Computer Science and Electrical Engineering Electronic Theses and Dissertations (UMKC)
Permanent URI for this collection
The items in this collection are the theses and dissertations written by students of the Department of Computer Science and Electrical Engineering. Some items may be viewed only by members of the University of Missouri System and/or University of Missouri-Kansas City. Click on one of the browse buttons above for a complete listing of the works.
Browse
Recent Submissions
Item Dynamic graph neural network framework for real-time multi-modal data analysis and predictive modeling(2025) Almousa, Ghadah Fahad M.; Lee, Yugyung, 1960-In recent years, Graph Neural Networks (GNNs) have become increasingly prominent for analyzing complex, interconnected data across fields such as transportation, social networks, and cybersecurity. Despite their advancements, many existing GNN models struggle to capture the intricate interactions among temporal, spatial, and domain-specific knowledge, particularly as these factors evolve dynamically, while also accounting for the complexities of multi-modal data in real time, with current GNN architectures often falling short in leveraging cross-modal correlations. We present a novel Dynamic Graph Neural Networks (DGNNs) Framework that integrates Partial Differential Equations (PDEs), temporal-spatial modeling, and domain-specific knowledge to address these gaps. By enabling real-time processing of multi-modal data, this framework bridges real-world dynamic systems with the evolving landscape of AI and machine learning applications. This interdisciplinary approach uniquely advances AI, machine learning, and big data analytics by harmonizing spatial-temporal dynamics, domain customization, and multi-modality integration in a cohesive framework. GNNs have become essential tools for analyzing complex, interconnected data in domains such as transportation, social networks, and cybersecurity. However, current GNN models often struggle to effectively capture the dynamic interactions of temporal, spatial, and domain-specific knowledge, especially when processing multi-modal data in real time. This dissertation presents the development of a DGNNs Framework designed to overcome these challenges, illustrated through extensive use cases. For instance, in traffic prediction, experiments using datasets such as Performance Measurement System Bay Area (PEMS-BAY), Metropolitan Traffic Los Angeles (METR-LA), and other PeMS Performance Measurement System datasets demonstrate the framework’s superior performance in prediction accuracy and robustness, effectively managing real-world data variability and spatial-temporal dependencies. Additionally, the framework efficiently models inter-variable dependencies in Multivariate Time Series (MTS) forecasting in domains such as energy, weather, and environmental monitoring, achieving stable long-horizon predictions through its PDE-enhanced graph structure. Ultimately, the framework’s capabilities extend to social media analysis for misinformation detection and rumor spread pattern discovery, with superior classification results on datasets like Pheme, Twitter15, Twitter16, and WEIBO. These examples showcase how the framework uncovers evolving patterns across platforms by processing multi-modal data inputs such as text and network interactions, surpassing traditional models.Item Data-driven modeling of infections using real-time location data and electronic health records(2025) Thota, Ravi Chandra; Uddin, Md Yusuf Sarwar (Mohammad Yusuf Sarwar)Hospital-acquired infections (HAIs) and respiratory disease outbreaks continue to pose significant challenges in indoor environments where the transmission dynamics are usually influenced by human movement patterns and contact tracing analytics. Traditional infection simulation models are based on synthetic movement assumptions and uses limited spatial representations which limits their capacity to analyze real-world disease transmission patterns. This dissertation addresses these limitations using data-driven modeling approach based on real-time movement and clinical data. The study outlines three enhancing disease/ infection modeling methodologies (i) mathematical modeling, (ii) agent-based simulation, and (iii) discrete-event simulation which are applied to two different contexts (i) academic indoor gatherings and (ii) hospital settings. Firstly, Ultra-Wideband (UWB) Real-Time Location System (RTLS) devices were deployed on four academic gatherings to capture second-level indoor movement data. These trajectories were used to model contact-driven respiratory disease spread dynamics in indoor settings through a mathematical modeling approach to calculate contact metrics, estimate transmission rates, and simulate basic reproduction numbers. Then, UWB RTLS devices were deployed in a post-surgery observation unit of an urban hospital to collect healthcare workers and mobile medical devices movement data. An agent-based model to simulate healthcare-associated infection transmission risk was developed to evaluate the impact of biosecurity measures such as mask use, hand hygiene, and device cleaning frequency, enabling systematic assessment of various intervention scenarios on infection spread dynamics. Further, electronic Health Record (EHR) data from an urban hospital were utilized to develop a discrete-event simulation model of Emergency Department patient flow, addressing the lack of operational understanding in infection and risk assessments. The model was developed to quantify how patient arrivals, service procedures, and the length of stay (LOS) affects the congestion and extended occupancy in specific ED areas. By modeling patient flow with observed clinical data the approach helps to identify where patients spend the most time and where crowding takes place thereby offering insight into delays and prolonged patient presence in certain ED areas. In summary, this dissertation demonstrates that integrating RTLS-derived movement data and EHR-based clinical data into modeling frameworks increases the accuracy, interpretability and practical relevance of disease models.Item Collaborative deep reinforcement framework for multimodality integration and learning(2025) Chandrashekar, Geetha; Lee, Yugyung, 1960-; Bumann, ErinPanoramic dental radiographs are essential in modern dental diagnostics, providing a comprehensive two-dimensional view of the oral cavity to identify abnormalities, restorations, and pathologies. However, manual interpretation is prone to variability caused by human fatigue, radiographic artifacts, and overlapping anatomical structures, which can reduce diagnostic precision and consistency. Although deep learning methods have improved automated segmentation and identification, most existing systems operate as static and isolated models, limiting their ability to adapt, collaborate, and improve once deployed in clinical environments. This dissertation develops and evaluates a collaborative deep reinforcement learning framework to address these limitations by enabling adaptive cooperation among multiple learning components. The proposed framework integrates complementary perception and identification models through a reinforcement-driven collaboration mechanism that dynamically optimizes their joint predictions. Rather than relying on fixed ensemble rules, an agent learns to adjust collaboration strategies based on performance-driven rewards, improving robustness under challenging conditions such as missing teeth, restorations, and orthodontic appliances. The framework operates through three key stages: independent model learning, collaborative inference via adaptive fusion, and reinforcement-based refinement guided by policy optimization. A carefully designed reward function promotes accurate localization, boundary consistency, and anatomically valid predictions, allowing the system to reduce uncertainty and iteratively improve its performance. Experimental evaluation on a publicly available panoramic radiograph dataset demonstrates that the proposed approach consistently outperforms conventional deep learning baselines in both tooth segmentation and identification. The framework achieves segmentation and identification accuracies that exceed 98%, while significantly reducing false detections and improving F1-scores in various test scenarios. Qualitative analyzes further confirm the improved boundary delineation and numbering consistency. From a clinical perspective, this work advances the development of self-improving and autonomous dental imaging systems capable of supporting diagnostic decision-making with greater accuracy and reliability. By bridging static inference with adaptive reinforcement driven collaboration, the proposed framework offers a scalable and interpretable solution with potential for extension to three-dimensional imaging, restoration analysis, and other real-world dental and medical applications.Item Intelligent robotics with digital-twin alignment : semantic navigation, manipulation, planning, and human-to-robot action transformation(2025) Alanazi, Ahmed Hamdan; Lee, Yugyung, 1960-This dissertation advances AI-empowered indoor robotics through four interconnected contributions that unify navigation, manipulation, semantic planning, and human-to-robot action transformation within a digital-twin-aligned framework. GRIP, a grid-aware semantic navigation module, integrates symbolic scene understanding with hybrid search-and-policy execution to achieve robust and context-aware ObjectNav. PathFormer, a transformer-based manipulation model structured around a 3D spatial--semantic grid, generates smooth, interpretable, and physically consistent trajectories that remain tightly aligned with digital-twin simulation. KG-Transformer, a knowledge-guided semantic planner, leverages a lightweight digital twin to calibrate execution, veto unsafe behaviors, and autonomously repair failing plans across diverse indoor environments. ActionFormer, an action-generation transformer, introduces a unified imitation-learning pipeline that integrates human-activity recognition, human-motion generation, and robot-motion generation. ActionFormer supports more than twenty complex human activities, producing robot-ready demonstrations that generalize across platforms and enable end-to-end imitation learning from video and landmark sequences. Collectively, these contributions establish a coherent foundation for AI-empowered robotics grounded in digital-twin intelligence. Across benchmarks and real-world deployments, GRIP yields up to 9.6% higher success rate and more than 2x gains in path efficiency (SPL, SAE). PathFormer produces digitally consistent manipulation trajectories validated through robust sim-to-real transfer. KG-Transformer achieves 99.6% executability, delivers a +4.6-point improvement on unseen-scene tasks, and eliminates safety violations in both simulated and multi-robot execution. ActionFormer attains state-of-the-art performance in human-activity recognition and high execution accuracy across more than 20 activities, generating realistic human-motion traces and corresponding robot-motion trajectories for embodied robotic demonstration. Together, these advances deliver a trustworthy, semantically aligned, and high-performance simulation-to-reality pipeline that significantly enhances the adaptability, reliability, and real-world readiness of autonomous indoor robotic systems.Item Ultra wideband pulse propagation in dispersive biological tissue : a computational, statistical and experimental study(2025) Drake, Doug Robert; Hassan, Ahmed M.; Caruso, Anthony N.The performance of implantable devices in biological media requires consistent coupling between the antenna and the surrounding environment. Electromagnetic losses in biological tissues can degrade antenna performance. This performance loss compounds within biological material due to reflections and dispersions caused by the high variations in dielectric properties from host to host. Variation could be caused by multiple molecular-level interactions that are expressed at the macro level through variations in the complex relative dielectric permittivities of biological tissues. Different concentrations of conducting ions or water content in the tissue could lead to large variations in conductivity and permittivity across tissues. To quantify the effects of these variations in dielectric tissue properties, multiple simulations are performed in which the dielectric properties of tissues are varied ±25% to approximate these molecular changes on the macro scale. These results are compiled into a meta-model using Polynomial Chaos Expansion and Kriging methods to create a computationally efficient statistical model for examining the varying behavior. After examining this behavior, an implantable electric-field probe is calibrated to quantify how changes in the dielectric properties of biological tissue affect the propagation of ultra-wideband electromagnetic pulses. By shielding a monopole antenna with a dielectric sheath, the antenna can exhibit more consistent capacitive coupling to the environment, improving measurements of local electric-field effects in different media. The methods developed herein for calibrating this probe can be applied to implantable antennas to achieve more consistent performance across diverse environmental conditions.