Computer Sciences Commons^™

Early Diagnosis And Detection Of Skin Cancer Using Deep Neural Network Models And Feature Extraction From Pre-Trained Cnns, Sahil Khanna

Harrisburg University Dissertations and Theses

Skin cancer is one of the most common and lethal cancer types. While accurate diagnosis at an early stage is essential for skin cancer treatment it remains difficult to achieve in many regions due to lack of sufficient dermatologists and proper diagnostic equipment. Prior studies show Convolutional Neural Network (CNN) models excel at skin lesion classification and consistently achieve better results than standard diagnostic practices. However, the focus of many studies remains confined to image-based learning while neglecting useful patient metadata that could improve prediction accuracy. This research project created a specialized CNN model to classify skin lesions and evaluated …

Advancing Academic Advising With Knowledge Graphs: Integrating Machine Learning And Llms For Personalized Course Planning, Sara Alshamsi

Thesis/ Dissertation Defenses

Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students' dependency on advisors while simultaneously providing accurate estimates of course demand …

A Comparative Study Of Neural Networks And Xgboost Models For Flight Time Prediction, Ioannis Paraschos, Taryn E. Trimble, Eshna Bhargava, Jake Klingler, Benjamin R. Nicolai

Beyond: Undergraduate Research Journal

Flight time prediction plays a crucial role in modern air travel, benefiting airlines and passengers alike. Accurate predictions enable airlines to optimize schedules, allocate resources effectively, and ensure passenger safety and satisfaction. In recent years, machine learning models, such as neural networks and XGBoost, have gained popularity for predicting flight times. This study aims to compare the performance of neural network and XGBoost models in predicting flight times, considering factors such as weather conditions, air traffic control, and aircraft performance. The results indicate that both models are effective, with XGBoost achieving slightly higher accuracy. However, neural networks offer advantages in …

A New Model For Educational Program Assessments Using Automated Collective Concept Maps, Andrew R. Paullin

Master's Theses (2009 -)

This paper presents: Epistemological principles; the origins and theoretical foundations of concept maps; the current state of related works; the contributions, methods, results, and future road map of this research; and A New Model for Educational Program Assessments. An understanding that knowledge results from an evolution of cognitive structures enables a scientific approach to enhance the efficiency of learning. Building on prior works, this research provides a novel algorithm and tool to automatically create Collective Concept Maps from Individual Concept Maps by utilizing a dictionary, thesaurus, Natural Language Processing, Machine Learning / Artificial Intelligence, and domain expertise. Abstraction Filters enable …

A Survey On Immersive Cyber Situational Awareness Systems, Hussain Ahmad, Faheem Ullah, Rehan Jafri

All Works

Cyber situational awareness systems are increasingly used for creating cyber common operating pictures for cybersecurity analysis and education. However, these systems face data occlusion and convolution issues due to the burgeoning complexity, dimensionality, and heterogeneity of cybersecurity data, which damages cyber situational awareness of end-users. Moreover, conventional forms of human–computer interactions, such as mouse and keyboard, increase the mental effort and cognitive load of cybersecurity practitioners when analyzing cyber situations of large-scale infrastructures. Therefore, immersive technologies, such as virtual reality, augmented reality, and mixed reality, are employed in the cybersecurity realm to create intuitive, engaging, and interactive cyber common operating …

Virtual Assistant For Pest Management, Viswanada Chakravarthy Karri

Master’s Dissertations

Effective pest identification and management are essential for ensuring agricultural productivity, especially in regions with limited expert access. This work proposes a virtual assistant based on a Retrieval-Augmented Generation (RAG) [1] framework to support pest management tasks. The system utilizes a multimodal dataset consisting of pest images and annotated textual interactions, adapted from the AgriLLaVA corpus [2]. The assistant combines retrieval mechanisms with generative language models to generate contextually grounded responses. It is designed for deployment on local hardware with limited computational resources, integrating open-source models for both retrieval and generation. Preliminary results suggest that this approach can provide accurate, …

2.5d Dual-Encoder U-Net For Lesion Segmentation In Chest Ct Scans, Jagannath Mukkara

Master’s Dissertations

Accurate segmentation of lesions in chest CT scans plays a vital role in diagnosing and monitoring pulmonary diseases such as COVID-19. In this, we introduce a novel 2.5D[1] dual-encoder U-Net model[2] that utilizes both the central slice and its neighboring slices to improve segmentation accuracy while keeping computational demands manageable. Our model incorporates residual connections[3] and feature fusion[4] to effectively merge multi-slice contextual information, overcoming the limitations found in traditional 2D and 3D methods. To ensure a reliable evaluation and avoid data leakage, we used patient-level data splitting. We validate our approach on a carefully curated chest CT dataset, showing …

Automated Grain-Matrix Segmentation In Photomicrographs Of Clastic Sedimentary Rocks Using Neuro-Visual Algorithms, Rajdeep Das

Doctoral Theses

Sediments and sedimentary rocks, covering almost sixty-five percent of exposed earth’s surface, contain features that allow us to interpret ancient depositional environments, and their role in the evolution of life on earth. Study of sedimentary rocks is also relevant to exploration of geo-economic resources including petroleum, ore minerals, and groundwater as well as research in environmental geology, anthropological studies, and the bi-directional relation of man and environment. One of the important and crucial steps in this study of the detrital sedimentary rocks like sandstone, is to know the size and shape of the grains/clasts (fragments of different minerals or rocks), …

Understanding Batch-Normalization In Deep Neural Networks, Pendyala Sai Srujan

Master’s Dissertations

Batch Normalization (BN) is a commonly used technique in various deep learning architectures for tasks such as image classification and object detection. It stabilizes and accelerates training by normalizing the activations of intermediate layers using mean and variance of the batch, allowing the use of higher learning rates and often improving generalization through implicit regularization. During inference, BN uses running estimates of batch statistics accumulated during training. However, if individual batches are not representative of the overall data distribution, these accumulated statistics may not accurately approximate the population statistics. This discrepancy can lead to a phenomenon known as **estimation shift**, …

A Study On Planar 2-Center Problem, Shince K. Baby

Master’s Dissertations

The Planar-k-Centre problem is an important problem in the class of Optimal Facility Location problems, where given n points in the planar, the objective is finding the smallest k congruent discs such that their union encompasses all points. This dissertation examines a variant of this problem in which the L1 metric is used to determine the distances rather than the standard Euclidean metric, which we call L1P2C and a closely related problem which we call Undirected k Square Coverage where there is no directional constraint for the k squares which contain the given set of points. We have found two …

Morphology Based Galaxy Classification, Ayan Mukherjee

Master’s Dissertations

Galaxy evolution is an area of vital importance in current research as it is believed to hold vital clues of the past as well as the future of the universe. The structure or morphology of a galaxy acts as an indicator of its stage of evolution and may also shed light on the course of its future evolution. The deployment of high-resolution telescopes like James Webb Telescope has made available large amount of high-resolution images, thereby, facilitating the deployment of high-performance Machine Learning and Deep Learning techniques. In the proposed work, two different methods have been assessed to achieve better …

Multi-Modal Large Language Model For Visual Question Answering On Medical Domain, Srimanta Singha

Master’s Dissertations

Artificial intelligence (AI) strategies such as Multimodal learning, which can integrate inputs of multiple modes, e.g., image and text, have shown significant promise in medical applications. In this dissertation, we present our related study of a Multimodal Large Language Model (MLLM) designed for Visual Question Answering (VQA) in the medical domain, based on both image and text input modalities to improve diagnostic reasoning and decision support. Our model processes medical images (e.g., chest Xrays, CT scans, and ultrasound images) along with clinical text to answer complex, domain-specific questions. We employ a cross-modal fusion mechanism to align visual features with textual …

The Critical Plastocapillary Number For A Newtonian Liquid Filament Embedded Into A Viscoplastic Fluid, Mohammad Tanver Hossain, Wonsik Eom, Arjun Shah, Andrew Lowe, Douglas Fudge, Sameh H. Tawfick, Randy Ewoldt

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

The yield stress of a viscoplastic material can stabilize an embedded fluid tunnel against capillarity-induced breakup, enabling remarkable technologies such as embedded 3D printing of intricate, freeform, and small components. However, there is persistent disagreement in the published literature between the observed minimum stable diameter, 𝑑min, and the theoretical plastocapillary length 𝑝𝑐 = 2𝛤∕𝜎𝑦, with interfacial tension 𝛤 and bath yield stress 𝜎𝑦, leading to a prior hypothesis that the apparent surface tension 𝛤 is much smaller to enforce 𝑑min = 𝑝𝑐 . Here we introduce and experimentally test a new hypothesis that the critical diameter is set by the …

Notes On The Invariance Of Tautness Under Lie Sphere Transformations, Thomas E. Cecil

Mathematics and Computer Science Department Faculty Scholarship

An embedding ϕ : V → Sⁿ of a compact, connected manifold V into the unit sphere Sⁿ ⊂ Rⁿ⁺¹ is said to be taut, if every nondegenerate spherical distance function d_p, p ∈ Sⁿ, is a perfect Morse function on V , i.e., it has the minimum number of critical points on V required by the Morse inequalities. In these notes, we give an exposition of the proof of the invariance of tautness under Lie sphere transformations due to ´Alvarez Paiva. First we extend the definition of tautness of submanifolds of S …

Multi-Level Differentiable Moving Particles With Partition Of Unity, Jinjin He

Dartmouth College Master’s Theses

Representing implicit geometry with intricate features has long been a challenge. Recent advances in Implicit Neural Representations (INRs) have shown great promise in applications such as 3D reconstruction, inverse rendering, and dynamic surface evolution. These methods leverage neural networks to model complex shapes continuously, offering advantages in resolution and flexibility over traditional discrete representations. Despite their success, efficiently handling fine geometric details and evolving dynamic scenes remains an open problem.

We introduce a differentiable moving particle representation based on the multi-level partition of unity (MPU) to model dynamic implicit geometries efficiently. Our approach employs two types of particles—feature particles and …

Virtual Reality’S Impact On Tourist Attitudes In Islamic Religious Tourism: Exploring Emotional Attachment And Vr Presence, Eman Alkhalifah, Ramy Hammady, Mahmoud Abdelrahman, Alyaa Darwish, Ella Cranmer, Ons Al-Shamaileh, Aikaterini Bourazeri, Timothy Jung

All Works

This study explores the integration of immersive technologies, specifically virtual reality (VR), to enhance tourist experiences in the rapidly expanding religious tourism sector. Despite VR’s potential, limited research has examined its impact on religious tourism. This study addresses this gap by investigating the role of emotional attachment in influencing VR presence during pre-, on-site, and postexperiences of VR-mediated religious tourism. A quantitative survey was conducted with 201 respondents who participated in VR religious tourism activities. The empirical analysis, conducted using SPSS and AMOS structural equation modeling (SEM), assessed how VR-mediated religious tourism impacts VR presence and tourist attitudes before actual …

Teamwork And Artificial Intelligence (Ai) : Examining The Effects Of Teammate Identity, Deception, And Ai Literacy On Team Dynamics And Performance In Human-Human Vs. Human-Ai Teams, Jenna Korentsides

Doctoral Dissertations and Master's Theses

As artificial intelligence (AI) continues to be integrated into collaborative work environments, understanding how humans interact with AI teammates is increasingly important. This study examined how people’s beliefs about who they are working with (whether a teammate is human or AI) can influence teamwork outcomes. Specifically, we explored how perceived teammate identity affects task performance and team experience, with a focus on trust and communication as potential mediators, and AI literacy (familiarity and comfort with AI) as a moderator. Participants completed a series of timed, collaborative problem-solving tasks using a bomb defusal simulation. Each participant worked with both a human …

Tellings Of The Pacific Ocean: A Landscape-Based Approach For Multispecies Design And Hci, Maliheh Ghajargar

Engineering Faculty Articles and Research

Environmental disturbances induced by climate change have caused significant changes in our ecosystems and are threatening the health of our environments. As a response to this issue, a growing body of work has emerged in HCI and design, which seeks to foreground more-than-human stories in support of making more sustainable and just futures. This research contributes to this broad agenda by probing graphic novels as a multispecies storytelling method for design and HCI. Combining ideas from Anna Tsing’s adventures of landscape and from HCI and design’s use of sequential art (e.g., storyboards), we use landscape as the main protagonist of …

Forecasting Influenza Rates Using Machine Learning: A Study Of Chatgpt's Predictive Accuracy, Sara Saleh

University Honors Theses

This study evaluates ChatGPT's ability to forecast influenza rates, such as the number of flu cases, hospitalizations, and death during peak season periods using CDC data, and comparing forecasts against actual results to calculate statistical accuracy and consistency. Influenza forecasting is essential for public health planning, but traditional methods may not always provide timely or accurate predictions. In this research study, ChatGPT was utilized to predict the influenza rates for the following week based on the previous week's data obtained from the FluView surveillance system. The predicted rates were compared to the actual influenza rates to assess the model's overall …

A Framework For Scalable And Controlled Hallucination Data Collection, Lin Ting Liang

Computer Science Senior Theses

This thesis addresses a key bottleneck in hallucination research: the scarcity and limitations of hallucination benchmark datasets. Existing datasets typically focus on a single type of hallucination and are expensive to produce due to the need for manual prompt creation and annotation. To overcome these challenges, we propose a novel mixture-of-experts (MoE) adversarial framework that actively induces hallucinations. Our framework employs three large language model (LLM) agents that iteratively and adversarially revise prompts to provoke hallucinated responses from a target question-answering model. It automates the generation of both intrinsic hallucinations (logical inconsistencies) and extrinsic hallucinations (inclusion of unverifiable external information). …

K-Mshc: Unmasking Minimally Sufficient Head Circuits In Large Language Models With Experiments On Syntactic Classification Tasks, Pratim Chowdhary, Peter Chin, Deepernab Chakrabarty

Computer Science Senior Theses

Understanding which neural components drive specific capabilities in mid-sized language models ($\leq$10B parameters) remains a key challenge. We introduce the $(\bm{K}, \epsilon)$-Minimum Sufficient Head Circuit ($K$-MSHC), a methodology to identify minimal sets of attention heads crucial for classification tasks as well as Search-K-MSHC, an efficient algorithm for discovering these circuits. Applying our Search-K-MSHC algorithm to Gemma-9B, we analyze three syntactic task families: grammar acceptability, arithmetic verification, and arithmetic word problems. Our findings reveal distinct task-specific head circuits, with grammar tasks predominantly utilizing early layers, word problems showing pronounced activity in both shallow and deep regions, and arithmetic verification demonstrating a …

Evaluating Vision Language Model Capabilities For Time Series Interpretation: An Empirical Study With Conversation Duration And Psychological Flourishing Data From The Studentlife Dataset, Jusung Park

Computer Science Senior Theses

This research investigates the capability of Vision Language Models (VLMs), specifically ChatGPT‑4o, to interpret and predict psychological outcomes based on visual representations of time series data. Leveraging conversation duration metrics and psychological flourishing scores from the StudentLife dataset, this study rigorously evaluates the predictive accuracy of VLMs using various methods, including zero‑shot on raw data, zero‑shot on graph data, few‑shot learning, qualitative labeling, and chain‑of‑thought reasoning. Despite multiple methodological enhancements, predictive performance remains modest, revealing significant challenges in quantitative interpretation of visualized temporal data by current multimodal models. We demonstrate that standardizing input tokens by using graph images rather than …

A Steiner Tree Vc Set System In Minor-Free (Di)Graphs, Eli Friedman

Computer Science Senior Theses

We propose a set system of maximum-covering minimum-density partial Steiner trees for planar and minor-free graphs. We show that this system has VC dimension at most h-1 for edge-weighted K_h-minor-free graphs, both directed and undirected. We also consider its geometric interpretation as a range space, proving it to be piercing.

In addition, we demonstrate how one can form a junction tree set system of bounded VC dimension from such Steiner trees. This is motivated by refining the junction tree set cover approach used in Chekuri and Jain's polylogarithmic approximation algorithm for Directed Steiner Forest in planar graphs [CJ25].

Character Relationship Prediction In Movies: Toward Emotionally-Aware Automatic Audio Descriptions, Seung Hyun Hahm

Computer Science Senior Theses

Automatic audio description (AD) systems support visually impaired audiences by narrating visual content, but they often fail to capture the interpersonal dynamics that underpin narrative understanding. In this work, we introduce a novel framework for character relationship prediction as a means of enriching audio descriptions with socially grounded context. Our contributions are threefold: (1) we propose the Character Relationship Module (CRM), which extends identity-aware video captioning with directed sentiment inference between character pairs; (2) we develop a scalable weak supervision pipeline that uses large language models to generate 669,520 relationship annotations across 202 films; and (3) we construct a complementary …

Bayesian Segmentation–Driven Informative Path Planning For Uav-Based Water Orthomosaic Generation, Phuc Dai Tran

Computer Science Senior Theses

This paper presents a comprehensive implementation

study of an informative path planning (IPP) algorithm

for autonomous water body detection and mapping using

unmanned aerial vehicles (UAVs). We propose a hybrid IPP

framework that seamlessly integrates Bayesian probabilistic

classification and real-time uncertainty quantification to achieve

superior flight efficiency and mapping accuracy compared

to conventional systematic coverage methods. Our approach

employs the state-of-the-art SegFormer deep learning segmentation

model in conjunction with log-odds-based orthomosaic

generation to produce high-fidelity water body maps under

diverse environmental conditions. Through random sampling of

the FloodNet dataset, we demonstrate that our IPP algorithm

maintains flight distance while achieving …

A First Look Into Parental Strategies, And Challenges Around Children’S Device Usage In Urban Nepal, Rizu Paudel, Prakriti Dumaru, Ankit Shrestha, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

There have been substantial changes in the landscape of technology use by children in Global South during COVID-19, when the shift to online learning platforms necessitated parents to avail personal devices (e.g., smartphones, computers) for their children to fulfill their educational needs. However, the use of devices by children are not limited to serving educational purpose only. Our study positions itself in a critical post-pandemic period in Nepal, characterized by the increase in device use by children, while a little study to date, investigated parental mediation in this developing country. To this end, we conducted semi-structured interviews with 20 parents, …

Motionteller: Multi-Modal Integration Of Wearable Time-Series With Llms For Health And Behavioral Understanding, Aiwei Zhang, Arvind Pillai, Andrew Campbell, Nicholas C. Jacobson

Computer Science Senior Theses

As wearable sensing becomes increasingly pervasive, a key challenge remains: how can we generate natural language summaries from raw physiological signals such as actigraphy - minute-level movement data collected via accelerometers? In this work, we introduce MotionTeller, a generative framework that natively integrates minute-level wearable activity data with large language models (LLMs). MotionTeller combines a pretrained actigraphy encoder with a lightweight projection module that maps behavioral embeddings into the token space of a frozen decoder-only LLM, enabling free-text, autoregressive generation of daily behavioral summaries.

We construct a novel dataset of 54,383 ⟨actigraphy, text⟩ pairs derived from real-world NHANES recordings, and …

An Efficient Algorithm For Finding High Harmonic Centrality Vertices In Graphs, John Balson

Computer Science Senior Theses

In this thesis we consider the problem of harmonic centrality in graphs. This measure is used widely in the study of real-world complex networks. In particular, we consider the problem of finding a high harmonic centrality vertex in time much faster than $O(mn)$, the time required to calculate the exact harmonic centrality of all vertices in a graph. The problem of calculating centrality measures faster has received much attention in recent years, since calculating the exact harmonic centrality of all vertices can be infeasible for large graphs; hence, faster algorithms are needed. This thesis proposes a new algorithm for finding …

An Approach To Stylometry Using Causal Language Models, Harrison F. Stropkay

Computer Science Senior Theses

We present a novel stylometric approach using large language models. By training separate models on individual authors' works, we find that each model achieves lower cross-entropy loss when predicting text from its training author compared to other authors' texts. Moreover, for any given text, the model trained on its true author’s corpus yields the lowest loss. We suggest that, in this way, a model trained on one author's works embodies the unique writing style of that author. We demonstrate our approach on works by eight known authors. This approach also confirms that R. P. Thompson wrote the well-studied 15th book …

Enhancing Iot Decentralization With Iota 2.0: A Dag-Based Fast Probabilistic Consensus Framework, Ayat N. Kadhum, Ahmed M. Al-Salih

Journal of Intelligent Informatics, Networking, and Cybersecurity

The integration of IoT and blockchain enhances security, trust, and data integrity but is hindered by security attacks, scalability, and high latency. In this work, a more efficient method of consensus using Directed Acyclic Graph (DAG)-based Fast Probabilistic Consensus (FPC) and Edwards-Curve Digital Signature Algorithm (EdDSA) is proposed to yield better security, efficiency, and decentralization. By eliminating mining, resource use is optimized, and consensus is hastened. Experimental results show a high throughput of 7228.05 Transactions Per Second (TPS), rapid consensus formation in just 7.62 rounds on average, and high adversary resilience, with the system successfully mitigating 89% of adversarial attacks. …