Engineering Commons^™

A Smart Hybrid Enhanced Recommendation And Personalization Algorithm Using Machine Learning, Aswin Kumar Nalluri

Electronic Theses, Projects, and Dissertations

In today’s age of streaming services, the effectiveness and precision of recommendation systems are crucial in improving user satisfaction. This project introduces the Smart Hybrid Enhanced Recommendation and Personalization Algorithm (SHERPA) a cutting-edge machine learning approach aimed at transforming how movie suggestions are made. By combining Term Frequency Inverse Document Frequency (TF-IDF) for content based filtering and Alternating Squares (ALS) with Weighted Regularization for filtering SHERPA offers a sophisticated method for delivering tailored recommendations.

The algorithm underwent evaluation using a dataset that included over 50 million ratings from 480,000 Netflix users encompassing 17,000 movie titles. The performance of SHERPA was …

Side Channel Detection Of Pc Rootkits Using Nonlinear Phase Space, Rebecca Clark

Undergraduate Honors Theses

Cyberattacks are increasing in size and scope yearly, and the most effective and common means of attack is through malicious software executed on target devices of interest. Malware threats vary widely in terms of behavior and impact and, thus, effective methods of detection are constantly being sought from the academic research community to offset both volume and complexity. Rootkits are malware that represent a highly feared threat because they can change operating system integrity and alter otherwise normally functioning software. Although normal methods of detection that are based on signatures of known malware code are the standard line of defense, …

Enhancing Cyber Resilience: Development, Challenges, And Strategic Insights In Cyber Security Report Websites Using Artificial Inteligence, Pooja Sharma

Harrisburg University Dissertations and Theses

In an era marked by relentless cyber threats, the imperative of robust cyber security measures cannot be overstated. This thesis embarks on an in-depth exploration of the historical trajectory and contemporary relevance of penetration testing methodologies, elucidating their evolution from nascent origins to indispensable tools in the cyber security arsenal. Moreover, it undertakes the ambitious task of conceptualizing and implementing a cyber security report website, meticulously designed to fortify cyber resilience in the face of ever-evolving threats in the digital realm.

The research journey commences with an insightful examination of the historical antecedents of penetration testing, tracing its genesis in …

The Role Of Attention Mechanisms In Enhancing Transparency And Interpretability Of Neural Network Models In Explainable Ai, Bhargav Kotipalli

Harrisburg University Dissertations and Theses

In the rapidly evolving field of artificial intelligence (AI), deep learning models' interpretability

and reliability are severely hindered by their complexity and opacity. Enhancing the

transparency and interpretability of AI systems for humans is the primary objective of the

emerging field of explainable AI (XAI). The attention mechanisms at the heart of XAI's work

are based on human cognitive processes. Neural networks can now dynamically focus on

relevant parts of the input data thanks to these mechanisms, which enhances interpretability

and performance. This report covers in-depth talks of attention mechanisms in neural networks

within XAI, as well as an analysis …

Decoding The Future: Integration Of Artificial Intelligence In Web Development, Dhiraj Choithramani

Harrisburg University Dissertations and Theses

The thesis explores AI's profound impact on web development, particularly in front-end and back-end processes. AI revolutionizes UI prototyping by automating design creation, enhancing both efficiency and aesthetics. It also aids in code review, content generation, and process flow experimentation, streamlining development workflows. Through AI-driven tools like GitHub's Copilot and Wix ADI, developers benefit from coding assistance and innovative design capabilities. Despite some challenges, AI's evolving role promises to reshape web development, offering unprecedented efficiency and user-centric solutions.

Enhancing Mobile App User Experience: A Deep Learning Approach For System Design And Optimization, Deepesh Haryani

Harrisburg University Dissertations and Theses

This paper presents a comprehensive framework for enhancing user experience in mobile applications through the integration of deep learning systems. The proposed system design encompasses various components, including data collection and preprocessing, model development and training, integration with mobile applications, dataset management service, model training service, model serving, hyperparameter optimization, metadata and artifact store, and workflow orchestration. Each component is meticulously designed with a focus on scalability, efficiency, isolation, and critical analysis. Innovative design principles are employed to ensure seamless integration, usability, and automation. Additionally, the paper discusses distributed training service design, advanced optimization techniques, and decision criteria for hyperparameter …

Cyber Attacks Against Industrial Control Systems, Adam Kardorff

LSU Master's Theses

Industrial Control Systems (ICS) are the foundation of our critical infrastructure, and allow for the manufacturing of the products we need. These systems monitor and control power plants, water treatment plants, manufacturing plants, and much more. The security of these systems is crucial to our everyday lives and to the safety of those working with ICS. In this thesis we examined how an attacker can take control of these systems using a power plant simulator in the Applied Cybersecurity Lab at LSU. Running experiments on a live environment can be costly and dangerous, so using a simulated environment is the …

Enhancing Information Architecture With Machine Learning For Digital Media Platforms, Taylor N. Mietzner

Honors College Theses

Modern advancements in machine learning are transforming the technological landscape, including information architecture within user experience design. With the unparalleled amount of user data generated on online media platforms and applications, an adjustment in the design process to incorporate machine learning for categorizing the influx of semantic data while maintaining a user-centric structure is essential. Machine learning tools, such as the classification and recommendation system, need to be incorporated into the design for user experience and marketing success. There is a current gap between incorporating the backend modeling algorithms and the frontend information architecture system design together. The aim of …

Protecting Return Address Integrity For Risc-V Via Pointer Authentication, Yuhe Zhao

Masters Theses

Embedded systems based on lightweight microprocessors are becoming more prevalent in various applications. However, the security of them remains a significant challenge due to the limited resources and exposure to external threats. Especially, some of these devices store sensitive data and control critical devices, making them high-value targets for attackers. Software security is particularly important because attackers can easily access these devices on the internet and obtain control of them by injecting malware.

Return address (RA) hijacking is a common software attack technique used to compromise control flow integrity (CFI) by manipulating memory, such as return-to-libc attacks. Several methods have …

Blockchain Design For A Secure Pharmaceutical Supply Chain, Zhe Xu

Masters Theses

In the realm of pharmaceuticals, particularly during the challenging times of the COVID-19 pandemic, the supply chain for drugs has faced significant strains. The increased demand for vaccines and therapeutics has revealed critical weaknesses in the current drug supply chain management systems. If not addressed, these challenges could lead to severe societal impacts, including the rise of counterfeit medications and diminishing trust in government authorities.

The study identified that more than the current strategies, such as the Drug Supply Chain Security Act (DSCSA) in the U.S., which focuses on unique authentication and traceability codes for prescription drugs, is needed to …

Extracting Dnn Architectures Via Runtime Profiling On Mobile Gpus, Dong Hyub Kim

Masters Theses

Due to significant investment, research, and development efforts over the past decade, deep neural networks (DNNs) have achieved notable advancements in classification and regression domains. As a result, DNNs are considered valuable intellectual property for artificial intelligence providers. Prior work has demonstrated highly effective model extraction attacks which steal a DNN, dismantling the provider’s business model and paving the way for unethical or malicious activities, such as misuse of personal data, safety risks in critical systems, or spreading misinformation. This thesis explores the feasibility of model extraction attacks on mobile devices using aggregated runtime profiles as a side-channel to leak …

An Efficient Privacy-Preserving Framework For Video Analytics, Tian Zhou

Doctoral Dissertations

With the proliferation of video content from surveillance cameras, social media, and live streaming services, the need for efficient video analytics has grown immensely. In recent years, machine learning based computer vision algorithms have shown great success in various video analytic tasks. Specifically, neural network models have dominated in visual tasks such as image and video classification, object recognition, object detection, and object tracking. However, compared with classic computer vision algorithms, machine learning based methods are usually much more compute-intensive. Powerful servers are required by many state-of-the-art machine learning models. With the development of cloud computing infrastructures, people are able …

Insights Into Cellular Evolution: Temporal Deep Learning Models And Analysis For Cell Image Classification, Xinran Zhao

Master's Theses

Understanding the temporal evolution of cells poses a significant challenge in developmental biology. This study embarks on a comparative analysis of various machine-learning techniques to classify cell colony images across different timestamps, thereby aiming to capture dynamic transitions of cellular states. By performing Transfer Learning with state-of-the-art classification networks, we achieve high accuracy in categorizing single-timestamp images. Furthermore, this research introduces the integration of temporal models, notably LSTM (Long Short Term Memory Network), R-Transformer (Recurrent Neural Network enhanced Transformer) and ViViT (Video Vision Transformer), to undertake this classification task to verify the effectiveness of incorporating temporal features into the classification …

The Development And Testing Of A Gyroscope-Based Neck Strengthening Rehabilitation Device, Nicole D. Devos

Electronic Thesis and Dissertation Repository

Neck pain can be debilitating, and is experienced by the majority of people at some point over the course of their life. Resistance training has been shown to have significant improvement in pain or disability for patients. There are few options available for telerehabilitation, and the use of gyroscope stabilizers is proposed for this use. A biomechanics model of a head--neck--gyroscope system was created. In order to also model the dynamics of such a system, this work proposes a blended method using the Denavit--Hartenberg (DH) convention, popular in the field of robotics, with the Lagrangian mechanics approach to analyze an …

Attribution Robustness Of Neural Networks, Sunanda Gamage

Electronic Thesis and Dissertation Repository

While deep neural networks have demonstrated excellent learning capabilities, explainability of model predictions remains a challenge due to their black box nature. Attributions or feature significance methods are tools for explaining model predictions, facilitating model debugging, human-machine collaborative decision making, and establishing trust and compliance in critical applications. Recent work has shown that attributions of neural networks can be distorted by imperceptible adversarial input perturbations, which makes attributions unreliable as an explainability method. This thesis addresses the research problem of attribution robustness of neural networks and introduces novel techniques that enable robust training at scale.

Firstly, a novel generic framework …

Understanding Quadrature Modulation By Designing A 7mhz Iq Test Bench To Encode The Polybius Square, William Lee Bradley

Dissertations and Theses

This thesis outlines the design of an IQ Test Bench that allows for experimentation of quadrature modulation techniques. Quadrature modulation utilizes two signals I and Q, 90° out of phase from each other, to greatly increase communication data rates. Using Desmos, a thorough mathematical analysis of waveform mixing is presented, and constellation diagrams are plotted from the results. From this an ancient fire signaling technique known as the Polybius Square is encoded into the system. The IQ Test Bench is built from fundamental components that would be contained within an RFFE: a local oscillator and two frequency mixers. The LO …

Fair Fault-Tolerant Approach For Access Point Failures In Networked Control System Greenhouses, Mohammed Ali Yaslam Ba Humaish

Theses and Dissertations

Greenhouse Networked Control Systems (NCS) are popular applications in modern agriculture due to their ability to monitor and control various environmental factors that can affect crop growth and quality. However, designing and operating a greenhouse in the context of NCS could be challenging due to the need for highly available and cost-efficient systems. This thesis presents a design methodology for greenhouse NCS that addresses these challenges, offering a framework to optimize crop productivity, minimize costs, and improve system availability and reliability. It contributes several innovations to the field of greenhouse NCS design. For example, it recommends using the 2.4GHz frequency …

Multi-Perspective Analysis For Derivative Financial Product Prediction With Stacked Recurrent Neural Networks, Natural Language Processing And Large Language Model, Ethan Lo

Dissertations, Theses, and Capstone Projects

This study developed a multi-perspective, AI-powered model for predicting E-Mini S&P 500 Index Futures prices, tackling the challenging market dynamics of these derivative financial instruments. Leveraging FinBERT for analysis of Wall Street Journal data alongside technical indicators, trader positioning, and economic factors, my stacked recurrent neural network built with LSTMs and GRUs achieves significantly improved accuracy compared to single sub-models. Furthermore, ChatGPT generation of human-readable analysis reports demonstrates the feasibility of using large language models in financial analysis. This research pioneers the use of stacked RNNs and LLMs for multi-perspective financial analysis, offering a novel blueprint for automated prediction and …

Unmanned Aerial Systems (Uas) Traffic Density Prediction And Multi-Agent Task Allocation, Chen Luo

Dissertations - ALL

In recent years, the field of Multi-Agent Systems (MAS) has garnered increasing attention. The essence of Multi-Agent Systems lies in orchestrating the coordination and collaboration of autonomous agents, endowing them with the ability to work collectively towards common goals. This characteristic makes MAS particularly germane in addressing the challenges posed by complex and dynamic environments, where theadaptability and decentralized decision-making of autonomous agents prove advantageous. To delve into the intricacies of MAS, three primary research directions have emerged. Firstly, we aim to develop a model rapidly and accurately to forecast future Unmanned Aerial Systems (UAS) traffic density patterns while simultaneously …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

Electronic Theses and Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Reinventing Integrated Photonic Devices And Circuits For High Performance Communication And Computing Applications, Venkata Sai Praneeth Karempudi

Theses and Dissertations--Electrical and Computer Engineering

The long-standing technological pillars for computing systems evolution, namely Moore's law and Von Neumann architecture, are breaking down under the pressure of meeting the capacity and energy efficiency demands of computing and communication architectures that are designed to process modern data-centric applications related to Artificial Intelligence (AI), Big Data, and Internet-of-Things (IoT). In response, both industry and academia have turned to 'more-than-Moore' technologies for realizing hardware architectures for communication and computing. Fortunately, Silicon Photonics (SiPh) has emerged as one highly promising ‘more-than-Moore’ technology. Recent progress has enabled SiPh-based interconnects to outperform traditional electrical interconnects, offering advantages like high bandwidth density, …

Gen-Acceleration: Pioneering Work For Hardware Accelerator Generation Using Large Language Models, Durga Lakshmi Venkata Deepak Vungarala

Theses

Optimizing computational power is critical in the age of data-intensive applications and Artificial Intelligence (AI)/Machine Learning (ML). While facing challenging bottlenecks, conventional Von-Neumann architecture with implementing such huge tasks looks seemingly impossible. Hardware Accelerators are critical in efficiently deploying these technologies and have been vastly explored in edge devices. This study explores a state-of-the-art hardware accelerator; Gemmini is studied; we leveraged the open-sourced tool. Furthermore, we developed a Hardware Accelerator in the study we compared with the Non-Von-Neumann architecture. Gemmini is renowned for efficient matrix multiplication, but configuring it for specific tasks requires manual effort and expertise. We propose implementing …

Control Of Fully-Actuated Aerial Manipulators And Omni-Directional Multirotors, Riley M. Mccarthy

Mechanical Engineering ETDs

This thesis details the system modeling, design, control, simulation, construction, and
testing of both a fully-actuated and omni-directional multirotor aerial system created
for the primary purpose of performing active tasks with their environment. This work
verifies the capabilities of both systems through empirical testing, and demonstrates
how through the use of new control methods and physical designs multirotors can
expand their purpose from passive inspection based tasks to active contact based
tasks. These systems take advantage of newly implemented control allocation features present in the PX4 flight control software, version 1.14. The use of which makes designing controllers for such …

Promise And Limitations Of Supervised Optimal Transport-Based Graph Summarization Via Information Theoretic Measures, Sepideh Neshatfar

Electronic Theses and Dissertations

Graph summarization is a fundamental problem in the field of data analysis, aiming to distill extensive graph datasets into more manageable, yet informative representations. The challenge lies in creating compressed graphs that faithfully retain crucial structural information for downstream tasks. A recent advancement in this domain introduces an optimal transport-based framework that enables the incorporation of a priori knowledge regarding the importance of nodes, edges, and attributes during the graph summarization process. However, the statistical properties of this innovative framework remain largely unexplored. This master's thesis embarks on a comprehensive exploration of the field of graph summarization, with a particular …

Chronic Kidney Disease Android Application, Paul Le

Computer Science and Engineering Senior Theses

Chronic kidney disease is increasingly recognized as a leading public health problem over the world that affects more than 10 percent of the population worldwide, where electrolytes and wastes can build up in your system. Kidney failure might not be noticeable until more advanced stages where it may then become fatal if not for artificial filtering or a transplant. As a result, it is important to detect kidney disease early on to prevent it from progressing to kidney failure. The current main test of the disease is a blood test that measures the levels of a waste product called creatine …

Brain-Inspired Spatio-Temporal Learning With Application To Robotics, Thiago André Ferreira Medeiros

USF Tampa Graduate Theses and Dissertations

The human brain still has many mysteries and one of them is how it encodes information. The following study intends to unravel at least one such mechanism. For this it will be demonstrated how a set of specialized neurons may use spatial and temporal information to encode information. These neurons, called Place Cells, become active when the animal enters a place in the environment, allowing it to build a cognitive map of the environment. In a recent paper by Scleidorovich et al. in 2022, it was demonstrated that it was possible to differentiate between two sequences of activations of a …

Convolution And Autoencoders Applied To Nonlinear Differential Equations, Noah Borquaye

Electronic Theses and Dissertations

Autoencoders, a type of artificial neural network, have gained recognition by researchers in various fields, especially machine learning due to their vast applications in data representations from inputs. Recently researchers have explored the possibility to extend the application of autoencoders to solve nonlinear differential equations. Algorithms and methods employed in an autoencoder framework include sparse identification of nonlinear dynamics (SINDy), dynamic mode decomposition (DMD), Koopman operator theory and singular value decomposition (SVD). These approaches use matrix multiplication to represent linear transformation. However, machine learning algorithms often use convolution to represent linear transformations. In our work, we modify these approaches to …

Docai, Riley Badnin, Justin Brunings

Computer Science and Software Engineering

DocAI presents a user-friendly platform for recording, transcribing, summarizing, and classifying doctor-patient consultations. The application utilizes AssemblyAI for conversational transcription, and the user interface allows users to either live-record consultations or upload an existing MP3 file. The classification process, powered by 'ml-classify-text,' organizes the consultation transcription into SOAP (Subjective, Objective, Assessment, and Plan) format – a widely used method of documentation for healthcare providers. The result of this development is a simple yet effective interface that effectively plays the role of a medical scribe. However, the application is still facing challenges of inconsistent summarization from the AssemblyAI backend. Future work …

Enhancing Accident Investigation Using Traffic Cctv Footage, Aksharapriya Peddi

Electronic Theses, Projects, and Dissertations

This Culminating Experience Project investigated how the densenet-161 model will perform on accident severity prediction compared to proposed methods. The research questions are: (Q1) What is the impact of usage of augmentation techniques on imbalanced datasets? (Q2) How will the hyper parameter tuning affect the model performance? (Q3) How effective is the proposed model compared to existing work? The findings are: Q1. The effectiveness of our model depends on the implementation of augmentation techniques that pay attention to handling imbalanced datasets. Our dataset poses a challenge due to distribution of classes in terms of accident severity. To address this challenge …

Remote Side-Channel Disassembly On Field-Programmable Gate Arrays, Brandon R. Baggett

<strong> Theses and Dissertations </strong>

Over the last two decades, side-channel vulnerabilities have shown to be a major threat to embedded devices. Most side-channel research has developed our understanding of the vulnerabilities to cryptographic devices due to their implementation and how we can protect them. However, side-channel leakage can yield useful information about many other processes that run on the device. One promising area that has received little attention is the side-channel leakage due to the execution of assembly instructions. There has been some work in this area that has demonstrated the idea’s potential, but so far, this research has assumed the adversary has physical …