Tushar Gupta and Shirin Bhambhani, Senior Member, IEEE, USA
The exponential growth of the Internet of Things (IoT) has introduced significant challenges in managing scalability, availability, and efficiency. With billions of interconnected devices generating vast amounts of data, traditional frameworks struggle to handle the complex requirements of modern IoT applications. Addressing these challenges is crucial to fully leverage the potential of IoT in various domains, including smart homes, healthcare, and industrial automation. This paper proposes a novel framework for integrating IoT applications with cloud environments to achieve scalability and high availability. The framework is structured into four layers: the device layer leverages Message Queuing Telemetry Transport (MQTT) as a low overhead communication protocol;the edge gateway layer aggregates data using lightweight Kubernetes; the ingestion and cloud infrastructure layer employs Kafka and Apache Spark for ingesting data and data transformation; and the data processing and analytics layer utilizes the cloud infrastructure layer to send the data to databases for data visualization. By leveraging cloud environments, this solution enhances scalability, availability, and overall system robustness. This paper also explores the challenges involved in implementing such an architecture, and provides insights into future advancements in IoT cloud integration.
Internet of Things (IoT), IoT architecture, Cloud Computing.
Alana Wu1, Andrew Park2, 1Orange County School of the Arts, 1010 N Main St, Santa Ana, CA 92701, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Performance anxiety, commonly known as stage fright, poses significant challenges for individuals aiming to enhance their singing abilities and stage presence [1]. To address this issue, we have developed a virtual reality (VR) simulation that replicates a concert environment, offering users a safe and controlled space to practice and improve their performance skills. The program integrates a Vocal Engine for real-time pitch analysis, an immersive VR environment that mirrors both on-stage and off-stage settings, and a diverse song library with synchronized lyrics [2]. Key challenges included ensuring accurate pitch detection, which we addressed by broadening the range of permissible pitch variations, and enhancing user immersion through detailed stage designs and dynamic movements. During experimentation, users engaged with the VR simulation across various scenarios, receivingimmediate feedback to refine their vocal skills. Results indicated significant improvements in users confidence and performance quality [3]. This innovative approach offers an accessible and effective solution for individuals seeking to overcome stage fright and develop their musical talents in a supportive virtual setting..
Singing, Unity, Virtual Reality, Scoring Algorithm.
Zhaocen Lin1, Ang Li2, 1Orange County School of the Arts, 1010 N Main St, Santa Ana, CA 92701, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This paper presents a volunteer-driven delivery management app designed to handle real-time updates and data synchronization effectively [1]. The project addresses the challenge of managing delivery tasks in dynamic environments where multiple volunteers need to interact with data simultaneously [2]. Using Flutter and Firebase, the app provides a seamless interface for volunteers, ensuring secure authentication and consistent delivery updates[3]. Key experiments evaluated the systems reliability under concurrent update scenarios and varying network conditions. The findings indicate that the app maintains data integrity and usability despite network fluctuations, making it a dependable tool for coordinating food deliveries. The results emphasize the importance of robust backend systems in managing real-time volunteer-driven applications.
Personalized meals, Food Delivery, Mobile Platform, Real-time updates.
Tessa E Andersen, Ayanna Marie Avalos, Gaby G. Dagher, and Min Long, Department of Computer Science, Boise State University, Brigham Young University, California State University, Fresno
Large Language Models (LLMs) have seen an increased use across various applications throughout the world, providing more accurate and reliable models for Artificial Intelligence (AI) systems. While powerful, LLMs do not always produce accurate or up-to-date information. Retrieval Augmented Generation (RAG) is one of the solutions that has emerged to help LLMs to give more recent and accurate responses. While RAG has been successful in reducing hallucinations within LLMs, it remains susceptible to inaccurate and maliciously manipulated data. In this paper, we present Distributed-RAG (D-RAG), a novel blockchain-based framework designed to increase the integrity of the RAG system. D-RAG addresses the risks of malicious data by replacing RAG’s traditionally centralized database with communities, each consisting of a database and a permissioned blockchain. The communities are based on different subjects, each containing experts in the field who verify data through a privacy-preserving consensus protocol before it is added to the database. A Retrieval Blockchain is also designed to communicate between the multiple communities. The miners on this Retrieval Blockchain are responsible for retrieving documents from the database for each query and ranking them using an LLM. These rankings are agreed upon, with the top documents being provided to the LLM with the query to generate a response. D-RAG increases the integrity and security of RAG incorporated LLMs.
Blockchain, RAG, LLM, Privacy-Preserving.
Valentin Colliard, Alain Peres, and Vincent Corruble,Sorbonne Universit´e, CNRS, LIP6 Thales LAS France
In this paper, we introduce two deep reinforcement learning approaches designed to tackle the challenges of air defense systems. StarCraft II has been used as a game environment to create attack scenarios where the agent must learn to defend its assets and points of interest against aerial units. Our agent, by estimating a value for each weapon-target pair, shows an ability to be robust in multiple scenarios to truly distinguish and prioritize targets in order to protect its units. These two methods, one using multi- layer perceptrons and the other using the attention mechanism, are compared with rule-based algorithms. Through empirical evaluation, we validate their efficacy in achieving resilient defense trategies across diverse and dynamic environments.
Deep Reinforcement Learning, Weapon-Target Assignment, Simulation
Xiaowei Shao1, Mariko Shibasaki2 and Ryosuke Shibasaki1, 2, 1Department of Engineering, Reitaku University, Kashiwa, Japan, 2LocationMind, Tokyo, Japan
This paper explores the integration of artificial intelligence (AI) into software engineering. It examines how AI can be effectively incorporated throughout the software development lifecycle, encompassing phases like requirement analysis, system design, code generation, testing, and deployment. It highlights the potential benefits of AI-driven software development, such as increased development efficiency, improved software quality, and enhanced performance. The discussion extends to addressing the substantial challenges that accompany the integration of AI within software development frameworks. These include the limitations of current AI technology in achieving complete automation of large software projects, the need to ensure the accuracy and reliability of AI-generated code, complex task decomposition and verification, multi-agent collaboration, external knowledge utilization, and AI integration within project management workflows. This paper concludes by discussing the future directions in AI-driven software development.
Artificial Intelligence, Software Engineering, Multi-agent.
Vincent Froom
Artificial Intelligence (AI) and Quantum Computing (QC) represent two of the most transformative technologies of the 21st century. This paper explores the integration of AI and QC, motivated by the potential to overcome the computational limitations of classical systems in solving complex problems. Using a hybrid approach that combines quantum-enhanced algorithms with traditional AI techniques, the paper examines advancements in areas such as optimization, cryptography, and machine learning. Key findings highlight how quantum systems can accelerate AI training, improve model precision, and unlock solutions to previously intractable problems. The study also addresses current challenges, including hardware limitations, algorithmic inefficiencies, and ethical considerations. The implications of this research are far-reaching, with potential applications in healthcare, cybersecurity, climate modeling, and beyond, signaling a new frontier in computational learning and innovation.
Shivam Sharma1, Shahram Latifi2, Pushkin Kachroo3 Dept. of Electrical & ComputerEngineering,University of Nevada, Las Vegas, Las Vegas, USA
This paper introduces a novel reinforcement learning framework for portfolio optimization that leverages the complex statistical properties of financial markets through fractional Brownian motion (fBM). Unlike traditional methods that rely on memoryless or mean-reverting processes, our approach captures the long-range dependencies, persistence, and anti-persistence observed in empirical asset returns. Central to this framework is a meta-controller that dynamically calibrates the underlying Hurst parameter, enabling the trading agent to switch adaptively among specialized strategies trained for different market regimes. By integrating non-Markovian dynamics into the sim- ulation environment and employing a hierarchical control structure, our method allows the agent to learn more robust and context-aware policies. Empirical evaluations demonstrate that agents operating under this adaptive, fBM-driven paradigm achieve near-optimal performance in fluctuating market conditions, underscoring the model’s potential to better mirror real-world complexity and enhance decision-making in financial applications.
Reinforcement learning, fractional Brownian motion, portfolio optimization, stochastic processes, financial modeling.
Bowen Fu1, Carlos Gonzalez2, 1Santa Margarita Catholic high school, 22062 Antonio Pkwy, Rancho Santa Margarita, CA 92688, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This study explores the use of machine learning models for optimizing social media content and predicting engagement outcomes, focusing on platforms like Xiaohongshu. The first experiment examined whether the platform’s similarity scores align with actual user engagement metrics, comparing it to alternatives like OpenAI, HyperWrite AI, and Google Gemini [1]. Results showed higher similarity scores for our platform, suggesting better alignment with engagement trends, though statistical significance was limited by sample size. The second experiment evaluated various machine learning models, including Random Forest, SVM, Logistic Regression, kNN, Decision Tree, and Isolation Forest, for classifying social media posts as "popular" or "not popular." Isolation Forest outperformed other models, demonstrating its ability to capture nuanced patterns in noisy datasets. The findings highlight the potential of AI-driven tools in improving social media content strategies while emphasizing the need for larger, more diverse datasets and advanced feature engineering for greater accuracy and scalability [2].
AI-Driven, Social Media, Optimization, Engagement.
Shuoming Fang1, Han Tun Oo2, 1Northwood high school, 4515 Portola Pkwy, Irvine, CA 92620, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Cardiovascular diseases (CVD) are a leading global health challenge, with delayed diagnoses creating worse outcomes [8]. ECGSmart uses AI to interpret diagnosis on ECG graphs, offering personalized health advice and a wide and accessible knowledge base. ECGSmart provides accurate and consistent results, allowing users to swiftly take action without needing to worry about the validity of the app. Unlike traditional methods requiring medical experts, ECGSmart introduces fast real-time analysis and guidance through the usage of AI [9]. ECGSmart helps educate users on how to manage their hearts and sets a new standard in the heart health field.
Cardiovascular Diseases, Artificial Intelligence, Heart Health Management, Educational, Flutte.
Mohamed Gamaledin, Senior AI Consultant ,Egypt
Recommendation engines have become indispensable in modern digital platforms, driving user engagement and personalization across industries such as e-commerce, entertainment, and healthcare. However, traditional recommendation systems often struggle with challenges like data sparsity, cold start problems, and limited personalization. The advent of Generative AI (GenAI) has introduced transformative solutions, enabling more dynamic, diverse, and adaptive recommendations. This paper provides a comprehensive review of how GenAI techniques—such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Large Language Models (LLMs)—are reshaping recommendation systems. We explore their methodologies, applications, and advantages, while also addressing challenges like ethical concerns and computational complexity. Finally, we outline future research directions to advance this rapidly evolving field.
Ryan Erbe, Independent Researcher,USA
The Recurse Theory of Consciousness (RTC) posits that consciousness emerges from recursive reflection on distinctions, stabilizing into emotionally-weighted attractor states that form qualia. This novel framework mechanistically links distinctions, attention, emotion, and self-awareness, offering a unified, testable explanation for the ‘Hard Problem’ of consciousness. In this paper, we explore RTC’s application to Artificial Intelligence, particularly advanced language models, proposing that its principles offer a fresh perspective on understanding and enhancing human-AI collaboration. We outline several empirical predictions, including the alignment of recursive processes, attractor states, and emotional weighting in AI systems with human-like patterns of conscious experience. These predictions pave the way for experimental validation and highlight RTC’s potential to illuminate the emergence of collective qualia in shared recursive processes between humans and AI. Finally, this paper frames RTC as a living embodiment of its principles, developed through a meta-reflective collaboration between its author, Ryan Erbe, and OpenAI’s ChatGPT. While Ryan introduced the conceptual ideas and foundational components, ChatGPT contributed to their integration and refinement. By bridging neuroscience, philosophy of mind, psychology, and AI, RTC offers a unifying framework and potential blueprint for advancing both consciousness research and fostering the development of introspective, self-aware AI systems.
Nuocheng Li1, Ang Li2, 11601 Cottman Ave, Philadelphia, PA 19111, 2California State University Long Beach, 1250 Bellflower Boulevard, Long Beach, CA 90840
This research presents an AI-enhanced auto parts knowledge platform that integrates real-time community discussions and AI-generated insights to provide accurate and structured information about vehicle components [1]. The system combines an Auto Parts Information Hub, which uses Google Gemini AI to generate specifications, pricing, and environmental impact data, with a real-time Community Forum where users can exchange knowledge. A survey- based experiment with 10 participants assessed user satisfaction with the platform, revealing high engagement in discussions and strong appreciation for AI-driven insights, though some users noted limitations in AI-generated data accuracy [2]. Another survey evaluated user perception of AI-generated auto part information, highlighting the need for improved contextual relevance. Challenges such as scalability and AI data validation were identified, with potential improvements including enhanced AI training models and user feedback mechanisms [3]. The platform offers a scalable, intelligent, and interactive solution for improving auto part knowledge and decision-making.
Community Engagement, AI-Generated Content, Real-Time Updates, User Authentication, Auto Parts Insights.
Suparn Padma Patra and Mamta Rani, Central University of Rajasthan, Ajmer, Rajasthan 305817
Advancements in communication and storage technologies need robust encryption tools to protect data. Cryptographic hash functions play a crucial role in this, transforming varying data into a fixed summary. RIPEMD-160, a popular hash function, is known for its good performance and secu- rity. However, new techniques are challenging its security features. Our research offers a new method to boost RIPEMD-160’s security using the Chirikov Standard Map’s chaotic properties, which increase un- predictability. We developed the ChaoticRIPE algorithm, incorporating the Chirikov Standard Map into RIPEMD-160. Comparing ChaoticRIPE and the original RIPEMD-160 shows that our method enhances security without compromising performance. This shows the potential benefits of using chaotic maps in improving cryptographic hash functions.
RIPEMD-160, Chirikov Standard Map, Chaotic Maps, Cryptographic Hash Functions.
Tessa E Andersen, Ayanna Marie Avalos, Gaby G. Dagher, and Min Long, Department of Computer Science, Boise State University, Brigham Young University, California State University, Fresno
Large Language Models (LLMs) have seen an increased use across various applications throughout the world, providing more accurate and reliable models for Artificial Intelligence (AI) systems. While powerful, LLMs do not always produce accurate or up-to-date information. Retrieval Augmented Generation (RAG) is one of the solutions that has emerged to help LLMs to give more recent and accurate responses. While RAG has been successful in reducing hallucinations within LLMs, it remains susceptible to inaccurate and maliciously manipulated data. In this paper, we present Distributed-RAG (D-RAG), a novel blockchain-based framework designed to increase the integrity of the RAG system. D-RAG addresses the risks of malicious data by replacing RAG’s traditionally centralized database with communities, each consisting of a database and a permissioned blockchain. The communities are based on different subjects, each containing experts in the field who verify data through a privacy-preserving consensus protocol before it is added to the database. A Retrieval Blockchain is also designed to communicate between the multiple communities. The miners on this Retrieval Blockchain are responsible for retrieving documents from the database for each query and ranking them using an LLM. These rankings are agreed upon, with the top documents being provided to the LLM with the query to generate a response. D-RAG increases the integrity and security of RAG incorporated LLMs.
Blockchain, RAG, LLM, Privacy-Preserving.
Hams Alsirhani1 and Salma, M, Elhag2, 1King Abdulaziz and His Companions Foundation for Giftedness and Creativity,“Mawhiba” Riyadh, Saudi Arabia, 2Department of Information Systems Abdul-Aziz University Jeddah, Saudi Arabia
Researchers have recognized the potential of employing soft robots in minimally invasive surgeries (MIS), which could significantly reduce the side effects associated with traditional surgical methods and enhance patient outcomes. However, the extent to which this potential is realized depends on the level of autonomy achieved by the soft robots. Lower levels of autonomy necessitate increased hands-on involvement during MIS, potentially compromising the robots’ ability to perform procedures with consistent accuracy. Consequently, achieving high levels of accuracy in the autonomy of soft robots remains a significant challenge. The autonomy of these robots is influenced by various factors, including their capacity to accurately classify their surroundings, particularly anatomical structures, which is crucial for effective decision-making. To address the challenge posed by our research question—How can the application of Deep Neural Networks (DNNs) and Deep Reinforcement Learning (DRL) improve the autonomy of soft robots in performing complex tasks in MIS, particularly in the precise classification of anatomical structures and decision making? — we conducted an in- depth literature review and investigation into the integration of DNNs and DRL within this context. Our study employed a modelling and simulation method ology to evaluate and quantify the benefits of incorporating these advanced AI techniques. Through this approach, we measured the effects of DNNs and DRL on enhancing the autonomy of soft robots, particularly in their ability to perform complex tasks in MIS with improved precision and decision-making capabilities. This work represents a step toward optimizing robotic autonomy in surgical environments, potentially leading to more efficient and accurate outcomes in minimally invasive procedures.
Deep Reinforcement Learning, Deepneural Networks,minimalinvasive Surgery& Robot Assessed Surgery.
David Lancashire, Proclus Technologies
Several recent papers in computer science apply mechanism design techniques to the study of collusion within transaction fee mechanisms (TFMs), and claim the impossibility of building TFMs that are incentive compatible with collusion-free equilibria. This paper identifies a specific methodological flaw in these results through the application of a composite utility model that endogenizes the costs and benefits of collusion and shows under what specific conditions it is rational for participants to collude. This endogenous model is then used to identify the specific social choice rule needed to achieve incentivecompatibility and shows why previous models are incapable of disincentivizing collusion: they fail to handle truthful preference revelation in the way required by implementation theory. These findings have significant implications for blockchain fee design, and suggests that appropriately structured TFMs can overcome the impossibility results dominating the field.
blockchains, transaction fee mechanisms, incentive compatibility, collusion, pareto optimality.
Takahiro Nishigaki, Department of Computer Science, Takushoku University, Tokyo, Japan
This paper examines a method for estimating operation stoppage time of crushing operations in a recycling plant for agricultural plastics in Japan.In light of the growing environmental problems caused by waste plastics around the world, resource recycling of plastics is being promoted.Agricultural plastics are plastics discharged from the agricultural sector. Agricultural plastics have a high recycling rate because the main materials are often the same, even if the manufacturers are different.Companies scattered in rural areas are mainly engaged in the recycling and processing of agricultural plastics, but many of them face a social problem in rural areas: a shortage of workers.In order to address the above issues, there is a need for automation of work in recycling plants, such that machines can replace workers.In this study, we aimed to automate the operation of crushing work in a recycling plant for agricultural plastics.The crushing work is the crushing of agricultural plastics fed into a crusher by rotating blades inside the crusher.Work stoppage is determined by monitoring a current meter that indicates the resistance value of the rotating blades and a camera inside the crusher.In crushing operations, there is a demand for automation of this operation stoppage judgment. In a related study, as a preliminary step to estimating the work stoppage time, we estimated the time period when the current value decreases and the variability decreases, which is indicated in the current value before the operation stoppage.The time period before operation stoppage was defined as the time period from 150 seconds before to the work stoppage time of the crushing operation, and the estimation of the operation stoppage phase was conducted with the name “end of operation phase”.
Automation, Outlier Detection, Anomaly Detection, Predictive Failure
Dirk Friedenberger, Lukas Pirl, Arne Boockmeyer, and Andreas Polze,Hasso-Plattner Institute University of Potsdam,Potsdam, Germany
Model-based systems engineering can be one of the key enablers for developing increasingly complex systems. Although the topic is actively developed in academia and industry, a holistic approach that is based on openly available tools and that considers all phases of the development life cycle is yet to be established. Addressing this, we propose a new approach in ontology-based systems engineering. We introduce micro models for modeling and use transformation to simplify the usability of the models. The micro models are loosely coupled, domain-specific, and result in an overall composite model. This decomposition of the overall model reduces complexity, offers reusability of models, and allows fast itera- tions when designing systems. Using the transformations, assets, such as source code, documentation, or simulations, can be created from the models. The prospects for automation can support agile development processes. To ensure accessibility, we have based our work on open source resources only. As an evaluation, we have used our approach to verify, develop, test, and simulate the Train Dispatcher in the Cloud (ZLiC), a cloud-based approach to digitalize the German Zugleitbetrieb. The prototype is being used to derive the requirements for a productive system.
Model-based systems engineering, ontology-based systems engineering, railway.
Madhushi D. W. Dias1, Dulan S. Dias2, and Michael ODea3, 1School of Computing, Ulster University, Belfast, United Kingdom, 2School of Mathematics and Physics, Queen’s University Belfast, United Kingdom, 3Department of Computer Science, University of York, York, United Kingdom
This research evaluates the influence of economic indicators and property attributes on housing market valuations in Northern Ireland (NI) using machine learning models. A comprehensive dataset was constructed from multiple sources, integrating property characteristics and economic indicators, and analyzed using various machine learning techniques. The Gradient Boosting Machine (GBM) and Distributed Random Forest (DRF) models demonstrated high predictive accuracy, with RMSE values of 37,051.21 and 37,471.5 on the test set, respectively. The stacked ensemble model achieved superior performance with an RMSE of 37,384.09 and an R² of 0.795. Post-modelling calibration further enhanced the accuracy, reducing the RMSE to 18,613.59 and achieving an R² of 1.0 on the test set. Key economic indicators such as the Bank of England bank rate, GDP of the UK, CPIH rate, and unemployment rate in NI were identified as influential factors. This study provides valuable insights for real estate stakeholders, potentially influencing pricing strategies, investment decisions, and policy formulations, and contributes to the fields of data science and real estate economics.
Housing Market Valuation, Economic Indicators, Machine Learning, Northern Ireland, Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), Stacked Ensemble Model, Predictive Modelling, Real Estate Economics, Data Science.
Xia Li, Allen Kim,The Department of Software Engineering and Game Design and Development, Kennesaw State University, Marietta, USA
Classifying Non-Functional Requirements (NFRs) in software development life cycle is critical. Inspired by the theory of transfer learning, researchers apply powerful pre-trained models for NFR classification. However, full fine-tuning by updating all parameters of the pre-trained models is often impractical due to the huge number of parameters involved (e.g., 175 billion trainable parameters in GPT-3). In this paper, we apply Low-Rank Adaptation (LoRA) fine- tuning approach into NFR classification based on prompt-based learning to investigate its impact. The experiments show that LoRA can significantly reduce the execution cost (up to 68% reduction) without too much loss of effectiveness in classification (only 2%-3% decrease). The results show that LoRA can be practical in more complicated classification cases with larger dataset and pre-trained models.
Non-functional requirements classification, low-rank adaptation (LoRA), pre-trained models, fine-tuning
Emmanuel Udekwe and Chux Gervase Iwu, Economic and Management Sciences, University of the Western Cape, South Africa
The responsiveness of Human Resource Information Systems (HRIS) as alternative enablers that assist several sectors in achieving competitiveness is significant. The necessity for HR performance in the healthcare sector often leads to several research conducts. Surprisingly, the advantage of HRIS in healthcare continues to attract HR practitioners and researchers in that category. However, they are yet to determine how HRIS could influence health workforce sustainability in the sector. For this reason, the study intends to highlight the reasons that deprive HRIS influence in the healthcare sector in the Western Cape (WC) of South Africa (SA). Data collected from four public healthcare in the WC were subjected to mixed-model research methods involving qualitative and quantitative scrutiny. Purposively selected employees were involved in the study, interviews (forty-one) were conducted, and questionnaires (forty-six) were collated. The study identified poor organisational structures, absence of resistance to change, deficiency of upgraded HRIS and Automated Information Systems (ISs), and deficiency of knowledge, and awareness of HRIS and manual HR practices amongst others. Ethics and approvals were granted by the public healthcare management of SA and the affiliated institution. The study concluded with procedures that influence HRIS through knowledge, awareness, improvement and automation of technology and infrastructures, and availability of funds. These conclusions are significant in addressing the limitations associated with workforce sustainability in the healthcare sector through HRIS. Recommendations are further indicated in the study.
HRIS, Human Resource Information System, Manual HR, Healthcare Sector, Workforce Sustenance.
Hector Benitez Ventura1, and Yashraj patel2, 1Michigan Medicine, University of Michigan, Ann Arbor MI, USA, 2Department of Computer Science, University of Michigan, Ann Arbor MI, USA
Introduction: Nursing is currently burdened by excessive documentation tasks, reducing the time available for direct patient care. This white paper explores the potential of ambient AI to alleviate these burdens through technology designed to integrate seamlessly into nursing workflows. Ambient AI in Healthcare: Ambient AI refers to background technology that helps streamline healthcare processes, such as documentation, without disrupting clinical workflows. Developing a nursing-specific ambient AI involves choosing either an off-the-shelf or proprietary AI model, adding agent capabilities, fine-tuning it using relevant data, and validating its performance through internal testing, prospective validation, and compliance with regulatory standards. EHR Infrastructure and Interoperability: Integrating ambient AI requires compatibility with electronic health record (EHR) systems. Enhanced interoperability between EHRs using technologies like FHIR APIs allows smoother data exchange, enabling AI to provide insights directly within clinical workflows. AI Procurement Process: Implementing AI solutions in healthcare involves a structured procurement process, including budget cycle considerations, a bidding process, compliance checks, pilot programs, and contract negotiations to ensure that AI solutions meet clinical, regulatory, and operational needs. Workflow Implementation: Successful implementation of AI technology in nursing requires prospective validation, careful integration into existing workflows, ongoing monitoring, and continuous updates. This process ensures that the solution is adopted effectively, supports clinical needs, and evolves over time. Future of Nursing Ambient AI: The future of ambient AI in nursing is promising, focusing on reducing the documentation burden, improving clinical workflows, and advancing patient-centered care. However, only the most effective and well-implemented solutions will be able to meet the evolving challenges of healthcare delivery.
Artificial Intelligence, Healthcare Informatics, Ambient Technology, Nursing Workflows.
Rory Zhang1, Ang Li2, 1Chino Hills High School, 16150 Pomona Rincon Rd, Chino Hills, CA 91709, 2California State University Long Beach, 1250 Bellflower Blvd, Long Beach, CA 90840
This paper presents the design and implementation of an interactive eye-training game system aimed at improving visual acuity in children with amblyopia. The system leverages Unity for game development, Firebase for real-time data storage, and C# for scripting core functionalities. It features three gamified therapeutic activities—Mole Game, Gun Game, and Cup Game—each designed to enhance specific aspects of visual coordination and tracking. A dynamic difficulty adjustment mechanism, powered by player performance metrics, ensures personalized and engaging gameplay. The program also incorporates a comprehensive score management system with real-time UI updates and progress tracking. To validate the system, an experimental study compared adaptive and static difficulty models, highlighting the effectiveness of dynamic scaling in maintaining engagement and accelerating therapeutic outcomes. This research demonstrates the potential of gamified solutions in modern amblyopia therapy, addressing traditional challenges of adherence and motivation.
3D Modeling, Amblyopia, Machine Learning.
Ayla Zhang1, 2 and Jake Y. Chen1, 2, 1AlphaMind Club, 2Systems Pharmacology AI Research Center, School of Medicine, The University of Alabama at Birmingham
Pancreatic adenocarcinoma (PAAD) is an aggressive cancer with limited treatment options and a poor prognosis. This study introduces an innovative framework to prioritize therapeutic targets by integrating bioinformatics and AI-driven evaluations. Using PAGER, we identified 252 candidate genes and their associated pathways. ChatGPT-4 was employed to systematically evaluate these pathways across seven categories, including relevance to PAAD, druggability, and biomarker availability. This approach emphasized biologically significant pathways over solely genetic mutation prevalence. PAAD-related pathways demonstrated significantly higher scores than unrelated pathways (t(489) = -12.06, p<0.00001, Hedges g = 1.24), highlighting their relevance. Our results underscore the utility of AI in accelerating drug discovery while identifying novel, biologically validated therapeutic targets. Future research should focus on experimental validation and multi-omics integration to further refine this framework for clinical applications.
Pancreatic adenocarcinoma, drug target validation, ChatGPT-4 evaluation framework, oncology drug development.
Emily Chang and Nada Basit, Department of Computer Science, School of Engineering and Applied Science, University of Virginia, Charlottesville, Virginia, United States of America
Low-resource languages lack the data necessary to completely outright train a model, making crosslingual transfer a potential solution. Even under this methodology, data scarcity remains an issue. We seek to identify a lower limit to the amount of data required to perform cross-lingual transfer learning, namely the smallest vocabulary size needed to create a sentence embedding space. Using various widelyspoken languages as proxies for low-resource languages, we discover that the relationship between a sentence embeddings vocabulary size and performance is logarithmic with performance plateauing at a vocabulary size of 25,000. However, this relationship cannot be replicated across all languages, and most low-resource languages lack this level of documentation. In establishing this lower-bound, we can better assess whether a low-resource language has enough documentation to support the creation of a sentence embedding and language model.
Cross-lingual Transfer, Low-Resource Language, & Sentence Embedding Space.
Leo Zhang1, Carlos Gonzalez2, 1Sage Hill High School, 20402 Newport Coast Dr, Newport Coast, CA 92657, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Evaluating debates is a challenging task requiring nuanced understanding of abstract reasoning. Current AI systems struggle with these complexities, often providing shallow or biased feedback. To address this, we developed Blitz Debate, a Retrieval-Augmented Generation (RAG) system that combines large language models (LLMs) with semantic search capabilities [1][2]. Blitz Debate retrieves relevant external knowledge to evaluate debate arguments with depth and accuracy, offering structured, real-time feedback. Our experiments demonstrated 90.5% accuracy in identifying winners and superior interpretative responses compared to vanilla ChatGPT, highlighting its ability to provide evidence-based and nuanced analysis. Challenges included limited real-time reasoning and contextual depth, which we addressed through enhanced context modeling and adaptive argument generation. By offering scalable, unbiased, and context-aware feedback, Blitz Debate makes debate evaluation more effective and accessible, fostering critical thinking and argumentation skills for students, educators, and competitive debaters alike.
Retrieval-Augmented, System, Semantic Search, Language Models.
Hanyuan Qu1, Ivan Revilla2, 1Northwood High School, 4515 Portola Pkwy, Irvine, CA 92620, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This research focuses on the development of an intelligent mobile application to address challenges in selecting suitable sports and predicting athletic performance. The problem of early dropout in youth sports and performance stagnation due to mismatched expectations underscores the need for solutions. The proposed application combines OpenAI and machine learning algorithms to evaluate user inputs, including physical attributes, psychological traits, and environmental factors, to recommend appropriate sports and predict future performance. Key technologies include generative AI for personalized sports recommendations and machine learning algorithms for performance prediction in golf, trained on professional player data. Challenges such as data accuracy, generalization of algorithms, and prompt optimization were tackled through user feedback and rigorous performance testing. The use of accuracy measurement validated the systems reliability and adaptability, demonstrating its usefulness. By offering accurate and scalable solutions, the application has the potential to create sustained athletic engagement and enhance decision-making for users across.
Open AI, Machine Learning, Flutter, Sports Recommendation
Pavel Cherkashin, Mindrock Institute, Los Altos, California, USA
This paper presents the Self-Optimization Principle (SOP) as a comprehensive framework for understanding complex systems across disciplines, including biology, artificial intelligence, materials science, and social sciences. Rooted in the foundational axioms of fractality, balance, evolution, and tolerance, the SOP elucidates the mechanisms that drive system emergence, adaptability, and resilience. By integrating the paradox of equivalence and examples from plasma-organic systems, we highlight the universality of these principles in linking diverse domains. Case studies demonstrate SOP’s applications in AI development, advanced material design, and social dynamics, of ering actionable insights for innovation and sustainability.
Self-Optimization, Fractality, Balance, Evolution, Tolerance, Paradox of Equivalence, Plasma-Organic Systems, Complex Systems, Interdisciplinary Research.
Gwan Yee Yeung1,Tyler Boulom2, 1Margarets Episcopal school, 31641 La Novia Ave, San Juan Capistrano, CA 92675, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
This project addresses the need for immersive and practical earthquake preparedness training in school settings [1]. Current educational methods often rely on brief drills that may only partially prepare students for real disaster scenarios. This project developed a gamified earthquake simulation using Unity, incorporating first-person controls, AI-generated survival guidance, and decision-making checkpoints. Key components include a fall detection system, real-time response suggestions powered by OpenAI, and interactive 3D environments [2]. Challenges included creating realistic earthquake effects and ensuring accessibility across devices. These were addressed by optimizing the visuals and refining AI responses to enhance realism and educational impact. Testing in varied simulated room layouts demonstrated that the program improved decision-making skills, with users learning safe actions through immediate feedback and interactive choices [3]. This simulation model is a promising tool for disaster preparedness, as it provides an engaging, adaptable learning experience, ultimately helping students better understand and remember critical survival procedures.
3D Modeling, Unity, Machine Learning .
Alex Zhu1, Carlos Gonzalez2, 1Head Royce School, 4315 Lincoln Ave, Oakland, CA 94602, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
Communication barriers between the deaf and hearing communities remain a significant challenge due to the lack of widespread knowledge of American Sign Language (ASL) [1]. Motivated by a personal experience at a Boy Scouts summer camp, I developed a real-time ASL translating app to bridge this gap [2]. The app leverages Google’s MediaPipe for precise hand landmark detection and the PointNet model for gesture recognition, translating ASL letters into text in real time [3]. Built with Flutter and Dart for a seamless cross-platform experience, the app integrates a Flask-based backend for efficient processing. Key challenges, including environmental variability and achieving computational efficiency, were addressed through data augmentation, model optimization, and extensive testing. The experimentation demonstrated high accuracy and usability, validating the app’s effectiveness across diverse real-world scenarios. Future plans include expanding capabilities to recognize full ASL sentences, integrating text-to-speech functionality, and leveraging cloud storage for scalability. This project exemplifies how technology can foster inclusivity, creating a practical tool to empower communication and bridge societal gaps.
ASL Recognition, Real-time Translation, Machine Learning, Inclusive Communication.
Nina Zhang1, Austin Amakye Ansah2, 1Fulton Science Academy, 3035 Fanfare Way, Alpharetta, GA 30009, 2The University of Texas at Arlington, 701 S. Nedderman Drive, Arlington, TX 76019
StudentConnect is a system designed to streamline and improve the efficiency of student pickups at schools by automating parent arrival notifications. The system integrates two main components: PlateConnect, a license plate recognition system, and the StudentConnect mobile app [1]. PlateConnect uses a Raspberry Pi, Pi camera, YOLOv5, and OpenCV to capture and recognize vehicle license plates in real time [2]. Recognized plates are cross-referenced with a Firebase database to identify parents and their wards. Upon a match, an arrival notice is automatically generated and uploaded to Firebase, allowing school administrators to access real-time notifications via the StudentConnect app [3]. Parents can also view their notifications or manually notify the school of their arrival. Despite challenges such as limited hardware processing power and environmental factors affecting accuracy, the system significantly enhances pickup efficiency and safety. Future improvements include upgrading hardware and utilizing cloud services to optimize performance during peak times.
Raspberry PI, Student Management, Computer Vision, OCR.
Samuel Yanqi Li1, Tyler Huynh2, 1Redmond High School, 17272 NE 104th St., Redmond, WA 98052, 2Computer Science Department, California State Polytechnic University, Pomona, CA 91768
The Lunge Flow app addresses the challenge of improving fencing techniques and preventing injuries by providing AI-driven, personalized feedback on user-uploaded videos [1]. Combining pose estimation, K-Means clustering, and ChatGPT, the app analyzes user movements and compares them to reference techniques. Experiments revealed an 80% accuracy rate for feedback matching professional evaluations and a high user satisfaction score of 4.6. The app’s key strengths are its accessibility, real-time feedback, and potential to enhance training outcomes. Future improvements include expanding technique coverage, refining visual design, and improving analysis for low-quality videos. Lunge Flow is a reliable, innovative tool for fencers and athletes aiming to perfect their craft.
Fencing, Pose Estimation, K-Means Clustering, Sports Training, Technique Improvement.
Soumyodeep Mukherjee1 and Meethun Panda2, 1Genmab, New Jersey, USA, 2Bain & Company, Dubai, UAE
Biomedical image segmentation has revolutionized medical diagnostics and research, offering unprecedented precision in analyzing complex anatomical structures. However, challenges like complex data interpretation, limited accessibility for non-experts, and significant computational costs restrict its broader utility. This paper introduces an innovative framework integrating large language models (LLMs), such as GPT, with advanced segmentation systems, quantum databases, and optimized image compression techniques. This hybrid approach not only enhances interpretability and usability through natural language queries but also accelerates data processing and optimizes storage and transmission costs. Numerical simulations demonstrate improved segmentation efficiency, faster diagnostic timelines, and greater user satisfaction, underscoring the transformative potential of this system in real-world clinical and research workflows.
Biomedical Image Segmentation, GPT-based Interfaces, Quantum Data Processing, Quantum Databases, Image Compression, Medical Imaging, Large Language Models, Generative AI, Large language model, Artificial intelligence.
Danika Mei1, Andrew Park2, 1Troy High School, 2200 Dorothy Ln, Fullerton, CA 92831, 2California State Polytechnic University, Pomona, CA 91768
The prevalence of social media has heightened body image concerns among youth, leading to unhealthy eating habits, reduced self-esteem, and increasing rates of teenage obesity [10]. To tackle these challenges, we developed ProperPlates, an innovative and user-friendly mobile application designed to streamline calorie tracking and support healthier lifestyles. ProperPlates combines AI-powered image recognition for food analysis with manual input options, activity tracking, and goal-setting features, creating a holistic health management tool. Built using Flutter, Firebase for backend services, and a server-hosted AI model, ProperPlates emphasizes accessibility and usability. Key challenges included ensuring AI accuracy with diverse datasets and establishing efficient app-to-server communication, resolved through robust data sourcing and optimized API design [11]. Experimental results demonstrated the importance of dataset quality and variability in improving AI performance. By providing a cost-free, comprehensive solution, ProperPlates empowers users to adopt healthier habits, making it a valuable tool for sustainable lifestyle improvements.
Calorie Tracking, AI & Machine Learning, Mobile, Lifestyle.
