Moh Khalid Hasan1, Md. Osman Ali2, Ke Wang2, Sijia Yang3, Wei Chen4, 1 James Madison University, USA,2RMIT University, Australia ,3 USTB, China,4 SIAT, China
Optical camera communication (OCC) is considered as a key enabler of optical wireless communication technology. In OCC, light-emitting diodes (LEDs) serve as the transmitter and rolling shutter (RS) cameras as the receiver for high-speed communication. However, the received luminance from the LED is critically important for reliable data retrieval in OCC, which faces challenges due to the inherent nature of data collection. Smartphones, typically equipped with RS cameras, represent one of the most promising platforms for the commercial deployment of OCC. To ensure system reliability, various methods have been proposed to address the diversity in pixel illumination values captured by smartphone cameras. Furthermore, AI-based approaches that make RS cameras compatible with low-speed mobile scenarios and enhance overall system performance also introduce additional system complexity. In this paper, we provide a systematic review of the state-of-the-art methods for data retrieval in smartphone camera-based OCC. In particular, we provide specific challenges due to important factors, such as communication distance variation and the blooming effect. Furthermore, we discuss recent advancements, especially promising AI applications in OCC. Finally, we outline open research directions on smartphone camera-based OCC.
Optical Camera Communication (OCC), Rolling Shutter Camera, Smartphone-based OCC, Blooming Effect.
Neil Langmead, University of Bath, United Kingdom
Modern software development faces significant challenges in release cycle optimization, particularly when addressing the fundamental question: what is the minimum effort required to release a software change? This paper introduces the concept of the NULL Release—a theoretical baseline representing the overhead of releasing software with zero functional changes—and proposes architectural approaches using Dependency Structure Matrices (DSMs) integrated into DevOps pipelines to minimize release cycle time. We present the T(x) pipeline model, a multi-tiered continuous integration framework that incorporates architectural analysis at each stage. A key contribution is demonstrating how DSM partitioning enables identification of independent subsystems, allowing parallel build and test execution with theoretical speedups exceeding 3x. Drawing on industrial case studies from Siemens Healthineers and the SmartBuild approach, we demonstrate how DSM-based architectural analysis can be automated within CI/CD pipelines to detect architectural violations, assess change impact, optimize build dependencies, and enable parallel execution.
DevOps, Dependency Structure Matrix, Continuous Integration, Software Architecture, NULL Release, CI/CD Pipeline, Build Parallelization
Mohammad Mansoori, Amira Soliman, and Farzaneh Etminani , Center for Applied Intelligent Systems Research (CAISR),Halmstad University, Sweden
Clinical notes contain unstructured text provided by clinicians during patient encounters.These notes are usually accompanied by a sequence of diagnostic codes following the International Classifi-cation of Diseases (ICD). Correctly assigning and ordering ICD codes is essential for medical diagnosis andreimbursement. However, automating this task remains challenging. State-of-the-art methods treated thisproblem as a classification task, leading to ignoring the order of ICD codes that is essential for differentpurposes. In this work, as a first attempt, we approach this task from a retrieval system perspective toconsider the order of codes, thus formulating this problem as a classification and ranking task. Our resultsand analysis show that the proposed framework has a superior ability to identify high-priority codes com-pared to other methods. For instance, our model’s accuracy in correctly ranking primary diagnosis codes is˜47%, compared to ˜20% for the state-of-the-art classifier. Additionally, in terms of classification metrics,the proposed model achieves a micro- and macro-F1 scores of 0.6065 and 0.2904, respectively, surpassingthe previous best model with scores of 0.597 and 0.2660.
generative language models, learning to rank, automatic medical coding, ICD coding, elec-tronic health records, pre-trained language models.
Sasirekha Oguri, John R. Talburt, and Mert Can Cakmak Center for Entity Resolution and Information Quality (ERIQ)University of Arkansas - Little Rock , USA
Entity resolution (ER) typically relies on pairwise similarity comparisons between records,which limits its ability to capture indirect relationships present in demographic occupancy data. An im-portant indirect pattern arises from household movement, where multiple individuals relocate togetheracross addresses, but detecting such patterns is difficult due to mixed-format records, noise, duplication,and the absence of stable identifiers. This paper proposes an AI-enhanced framework for detecting indirectentity links associated with household movement in unstandardized name–address data. The approachintegrates prompt-based large language model (LLM) named entity recognition for extracting personalnames and addresses without extensive preprocessing, semantic text embeddings for robust similaritycomputation, and graph-based reasoning to infer group-level movement patterns. Experimental evaluationon SPX benchmark datasets (S8–S12) generated using the Synthetic Occupancy Generator demonstratesthat incorporating indirect household movement evidence improves recall by 8–15% while maintaining highprecision, yielding F1-score gains of 6–8% over a strong pairwise baseline.
Entity Resolution, Household Movement Detection, Indirect Linkage, Named Entity Recog-nition, Large Language Models, Semantic Text Embeddings, Graph-Based Clustering, Occupancy Data,Synthetic Data, Data Integration
Ivy Gu1, Rodrigo Onate2, 1Palo Alto high school, 50 Embarcadero Rd Palo Alto, CA 94301 2California State University, Fullerton, 800 N State College Blvd, Fullerton, CA 92831
Students increasingly struggle to engage effectively with study materials, with only 34% reporting active learning engagement and 65% experiencing academic anxiety. AIvy is an AI-powered web application that addresses this dual challenge by transforming uploaded study materials into personalized, interactive learning experiences while tracking student wellness. The system leverages OpenAI’s GPT-4o model to extract text from diverse document formats using vision capabilities, analyze content to generate targeted summaries and five-question quizzes aligned with user specified learning objectives, and recommend educational YouTube videos [9]. A parallel wellness journaling system tracks daily mood, study preferences, and focus patterns, generating personalized study recommendations. Built on a serverless architecture with Vercel Python functions and Firebase for authentication and data persistence, AIvy ensures API key security while maintaining responsive performance [10]. Experimental evaluation demonstrated 88.2% mean quiz quality and 88.6% text extraction accuracy across document types, confirming the system’s viability as a comprehensive educational companion.
Artificial Intelligence, Large Language Models, Personalized Learning, Quiz Generation, Student Wellness
Siying Wang1, Xuan Wang2, Yining Tang3, Chao Wu3,1School of Information Resources Management, Renmin University of China, Beijing, China,2China Media Group, Beijing, China ,3School of Public Affairs, Zhejiang University, Hangzhou, China
Simulating public opinion evolution is a core focus of computational social science. Traditional agent-based models rely on predefined heuristic rules, failing to capture the semantic features and cognitive processes of human natural language interactions. While large language models offer new approaches for artificial society construction, existing frameworks have limitations in scalability and memory management. Taking the Fukushima nuclear wastewater discharge event as the background, this study uses an open-source multi-agent social simulation framework, designing four progressive intervention scenarios to analyze agents cognitive synergy and public opinion trajectories. Results show the framework mitigates role drift and premature consensus, reproduces the public opinion evolution trajectory, providing empirical insights for policy testing and LLM-driven social computing.
Multi-agent simulation, Public opinion evolution, Nuclear wastewater discharge, Computational social science
Liying (Victoria) Qu1 , Yu Sun2 , 1The Ethel Walker Schoo, 230 Bushy Hill Road, Simsbury, CT 06070, 2California State Polytechnic University, Pomona, CA 91768
Diabetes mellitus affects over 537 million adults globally, demanding continuous self-management that conventional pharmacological approaches alone cannot fully address. Music therapy has emerged as a promising complementary intervention, with clinical research demonstrating that slow-tempo music can reduce blood glucose by 15-30 mg/dL through parasympathetic activation and cortisol reduction. BeatSugar is a cross-platform mobile application that integrates real-time blood sugar and heart rate monitoring with personalized, evidence-based music therapy recommendations. The system employs a context-aware algorithm that maps blood glucose levels, measurement timing, and diabetic status to clinically appropriate music tempos, incorporating Traditional Chinese Medicine Five- Element tonal sequences alongside AI-generated therapeutic compositions. A personalized effectiveness scoring engine learns from individual listening sessions, adapting recommendations based on measurable health outcomes. Experimental evaluation demonstrates 94.2% recommendation accuracy and algorithm convergence within 8-12 sessions. BeatSugar offers a scientifically grounded, scalable approach to complementary diabetes management through accessible digital music therapy.
Music Therapy, Diabetes Management, Blood Sugar Regulation, Mobile Health, Personalized Recommendations
Weizhao Chen1, Cesar Magana2, 1Esperanza High School, 1830 Kellogg Dr, Anaheim, CA 92807, 2California State University Long Beach, 1250 Bellflower Blvd, Long Beach, CA 90840
General aviation pilots frequently face fatal accidents due to cognitive overload when manually interpreting complex weather and terrain data mid-flight. To solve this, we developed SkyAware, an active, intelligent flight companion. Built with Flutter, the application integrates the Gemini API, Open Maps Terrain, and AviationWeather data to provide real-time 3D hazard monitoring and conversational safety briefings [1]. Core challenges included accurately synchronizing asynchronous APIs, ensuring AI hazard analysis reliability, and visualizing dense spatial data. We mitigated synchronization latency by implementing predictive forward vectoring. Experimentation using historical NTSB events and live MSFS 2024 telemetry yielded our most important results: an 86% mean AI hazard detection accuracy and a highly responsive 1,340ms average warning latency [2]. The results indicate that SkyAware effectively translates raw metrics into actionable insights, improving pilot decision-making. By proactively preventing alert fatigue, SkyAware empowers safer mid-flight decision-making and save lives in the cockpit.
Real-time data analysis, Aviation assistance, Electronic Flight Bag (EFB) companion, Profound Private pilot tool
Isaac Rudnick, Computer Science Department California Polytechnic State University San Luis Obispo, United States
By Zadeh’s original formulation, likelihood istributions can be seen as a unique kind of fuzzy set whose logical operations have meaningful probabilistic interpretations. In this work, we develop a variant of this fuzzy set in which an arbitrary number of fuzzy logic operations may be applied without increasing the space and time required for membership evaluation. By using a truncated Fourier series approximations, one can get a reasonable estimate of these fuzzy sets. Soundness is proven with respect to Zadeh’s orig- inal definitions and relevance to evaluation of Standard Additive Models (SAMs) is demonstrated with an analysis of complexity and scaling properties.
fuzzy sets, fuzzy logic, standard additive models, gaussian mixture models, fourier series
Eric Jia Luo Lu1, Rodrigo Onate2, 1Crean Lutheran High School, 22500 Sand Canyon Ave, Irvine, CA 92618, 2California State University, Fullerton, 800 N State College Blvd, Fullerton, CA 92831
Science museums struggle to provide personalized, age-appropriate experiences for diverse family audiences, leading to suboptimal learning outcomes and visitor engagement. This paper presents an AI-powered mobile companion application for Discovery Cube Orange County that addresses these challenges through intelligent personalization and interactive guidance. Built with Flutter and OpenAI’s GPT-4, the system integrates three core components: a profile management system storing child demographics, an AI recommendation engine generating personalized exhibit suggestions, and an interactive tour system combining QR code scanning with conversational AI assistance [8]. Implementation challenges included managing API response latency, ensuring age-appropriate content accuracy, and handling variable network conditions. Experimental evaluation across 60 age-appropriateness trials achieved a mean rating of 4.45/5.0, with strongest performance for ages 8-10 [1]. Network performance testing revealed bandwidth as the critical factor, with response times ranging from 1.8 to 5.4 seconds. The system demonstrates that AI-driven personalization makes museum experiences more accessible and educationally effective than traditional AR-based or static content approaches, offering a scalable model for informal STEM education enhancement.
AI-powered personalization, Museum companion application, GPT-4 recommendation engine, QR code exhibit navigation, Child profile management
Qianle Chen1 , Yu Sun2 , 1Arnold O. Beckman High School, Irvine, CA, USA 92602, 2California State Polytechnic University, Pomona, CA, USA 91768
Accurate and accessible environmental monitoring has become essential for public health, policy-making, and scientific research, yet traditional government-operated air quality stations remain expensive and geographically sparse. This paper presents AtmoFlow, a low-cost, open-source air quality monitoring framework that integrates a Raspberry Pi microcomputer with two consumer-grade sensors—the BME280 for temperature and humidity via the I2C protocol and the PMS5003 for particulate matter (PM2.5 and PM10) via the UART protocol. Custom Python scripts handle data acquisition, calibration, noise filtering through rolling averages, and adaptive local-cloud storage with batch uploads. A companion mobile application provides real-time visualization with color-coded air quality indicators and supports external API integration for overlay data. The system was evaluated in both controlled indoor and real-world outdoor environments across urban and suburban settings. Indoor calibration tests against a reference-grade monitor yielded a Pearson correlation coefficient of 0.94 for PM2.5 readings, while outdoor deployments demonstrated the system’s ability to capture rapid pollutant fluctuations during traffic peaks. AtmoFlow achieves measurement fidelity comparable to reference instruments at a fraction of the cost, lowering the barrier to entry for communities and researchers seeking localized, real-time environmental data.
air quality monitoring, low-cost sensors, Raspberry Pi, PMS5003, BME280, IoT, particulate matter
Zonglin Li1 , Austin Amakye Ansah2 , 1Anglo-Chinese School, 121 Dover Rd, Singapore 139650, 2The University of Texas at Arlington, 701 S Nedderman Dr, Arlington, TX 76019
Manual inspection of photovoltaic systems is expensive, hazardous, and prone to inconsistency. This paper presents SunScout, a mobile application for offline solar-panel image management and on-device fault classification. The current mobile release organizes drone, gallery, and camera captures into reusable datasets and analyzes each stored asset with a fine-tuned EfficientNetB0 classifier deployed through ONNX Runtime. On the cleaned 1,575-image dataset, a frozen MobileNetV2 baseline reached 90.79% validation accuracy, while the proposed EfficientNetB0 model achieved 94.29%, a 3.50 percentage point improvement. Together, these results show that accurate solar fault analysis can be delivered on a consumer smartphone without requiring a persistent network connection.
Solar panel inspection, Fault classification, EfficientNet, Computer vision, Mobile deployment, On-device inference
Alex Tang1,Tyler Boulom2, 1 Westview High School, 13500 Camino Del Sur, San Diego, CA 92129, 2Woodbury University, 7500 N Glenoaks Blvd, Burbank, CA 91504
California agriculture faces the combined pressures of severe drought, high crop-waste rates, and unaffordable commercial precision-agriculture platforms, which together disproportionately affect small and mid-sized growers. This paper proposes an integrated plant-health monitoring platform that combines a Raspberry-Pi field node for image capture and environmental sensing, a multimodal vision model for species identification and health assessment, and a Flutter mobile client that presents results to the grower through a simple dashboard. The client implements a layered fallback between the live Pi, an on-disk cache, and a bundled sample dataset so that it remains functional under intermittent connectivity, and it caches plant images transparently to accelerate repeated views. Two experiments evaluated the system: species identification reached 87.5 percent accuracy across four visually similar species, and time-to-first-paint ranged from 0.38 seconds on cached data to 1.34 seconds under degraded networks. The platform demonstrates that practical precision agriculture is achievable at consumer-hardware scale.
Artificial Intelligence, Precision Agriculture, Plant Health Monitoring, Crop Waste, Soil Conditions, Internet of Things, Mobile Computing
Zijia Li1, Andrew Park2, 1 Concord Academy, 166 Main Street, Concord, MA 01742, 2University of California, Irvine, Irvine, CA 92697
Parkinsons disease creates a long-term rehabilitation problem because patients often need frequent movement therapy, yet access, adherence, and motivation remain difficult to sustain. MirrorMove PD is a prototype therapeutic dance system designed to address that problem through a Flutter mobile app, a Python desktop companion, and a local HTTP control bridge. The mobile app manages authentication, goals, progress, and song selection, while the desktop component displays guided choreography and session playback. Experimental scripts using MediaPipe and reference landmark extraction support future movement analysis and scoring. The project must address three major challenges: reliable pose comparison, dependable phone-to-desktop communication, and meaningful workout metrics. Two preliminary approximate experiments suggest that trust in scoring depends on keeping feedback close to user expectations and that repeated use may improve short-term confidence. Overall, the prototype is promising because it combines evidence-informed dance rehabilitation with a practical home-use delivery model that is accessible, structured, and expandable.
Dance, Exercise, Parkinson’s, Rehabilitation, Flutter
Yuxuan Hao1, Laurie Delinois2 1Bellevue High School, 10416 SE Wolverine Way, Bellevue, WA 98004, 2Pace University, One Pace Plaza, New York, NY 10038
Predicting a rocket’s maximum altitude and landing location is difficult because wind changes with altitude and small timing errors can create large drift [1]. This project proposes a Unity based simulator that combines layered wind data with rocket physics and a machine learning landing predictor [2]. RocketPhysics simulates thrust, mass burn, aerodynamic drag from wind relative airspeed, and parachute deployment. WindDriftCalculator loads the wind layers, supplies wind to the flight model and records the final drift after landing. RocketDriftAgent uses ML-Agents to output a two-axis drift estimate from engine parameters and the wind profile, then scores it by landing error. Design challenges included unit consistency, reliable logging, and stable training rewards. In 20 test launches, 18 predictions were within 25 meters, which is 90 percent accuracy. The results show the approach is practical for launch planning, education, and reducing lost rockets in typical conditions.
Rocket Simulation, Wind Drift Modeling, ML Landing Prediction, Unity ML-Agents
Kevin Shi1, Jonathan Sahagun2, 1TVT Community Day School, 5 Federation Way, Irvine, CA 92603, 2California State University, Los Angeles, 5151 State University Dr, Los Angeles, CA 90032
Virtual museums offer global access to cultural heritage, yet creating immersive 3D exhibition environments traditionally requires extensive 3D modeling expertise, limiting adoption to well-funded institutions. This paper presents the Virtual Museum Generator, a Unity-based application that transforms any 2D architectural floorplan image into a fully navigable 3D museum environment with automatically placed artwork. The system employs a two-stage wall detection algorithm combining grayscale thresholding with neighborhood density filtering to robustly identify structural walls from diverse floorplan styles. A greedy rectangle merging algorithm optimizes the generated geometry, achieving a mean 95.4% reduction in wall object count compared to per-pixel extrusion. A ScriptableObject-driven theming system enables visual customization including materials, lighting, and curated artwork collections. First-person exploration with raycast-based artwork interaction allows users to examine individual pieces in detail. Experimental evaluation demonstrated a mean wall detection F1 score of 0.91 and real-time generation performance for floorplans up to 1024x768 pixels.
Virtual museum, Procedural content generation, Floorplan reconstruction, Image-based wall detection, Unity game engine
Weiyue Yan1, Moddwyn Andaya2, 1Pacific Academy Irvine, 4947 Alton Pkwy, Irvine, CA 92604, 2California State University, Sacramento, 6000 Jed Smith Dr, Sacramento, CA 95819
This project develops a Unity-based simulation platform that helps students and beginner designers analyze vehicle aerodynamics without expensive wind tunnel testing [6]. Air resistance plays an important role in vehicle performance, but traditional aerodynamic testing methods require costly equipment and complex professional software. To address this problem, the project introduces an interactive simulation environment where users can upload 3D car models, select or upload maps, and simulate airflow conditions [7]. The system is built around three main components: Properties, CFD simulation, and Map. These components work together to control inputs, generate aerodynamic visualization, and manage user interaction. The CFD system uses a simplified real-time approach based on dynamic pressure and precomputed surface responses to provide stable and interactive feedback. During development, challenges such as path design, model scaling, and collision detection were addressed through physics adjustments and automated systems. Experimental evaluation compared the system against ANSYS Fluent, showing an average error of 5.5%, indicating that the platform provides reasonably accurate results while maintaining high performance and accessibility.
CFD Simulation, Spline, 3D modeling, Unity
Jocelyn Zhang1, Andrew Park2, 1University High School, 4771 Campus Dr, Irvine, CA 92612, 2University of California, Irvine, Irvine, CA 92697
Figure skating is a physically demanding and expensive sport, and beginners often lack enough accessible support to practice safely and improve efficiently. Skate Sensor addresses this problem through a wearable sensing system paired with a mobile application that helps users analyze skating techniques and access educational resources [1]. The project combines two shin-mounted sensor pods, a Flutter mobile app, and machine learning models developed with Python and PyTorch [2]. Together, these components collect motion data, synchronize left and right leg activity, classify techniques, and evaluate whether an attempt matches successful motion patterns. Several implementation challenges had to be considered, including sensor synchronization, limited training data, and memory use within the app’s media features. These issues were addressed through timeline alignment, expanded data collection strategies, and more efficient loading of visual content. Experimental design focused on model accuracy and the impact of informational screens. Overall, Skate Sensor demonstrates strong potential as a practical tool for safer, more informed, and more independent beginner training.
Figure Skating, Coaching, Injuries, Skating techniques, Artificial Intelligence
Kunqi Miao and Cesar Magana, California State University, USA
Neurological and psychiatric conditions including Alzheimers disease, PTSD, depression, and schizophrenia affect hundreds of millions of people globally, yet existing pharmaceutical treatments are expensive, inconsistent, and out of reach for many. This paper proposes frequency-based music therapy, delivered through an AI-powered mobile application called Querey, as a clinically grounded and non-invasive alternative. Querey is built around three components: a state-based discovery survey, an adaptive AI coach, and a mood stimulation engine rooted in brainwave entrainment and BPM science [9]. Challenges included music licensing constraints, navigating App Store deployment as a first-time developer, and maintaining data accuracy across the personalization pipeline. Experiments showed a mean satisfaction score of 7.5 out of 10 for BPM accuracy, with calming prescriptions outperforming energizing ones, and a twelve-week clinical trial comparing Querey against live therapy and passive listening across diagnosed populations [1]. When technology is designed around how the brain actually works, the results speak for themselves.
Music Treatment, Machine Learning, Recovery, Bpm
