Digital Commons Network^™

Reimagining The Machine Vision Pipeline In Cyber Physical Systems For Trustworthiness And Efficiency, Adith Boloor

McKelvey School of Engineering Graduate Student Theses & Dissertations

Cyber-physical systems (CPS), including autonomous vehicles, drones, and mobile robots, rely on intricate sensors, actuators, and machine learning algorithms to perceive the physical world and execute actions within their surroundings. In the context of vision-driven CPS, achieving this demands processing a substantial volume of visual data captured by on-board cameras. The data is subsequently channeled through digital processors and harnessed by deep neural networks for tasks such as image classification, object detection, and depth perception. This data-centric, machine-vision-infused CPS fosters intelligent decision-making, thereby enhancing overall system performance. Trustworthiness, encompassing the robustness of the entire machine-vision pipeline, and system-level efficiency are …

Reimagining The Machine Vision Pipeline In Cyber Physical Systems For Trustworthiness And Efficiency, Adith Boloor

McKelvey School of Engineering Graduate Student Theses & Dissertations

Cyber-physical systems (CPS), including autonomous vehicles, drones, and mobile robots, rely on intricate sensors, actuators, and machine learning algorithms to perceive the physical world and execute actions within their surroundings. In the context of vision-driven CPS, achieving this demands processing a substantial volume of visual data captured by on-board cameras. The data is subsequently channeled through digital processors and harnessed by deep neural networks for tasks such as image classification, object detection, and depth perception. This data-centric, machine-vision-infused CPS fosters intelligent decision-making, thereby enhancing overall system performance. Trustworthiness, encompassing the robustness of the entire machine-vision pipeline, and system-level efficiency are …

Multimodal Representation Learning Frameworks For Modeling Progression And Heterogeneity In Alzheimer’S Disease, Sayantan Kumar

McKelvey School of Engineering Graduate Student Theses & Dissertations

Alzheimer’s Disease (AD) is the leading cause of dementia, characterised by cognitive and functional impairments that disrupt daily activities. Different clinical modalities such as neuroimaging biomarkers, cognitive assessments, fluid biomarkers and genetic data provide unique and complementary information, contributing to a more comprehensive understanding of disease progression and heterogeneity in disease characteristics. With recent advancements in computational capabilities, particularly in deep learning, multimodal representation learning frameworks aim to integrate diverse clinical modalities into a cohesive framework, capturing the most significant patterns within each modality. Existing data-driven multimodal representation learning frameworks in AD research have two major limitations. First, AD progresses …

Development Of A Climbing Performance Analysis Tool Using Computer Vision, Guy Ludford

The Plymouth Student Scientist

Indoor bouldering, a rapidly growing sport in the UK and globally, has seen a significant rise in participation, paralleled by an increase in the use of fitness apps and wearable trackers. Despite this growth, tracking and recording metrics for indoor climbing remains a challenge. This paper proposes an automated tool utilising computer vision and a gym-wide camera system to collect data on routes climbed and attempts made, without the need for manual logging. This tool aims to provide climbers with detailed performance analysis and support climbing gyms in optimising route setting and member engagement. Initial market research and discussions with …

Enhancing Graph Neural Networks By Editing Graphs, Jiayu Li

Dissertations - ALL

Graphs are pervasive in both the natural world and various domains of science and engineering. Numerous advanced classifiers, such as Graph Neural Networks (GNNs), have been developed to perform node classification on these graphs. However, as graphs become denser with an increasing number of edges, GNNs often suffer from suboptimal generalization performance due to the presence of task-irrelevant connections. These redundant connections can introduce noise, consume excessive computational resources, and degrade performance. Identifying and preserving critical connections in large-scale graphs, while pruning unnecessary ones, is crucial for enhancing the efficiency and accuracy of GNNs in node classification, particularly for GCNs. …

Optimal Operation Scheduling Of Integrated Energy System Considering Energy Priority, Dongli Jia, Keyan Liu, Zhaoying Ren, Zezhou Wang, Dongsheng Tang

Journal of System Simulation

Abstract: Integrated with the actual situation of power grid and the growth of new energy, a multiobjective model for optimal scheduling of the integrated energy system(IES) is established based on the analysis of the energy-flow relationship of the IES and taking into account the priority of energy utilization and the load demand response in terms of the mismatch between the distributed energy sources and the loads, the net benefit of the unit cost of the IES, and the load response degree. Combined with the equipment and the environmental benefits system, a priority constraint for energy utilization has been established for …

Research On Scheduling Strategies Simulation For Building Air-Conditioning Systems Based On Transfer Imitation Learning, Qiaochu Wang, Yan Ding, Chuanzhi Liang, Haozheng Zhang, Chen Huang

Journal of System Simulation

Abstract: To solve the problem of unstable performance and inefficient training process of low-quality data conditions at the initial stage of online deployment of air conditioner scheduling, we propose a migration-imitation learning-based air conditioning scheduling strategy simulation method. Reinforcement learning methods are used to generate building operation strategies. A standard building simulation model serves as the source domain, upon which migration learning is applied. An imitation learning loss function is incorporated into the intelligent loss function to enhance algorithm performance. The results indicate that, compared with the non-use of migration learning, the proposed method can improve the operational efficiency by …

Behavioral Modeling Of Manned-Unmanned Cooperative Air Combat Based On Improved Abc Algorithm, Peng Wang, Haoyu Liu, Ni Li, Zexi Yu, Shangjie Jia

Journal of System Simulation

Abstract: To solve the problem of difficulty in establishing collaborative behavior models and weak adversarial capabilities in typical MAV/UAV air combat scenarios, a mixed decision based MAV/UAV behavior modeling framework is proposed. Using collaborative rule sets, rule subsets, tactical action sets, and other tools, a hierarchical decision collaborative behavior model supporting five types of collaborative tactics, including grinding tactics and unilateral flanking tactics, is constructed in this framework. a behavior model parameter optimization method based on an improved artificial bee colony (ABC) algorithm is proposed. By using the Mason rotation method to initialize the population, a better initial honey source …

Privacy Protection In Machine Learning Via Exploitation Of Constrained Adversarial Evasion, Brian Testa

Dissertations - ALL

Deep neural networks are extensively applied to real-world tasks. In many cases, the data feeding these tasks are human generated content, which emphasizes the criticality of privacy and data protection. The diverse modalities of this user data provide fertile ground for 3rd parties to monetize a user’s data. This work considers two such modalities: user speech when interacting with smart speaker voice assistants (VAs) and images shared with online service providers. In these cases, the user would like to support some form of machine learning (ML) inference without allowing others. A user interacting with a smart speaker would like the …

Harmonic Impedance Modeling And Oscillation Analysis Of Modular Multilevel Converter, Yuhong Wang, Wensheng Chen, Shilin Gao, Jianquan Liao, Yangfan Cheng

Journal of System Simulation

Abstract: To facilitate rapid analysis of the oscillation stability mechanism in modular multilevel converter-based high voltage direct current (MMC-HVDC) systems and streamline the simulation process for determining MMC impedance characteristics, a simplified mathematical simulation model for MMC closed-loop impedance is developed using the harmonic state space method. This model considers various control strategies and includes both AC-side and DC-side impedance models. By applying a Nyquist criterion-based impedance analysis method, the stability mechanisms on the AC and DC sides of the MMC are examined. In addition, a data-driven oscillation stability analysis method is also proposed, leveraging a global sensitivity algorithm based …

Path Planning Of Desert Robot Based On Deep Reinforcement Learning, Ming Li, Wangzhong Ye, Jiehua Yan

Journal of System Simulation

Abstract: Due to the complexity and variability of the desert environment, the key to the high-efficient of mobile robot is how to avoid obstacles and plan its path. To solve the problems of poor search efficiency and slow convergence of deep reinforcement learning algorithm in complex environment, an improved deep reinforcement learning path planning algorithm is proposed. The exploration factor is improved and dynamically adjusted according to the convergence degree of the algorithm, so that the exploration factor dynamically decreases with the increase of the understanding degree of the agent to the environment, thus speeding up the convergence speed of …

Architecture And Key Technologies Of New Research Informatization Infrastructure Platform Under The Fifth Research Paradigm, Fangyu Liao, Yang Wang, Rongqiang Cao, Bo Zhang, Zhenyu Li, Huajin Wang, Xin Chen, Dong Li, Yangang Wang, Xin Wei

Bulletin of Chinese Academy of Sciences (Chinese Version)

The basic platform of research informatization is an indispensable pedestal for modern scientific research and an important manifestation of national scientific and technological innovation capability. As the research paradigm continues to evolve, the architecture and technologies of research informatization infrastructure platform are bound to evolve as well. The new research paradigm brings unique demands and challenges to the algorithmic computility, network transmission capacity, and data storage and management. Consequently, it is an urgent requirement for research informatization infrastructure platform to make technological breakthroughs in the areas of intelligent computility, large-scale data storage and high throughput read/write, cross-network software and hardware …

Five Key Issues And Governance Strategies In Integration Of China’S National Computing Power, Tao Hong, Le Cheng

Bulletin of Chinese Academy of Sciences (Chinese Version)

Computing power, as a core element of artificial intelligence, has not received sufficient research and attention compared to data and algorithms, and has become the short board of China in international artificial intelligence competition. In fact, the integrated construction of the arithmetic system is not only an inherent requirement for the development of the digital industry, but also a regular guide for the growth of the digital economy, and a core driver for the transformation of the digital society. Although it has always secured endorsement by national policy, the relevant legal norms and actual layout are still insufficient, and the …

A Confidence-Based Knowledge Integration Framework For Cross-Domain Table Question Answering, Yuankai Fan, Tonghui Ren, Can Huang, Beini Zheng, Yinan Jing, Zhenying He, Jinbao Li, Jianxin Li

Research outputs 2022 to 2026

Recent advancements in TableQA leverage sequence-to-sequence (Seq2seq) deep learning models to accurately respond to natural language queries. These models achieve this by converting the queries into SQL queries, using information drawn from one or more tables. However, Seq2seq models often produce uncertain (low-confidence) predictions when distributing probability mass across multiple outputs during a decoding step, frequently yielding translation errors. To tackle this problem, we present CKIF, a confidence-based knowledge integration framework that uses a two-stage deep-learning-based ranking technique to mitigate the low-confidence problem commonly associated with Seq2seq models for TableQA. The core idea of CKIF is to introduce a flexible …

Gmr-4234 Evaluating Instance Segmentation Models On Histopathology Datasets, Sai Chandana Koganti

C-Day Computing Showcase

Instance segmentation is transforming digital pathology by enhancing the speed and accuracy of tissue sample analysis through advanced image processing techniques. Whole Slide Imaging (WSI) converts traditional microscope slides into high-resolution digital formats, enabling detailed examinations. This paper presents a brief experimental survey of instance segmentation models on two prominent histopathology datasets: PanNuke and NuCLS. Unlike previous surveys that merely describe deep learning models for general pathology images, we conduct experiments using state-of-the-art models including Mask R-CNN, Detectron2, YOLOv8, YOLOv9, and HoverNet on both datasets. Our study evaluates these models for both binary and multiclass instance segmentation tasks. The NuCLS …

Gpr-187 Deep Learning Models For Protein-Protein Binding Affinity Prediction, Lingtao Chen

C-Day Computing Showcase

Binding affinity (BA) prediction is important for drug discovery and protein engineering. It seeks to understand the interaction strength between proteins and their ligands (or proteins). This information assists in the design of proteins with enhanced or novel functions, as well as understanding the molecular mechanisms of drug action. This paper presents the development and comparative analysis of two deep learning models, a convolutional neural network (CNN) and a transformer model. Many variants of models in this research were developed using TensorFlow. One model that utilizes ProteinBERT was developed using PyTorch. The CNN model captures local sequence features effectively, while …

Gmr-196 Integrated Sentiment And Behavioral Analysis Of Online Product Reviews, Kiran Yepuri, Naveen Mahankali

C-Day Computing Showcase

The "Integrated Sentiment and Behavioral Analysis of Online Product Reviews" project helps businesses gain actionable insights from Product reviews by combining sentiment and behavioral analysis using NLP models like VADER and BERT. This dual approach categorizes reviews as positive, neutral, or negative and identifies themes such as preferences and complaints through Named Entity Recognition and topic modeling. By capturing both the emotional tone and specific product feedback, this method highlights consumer likes and pain points, assisting in targeted improvements for product design and customer service. The project addresses challenges in analyzing complex expressions like sarcasm, providing a robust framework for …

Gpr-185 A Multimodal Approach To Quiz Generation: Leveraging Rag Models For Educational Assessments, Mourya Teja Kunuku

C-Day Computing Showcase

Crafting quiz questions that effectively assess students’ understanding of lectures and course materials, such as textbooks, poses significant challenges. Recent AI-based quiz generation efforts have predominantly concentrated on static resources, like textbooks and slides, often overlooking the dynamic and interactive elements of live lectures—contextual cues, discussions, and interactions—that contribute to the learning experience. In this work, we propose a Retrieval-Augmented Generation (RAG) model that processes multimodal inputs by combining text, audio, and video to produce quizzes that capture a fuller context. Our method incorporates Whisper for audio transcription and utilizes a Large Vision-Language Model (LVLM) to extract essential visual data …

Uc-184 Onaccount A Web-Based Accounting Software, Manuel A Jackson, Russell E Steele, Grzegorz Loj, Zachary B Powell

C-Day Computing Showcase

This project streamline and improve the efficiency of the whole accounting process, by using current best practices for user interaction engineering and current design practices. Our software should be able to provide secure, user-friendly, and accessible financial management solutions anywhere and everywhere through various devices including desktop and mobile. Allowing users to manage their accounts whenever it seems necessary while still maintaining a high level of security. The project is inspired by the various complexity and problems regarding the accounting process in the real world such as financial reporting, miscalculations, and data security; by streamlining this process and making it …

Tubarr: A Self-Hosted Video Archiver, Joshua Sheputa

Honors Program Theses and Projects

Over the past few years, I’ve been slowly expanding my homelab, a personal setup for me to experiment with software, hardware, and deployment configurations. One driving force behind this is my desire to digitize and save anything that is important to me or that I want easy access to. I started with my family’s old CD collection, then moved on to any Blu-rays movie discs we had. Eventually, I started thinking about what else I care about and don’t want to lose track of. This brought me to the thought that any YouTube video that I may want to revisit …

Integrating Criminological Theories In Cybersecurity Risk Assessment: A Study Of The Traci Framework's Application To Critical Infrastructure, Connor S. Martin

Doctoral Dissertations and Projects

This dissertation explores the application of the Taxonomy for Risk Assessment of Cyberattacks on Critical Infrastructure (TRACI) framework, a tool designed to systematically evaluate cybersecurity threats against critical infrastructure. TRACI integrates principles from Routine Activity and Rational Choice Theories to provide a detailed and comprehensive understanding of cybersecurity risks. This integration facilitates an in-depth analysis not only of how cyberattacks occur but also of the underlying reasons they are initiated, by categorizing and assessing risks based on factors such as attacker motivations and systemic vulnerabilities. By employing ANOVA to assess variations in risk assessment scores across TRACI's designated categories—Assets, Risk …

Schedulability Analysis Of Multi-Phase Limited-Preemption Tasks, Benjamin Standaert

McKelvey School of Engineering Graduate Student Theses & Dissertations

This work addresses hard real-time systems, in which tasks must be scheduled so that they are guaranteed to meet deadlines. In particular, when tasks execute across multiple domains with high preemption costs, the combined cost of these preemptions can cause the system to become unschedulable. The number of preemptions must therefore be bounded to limit the overall task execution time, while ensuring that task blocking times are small enough to allow the system to be schedulable. Prior work introduces the Multi-Phase Secure model, which describes a more exact version of this scenario, and an algorithm to determine schedulability of sporadic …

Safety And Optimality Monitors For Learning-Enabled Systems Using Conformal Prediction, Jackson Cox

McKelvey School of Engineering Graduate Student Theses & Dissertations

The use of machine learning to create data-driven plant models and controllers has led to an increased need for safety and optimality monitors for model-based systems. System plant models are subject to uncertainty due to learning constraints such as unseen data and overfitting or physical constraints such as unknown dynamics and noise. This uncertainty is detrimental to safety-critical systems and must be properly regulated. To curb this uncertainty, we create prediction sets using the guarantees provided by Conformal Prediction. With a user-specified high probability, these prediction sets contain the true plant system states for an entire prediction horizon, which we …

Feasibility Of Large Language Models For Ceus Li-Rads Categorization Of Small Liver Nodules In Patients At Risk For Hepatocellular Carcinoma, Jiayan Huang, Rui Yang, Xiaotong Huang, Keyu Zeng, Yan Liu, Jun Luo, Andrej Lyshchik, Qiang Lu

Department of Radiology Faculty Papers

BACKGROUND: Large language models (LLMs) offer opportunities to enhance radiological applications, but their performance in handling complex tasks remains insufficiently investigated.

PURPOSE: To evaluate the performance of LLMs integrated with Contrast-enhanced Ultrasound Liver Imaging Reporting and Data System (CEUS LI-RADS) in diagnosing small (≤20mm) hepatocellular carcinoma (sHCC) in high-risk patients.

MATERIALS AND METHODS: From November 2014 to December 2023, high-risk HCC patients with untreated small (≤20mm) focal liver lesions (sFLLs), were included in this retrospective study. ChatGPT-4.0, ChatGPT-4o, ChatGPT-4o mini, and Google Gemini were integrated with imaging features from structured CEUS LI-RADS reports to assess their diagnostic performance for sHCC. …

The Chinese Room And Creating Consciousness: How Recent Strides In Ai Technology Revitalize A Classic Debate, Thomas Held

Departmental Honors & Graduate Capstone Projects

Since 1950, when Alan Turing first posed the question of whether a machine could think, the possibility of artificial consciousness has sparked intense and ongoing debate, and strong positions have been staked out on each side of the argument. On the one hand, the historically popular functionalist school of thought claims that any system capable of producing suitably “conscious” behavior in a given environment should be considered conscious. On the other hand, John Searle’s famous “Chinese Room” argument insists that this cannot be the case, and that consciousness is in all likelihood not artificially reproducible. However, both positions have issues—the …

Microservice Architecture For Social Media Data Collection, Analysis, And Dashboarding, Sai Ram Manohar Koya

Theses and Dissertations

This research presents a novel methodology for the collection, processing, and analysis of social media data using a microservices-based architecture. The proposed system integrates multiple data streams from various social media platforms, transforming this information into a unified, JSON-based DataObject model for seamless processing and analysis. Unlike monolithic architectures, the microservices approach offers scalability and flexibility, allowing the system to handle the high velocity, variety, and volume of unstructured social media data, including text, images, and videos. By leveraging NoSQL databases like MongoDB, the methodology efficiently manages data in a semi-structured format, supporting real-time analytics such as sentiment analysis, toxicity …

Exploration Of The Gap Between The Secure Web Application Development Competencies Needed By Industry And Those Competencies Provided By Graduates Of U.S. Undergraduate Software Engineering Programs, Gary Allen Harris

Theses and Dissertations

Literature demonstrates that threats and attacks on computer systems and networks have been around since the beginning of computing, and the number, severity, sophistication, and costs of attacks and data breaches are continuing to grow. Several studies suggest that one of the most common causes of data breaches is insecure web applications that contain vulnerable application code. These studies suggest that poor secure web application development practices are a prime cause of the susceptible web applications. Additionally, studies suggest that higher education is not meeting industry’s secure software/web application development needs. Employers have reported that they are not getting the …

Artificial Intelligence-Based Methodologies For Early Diagnostic Precision And Personalized Therapeutic Strategies In Neuro-Ophthalmic And Neurodegenerative Pathologies, Rahul Kumar, Ethan Waisberg, Joshua Ong, Phani Paladugu, Dylan Amiri, Jeremy Saintyl, Jahnavi Yelamanchi, Robert Nahouraii, Ram Jagadeesan, Alireza Tavakkoli

SKMC Student Presentations and Publications

Advancements in neuroimaging, particularly diffusion magnetic resonance imaging (MRI) techniques and molecular imaging with positron emission tomography (PET), have significantly enhanced the early detection of biomarkers in neurodegenerative and neuro-ophthalmic disorders. These include Alzheimer's disease, Parkinson's disease, multiple sclerosis, neuromyelitis optica, and myelin oligodendrocyte glycoprotein antibody disease. This review highlights the transformative role of advanced diffusion MRI techniques-Neurite Orientation Dispersion and Density Imaging and Diffusion Kurtosis Imaging-in identifying subtle microstructural changes in the brain and visual pathways that precede clinical symptoms. When integrated with artificial intelligence (AI) algorithms, these techniques achieve unprecedented diagnostic precision, facilitating early detection of neurodegeneration and …

Improving Clinical Information Extraction From Electronic Health Records: Leveraging Large Language Models And Evaluating Their Outputs, Kriti Bhattarai

McKelvey School of Engineering Graduate Student Theses & Dissertations

Accurate extraction of clinical entities and phenotypes from unstructured electronic health record (EHR) text is crucial for various clinical research tasks, including cohort identification, tracking temporal patterns in disease progression and deciding treatment course. However, this task remains challenging due to the complexity and ambiguity of medical language. This dissertation explores the application of advanced generative pre-trained transformer (GPT) models, such as GPT-4, GPT-3.5-turbo, Llama-3.1, Llama-3 and Flan-T5, for clinical entity and phenotype extraction from EHRs. Building upon these findings, this dissertation also investigates a hybrid approach where integration of external knowledge sources, such as Unified Medical Language System (UMLS) …

Enabling Per-File Data Recovery From Ransomware Attacks Via File System Forensics And Flash Translation Layer Data Extraction, Josh Dafoe, Niusen Chen, Bo Chen, Zhenlin Wang

Michigan Tech Publications

Ransomware attacks are increasingly prevalent in recent years. Crypto-ransomware corrupts files on an infected device and demands a ransom to recover them. In computing devices using flash memory storage (e.g., SSD, MicroSD, etc.), existing designs recover the compromised data by extracting the entire raw flash memory image, restoring the entire external storage to a good prior state. This is feasible through taking advantage of the out-of-place updates feature implemented in the flash translation layer (FTL). However, due to the lack of “file” semantics in the FTL, such a solution does not allow a fine-grained data recovery in terms of files. …