Computer Sciences Commons^™

Explainability In Multivariate Time Series Classification Machine Learning Models, Emanuel Sanchez, Giovanni Battaglia

23rd Annual A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity (2024)

Explainability within models is a crucial part of machine learning (ML) models because it promotes trust in the models by providing insights into how their predictions were determined. Our study applies the classification model XCM's explainability component in identifying the critical features leading to classification decisions on data collected while participants performed patient-handling tasks on manikins. Studies show that nurses sustain musculoskeletal injuries early in their career, attributable to some extent to posture adopted during patienthandling tasks. The ML models classify posture adopted during tasks as "good", "poor", or, in some cases, "neutral", where good posture minimizes the risk of …

Classifying Patient Handling Techniques To Reduce Risk Of Musculoskeletal Injury In Nursing Students, Giovanni Battaglia, Emanuel Sanchez

23rd Annual A. Paul and Carol C. Schaap Celebration of Undergraduate Research and Creative Activity (2024)

Nurses suffer musculoskeletal injuries at a higher proportion than the general population due to physical strain and poor posture during patient-handling tasks; studies show that back injuries occur at a rate of 28.9 cases per 10,000 registered nurses. The purpose of this study is to apply multivariate time series classifiers (MTSCs) to classify six patient-handling tasks and the quality of subject posture (good, poor, or neutral) during these tasks. Manikins weighing 44 lbs, 66 lbs, and 110 lbs simulated patients. In this proof-of-concept study the XCM, ResNet, and MiniRocket MTSCs were trained with data collected from four non-nursing students using …

Citdet, Jordan A. James, Heather K. Manching, Matthew R. Mattia, Kim D. Bowman, Amanda M. Hulse-Kemp, William J. Beksi

Computer Science and Engineering Datasets - Archive

The CitDet dataset is composed of images captured at the USDA Agricultural Research Service Subtropical Insects and Horticulture Research Unit in Fort Pierce, FL, USA. Data was collected between October 2021 and October 2022. 579 images were captured from different sections of the orchard using the open-source application Field Book on Android tablets. While collecting images, we faced the camera in a portrait orientation directly centered on the tree of interest. All images were taken at the edge of the soil in the tree row to simulate a ground-based robot imaging the tree while moving between two rows of trees. …

Mathematically Rigorous Deep Learning Paradigms For Data-Driven Scientific Modeling, Owen Nicholas Davis

Mathematics & Statistics ETDs

This dissertation explores the crucial role of data-driven modeling in science and engineering, with a focus on developing surrogate models to accelerate large-scale computational tasks, aiding in both outer-loop functions like uncertainty quantification and expensive inner-loop tasks within broader computational frameworks. Challenges arise with increased problem dimension and sparse, noisy training data, particularly significant when constructing surrogates for very expensive computational models where acquiring sufficient high-fidelity training data is unfeasible. In such scenarios, training surrogates from an ensemble of multifidelity information sources of varying accuracy and cost becomes essential. We emphasize neural network-based modeling paradigms, which are flexible in integrating …

Immersive Japanese Language Learning Web Application Using Spaced Repetition, Active Recall, And An Artificial Intelligent Conversational Chat Agent Both In Voice And In Text, Marc Butler

MS in Computer Science Project Reports

In the last two decades various human language learning applications, spaced repetition software, online dictionaries, and artificial intelligent chat agents have been developed. However, there is no solution to cohesively combine these technologies into a comprehensive language learning application including skills such as speaking, typing, listening, and reading. Our contribution is to provide an immersive language learning web application to the end user which combines spaced repetition, a study technique used to review information at systematic intervals, and active recall, the process of purposely retrieving information from memory during a review session, with an artificial intelligent conversational chat agent both …

Data Profits Vs. Privacy Rights: Ethical Concerns In Data Commerce, Amiah Armstrong

Cybersecurity Undergraduate Research Showcase

In today’s digital age, the collection and sale of customer data for advertising is gaining a growing number of ethical concerns. The act of amassing extensive datasets encompassing customer preferences, behaviors, and personal information raises questions of its true purpose. It is widely acknowledged that companies track and store their customer’s digital activities under the pretext of benefiting the customer, but at what cost? Are users aware of how much of their data is being collected? Do they understand the trade-off between personalized services and the potential invasion of their privacy? This paper aims to show the advantages and disadvantages …

The Borderline Between Beneficial And Dishonest Ai: A Technical Report, Seth Richards, Katherine Shell, Seth Wright

Student Works

Artificial Intelligence (AI) has been used since 1950 but it was largely overlooked by the public until 2022. Current discussions about AI center around academic integrity. This report seeks to understand if AI can be handled, used, or accepted in Lipscomb’s academic environment as a beneficial aid to writing and research, without actively doing these tasks for an individual. Generative AI is a neural network, which enables it to receive input, gather information from a database of existing content, and create new content [2]. Due to the nature of generative AI, its beneficial contributions to academia are extremely limited.

Individualized Learning As An Ai Tool: A Technical Report, Petsimnan Blessing Dayit, Kasen Holt, Nuala Roper

Student Works

The purpose of the report’s research is to test and analyze whether Artificial Intelligence (AI) platforms can be used as beneficial tools for individualized learning at Lipscomb University without violating the Academic Integrity Policy. The methods section evaluates AI on the scopes of accuracy, analytical thinking, and adaptability. The results demonstrated how each platform responded to the prompts within the lines of the scope. The answers they gave were accurate, detailed, and contained various adaptations to make explanations clearer for the user. The team concluded that AI can be used at Lipscomb as a beneficial tool for students in their …

Artificial Sociality, Simone Natale, Iliana Depounti

Human-Machine Communication

This article proposes the notion of Artificial Sociality to describe communicative AI technologies that create the impression of social behavior. Existing tools that activate Artificial Sociality include, among others, Large Language Models (LLMs) such as ChatGPT, voice assistants, virtual influencers, socialbots and companion chatbots such as Replika. The article highlights three key issues that are likely to shape present and future debates about these technologies, as well as design practices and regulation efforts: the modelling of human sociality that foregrounds it, the problem of deception and the issue of control from the part of the users. Ethical, social and cultural …

Context-Aware Affective Behavior Modeling And Analytics, Md Taufeeq Uddin

USF Tampa Graduate Theses and Dissertations

Affective computing (AC) is a sub-domain of AI that has the potential to assist people by assessing mental states and making appropriate recommendations to patients, loved ones, caregivers, and domain experts. Humans usually produce an enormous amount of data (such as face videos) every day. One of the major challenges for affective computer vision is to efficiently deal with high volumes of data to facilitate automated model development. To cope with this challenge, we developed computer vision algorithms that measure the expressivity of the human face from video data. More precisely, the developed algorithms can map complex affect information from …

Assessing The Promise And Pitfalls Of Chatgpt For Automated Cs1-Driven Code Generation, Fawad Khan, Max Ramsdell

Student Research Symposium

Definition and Overview of Large Language Models:

• Large Language Models (LLMs) are advanced AI algorithms designed to understand, generate, and interact with human language at a vast scale.

The Evolution of LLMs:

• The development of LLMs has progressed
• 1960 - Basic LLM - basic predictive text functions
• 2017- Transformers - Core model powering ChatGPT introduced
• 2022 - ChatGPT context-aware systems

Assessing Chatgpt As A Programming Exercise Generator, Maxwell Ramsdell, Fawad Khan

Student Research Symposium

Motivation

• Proximal Zone of Development
• Teaching Efficiency
• Cross-Discipline Applications

For these to work, we need to evaluate the effectiveness with which chatGPT writes coding exercises

Application Of T Gates For Anti-Concentration In Clifford Circuits, Matthew Dominicis, Mason Toombs, Gabriel Riddle, Parineeta Puja Saha, Himanth Bobba

Undergraduate Research Conference at Missouri S&T

Our study examines the integration of non-Clifford T gates into randomly generated Clifford circuits to enhance their universal unitary capacity. We investigate the impact of T gates on circuit output randomness, focusing on generating random Clifford circuits and analyzing the effects of T gates. Through simulations and analysis, we assess the effectiveness of this modification in achieving outputs consistent with Anti concentration properties while minimizing the required number of Clifford gates. Our findings provide valuable insights into quantum circuits, with implications for quantum computing applications.

A Fisher Information-Based Approach To Improve Labeling Efficiency Of Neural Network Models In Image Classification, Joshua Caruso

Undergraduate Research Conference at Missouri S&T

Active learning is a framework for training machine learning models where the goal is to reduce the number of labels used during training. Neural network models used for image classification require a large training dataset to achieve good accuracy. This project will use active learning to reduce the number of labels needed for training neural network models. We propose to use the Fisher information of the neural network parameters to actively select which images are labelled and included in the training data. A key challenge is the large number of parameters in commonly used neural network models, which significantly increases …

Ta Theoretical Framework For Comparing Rlhf Method, Matthew Dominicis

Undergraduate Research Conference at Missouri S&T

Reinforcement Learning from Human Feedback (RLHF) can be used as a means to align Al agents and Large Language Models (LLM) to better represent human expectations. There is a myriad of RLHF methods that exist, however it is difficult to benchmark and compare such methods in terms of alignment, training cost, data collection cost, and other metrics. This project aims to create a robust classification for different RLHF methods from a theoretical point of view. Additionally, this project will attempt to propose bounds for the degree of influence on LLMs that stems from human feedback. Open source LLMs will be …

Enhancing Galaxy Surveys With Machine Learning, Steven Karst

Undergraduate Research Conference at Missouri S&T

Applications of machine learning (ML) or artificial intelligence (Al) to problems in astrophysics and cosmology have recently entered a golden era. In response, we have updated two of our recent ML/Al efforts that contribute to galaxy surveys whose main scientific target is to reveal the nature of the Comsic Acceleration or Dark Energy. We first revised our effort to infer cosmological information beyond the survey geometry using Graph Neural Networks (GNNs) to take advantage of supercomputing resources on campus. We then updated our methods for galaxy target selection in the Subaru Prime Focus Spectrograph (PFS) survey with modern reinforcement learning …

Enhancing Galaxy Surveys With Machine Learning, Steven Karst

Undergraduate Research Conference at Missouri S&T

Applications of machine learning (ML) or artificial intelligence (AI) to problems in astrophysics and cosmology have recently entered a golden era. In response, we have updated two of our recent ML/ AI efforts that contribute to galaxy surveys whose main scientific target is to reveal the nature of the Cosmic Acceleration or Dark Energy. We first revised our effort to infer cosmological information beyond the survey geometry using Graph Neural Networks (GNN) to take advantage of supercomputing resources on campus. We then updated our reinforcement learning methods for galaxy target selection in the Subaru Prime Focus Spectrograph (PFS) survey with …

Effects Of Reproduction On Senescence In Local Species, Nathan Smith

Undergraduate Research Conference at Missouri S&T

Understanding the impact of reproduction on the aging process within species populations remains an ongoing challenge in ecological and evolutionary research. In this study, we aim to clarify the relationship between reproduction and senescence using agent-based modeling using wild species data sets. Our objectives include investigating how variations in reproductive rates influence the lifespan and aging trajectories of individuals within populations, as well as identifying potential mechanisms underlying these effects. We will employ agent-based modeling to simulate populations and explore the dynamics of reproduction and senescence using publicly available datasets of local wild species. By manipulating parameters related to reproductive …

Neural Machine Translation Vs. Computer Assisted Technology: Machine Translation Post Editing Human Quality Assurance, Sarah Aland, Sarah Kane, Kenya Merida Millan

Student Research Symposium

What is neural machine Translation (NMT) and Computer Assisted Technology (CAT)?

Simulating Inter-Species Competition In C. Elegans, Kevin Lai

Undergraduate Research Conference at Missouri S&T

In biological research, understanding the life cycles of Caenorhabditis elegans (C. elegans) is pivotal for insights into developmental biology, genetics, and population dynamics. Our project builds on Worm-Pop, a Python-based multi-agent simulation of Caenorhabditis elegans (C. elegans) , to enhance its capabilities in simulating survival strategies, reproductive success, and genetic drift. The current model simulates a uniform population without inter-agent interactions. I plan to introduce multiple species of worms into the simulation to study competitive dynamics and determine which variants are most successful under various conditions. Pheromones significantly influence C. elegans behavior, affecting mating, foraging, and social interactions. To address …

A Smart Resume Builder Tool Using Generative Ai, Ivan A. Velo Castaneda, Anas Hourani, Magdalene Moy

SACAD: Scholarly Activities

Crafting a standout resume is crucial in today’s competitive job market. Not only does it create a strong first impression on employers but it also it opens the doors for endless job opportunities. Despite existing resume assistance for FHSU students on the Career Services page, there's a lack of tools for generating or streamlining the resume writing process. To address this issue, an efficient resume builder utilizing OpenAI’s GPT-3.5 model was developed specifically for FHSU students. Its key features include intuitive template selection, dynamic AI-generated content for tailored resumes, multi-format output supporting PDF and Word formats, and a user-friendly experience …

Image De‑Photobombing Benchmark, Vatsa S. Patel, Kunal Agrawal, Samah Baraheem, Amira Yousif, Tam Nguyen

Computer Science Faculty Publications

Removing photobombing elements from images is a challenging task that requires sophisticated image inpainting techniques. Despite the availability of various methods, their effectiveness depends on the complexity of the image and the nature of the distracting element. To address this issue, we conducted a benchmark study to evaluate 10 state-of-the-art photobombing removal methods on a dataset of over 300 images. Our study focused on identifying the most effective image inpainting techniques for removing unwanted regions from images. We annotated the photobombed regions that require removal and evaluated the performance of each method using peak signal-to-noise ratio (PSNR), structural similarity index …

Megordle: A Wdolre Usclnbaermr, Meg Arney

Undergraduate Research Conference

Our goal was to make a dynamic word unscrambler app based on the random generation of words from a database. The original database contains 4,320 of the most common words in the English language. This project was originally designed in Visual Studio Code in java and takes input from the terminal. The project was later translated into C# and transferred into Unity to provide a visual and dynamic interface for users.

No Generation Without Representation: Solving Ai Art Attribution With Sno-E, Sadie Campbell

Undergraduate Research Conference

Artificial intelligence has sparked a new-age debate about its ethical implications, specifically in the world of art. The Signature Neural Operative- Environment (SNO-E) is a multidisciplinary solution that draws on computer science, statistics, and art. It addresses the issue of proper attribution for Al-generated artworks through a Convolution Neural Network that adopts signature checks to cite artists whose works are sampled by Al. This novel approach ensures proper recognition and compensation for artists in the Al-generated era.

Software Based Approach To Realtime Sports Graphics, Honesty Beaton

SACAD: Scholarly Activities

My research presents a software-based approach to real-time sports graphics, leveraging Unity, C#, and OpenCV. We aimed to enhance viewer engagement by providing dynamic and interactive graphics during sports broadcasts. My method involves real-time analysis of video feeds to cut out players, place them onto a virtual court, and underlay immersive visuals, giving the appearance that virtual visuals physically exist beneath a player. Evaluation of this approach demonstrates the effectiveness of utilizing a software-based approach for real-time sports graphics, akin to traditional hardware-based solutions

Gender Detection In Facial Images: A Comprehensive Cnn Analysis, Jose N T Ambrosio, Anas Hourani, Magdalene Moy

SACAD: Scholarly Activities

This research investigates the construction of a robust gender detection system using facial features and Convolutional Neural Networks (CNNs), exploring the impact of different layer configurations on accuracy and computational efficiency. With a validation accuracy of 91%, findings illuminate the nuanced relationship between precision and computational resources, enriching discussions on facial recognition technologies.

Artificial Intelligence Could Probably Write This Essay Better Than Me, Claire Martino

Augustana Center for the Study of Ethics Essay Contest

No abstract provided.

An Exploration Of Companion Robots, Annelyse Lockhart

2024 Student Academic Showcase

Japan and the United States have a drastically different view towards artificial intelligence and smart machines. Within my project, I did an exploratory analysis of robotics within the United States and Japan, and posed the question as to why Japan has substantially more robotics within their day-to-day life. I took an in-depth look at Japanese robotics that do not exist within the United States, as well as explored the biases behind smart machines in both cultures. Judging Category: Exploratory

Ua12/2/1 College Heights Herald: Big Red By Ai, Wku Student Affairs

WKU Administration Documents

Magazine edition of the College Heights Herald for the period March 3 - April 8, 2024.

• Big Red, Is That You?
• Anderson, Alexandria. Letter from the Editor - Artificial Intelligence
• Phelps, Maggie. What is AI? - Artificial Intelligence
• AI’s Impact on Higher Education
• Reed, Bailey. Students Share Opinions on AI
• Abney, Shayla. WKU Faculty Discuss AI in Courses
• Hawkins, Kaylee. AI’s Impact on Blackboard Ultra
• Randolph, Eli. AI Recreates a WKU Tour
• Shaw, Cameron. WKU Department of Political Science Hosts Dead President’s Tour

Performing Distributed Quantum Calculations In A Multi-Cloud Architecture Secured By The Quantum Key Distribution Protocol, Jose Luis Lo Huang, Vincent C. Emeakaroha

Department of Computer Science Publications

Quantum computing (QC) is an emerging area that yearly improves and develops more advances in the number of qubits and the available infrastructure for public users. Nowadays, the main cloud service providers (CSP) are implementing different mechanisms to support access to their quantum computers, which can be used to perform small experiments, test hybrid algorithms and prove quantum theories. Recent research work have discussed the low capacity of using quantum computers in a single CSP to perform quantum computation that are needed to solve different experiments for real world problems. Thus, there are needs for computing powers in the form …