijkstra’s algorithm is introduced for generating transfer zone samples, in a way that accounts for transport network connectivity to ensure transfer feasibility. The end result is a modularised algorithm that knits together and extends the most effective existing shortest path algorithms for open and public transport networks using neural networks as a look ahead mechanism for generating many efficient multi-modal journey alternatives. In experiments based on a large scale transport network, query response times are shown to be suitable for real-time applications, and are found to be independent of transfer zone sample size, despite larger transfer zone samples leading to higher quality and more diverse Pareto sets of journeys, a win-win scenario.

Abstract: Supply chain risk prediction has become increasingly critical as organizations navigate complex and volatile environments characterized by rapid market changes, geopolitical uncertainties, and supply disruptions. In this context, effective risk management is essential for maintaining operational efficiency and competitiveness. This study proposes an innovative integrated model that combines Random Forest, Gradient Boosting Machine (GBM), and Neural Networks to enhance prediction accuracy and reliability in supply chain risk assessment. By employing comprehensive data preprocessing techniques—such as missing value imputation, normalization, and anomaly detection—alongside advanced algorithmic strategies, the model effectively addresses the limitations of traditional approaches. The integration of these diverse machine learning techniques not only leverages their individual strengths but also enhances the model's adaptability and robustness in varying scenarios.

Abstract:

The integration of artificial intelligence (AI) tools into graphic design education has gained attention as a means to simplify skill acquisition for beginners. Traditional graphic design tools often present steep learning curves, making it difficult for novice learners to acquire practical skills without extensive technical expertise. This paper proposes the IIH-AILP Model, a structured pedagogical framework designed to leverage AI-powered platforms such as Canva and Adobe Firefly to improve accessibility, inclusivity, and efficiency in graphic design education. The methodology employs a 12-week intervention with a mix of sequential and integrated components, including pre- and post-assessments, modular learning, skill progression, gamified engagement, and comparative evaluations. Participants’ design abilities were assessed across creativity, task completion time, and learning curve improvements using carefully designed evaluation metrics. The results demonstrate that the IIH-AILP model significantly reduces the learning curve, enhances creativity, and improves task efficiency, confirming the potential of AI-powered graphic design platforms to streamline education for beginners with little to no technical expertise.

Abstract: This study introduces a novel Gaussian process (GP) regression framework that probabilistically enforces physical constraints, with a particular focus on equality conditions. The GP model is trained using the quantum-inspired Hamiltonian Monte Carlo (QHMC) algorithm, which efficiently samples from a wide range of distributions by allowing a particle's mass matrix to vary according to a probability distribution. By integrating QHMC into the GP regression with probabilistic handling of the constraints, the approach balances the computational cost and accuracy in the resulting GP model as the probabilistic nature of the method contributes to shorter execution times compared with existing GP-based approaches. Additionally, an adaptive learning algorithm is introduced to optimize the selection of constraint locations, further enhancing the method's flexibility. The effectiveness and efficiency of this approach are demonstrated through several applications: estimating hyperparameters for high-dimensional GP models under noisy conditions and reconstructing a sparsely observed steady-state heat transport problem. The numerical results indicate that the proposed approach accelerates the process while maintaining the accuracy.

Abstract: Every Blockchain architecture is built upon two major pillars: a. The hash-based, block-binding mechanism and b. The consensus-achievement mechanism. While the entropic behavior of a. has been extensively studied in the literature over the past decades, the same does not hold for b. In this work, we explore the entropic behavior of the fully distributed Blockchain consensus mechanisms. We quantify the impact of witnessing as a consensus-achievement process under the perspectives of Shannon information entropy and Lyapunov stability. We demonstrate that Blockchain consensus, expressed as the complement of the collective disagreement in a system, is a Lyapunov function of the number of active witnesses W. The more the witnessing in a system, the less the entropy of the system becomes, pushing it to converge to more stable states. We prove that the entropy drop is steepest for low values of W. A new metric for the efficiency of the consensus process based on the Shannon information entropy is introduced, laying the foundations for future studies on Blockchain-based systems optimization.