Engineering Commons^™

Llm-Powered Question Answering For Object States In Virtual Reality, Shiyi Ding

Master's Theses

Recent advances in large language models (LLMs) and multimodal large language models (MLLMs) enable natural language–based querying in virtual reality (VR). However, VR environments are highly localized, personalized, and dynamic, making it challenging for general-purpose models to answer environment-specific queries or reason about subtle object state changes. To address these challenges, this thesis develops two systems for 3D question answering in VR.

First, we present RAG-VR, the first retrieval-augmented 3D question-answering system designed for VR. RAG-VR augments an LLM with external knowledge retrieved from a localized knowledge database and includes a pipeline for extracting environmental and user-related information. To improve …

From 2d To 3d: Multi-Agent Reinforcement Learning For Spectrum-Constrained Urban Air Mobility., Qingyang Li

Electronic Theses and Dissertations

Advanced Air Mobility (AAM) and Urban Air Mobility (UAM) are accelerating a transformation of air transportation but face acute spectrum congestion in dense urban environments. Reliable Control and Non-Payload Communications (CNPC) must be maintained at all times to ensure safe operations, even as fleets of aerial vehicles (AVs) transport passengers and cargo between distributed vertiports. We first develop a 2D formulation that jointly optimizes discrete headings, velocities, and spectrum allocation to minimize total mission time while satisfying quality of service (QoS) and collision-avoidance constraints, and we demonstrate significant gains over non-learning and learning baselines. Building on this 2D framework, we …

Mozgus, Damian Cerda, Madison Lopez

Computer Science and Software Engineering

The indie game market is flooded with genre experiments, yet few successfully combine fast-paced action with meaningful strategic decision-making. Our project aims to fill this gap by creating a game that fuses top-down action combat with resource-management tycoon mechanics. We found that in many games, the management phases lack mechanical stakes. Our goal was to intertwine these systems so that choices made in one phase meaningfully impact the other.

Reinforcement Learning Based Security Schemes For Distributed Ai Systems, Ashan Chamath Gunawardena

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Distributed machine learning (DML) is a component of modern intelligent systems, enabling collaborative training across devices such as mobile clients, vehicles, and edge networks. However, the decentralized nature of these systems introduces vulnerabilities, particularly data poisoning attacks that compromise model integrity and degrade performance. Traditional defenses, such as statistical filtering, robust aggregation, and privacy-preserving techniques, often struggle to adapt to overwhelming adversaries or operate under strict privacy and real-time constraints. This dissertation proposes the use of reinforcement learning (RL) and deep reinforcement learning (DRL) based misbehavior detection schemes that dynamically identify poisoning attempts in distributed AI systems, including federated learning, …

Making Deep Neural Networks Trustworthy: Intelligibility And Safety Through Symbolic Methods, Eleanor Catherine Quint

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

The rapid adoption of deep learning has come at the cost of properties long valued in artificial intelligence: intelligibility and safety. This dissertation develops methods that restore these properties by coupling neural networks with symbolic structure.

First, for supervised classification, I propose a differentiable decision tree integrated with a supervised variational autoencoder. The resulting model maintains competitive accuracy and generative performance while exposing clear macro-features in its latent space, improving interpretability.

Second, for reinforcement learning, I extend constrained Markov decision processes by specifying constraints in formal languages. This formal language constrained MDP enables the use of automata for state augmentation, …

3d Face Modeling From 2d Images Using Deep Neural Networks, Mario Alberto De La Cruz Armendariz

Open Access Theses & Dissertations

Applications of 3D face reconstruction include biometric authentication, personalized avatars and digital identity, medical visualization, forensic analysis, and broader human-computer interaction. We propose an approach to 3D face reconstruction that can generate a fully textured 3D facial model using only two grayscale images: a front view and a profile view of the subject. Once trained, the system can perform the reconstruction autonomously without manual intervention. Unlike traditional methods requiring multi-camera setups, depth sensors, or cloud-based processing, the proposed approach runs fully offline on a standard CPU, supporting dynamic execution across CPU cores and eliminating the need for a dedicated GPU. …

Efficient Adaptive Spline-Based Path Planning For In-Space Servicing, Assembly, And Manufacturing Applications, Christian Lozoya

Open Access Theses & Dissertations

Autonomous robotic systems operating in cluttered and partially observed environments require trajectory generation methods that produce smooth and dynamically feasible motion while reacting to locally sensed obstacles. This requirement is especially pronounced for free-flyer and in-space servicing, assembly, and manufacturing (ISAM) platforms, where onboard sensing is sparse, global environmental information is unavailable, and communication or computational resources are constrained. In such settings, motion plans must be updated online using incomplete and rapidly changing local observations, while avoiding excessive replanning that can lead to oscillatory or unstable behavior. Many existing approaches either rely on dense optimization over extended horizons, which is …

Further Insights Into The Network Link Outlier Factor's (Nlof) Light-Load Penalty, Sunday Oluwaleke Ogundele

Open Access Theses & Dissertations

This research investigates the performance of the Network Link Outlier Factor with Most Likely Links (NLOF:MLL), under varying network load conditions. Earlier studies reported that the NLOF:MLL algorithm experienced a noticeable drop in fault-localization accuracy when operating in lightly loaded networks. To further examine this limitation, 240 experiments were carried out to observe how the algorithm responds as overall network load increases. The evaluation focused on the classification performance metrics: precision, recall, and F1-score. The results show that NLOF:MLL’s effectiveness improves as network load increases but that the rate of improvement slows progressively, eventually stabilizing in a pattern consistent with …

Design And Testing Of A Vr Escape Room Game For Philippine Martial Law History, Eric Cesar Vidal, Jr., Johanna Marion R. Torres, Jesus Alvaro Pato, Kenneth King L. Ko

Department of Information Systems & Computer Science Faculty Publications

This paper presents a Virtual Reality Educational Escape Room game where players learn about the highly divisive Martial Law period in Philippine history. We describe the game’s general design and the results of a user test to evaluate the game in terms of VR presence, immersion, and overall usability.

User Evaluation Of A Virtual Patient For Philippine Medical Education, Ma. Mercedes T. Rodrigo, Samantha Castaneda, James Alvir Maclin V. Alaan, Paolo Santino P. Caoile

Department of Information Systems & Computer Science Faculty Publications

Caladrius is a virtual patient system designed for use in Philippine medical schools. It responds to the need for medical interview training, for greater variety in teaching-learning strategies, and for culturally appropriate technologies. It has two versions: a text-only version whose interface is similar to a chat interface, and an audio version that accepts speech input and responds with speech output. In a prior test of Caladrius, users requested improved audio response time and the inclusion of different patient personalities. A subsequent version of Caladrius was created to comply with these requests. As much of the lag was attributable to …

Property Management System, Abbas Kurnool

Electronic Theses, Projects, and Dissertations

The real estate industry generates and manages large amounts of data, including tenant information, lease agreements, property maintenance schedules, and financial transactions. Reliance on traditional manual methods often results in inefficiencies, fragmented data, and delays in decision-making. To overcome these challenges, this project presents the design and implementation of a Real Estate Property Management System (REMS) for Future Properties, a company aiming to optimize its operations through digital transformation.

The proposed system is developed on Microsoft Dynamics 365 as the core platform, integrated with the Microsoft Power Platform tools (Power Apps, Power Automate, and Power Pages). This integrated framework provides …

The Future Is Now: Empowering Society Through Ai Literacy, Jason S. Wrench, Sanae Elmoudden

Milne Open Textbooks

Artificial Intelligence (AI) is no longer a futuristic concept—it is the reality of the present. From the algorithms shaping our social media feeds to the generative tools transforming our workplaces, AI has permeated every aspect of modern life. The Future is Now moves beyond the hype to provide a comprehensive roadmap for understanding, navigating, and shaping this technological revolution.

Demystifying the Machine

This textbook serves as a user-friendly guide to the “black box” of AI. It breaks down complex technical concepts—from machine learning and neural networks to large language models—making them accessible to students across all disciplines. By establishing a …

Integrating Due Process Into Large Language Models., Joshua Paul Johnson

Electronic Theses and Dissertations

This research investigates the ability of large language models (LLMs) to recognize due process issues. Due process is a legal concept focused on the protection of the individual during interactions with government when life, liberty, or property are being impacted. Due process presents both substantive and procedural aspects that are challenging to incorporate into generative artificial intelligence. Through assessing model performance, creating benchmarking techniques, retrieval-augmented generation (RAG), and fine-tuning, this work seeks to measure due process recognition performance and improve performance in identifying due process issues. The results of evaluating larger parameter LLMs such as from Google, Meta, and OpenAI …

Multi-Modal Data-Efficient Learning For 3d Machine Vision, Zhimin Chen

All Dissertations

The rapid progress of 3D computer vision has enabled a wide range of applications in autonomous driving, robotics, and augmented reality. Despite this growth, training robust 3D perception models remains challenging due to limited labeled data, the complexity of integrating multiple modalities, and the inherently imbalanced and long-tailed nature of 3D datasets. This dissertation addresses these challenges by proposing data-efficient, multi-modal learning frameworks that improve the accuracy, generalization, and scalability of 3D scene understanding.

In the semi-supervised setting, this work presents novel approaches that combine limited annotations with large amounts of unlabeled data to enhance 3D object classification and retrieval. …

Securing Connected And Autonomous Vehicles, Owana Marzia Moushi

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

A vehicular network is susceptible to various security flaws and attacks. Cryptographic techniques are used in vehicular networks but these alone cannot provide proper security to the network. Identifying various types of attacks is necessary to secure vehicular communication networks. In this dissertation, we focused on detecting various insider attacks in vehicular networks to enhance the security of the network.

Our first contribution in this dissertation is the detection of both binary and multi-class data replay and data replay Sybil attacks in vehicular networks. A publicly available dataset, VeReMi-Extension is used to detect these attacks. This dataset has been reformulated …

Real-Time, Co-Regulated Design For Cyber-Physical, Multi-Rotor Uas Swarms, Grant Simon Phillips

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Uncrewed Aerial Systems (UAS) have been integrated into a wide range of research and industrial applications, with growing interest in extending mission duration and spatial coverage through coordinated multi-UAS systems, or swarms. While swarming offers the potential for extended mission endurance and robustness through advanced path-planning, control, and estimation algorithms, significant challenges arise when implementing these methods on decentralized platforms composed of size, weight, and power-constrained (SWaP) vehicles. Limitations in onboard computational capacity and congested communication channels can break critical design-time assumptions, which at best, will degrade application quality of service, and at worst, destabilize the fleet through excessive delays …

Qualitative Stereo Vision Using Distributed Extended Waltz Filtering, Ben Mathew

Theses and Dissertations

Stereo vision is a fundamental problem in computer vision, aimed at reconstructing three-dimensional scene structure from two or more two-dimensional images. Traditional stereo algorithms rely on quantitative disparity estimation, often constrained by calibration precision, lighting variations, and surface texture. In contrast, our proposed Qualitative Stereo Vision seeks to understand depth relationships and spatial configurations from multiple planar views through symbolic reasoning and constraint satisfaction, offering a more flexible and cognitively plausible approach to scene interpretation.

This dissertation presents a novel framework called Distributed Extended Waltz Filtering, designed to provide qualitative stereo vision, particularly in the presence of occlusions—a persistent challenge …

Design Principles For Customer‑Engaging Digital Service Systems: An Action Research Study, Keng Siau, Xiaofeng Chen, Xin Tan

Research Collection School Of Computing and Information Systems

Digital services represent a business approach employed by organizations to operate in the digital environment. However, systematic development guidelines for developing quality digital service systems are lacking in the literature. The authors identified four general challenges for developing and implementing customer-engaging digital service systems (CEDSS). By employing the method of canonical action research in a digital service system project, they derived 10 design principles for developing high-quality CEDSS. They empirically evaluated the design principles in the development project and through follow-up focus group sessions. The design principles provide applicable and actionable guidelines for the development of CEDSS.

Hallucination Techniques For Self-Supervised Synthetic Datasets For Mobile Robots, Wyatt D. Colburn

Master's Theses

Classical techniques in autonomous navigation struggle in tightly constrained spaces. Machine learning has been shown to perform better in these difficult environments but most techniques require large amounts of navigation experience for training. Using a new machine learning paradigm learning from hallucination (LfH), training data can be collected in a safe environment and not require supervision. Data is collected in real time while an agent performs a random walk in free space, supervision is not required as there are no obstacles for the robot to run into. After a random walk a post processing pipeline will hallucinate a safety corridor …

Human Identification And Action Recognition Using Small Data And Deep Domain Adaptation, Alexander M. Glandon

Electrical & Computer Engineering Theses & Dissertations

Human identification and human action recognition problems are two important research areas for real-world security and surveillance applications. In both human identification and action recognition, it is necessary to operate by collecting small datasets in the field, possibly in a short time window of observation. This dissertation studies and develops computational modeling and high-performance machine learning (ML) and deep learning (DL) models for human identification and human action recognition using small amounts of data. These methods and computational models may be useful for different security and surveillance applications.

This dissertation on human recognition develops a ML computational model to estimate …

Blind Medical Image Watermarking Method Using Combined Nsct/2d-Dct Domains, Ali Kouadri, Ali Benziane, Abdelhalim Rabehi, Mohamed Lebcir

Iraqi Journal for Computer Science and Mathematics

This paper presents a novel blind watermarking framework that combines Non-Subsampled Contourlet Transform (NSCT) and 2D Discrete Cosine Transform (DCT) domains. The proposed method embeds the watermark’s data within low-frequency coefficients of sub-vectors extracted from a concatenated NSCT/2D-DCT transforms processing. The embedding procedure involves simple differential processing which ensures a straightforward watermark extraction. Extensive testing across medical imaging modalities (X-ray, CT, MRI, ultrasound) confirmed strong imperceptibility and robustness against attacks like JPEG compression, noise, filtering, and geometric manipulations. Compared to contemporary techniques, our NSCT/2D-DCT method shows stronger robustness against attacks without compromising diagnostic quality, proving its viability for medical image …

An Enhanced Cyber Security For Finger Knuckle Print Recognition System Using Rubik’S Cube With Rabbit Encryption Algorithm, Haitham Salman Chyad, Tarek Abbes

Iraqi Journal for Computer Science and Mathematics

Cybersecurity in biometric systems is an urgent requirement due to their increasing use in identity verification, especially in smartphones, surveillance systems, and electronic transactions. These systems depend on distinctive and immutable biological features, such as fingerprints, Knuckles and facial features, making them potential targets for cyberattacks. In this context, the need to develop advanced security mechanisms, including encryption, forgery detection, and multi-factor authentication, has emerged to guarantee the confidentiality of biometric data and protect it from identity theft or manipulation. This trend emphasizes the need to integrate cybersecurity and biometric technologies to secure and ensure the reliability of systems in …

Retrieval Augmented Framework For Deepfake Audio Detection, Avinash Saxena

Master's Theses

The widespread use of AI-based audio deepfakes threatens severely to undermine media integrity and public trust. Speech synthesis techniques have improved dramatically in voice conversion (VC) and text-to-speech (TTS) in recent years, making forgeries sound highly realistic, and concerns are raised about possible malevolent uses. Existing state-of-the-art techniques for identifying fake speech have proven to be effective in some cases but are still limited in application and robustness when faced with novel attacking strategies, different acoustic conditions, or alternative linguistic domains. To address some of these limitations, the current research presents a novel deepfake audio detection system based on personalized …

Grey Wolf Optimization Of Pi Controller For Power Management In Wind Farms: A Novel Approach, Anis Feddaoui, Lotfi Farah, Abdelouahab Benretem, Mohammed Abdeldjalil Djehaf

Turkish Journal of Electrical Engineering and Computer Sciences

This study proposes a novel power management strategy for wind farms using a grey wolf optimization (GWO)-based PI controller. The method aims to enhance active and reactive power control in systems employing dou bly fed induction generators. Three control strategies are evaluated—namely, a classical frequency-domain PI controller, an Artificial Neural Network (ANN)-based controller, and the proposed GWO-based PI controller—the last of which represents the main contribution. The classical PI and ANN controllers are included strictly for comparative bench marking. MATLAB simulations demonstrate that the GWO-beased PI controller offers superior dynamic performance, particularly in settling time and overshoot reduction. A power …

Fpga-Based Takagi-Sugeno Fuzzy Controller For Quadrotor Uav Stabilization And Trajectory Tracking, Hocine Khati, Mohamed Amine Nehmar, Arezki Fekik, Mohand Achour Touat, Hand Talem, Rabah Mellah

Turkish Journal of Electrical Engineering and Computer Sciences

This study presents the implementation of a fuzzy logic–based control system on a field-programmable gate array (FPGA) for a quadrotor autonomous aerial vehicle (UAV). The objective is to design and integrate six Takagi–Sugeno fuzzy controllers to regulate roll, pitch, and yaw angles, along with longitudinal, latitudinal, and altitude movements, thereby stabilizing the UAV and enabling it to follow a desired trajectory. Due to the computational complexity of the six controllers, achieving the desired performance requires considerable processing time, which can adversely affect the quadrotor’s mission. Owing to their high processing power and operating frequency, FPGAs enable the control algorithm to …

Towards A Generalized And Optimized Apriori Approach, Artem Abdikov

Master's Theses

Apriori is a machine learning algorithm developed in 1994 by R. Agrawal and R. Srikant for association rule mining purposes. This family of algorithms takes transactional data and analyzes relationships between variables in large datasets. The typical output of such algorithms is a prediction that if users choose item X, it is highly likely that they will also choose item Y. Apriori is known to be a robust algorithm and is used by many large companies in order to analyze user tendencies and even make recommendations. Although Apriori is a powerful algorithm, its original implementation is known to have limitations, …

A Feature-Free Deep Learning Approach For Midair Hand Gesture Recognition From Surface Electromyogram (Semg) Data, Yasir Altaf, Abdul Wahid, Mudasir Manzoor Kirmani

Turkish Journal of Electrical Engineering and Computer Sciences

Midair hand gesture recognition plays a crucial role in applications such as sign language recognition and human-computer interaction, particularly for supporting individuals with partial or complete hearing loss. However, recognizing gestures in midair remains challenging due to the rapid and complex nature of hand movements. To address this, noninvasive techniques like surface electromyography (sEMG)—which captures muscle activity through sensors placed on the skin—have gained attention. sEMG provides rich time-series data that reflect both spatial and temporal muscle dynamics. In this study, we propose a deep learning architecture that combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to classify …

Integrated Log Spectrogram Convolutional Neural Network (Ils-Cnn) For Robust Spoken Digit Recognition, Awais Ahmed

Turkish Journal of Electrical Engineering and Computer Sciences

Spoken digit recognition (SDR), a type of supervised automatic speech recognition, is essential for various human-machine interaction applications, including banking operations, dialing systems, price extraction, and airline reservation systems. However, designing an effective SDR system presents several challenges, such as developing labeled audio data, selecting appropriate feature extraction methods, and creating high-performance models. To overcome these challenges, a novel approach for robust spoken digit recognition using an integrated log spectrogram convolutional neural network (ILS-CNN) has been proposed. The proposed work presents an efficient SDR method by taking advantage of a log spectrogram layer directly within the neural network to enhance …

Railway Track Condition Monitoring Based On Sensor Data And Artificial Neural Networks, Ivan Kots, Alina Isaeva, Mark Denisenko, Alexander Sinyukin, Andrey Kovalev

Turkish Journal of Electrical Engineering and Computer Sciences

Monitoring the condition of engineering objects is one of the urgent tasks of industry, construction, and transport infrastructure. This article describes a system for condition monitoring and diagnostics of rail tracks in real time. Compared with other similar studies, the proposed system has the advantages of compactness, usability, scalability and versatility of application. The proposed monitoring system is based on an Nvidia Jetson Nano embedded computing board and also includes inertial sensor modules, a microphone, a geolocation module, communication modules, an SSD storage device, and a battery. The prototype of the diagnostic module is a portable device that can be …

Modeling And Simulation Of Dynamic Energy Management Systems For Smart Buildings, Onur Özel, Ali̇ Rifat Boynueğri̇, Hayri̇ Yi̇ği̇t, Burak Tekgün

Turkish Journal of Electrical Engineering and Computer Sciences

This study presents a dynamic energy management system tailored for smart residential buildings, integrating thermal and electrical models to achieve both natural gas and electricity bill cost reduction. By harnessing wind and solar energy sources, the system aims to meet the diverse energy needs of modern homes. Through load shifting and thermal storage strategies, known as power-to-heat (P2H) approaches, the system ensures efficient renewable energy utilization while maintaining resident comfort. Validation of the proposed system was conducted using real-world data from the Yıldız Technical University Smart Home Laboratory, demonstrating its practical applicability and effectiveness. Results indicate significant reductions in both …