Computer Engineering Commons^™

Computer Vision And Deep Learning-Based Decision Support System Using Eye Motion Tracking For Nystagmus Detection, Kowshik Balasubramanian

Electronic Theses and Dissertations 2020 - Present

This thesis presents the design, implementation, and experimental validation of an artificial intelligence (AI)-driven system for detecting and quantifying nystagmus an involuntary, rhythmic oscillation of the eyes intended as a portable, low-cost complement to conventional Videonystagmography (VNG). The complete pipeline integrates six algorithmic stages: face landmark detection, contrast enhancement, background-aware pixel thresholding, grid-based vertical column filtering, connected-component cluster analysis, and centroid computation, operating in real time on standard smartphone video to extract a sub-pixel normalized iris position time-series without any specialized eye-tracking hardware or infrared illumination. The system supports diagnostic decision-making, highlighting its promise for incorporation into telemedicine settings. The …

Open Multi-Agent Systems: The Free-Range-Zoo Framework And Moasei Competition, Ceferino J. Patino Iv

School of Computing: Dissertations, Theses, and Student Research

The field of multi-agent reinforcement learning (MARL) has made significant strides in addressing sequential decision-making problems under uncertainty. However, traditional MARL frameworks assume closed-world settings with fixed agent sets, static task distributions, and unchanging environment dynamics. This thesis presents two complementary contributions that advance the state of open-world multi-agent systems research: (1) the free-range-zoo framework, an open-source environment suite for MARL in open environments featuring dynamic agent populations, evolving task sets, and changing operational frames; and (2) the MOASEI Competition, an international benchmarking event that leverages free-range-zoo to evaluate how artificial agents handle openness in complex, partially observable domains. The …

Extraction And Interpretation Of Eeg Features For Diagnosis And Severity Prediction Of Ad And Ftd Using Deep Learning, Tuan Vo

Electronic Theses and Dissertations 2020 - Present

Alzheimer’s disease (AD) is the most common form of dementia and is characterized by progressive cognitive decline and memory impairment. Frontotemporal dementia (FTD), the second most prevalent form, primarily affects the frontal and temporal lobes and often leads to changes in personality, behavior, and language. Due to overlapping clinical symptoms, FTD is frequently misdiagnosed as AD. Electroencephalography (EEG) offers a portable, non-invasive, and cost-effective method for studying brain activity; however, its diagnostic utility for differentiating dementia subtypes is limited by signal complexity and noise. In this dissertation, I propose an EEG-based feature extraction framework that leverages deep learning to identify …

Sdn Controller For Distributed Quantum Computing, Firas Selmi

Masters Theses

Quantum networks promise transformative capabilities for computation [1], but current hardware remains limited; state-of-the-art quantum processors still operate with only a few hundred qubits [2], far below the scale required for practical applications. This limitation motivates the use of Distributed Quantum Computing (DQC), where computation is performed across multiple interconnected nodes. However, efficient DQC requires global network awareness and orchestration, a role analogous to Software-Defined Networking (SDN) in classical systems. In this work, we investigate the impact of SDN-inspired control logic on quantum networks by executing a scaled distributed implementation of Shor’s algorithm to factor N = 15 over a …

Llm For Clinical Named Entity Recognition: A Study On Rag With Pubmed And Umls, Apoorv Tripathi

Electronic Theses and Dissertations 2020 - Present

The first step of biomedical NLP is recognizing clinical named entities, which consist of identifying and categorizing a variety of clinical entities such as diseases, symptoms, genetics, diagnostic tests, procedures, etc. from a body of unstructured clinical text. This study presents a PubMed and UMLS based Retrieval Augmented Generation framework which improves the performance of the Large Language Models to identify clinical entities by providing context. In particular, the framework consists of a two-stage pipeline, where candidate tokens are identified from initial LLM-based classification and refined with retrieved context from either PubMed or UMLS. The proposed framework is assessed across …

Shelter Portal: Qr-Based Service Tracking For Low-Barrier Shelters, Kate Steele, Colton Knopik, Michael Fischer

2026 Symposium

Shelter Portal is a web-based service tracking application developed for low-barrier shelters, including Catholic Charities’ House of Charity and Rising Strong programs. Many shelters still rely on manual headcounts and estimated meal totals, which are labor-intensive, error-prone, and insufficient for tracking individual service use over time. This limits operational visibility and makes it difficult to generate reliable reports, identify usage trends, and support external reporting requirements. Shelter Portal addresses this problem by providing a more accurate and privacy-conscious way to document shelter services.

The system was designed as a kiosk and web-based platform that uses scannable QR code cards to …

Uscis-Grounded Ai: Preventing Hallucinations In Immigration Legal Services, Hephzibah Igwe

ONU Student Research Colloquium

Artificial intelligence chatbots increasingly provide legal information to consumers, but AI "hallucinations" (confidently stated but incorrect responses) pose serious risks in immigration law. Incorrect information about USCIS forms, fees, processing times, or filing procedures can result in visa denials, deportation proceedings, or permanent bars to entry.

This research presents a novel "source-grounded AI" system that eliminates hallucinations in immigration legal information. Rather than relying solely on large language models (LLMs) trained on general internet data, the system uses USCIS.gov as the primary source of truth for all operational data including current forms, fees, processing times, filing addresses, and policy updates. …

A Trojan Attack On Tdma Synchronization In Energy-Harvesting Wireless Networks, Ethan Berei

ONU Student Research Colloquium

This paper investigates a Trojan attack targeting the time-division multiple access (TDMA) synchronization mechanism in single-hop energy-harvesting wireless networks. The attack compromises a single node, which subtly skews its transmission timing to operate outside its assigned time slot, causing localized transmission overlaps and triggering repeated network-wide resynchronization events. This behavior shortens the synchronization interval, significantly increases control-plane traffic, and leads to higher energy consumption and delay in energy-constrained networks. The attack is modeled within a finite state machine (FSM) framework and experimentally evaluated under varying energy-harvesting conditions. Experimental results show that the number of synchronization events can increase by up …

Enhancing Lane Detection In Autonomous Vehicles Using Data Augmentation For Adverse Environmental Conditions, Rutvikkumar Dave

Electronic Theses and Dissertations 2020 - Present

To make sure that self-driving and connected automobile technologies are safe and work well, it’s really important that they can correctly identify lanes. But lane detection Algorithms typically have a hard time working well when the weather is bad, such when it rains, fogs, or goes too fast. The circumstances cause visual distortions that make existing computer vision systems less reliable, which makes it harder requires autonomous navigation systems to work well. This paper introduces a comprehensive lane detection system that integrates synthetic Weather-informed data augmentation combined with a Weather-aware Temporal Lane Detection Network (WTLDNet) to make it easier for …

Integration Of Bayesian Networks And Neural Networks For High-Dimensional Data Analysis, Cooper Schmer

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

High-dimensional biomedical datasets, such as omics data, present significant challenges for predictive modeling due to noise, redundancy, and computational complexity. This thesis proposes a hybrid framework that integrates Bayesian Networks (BNs) and Artificial Neural Networks (NNs) to improve classification performance of such data sets while reducing input dimensionality. Central to this work is a novel feature selection method based on d-separation, a structural property of Bayesian networks that encodes conditional independence relationships.

The proposed approach introduces a count-based d-separation metric to quantify the relevance of variables to a target outcome, along with a thresholding scheme to balance feature selection robustness …

Method For Testing And Evaluating Intelligence Level Of Virtual Forces Based On Operational Experiments, Dayong Liu, Zhiming Dong, Weidong Zhang, Wenjun Zhang, Jiancheng Gao

Journal of System Simulation

Abstract: The intelligence level of virtual forces is a key factor affecting the credibility and effectiveness of tactical confrontation simulations. To address the current lack of a testing and evaluation system, a method for testing and evaluating the intelligence level of virtual forces based on operational experiments is proposed. Guided by operational experiment theory, the method stimulates the intelligent behavior of virtual forces by constructing dynamic confrontation environments, and collects, calculates, analyzes, and evaluates their intelligence performance data according to a systematic process. The overall architecture, logical functional modules, and basic evaluation process of the method are designed. A "4M" …

Research On Control Of Coaxial Dual-Rotor Unmanned Aerial Vehicle Based On Improved Reaching Law, Xinhang Chen, Xiaodong Ling, Chengchang Lang, Shijun Zheng, Yiqi Tang

Journal of System Simulation

Abstract: To address the issues of significant chattering, slow convergence speed, and large overshoot in the control system of a coaxial dual-rotor unmanned aerial vehicle, a control method based on an improved double-power and hyperbolic function integral sliding mode reaching law was proposed. A novel reaching law was designed to achieve fast convergence when the system state is far from the sliding surface and smooth transition when approaching the sliding surface, thereby enhancing the overall convergence speed of the system and ensuring that the system reaches the sliding surface within a finite time. The saturation characteristic of the hyperbolic function …

Large Language Model For X Language Simulation: Architecture, Key Technologies, And Typical Applications, Laichunyang Peng, Fei Ye, Xiaoming Guo, Jinglin Zhou

Journal of System Simulation

Abstract: General-purpose large language models lack training on X language-specific corpora, and traditional fine-tuning methods lack targeted adaptation to the interdisciplinary integration and multimodule coupling of X language, resulting in problems such as non-standard syntax and semantic deviation in generated code. To address these issues, this paper systematically proposed the definition and integrated architecture of a large language model for X language simulation. Modeling subclasses were defined according to the disciplines and classes of X language, and dedicated adapters were constructed for each subclass. By merging their weights during the inference phase, the incremental integration of multi-domain modeling skills was …

Vehicle Routing Optimization For Underground Mines Considering Fuzzy Demand And Time Tolerance, Guorong Wang, Haishun Deng, Ziming Kou, Xuanxuan Yan, Zhixiang Huang

Journal of System Simulation

Abstract: To solve the problem of material demand fluctuation and different time windows in auxiliary transportation of underground mines, a routing optimization method for material distribution considering fuzzy demand and time tolerance was proposed. Based on the fuzzy credibility theory, uncertain demand was constrained by fuzzy chance constraints, and a multi-objective routing optimization model for underground mine auxiliary transportation was constructed with the objectives of minimizing the total operating cost of vehicles and maximizing time tolerance. A multi-objective genetic algorithm with mixed dominance strength was designed to solve the model. By calculating the deviation difference of Pareto frontier solutions, …

Auv Path Planning Integrating Local-Global Strategies In Unknown Environments, Wenlong Meng, Yanbo Pu, Ya Gong

Journal of System Simulation

Abstract: Existing path planning algorithms often struggle to efficiently explore and generate high-quality trajectories. To address this issue, this paper proposes a path planning algorithm that integrates local-global strategies. By employing the rolling window technique, the global one-time path planning problem is transformed into an iterative process of multiple local planning stages. During the global exploration phase, the rolling window is used to determine high-level path branches and to identify branch waypoints, thereby refining the calculation of local paths. In the local exploration phase, an improved RRT-Connect algorithm is proposed, which combines adaptive circular sampling with dynamic step length to …

Modelling Method Of Unmanned Vehicle Dynamics Based On Neural Network, Jun Wang, Min Liu, Xiaochuan Zhang, Yishan Ding, Juhui Feng, Ye Zhuang

Journal of System Simulation

Abstract: To address the challenges of high data acquisition costs of test data on dynamic characteristics between tires and soft terrain and low speed of numerical calculation for unmanned vehicles in complex terrestrial environments, a modeling method of unmanned vehicle dynamics based on a neural network was proposed. Tire-terrain contact dynamics models were built by using discrete element method (DEM) simulations for tire-terrain contact and experimental data, thereby creating a dataset of tire contact forces for various tire materials in terrestrial environments. The neural network was applied to regressively learn the dataset, and a nonlinear neural network tire model was …

Large-Scale Multi-Objective Evolutionary Algorithm Based On Multi-Region Dynamic Grouping, Binhao Liang, Jingxuan Wei, Fengqin Liang

Journal of System Simulation

Abstract: The decision variable dimension of large-scale multi-objective optimization problems can reach hundreds or even thousands. For existing large-scale multi-objective evolutionary algorithms based on decision variable analysis, which usually consume a large amount of computational resources for grouping and fail to consider the interactions between convergence-related variables and diversity-related variables, a large-scale multi-objective evolutionary algorithm based on multi-region adaptive dynamic grouping was proposed. The algorithm employed a Gaussian mixture model to partition the decision space into multiple regions; within each region, feature vectors were constructed for each decision variable, and spectral clustering was utilized to perform grouping. To validate …

Intelligent Competition Platform And Mode Driven By Cloud-Native Simulation, Long Qin, Hesong Huang, Lujia Yin, Chuan Ai, Qi Zhang, Xinmeng Li

Journal of System Simulation

Abstract: To solve the problems faced by the adversarial competition mode of agents, including difficult development and deployment, low resource utilization, poor reusability, and difficulty in accessing reinforcement learning algorithms, a new agent simulation training platform was designed. The software components of the competition platform were decoupled based on cloud-native technology; a high-performance simulation engine for the competition environment was proposed; a new method of an embedded reinforcement learning model for an intelligent control terminal was designed, with multiple online and offline policy-based reinforcement learning algorithms set. The experiment demonstrates that the development and deployment of the system is efficient, …

Intersection Positioning Algorithm With Spatial Translation Based On Sar Scene Matching, Cheng'en Pu, Yumin Lai, Rui Shi, Yan Liao, Kezi Meng, Lifeng Qu

Journal of System Simulation

Abstract: To address the problem that the positioning precision of the inertial navigation system cannot meet the requirements of autonomous positioning when the aircraft flies, an autonomous positioning method with spatial translation based on circular scanning scene matching of SAR was proposed. The spatial translation positioning model of the aircraft was established according to the position of the ground matching points obtained by single point and single circular scanning scene matching of SAR, the oblique distance between the matching points and the aircraft, and the inertial measurement information of the aircraft. The characteristic information of the matching point sequence was …

State Monitoring Of Nuclear Power Connection Sleeve Quality Inspection Equipment Driven By Digital Twin, Yandong Nan, Jinda Zhu, Xinbin Lu, Zhiying Qin, Dandan Qi, Zhiheng Ding

Journal of System Simulation

Abstract: To address the problems of delayed state perception, single monitoring dimension, and insufficient visualization in the quality inspection equipment for nuclear power connection sleeves, a state monitoring method driven by digital twin was proposed. A digital twin-based collaborative state monitoring framework for the inspection equipment was constructed. Based on the OPC UA technology, a multi-source information interconnection model was established. A finite state machine model was employed to discretize and logically drive the inspection process, and a hierarchical verification strategy was proposed to establish a multi-dimensional motion state monitoring mechanism. A surrogate model coupling the radial basis interpolation function …