Digital Commons Network^™

Analysing An Imbalanced Stroke Prediction Dataset Using Machine Learning Techniques, Viswapriya Subramaniyam Elangovan, Rajeswari Devarajan, Osamah I. Khalaf, Mhd Saeed Sharif, Wael Elmedany

Karbala International Journal of Modern Science

A stroke is a medical condition characterized by the rupture of blood vessels within the brain which can lead to brain damage. various symptoms may be exhibited when the brain's supply of blood and essential nutrients is disrupted. To forecast the possibility of brain stroke occurring at an early stage using Machine Learning and Deep Learning is the main objective of this study. Timely detection of the various warning signs of a stroke can significantly reduce its severity. This paper performed a comprehensive analysis of features to enhance stroke prediction effectiveness. A reliable dataset for stroke prediction is taken from …

Extraction Of Morphometric Features The Shape Of Mangrove Leaves Based On Digital Images And Classification Using The Support Vector Machine, Ishak Ariawan, Della Ayu Lestari, Luthfi Anzani, Tri Yanti, Cakra Rahardjo, M. Saleh, Sahril Angga Permana, Dea Aisyah Rusmawati

Karbala International Journal of Modern Science

At present, several botanists still rely on the use of manual estimating methods to assess the carbon content in mangrove. However, these methods have been reported to be extremely time-consuming, showing the need to develop a system for prediction. An effective solution lies in the creation of an artificial intelligence application, which can provide rapid and cost-effective results. In constructing this application, careful consideration must be given to the selection of parameters or attributes. Species is an essential parameter for the assessment of carbon content, but its determination has proven to be challenging due to the similarities of mangrove. The …

Helping The Home Cook: How Unsupervised Machine Learning Can Prevent Food Waste, Ryan B. Watson

Honors Projects

A common problem for the home cook is having too much of one food ingredient leftover, then not knowing what to do with it. To alleviate this problem, I propose using an unsupervised machine learning model to recommend recipes based on what ingredients the home cook wants to use. This model is built with FastText and trained on the recipe ingredients in the RecipeNLG dataset. Recipes are recommended based on which recipe ingredient set is most similar to the recipe ingredients provided in the user input. This solution will reduce consumer food waste by giving the home cook the information …

Re-Instatement Of Pell Grants For Incarcerated Students: Implications For Cs Education, E. Hogan, D. J. Mir, A. Cencini, Keith O'Hara, A. G. S. Raj, W. G. Griswold, L. Porter

Computer Science Faculty Works

The US incarcerates more people, and at a higher rate, than any other country in the world—predominantly low-income people of color. Higher education in prison (HEP) has a powerful impact on justice-impacted people, improving their quality of life during incarceration and reducing their likelihood of returning to prison post-release. HEP nearly disappeared in 1994 after Pell Grant eligibility was eliminated for incarcerated students, which was recently reinstated. More computing educators can reach incarcerated students with digital literacy skills, core computing content, and critical analyses of the impacts of computing on society. CS education researchers can also support the growth of …

High-Dimensional Data Analysis Using Parameter Free Algorithm Data Point Positioning Analysis, S. M. F. D. Syed Mustapha

All Works

Clustering is an effective statistical data analysis technique; it has several applications, including data mining, pattern recognition, image analysis, bioinformatics, and machine learning. Clustering helps to partition data into groups of objects with distinct characteristics. Most of the methods for clustering use manually selected parameters to find the clusters from the dataset. Consequently, it can be very challenging and time-consuming to extract the optimal parameters for clustering a dataset. Moreover, some clustering methods are inadequate for locating clusters in high-dimensional data. To address these concerns systematically, this paper introduces a novel selection-free clustering technique named data point positioning analysis (DPPA). …

An Innovative Approach On Yao’S Three-Way Decision Model Using Intuitionistic Fuzzy Sets For Medical Diagnosis, Wajid Ali, Tanzeela Shaheen, Iftikhar Ul Haq, Florentin Smarandache, Hamza Ghazanfar Toor, Faiza Asif

Neutrosophic Systems with Applications

In the realm of medical diagnosis, intuitionistic fuzzy data serves as a valuable tool for representing information that is uncertain and imprecise. Nevertheless, decision-making based on this kind of knowledge can be quite challenging due to the inherent vagueness of the data. To address this issue, we employ power aggregation operators, which prove effective in combining several sources of data, such as expert thoughts and patient information. This allows for a more correct diagnosis; a particularly crucial aspect of medical practice where precise and timely diagnoses can significantly impact medication policy and patient results. In our research, we introduce a …

A Graph Neural Network Visual Slam Algorithm For Large-Angle View Motion, Jinhui Liu, Mengyuan Chen, Pengpeng Han, Hebao Chen, Yukun Zhang

Journal of System Simulation

Abstract: Aimed at the difficulty of feature point extraction in mobile robots with drastic changes in illumination or sparse texture scenes under large-angle view motion, difficulty in matching features at extreme angles leads to large errors in Epipolar Geometry calculations, a fusion of an improved graph neural network based visual SLAM algorithm (GNN-SLAM) is proposed. The priori location estimation feature extraction network is proposed to achieve fast and uniform detection and description of image feature points by a priori location estimation and to construct real and accurate feature point information. The graph attention mechanism feature matching network is proposed to …

Implementation And Numerical Simulation On Object-Oriented Elastic-Plastic Finite Element Method Based On Python, Henghui Li, Yingxiong Xiao

Journal of System Simulation

Abstract: With the continuous expansion of the application fields of finite element methods, higher requirements are put forward for the scalability of finite element methods. In order to overcome the defects of the traditional finite element methods, a simple and easily extensible object-oriented elasticplastic finite element program framework is proposed based on Python. Combined with the characteristics of Python, we design some finite element classes such as the pre-processing class, the post-processing class, the linear solution class, the stress integration class and the analysis class. By applying the resulting framework to several typical elastic-plastic mechanical problems and comparing the results …

Image Self-Enhancement De-Hazing Algorithm Combined With Generative Adversarial Network, Wanjun Liu, Yuqian Cheng, Haicheng Qu

Journal of System Simulation

Abstract: To solve the problem that existing dehazing models are prone to over fitting after training with synthetic hazy image data sets, an image self-enhancement dehazing algorithm is proposed in combination with generative adversarial network. The depth information of an image is estimated while combining two Generative Adversarial Networks. The first GAN uses a clear image to learn the process of image hazing, and then adopts the hazed image generated by it as the input of the second GAN to guide the second GAN to correct dehazing. In order to reduce the difference before and after image processing, the consistency …

An Innovative Approach On Yao’S Three-Way Decision Model Using Intuitionistic Fuzzy Sets For Medical Diagnosis, Wajid Ali, Tanzeela Shaheen, Iftikhar Ul Haq, Florentin Smarandache, Hamza Ghazanfar Toor, Faiza Asif

Neutrosophic Systems with Applications

In the realm of medical diagnosis, intuitionistic fuzzy data serves as a valuable tool for representing information that is uncertain and imprecise. Nevertheless, decision-making based on this kind of knowledge can be quite challenging due to the inherent vagueness of the data. To address this issue, we employ power aggregation operators, which prove effective in combining several sources of data, such as expert thoughts and patient information. This allows for a more correct diagnosis; a particularly crucial aspect of medical practice where precise and timely diagnoses can significantly impact medication policy and patient results. In our research, we introduce a …

Towards Machine Proficiency With Semantic Underspecification, Zachary S. Gottesman

Dartmouth College Master’s Theses

Human natural language communication frequently relies on extra-linguistic information to fill in gaps in the linguistic signal left by semantic underspecification, or the omission of details that can be inferred from prior knowledge or other modalities. Underspecification is particularly common in conversations between acquaintances, since these interlocutors share context. Underspecification is a key and beneficial feature of natural language that improves efficiency, although it can cause communication to fail if it is not resolved correctly. For language models to communicate effectively and in a human-like fashion, they must learn how to recognize and utilize underspecified language. This thesis argues that …

Latent Auto-Recursive Composition Engine: A Generative System For Creative Expression In Human-Ai Collaboration, Yenkai Huang

Computer Science Senior Theses

This thesis investigates the shifting boundaries of art in the era of Generative AI, crit-
ically examining the essence of art and the legitimacy of AI-generated works. Despite
significant advancements in the quality and accessibility of art through generative
AI, such creations frequently encounter skepticism regarding their status as authentic
art. To address this skepticism, the study explores the role of creative agency in var-
ious generative AI workflows and introduces an ”artist-in-the-loop” system tailored
for image generation models like Stable Diffusion. This system aims to deepen the
artist’s engagement and understanding of the creative process. Additionally, a novel
tool, …

Scalable Pythagorean Mean-Based Incident Detection In Smart Transportation Systems, Md Jaminur Islam, Jose Paolo Talusan, Shameek Bhattacharjee, Francis Tiausas, Abhishek Dubey, Keiichi Yasumoto, Sajal K. Das

Computer Science Faculty Research & Creative Works

Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. to materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. in this article, we first propose a scalable data-driven anomaly-Based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. …

Improved Models Of Elastic Scheduling, Marion Baumli Sudvarg

McKelvey School of Engineering Graduate Student Theses & Dissertations

In real-time computing systems, \textit{timely} execution is a requirement of \textit{correct} execution. Such systems are widely found in robotics and autonomous vehicle applications, mobile spectrometry of atmospheric aerosols, real-time hybrid simulation for natural hazards engineering, and in prompt localization of transients such as gamma-ray bursts for time-domain and multi-messenger astrophysics. \textit{Elastic scheduling} provides a framework to adjust computational rates and workloads in systems for which timeliness cannot otherwise be guaranteed. While originally proposed for periodic tasks executing on a single processor, elastic scheduling has since been extended to sequential and parallel execution on multiple processors and to earliest deadline first …

Mending Trust In Ai: Trust Repair Policy Interventions For Large Language Models In Visual Data Journalism, Hangxiao Zhu

McKelvey School of Engineering Graduate Student Theses & Dissertations

Trust in Large Language Models (LLMs) emerged as a pivotal concern. This is because, despite the transformative potential of LLMs in enhancing the interpretability and interactivity of complex datasets, the opacity of these models and instances of inaccuracies or biases have led to a significant trust deficit among end-users. Moreover, there is a tendency for people to personify AI tools that utilize these LLMs, attributing abilities and sensibilities that they do not truly possess. This thesis exploits this personification and proposes a comprehensive framework of trust repair policies tailored to address the challenges inherent in LLM annotations within data journalism …

An Examination Of Behavior Of Youtube Commenters, John E. Leonard

Computer Science ETDs

YouTube comments are a unique form of social media, as viewers mainly interact with other viewers through comments sections, and cannot choose to interact with specific people. This lack of control over which comments are presented to them forces users to view spam.

Multiple general patterns of behavior were found in the dataset of YouTube comments. For example, most users posted just after a video’s publication. In addition, users tended to watch videos in the evening over the early morning.

A novel method was found for quantifying the likelihood of coordinated accounts being controlled by one person using time sharing. …

Online Temporal Data Mining And Learning: Pursuing Enhanced Efficiency And Robust Algorithms, Sheng Zhong

Computer Science ETDs

Time series data mining and learning serve as a cornerstone across various domains, including finance, healthcare, and science. Recent advancements in network and sensor technologies have ignited an increasing interest in real-time temporal data mining and learning techniques. Various tasks benefit from these techniques, such as environmental monitoring, event detection, anomaly identification, and forecasting. However, these techniques still face significant challenges in the online environment settings, encompassing aspects like efficiency, accuracy, robustness, and scarcity of labeled data. This dissertation presents four innovative solutions: FilCorr, DCT-MASS, FewSig, and BitLINK to overcome these challenges. We evaluate each method and showcase their practical …

Manipulative, Dark, And Unethical Design Practices In Ui & Ux Design, Ryan Edward Brown

Honors Theses

This thesis examines the pervasive and detrimental effects of manipulative user interface and user experience design (UI/UX) practices on individuals and society. Focusing on three critical areas – accessibility, dark patterns, and polarization – the study employs a mixed-methods approach, combining findings from a comprehensive literature review, an analysis of specific design patterns and methods, and a survey of user experiences.
The literature review covers topics such as the importance of accessibility in design education, the prevalence of dark patterns in mobile and desktop sites, the role of personalization algorithms in shaping user experiences, and the formation of echo chambers …

Program Analysis Of C For Conversion To Memory-Safe Rust, Dylan Cassidy

Honors Scholar Theses

C is a memory-unsafe language, which can cause software security issues. Rust is a more recent high-performance language that has memory-safe features, which motivates developers to move software to Rust. However, given the large existing C codebase, this is a tedious task, and current approaches result in memory-unsafe blocks of code remaining unsafe after conversion. We seek to use program analysis techniques to create software that identifies blocks of C code that could be safely converted to memory-safe Rust, despite using seemingly memory- unsafe access patterns. We performed manual translation of functions within the libGeoIP C library to Rust, ensuring …

Removal Of Phenol From Oilfield Produced Water Using Non-Conventional Adsorbent Medium By An Eco-Friendly Approach, Salem Jawad Alhamd, Mohammed Nsaif Abbas, Hassan Jameel Jawad Al-Fatlawy, Thekra Atta Ibrahim, Zaid Nsaif Abbas

Karbala International Journal of Modern Science

Petroleum extraction generates substantial quantities of produced water, a challenge compounded by water scarcity in oil-producing regions, notably the Middle East. Leveraging produced water effectively, adhering to environmental standards, can offer a viable solution to the issue of water scarcity. This study explores the potential of mandarin peels as an available, cost-effective adsorbent for treating synthetic aqueous solution simulated to oil-field produced water, specifically targeting phenol, a dangerous pollutant. Employing a batch-mode adsorption unit, six operational factors—phenol concentration, acidity, agitation speed, contact time, adsorbent dose, and temperature—were investigated. Results revealed an inverse relationship between phenol removal and pH, concentration, and …

A Nlp Approach To Automating The Generation Of Surveys For Market Research, Anav Chug

Honors College Theses

Market Research is vital but includes activities that are often laborious and time consuming. Survey questionnaires are one possible output of the process and market researchers spend a lot of time manually developing questions for focus groups. The proposed research aims to develop a software prototype that utilizes Natural Language Processing (NLP) to automate the process of generating survey questions for market research. The software uses a pre-trained Open AI language model to generate multiple choice survey questions based on a given product prompt, send it to a targeted email list, and also provides a real-time analysis of the responses …

Theoretical Spectroscopic Predictions Of Electronically Excited States, Noah R. Garrett

Honors Theses

The quest for faster computation of anharmonic vibrational frequencies of both ground and excited electronic states has led to combining coupled cluster theory harmonic force constants with density functional theory (DFT) cubic and quartic force constants for defining a quartic force field (QFF) utilized in conjunction with vibrational perturbation theory at second order (VPT2). This work shows that explicitly correlated coupled cluster theory at the singles, doubles, and perturbative triples level [CCSD(T)-F12] provides accurate anharmonic vibrational frequencies and rotational constants when conjoined with any of B3LYP, CAM-B3LYP, BHandHLYP, PBE0, and ωB97XD for roughly one-quarter of the computational time of the …

Simulating Cross-Scale Solid-Fluid Interaction Phenomena, Jinyuan Liu

Dartmouth College Ph.D Dissertations

Solid-fluid interactions are ubiquitous in nature, and accurate simulation methods are essential for realistic animation, industrial design, and engineering analysis. Com- pared to large-scale coupling phenomena, simulating fine-scale interactions poses extra challenges due to factors such as surface tension, material wettability, and geometric complexity. In this thesis, we pursue novel methodologies to accurately model in- terfacial dynamics between surface-tension fluids and codimensional solids, involving capillary interactions, controllable wettability, and robust contact behaviors. Our ini- tial approach involves developing a novel three-way coupling method, which utilizes a thin liquid membrane, modelled as a simplicial mesh, to facilitate accurate momen- tum transfer, …

We Need A “Building Inspector For Iot” When Smart Homes Are Sold, Timothy J. Pierson, Cesar Arguello, Beatrice Perez, Wondimu Zegeye, Kevin Kornegay, Carl A. Gunter

Dartmouth Scholarship

Internet of Things (IoT) devices left behind when a home is sold create security and privacy concerns for both prior and new residents. We envision a specialized “building inspector for IoT” to help securely facilitate transfer of the home.

Hls Taking Flight: Toward Using High-Level Synthesis Techniques In A Space-Borne Instrument, Marion Sudvarg, Chenfeng Zhao, Ye Htet, Meagan Konst, Thomas Lang, Nick Song, Roger D. Chamberlain, Jeremy Buhler, James H. Buckley

Computer Science Faculty Research & Creative Works

FPGAs are widely deployed on high-energy astrophysics telescopes to preprocess and reduce sensor data read out by front-end electronics. Across instruments, these computational pipelines have similar semantics, sharing common stages such as pedestal subtraction, signal integration, zero-suppression, island detection, and centroiding. However, diverse telescope designs require unique implementations of these algorithms, and the logic is often rewritten from scratch for a new instrument. As an alternative, High-Level Synthesis (HLS) tools enable these algorithms to be implemented in a high-level language, which eases modifications and enables fast prototyping and deployment. Nonetheless, writing performant HLS code requires augmentation of the code with …

Surmounting Challenges In Aggregating Results From Static Analysis Tools, Dr. Ann Marie Reinhold, Brittany Boles, A. Redempta Manzi Muneza, Thomas Mcelroy, Dr. Clemente Izurieta

Military Cyber Affairs

Aggregation poses a significant challenge for software practitioners because it requires a comprehensive and nuanced understanding of raw data from diverse sources. Suites of static-analysis tools (SATs) are commonly used to assess organizational security but simultaneously introduce significant challenges. Challenges include unique results, scales, configuration environments for each SAT execution, and incompatible formats between SAT outputs. Here, we document our experiences addressing these issues. We highlight the problem of relying on a single vendor's SAT version and offer a solution for aggregating findings across multiple SATs, aiming to enhance software security practices and deter threats early with robust defensive operations.

Generative Machine Learning For Cyber Security, James Halvorsen, Dr. Assefaw Gebremedhin

Military Cyber Affairs

Automated approaches to cyber security based on machine learning will be necessary to combat the next generation of cyber-attacks. Current machine learning tools, however, are difficult to develop and deploy due to issues such as data availability and high false positive rates. Generative models can help solve data-related issues by creating high quality synthetic data for training and testing. Furthermore, some generative architectures are multipurpose, and when used for tasks such as intrusion detection, can outperform existing classifier models. This paper demonstrates how the future of cyber security stands to benefit from continued research on generative models.

The Impact Of Heterogeneous Voting Strategies And Candidate Issue Adaptation On Elections: An Agent-Based Model, Harmony Peura

Departmental Honors & Graduate Capstone Projects

Political candidates in a democracy articulate positions on the issues of the day, but they are also highly aware of voter sentiment on those issues, and tailor their campaigns accordingly as they seek to win elections. Voters, too, adjust their political opinions based on (among other things) interactions with others in their social network. I present an agent-based simulation that models this dynamic interplay between candidates and voters, in order to shed light on what outcomes candidates can expect to result from a policy of “chasing” votes. The voters in the simulation differ from one another in the decision procedure …

Static Reflective Surfaces For Improved Terahertz Coverage, Thanh Le, Suresh Singh

Computer Science Faculty Publications and Presentations

LoS (Line of Sight) MIMO (Multiple Input Multiple Output) is considered the best way to deliver high capacity channels for terahertz communications due to the severe attenuation suffered by reflected components. Unfortunately, terahertz links are easily blocked by any obstruction resulting in link breakage. Therefore, it is necessary to provide alternative paths via reflectors. A problem shared by LoS paths and reflected paths (via polished reflectors) is that the channel matrix is rank 1 in the far-field. As a result, the achieved capacity is lower than what can theoretically be achieved in a rich multi-path environment. In this work, we …

Virtual Pair Programming And Online Oral Exams: Effects On Social Interaction, Performance, And Academic Integrity In A Remote Computer Programming Course, M. V. Lubarda, A. M. Phan, C. Schurgers, N. Delson, M. Ghazinejad, S. Baghdadchi, M. Minnes, Minju Kim, C. Pilegard, J. Relaford-Doyle, C. L. Sandoval, H. Qi

Psychology Faculty Articles and Research

Background and context

Pair programming and oral exams were deployed in tandem in a remote undergraduate computer programming course to promote social interaction and enhance learning.

Objectives

We investigate their impact on social interactions, sense of connection, academic performance, and academic integrity within a virtual learning environment, and explore the dynamics of student collaboration in the context of voluntary pair programming.

Method

Students’ coding activities, pairing preferences, and performance were survey responses were recorded and analyized.

Findings

First and second year students were more likely to participate in virtual pair programming than their more senior classmates. Willingness to pair program …