Computer Sciences Commons^™

Disentangling Cyclic Causality: An Instance-Based Framework For Causal Discovery, Chase A. Yakaboski

Dartmouth College Ph.D Dissertations

---

Correlation does not imply causation" is one of the fundamental principles taught in science, emphasizing that associations between variables do not necessarily indicate causality. Yet, over the past three decades, extensive research has begun to challenge this perspective by developing sophisticated methods to differentiate causal from correlative relationships. This research suggests that correlations often involve a blend of confounded and causal interactions, which, given certain assumptions, can be disentangled to uncover actionable insights and deepen our understanding of physical, biological, and societal systems.

Accurately discovering causal relationships from data amidst cyclic dynamics remains a challenging open problem in causality research. …

---

Mitigating Safety Issues In Pre-Trained Language Models: A Model-Centric Approach Leveraging Interpretation Methods, Weicheng Ma

Dartmouth College Ph.D Dissertations

---

Pre-trained language models (PLMs), like GPT-4, which powers ChatGPT, face various safety issues, including biased responses and a lack of alignment with users' backgrounds and expectations. These problems threaten their sociability and public application. Present strategies for addressing these safety concerns primarily involve data-driven approaches, requiring extensive human effort in data annotation and substantial training resources. Research indicates that the nature of these safety issues evolves over time, necessitating continual updates to data and model re-training—an approach that is both resource-intensive and time-consuming. This thesis introduces a novel, model-centric strategy for understanding and mitigating the safety issues of PLMs by …

---

Scalable Methods For Resource-Constrained Adaptive Sampling, Kizito Masaba

Dartmouth College Ph.D Dissertations

---

As the global community confronts the pressing issues of climate change, the importance of environment monitoring cannot be overstated. This process is essential in identifying and tracking critical environmental trends to facilitate efficient and effective conservation efforts. Traditionally, scientists perform this task using hand-held, in-situ instruments. With the recent robot advancements, this task can be fully automated by applying multi-robot systems to a task referred to as multi-robot adaptive sampling. However, the cost of purchasing and operating robot systems for this application are still prohibitive due to various environmental, technological, and logistical constraints. Some of the outstanding constraints to the …

---

A Memory Efficient Deep Recurrent Q-Learning Approach For Autonomous Wildfire Surveillance, Jeremy A. Cantor

UNF Graduate Theses and Dissertations

---

Previous literature demonstrates that autonomous UAVs (unmanned aerial vehicles) have the po- tential to be utilized for wildfire surveillance. This advanced technology empowers firefighters by providing them with critical information, thereby facilitating more informed decision-making processes. This thesis applies deep Q-learning techniques to the problem of control policy design under the objective that the UAVs collectively identify the maximum number of locations that are under fire, assuming the UAVs can share their observations. The prohibitively large state space underlying the control policy motivates a neural network approximation, but prior work used only convolutional layers to extract spatial fire information from …

---

Feedback Loops: Feedback Machines, Patrick Barry

Articles

---

Yes, AI raises serious concerns about bias, privacy, copyright infringement, environmental sustainability, and a whole bunch of other important topics. But if you are looking for a positive use case - and a new way to approach professional development - try asking chatgpt or some other AI chatbot for feedback, especially on something you've written.

---

Media Haze Classification In Retinal Images Using Deep Learning, Jonathan O'Berry

UNF Graduate Theses and Dissertations

---

Media Haze (MH) is a condition that affects an individual’s quality of life by affecting their eyes. Current practice is to detect MH by manually examining retinal fundus (retinal) images. The analysis of images being used as the prevalent technique for identifying the MH condition strongly suggests that automation of this process may be possible. In recent years, machine learning, specifically computer vision, has allowed for the automation of tasks relating to image analysis. This ability to automate has also recently been shown in the medical field for some eye conditions and diseases. This thesis centers around the problem of …

---

Using Pose Estimation Software To Predict Actions In Sabre Fencing, Micah Edwin Peters Ii

Honors College Theses

---

Fencing is a combat sport that uses three different swords: epee, foil, and sabre. Due to its fast-paced nature and employment of right of way, sabre fencing is often considered the most difficult of the three to learn. Computer vision and pose estimation software can be used to lower the barrier of entry to sabre fencing by identifying the different actions in sabre fencing. This project focuses on using open-source software to design a program that can identify the sabre parries as well as the main sabre movements. This program could be used to help newer fencers and spectators better …

---

Ethical Decision-Making In Older Drivers During Critical Driving Situations: An Online Experiment, Amandeep Singh, Sarah Yahoodik, Yovela Murzello, Samuel Petkac, Yusuke Yamani, Siby Samuel

Psychology Faculty Publications

---

The present study examined the impact of aging on ethical decision-making in simulated critical driving scenarios. 204 participants from North America, grouped into two age groups (18–30 years and 65 years and above), were asked to decide whether their simulated automated vehicle should stay in or change from the current lane in scenarios mimicking the Trolley Problem. Each participant viewed a video clip rendered by the driving simulator at Old Dominion University and pressed the space-bar if they decided to intervene in the control of the simulated automated vehicle in an online experiment. Bayesian hierarchical models were used to analyze …

---

Leveraging Machine Learning To Study How Temperature Scores Predict Pre-Term Birth Status, Erich Seamon, Jennifer A. Mattera, Sarah A. Keim, Esther M. Leerkes, Jennifer L. Rennels, Andrea J. Kayl, Kristy M. Kulhanek, Darcia Narvaez, Sarah M. Sanborn, Jennifer B. Grandits, Christine Dunkel Schetter, Mary Coussons-Read, Amanda R. Tarullo, Sarah J. Schoppe-Sullivan, Mariah E. Thomason, Julie M. Braungart-Rieker, Julie C. Lumeng, Shannon N. Lenze, Lisa M. Christian, Darby E. Saxbe, Laura R. Stroud, Christina M. Rodriguez, Stephanie Anzaman-Frasca

Psychology Faculty Publications

---

Background

Preterm birth (birth at <37 completed weeks gestation) is a significant public heatlh concern worldwide. Important health, and developmental consequences of preterm birth include altered temperament development, with greater dysregulation and distress proneness.

Aims

The present study leveraged advanced quantitative techniques, namely machine learning approaches, to discern the contribution of narrowly defined and broadband temperament dimensions to birth status classification (full-term vs. preterm). Along with contributing to the literature addressing temperament of infants born preterm, the present study serves as a methodological demonstration of these innovative statistical techniques.

Study design

This study represents a metanalysis conducted with multiple samples (N = 19) including preterm (n = 201) children and (n = 402) born at term, with data combined across investigations to perform classification analyses.

Subjects …

---

Synthetic Health Data: Real Ethical Promise And Peril, W. Nicholson Price Ii, Daniel Susser

Other Publications

---

Modern health research and development faces a dilemma. On the one hand, there is more data than ever — in electronic health records, in lab research, in public datasets, and on the internet — from which to extract potentially transformative scientific insights and to use as the basis for developing breakthrough health care technologies. On the other hand, using this data entails various risks: threats to patient privacy, skewed samples and approaches to analysis that can perpetuate demographic and other biases, and uneven access to data about rare conditions and small patient subgroups. Generating synthetic data has emerged as one …

---

Hack24f: Ai Audio Extractor, David Wu, Tiffany Nham

Paul English Applied Artificial Intelligence (AI) Institute Publications

---

I want to make a next.js website locally and then be able to hopefully deploy on Vercel. Within the website I want to be able to use AI to separate the instruments (vocals, piano, guitar, drums, bass, etc.) and also identify which notes are being played. I was thinking that we might be able to use an AI stem splitter to separate the audio tracks and use another AI model for note detection.

---

Hack24f: Ai Conversations In Healthcare, Patrick Finger, Hannah Neale, Anthony Ferreira, Ayaz Mohammed

Paul English Applied Artificial Intelligence (AI) Institute Publications

---

Nursing students often complete clinical hours under the supervision of instructors in traditional hospital settings. However, obtaining individualized, consistent feedback from patients about their interactions with nursing students is often not feasible. This limits students' ability to fully understand how their communication skills are perceived and how they can improve. Currently, there are no models that represent realistic real life conversations with patients. Most virtual simulation models used for nursing students provide scripted responses that do not feel genuine.

---

Hack24f: The Empathy Architects, Michael Rejtig, Ajanee Igharo, Emma Kelminson, Jackson Comeau

Paul English Applied Artificial Intelligence (AI) Institute Publications

---

Problem Statement: We want to help patients from underserved communities feel more safe, respected and comfortable in interacting with healthcare providers during the initial in-person encounters while also helping providers build empathy and implement socio-emotionally competent communication behaviors. Solution: Empathy Evolution is an AI-powered role-playing game that helps patients simulate their ideal communication with healthcare providers.

---

Sub-Band Backdoor Attack In Remote Sensing Imagery, Kazi Aminul Islam, Hongyi Wu, Chunsheng Xin, Rui Ning, Liuwan Zhu, Jiang Li

Electrical & Computer Engineering Faculty Publications

---

Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in …

---

Computer-Aided Craniofacial Superimposition Validation Study: The Identification Of The Leaders And Participants Of The Polish-Lithuanian January Uprising (1863–1864), Rubén Martos, Rosario Guerra, Fernando Navarro, Michela Peruch, Kevin Neuwirth, Andrea Valsecchi, Rimantas Jankauskas, Oscar Ibáñez

Faculty, Staff and Student Publications

---

In 2017, a series of human remains corresponding to the executed leaders of the "January Uprising" of 1863-1864 were uncovered at the Upper Castle of Vilnius (Lithuania). During the archeological excavations, 14 inhumation pits with the human remains of 21 individuals were found at the site. The subsequent identification process was carried out, including the analysis and cross-comparison of post-mortem data obtained in situ and in the lab with ante-mortem data obtained from historical archives. In parallel, three anthropologists with diverse backgrounds in craniofacial identification and two students without previous experience attempted to identify 11 of these 21 individuals using …

---

Ai And Ml-Based Risk Assessment Of Chemicals: Predicting Carcinogenic Risk From Chemical-Induced Genomic Instability, Ajay Vikram Singh, Preeti Bhardwaj, Peter Laux, Prachi Pradeep, Madleen Busse, Andreas Luch, Akihiko Hirose, Christopher J. Osgood, Michael W. Stacey

Biological Sciences Faculty Publications

---

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, …

---

Spatially-Aware Speaker For Vision-And-Language Navigation Instruction Generation, Muraleekrishna Gopinathan, Martin Masek, Jumana Abu-Khalaf, David Suter

Research outputs 2022 to 2026

---

Embodied AI aims to develop robots that can understand and execute human language instructions, as well as communicate in natural languages. On this front, we study the task of generating highly detailed navigational instructions for the embodied robots to follow. Although recent studies have demonstrated significant leaps in the generation of step-by-step instructions from sequences of images, the generated instructions lack variety in terms of their referral to objects and landmarks. Existing speaker models learn strategies to evade the evaluation metrics and obtain higher scores even for low-quality sentences. In this work, we propose SAS (Spatially-Aware Speaker), an instruction generator …

---

Triphlapan: Predicting Hla Molecules Binding Peptides Based On Triple Coding Matrix And Transfer Learning, Meng Wang, Chuqi Lei, Jianxin Wang, Yaohang Li, Min Li

Computer Science Faculty Publications

---

Human leukocyte antigen (HLA) recognizes foreign threats and triggers immune responses by presenting peptides to T cells. Computationally modeling the binding patterns between peptide and HLA is very important for the development of tumor vaccines. However, it is still a big challenge to accurately predict HLA molecules binding peptides. In this paper, we develop a new model TripHLApan for predicting HLA molecules binding peptides by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. We have found the main interaction site regions between HLA molecules and peptides, as well as the correlation between HLA encoding and binding …

---

Artificial Intelligence For The Electron Ion Collider (Ai4eic), C. Allaire, R. Ammendola, E.-C. Aschenauer, M. Balandat, M. Battaglieri, J. Bernauer, M. Bondì, N. Branson, T. Britton, A. Butter, I. Chahrour, P. Chatagnon, E. Cisbani, E. W. Cline, S. Dash, C. Dean, W. Deconinck, A. Deshpande, M. Diefenthaler, R. Ent, C. Fanelli, M. Finger, M. Finger Jr., E. Fol, S. Furletov, Y. Gao, J. Giroux, N. C. Gunawardhana Waduge, O. Hassan, P. L. Hegde, R. J. Hernandez-Pinto, A. Hiller Blin, T. Horn, J. Huang, A. Jalotra, D. Jayakodige, B. Joo, M. Junaid, N. Kalantarians, P. Karande, B. Kriesten, R. Kunnawalkam Elayavalli, Y. Li, M. Lin, F. Liu, S. Liuti, G. Matousek, M. Mceneaney, D. Mcspadden, T. Menzo, T. Miceli, V. Mikuni, R. Montgomery, B. Nachman, R. R. Nair, J. Niestroy, S. A. Ochoa Oregon, J. Oleniacz, J. D. Osborn, C. Paudel, C. Pecar, C. Peng, G. N. Perdue, W. Phelps, M. L. Purschke, H. Rajendran, K. Rajput, Y. Ren, D. F. Renteria-Estrada, D. Richford, B. J. Roy, D. Roy, A. Saini, N. Sato, T. Satogata, G. Sborlini, M. Schram, D. Shih, J. Singh, R. Singh, A. Siodmok, J. Stevens, P. Stone, L. Suarez, K. Suresh, A. -N. Tawfik, F. Torales Acosta, N. Tran, R. Trotta, F. J. Twagirayezu, R. Tyson, S. Volkova, A. Vossen, E. Walter, D. Whiteson, M. Williams, S. Wu, N. Zachariou, P. Zurita

Computer Science Faculty Publications

---

The Electron-Ion Collider (EIC), a state-of-the-art facility for studying the strong force, is expected to begin commissioning its first experiments in 2028. This is an opportune time for artificial intelligence (AI) to be included from the start at this facility and in all phases that lead up to the experiments. The second annual workshop organized by the AI4EIC working group, which recently took place, centered on exploring all current and prospective application areas of AI for the EIC. This workshop is not only beneficial for the EIC, but also provides valuable insights for the newly established ePIC collaboration at EIC. …

---

Evaluating Pre-Trial Programs Using Interpretable Machine Learning Matching Algorithms For Causal Inference, Travis Seale-Carlisle, Saksham Jain, Courtney Lee, Caroline Levenson, Swathi Ramprasad, Brandon Garrett, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky

Faculty Scholarship

---

After a person is arrested and charged with a crime, they may be released on bail and required to participate in a community supervision program while awaiting trial. These ‘pretrial programs’ are common throughout the United States, but very little research has demonstrated their effectiveness. Researchers have emphasized the need for more rigorous program evaluation methods, which we introduce in this article. We describe a program evaluation pipeline that uses recent interpretable machine learning techniques for observational causal inference, and demonstrate these techniques in a study of a pre-trial program in Durham, North Carolina. Our findings show no evidence that …

---

Deepfakes In Court: How Judges Can Proactively Manage Alleged Ai-Generated Material In National Security Cases, Abhishek Dalal, Chongyang Gao, Paul W. Grimm, Maura R. Grossman, Daniel W. Linna Jr., Chiara Pulice, V. S. Subrahmanian, John Tunheim

Faculty Scholarship

---

Dall-E. ChatGPT GPT-4. Words that did not exist in the English lexicon just a few years ago are now commonplace. With the widespread availability of Artificial Intelligence (AI) tools, specifically Generative AI, whether in the context of text, audio, video, imagery, or even combinations of these, it is inevitable that trials related to national security will involve evidentiary issues raised by Generative AI. We must confront two possibilities: first, that evidence presented is AI-generated and not real and, second, that other evidence is genuine but alleged to be fabricated. Technologies designed to detect AI-generated content have proven to be unreliable, …

---

Human Psychology And Robot Evidence In The Courtroom, Alternative Dispute Resolution, And Agency Proceedings, Sara Sun Beale, Hayley Lawrence

Faculty Scholarship

---

In human–robot interactions in legal proceedings, human responses to robot-generated evidence will present unique challenges to the accuracy of litigation as well as ancillary goals such as fairness and transparency, though it may also enhance accuracy in other respects. The most important feature of human–robot interactions is the human tendency to anthropomorphize robots, which can generate misleading impressions and be manipulated by designing robots to make them appear more trustworthy and believable. Although robot-generated evidence may also offer unique advantages, there are concerns about the degree to which the traditional methods of testing the accuracy of evidence, particularly cross-examination, will …

---

Diffusion Model Approach To Simulating Electron-Proton Scattering Events, Peter Devlin, Jian-Wei Qiu, Felix Ringer, Nobuo Sato

Physics Faculty Publications

---

Generative artificial intelligence is a fast-growing area of research offering various avenues for exploration in high-energy nuclear physics. In this work, we explore the use of generative models for simulating electron-proton collisions relevant to experiments like the Continuous Electron Beam Accelerator Facility and the future Electron-Ion Collider (EIC). These experiments play a critical role in advancing our understanding of nucleons and nuclei in terms of quark and gluon degrees of freedom. The use of generative models for simulating collider events faces several challenges such as the sparsity of the data, the presence of global or eventwide constraints, and steeply falling …

---

Advancing Machine Learning Interpretability: Lime Applications To Temporal Data And A Novel Method Of Counterfactual Generation, Shou Nakano, Yang Liu

Theses and Dissertations (Comprehensive)

---

As machine learning has advanced significantly over the past decade, predictive models have achieved substantial success across various domains. However, they often lack transparency in their decision-making processes. This opacity presents risks, particularly in sectors like healthcare and finance, where transparency is crucial. To address these challenges, explainable artificial intelligence (XAI) has risen in importance. Techniques such as LIME (Local Interpretable Model-agnostic Explanations) have been developed, utilizing simpler alternative models like linear regression or tree-based models to explain decisions for specific instances.

This thesis initially concentrates on the application of LIME to three global annual datasets, specifically within the relatively …

---

Advancing Chronic Kidney Disease Prediction Through Machine Learning And Deep Learning With Feature Analysis, Shiddarth Dey Tusar, S. M. Ahad Ali Chowdhury, Md. Jalal Uddin Chowdhury, Rana M. Pir, H. M. Nur A. Alam, Muhammad Rezaur Rahman, Md. Nural Absar Siddiky, Muhammad Enayetur Rahman

Electrical & Computer Engineering Faculty Publications

---

Chronic Kidney Diesease (CKD) is a significant health issue, ranking as the fourth leading cause of mortality worldwide. The traditional diagnosis and treatment process, reliant on medical experts, is time-consuming. Therefore, thereis an urgent need for more efficient diagnostic methods to improve patient outcomes and reduce mortality rates. In this study, we employ Machine Learning (ML) and Deep Learning (DL) techniques to predict CKD based on important features. Feature analysis was performed using a correlation matrix and the LASSO algo-rithm to identify the most relevant features for model training. We evaluated several ML and DL classifiers, including Logistic Regression (LR), …

---

Machine Learning Based Intrusion Detection Framework For Can Bus Vulnerabilities In Modern Vehicles, Obinna C. Agbo

Graduate Theses, Dissertations, and Problem Reports (ETD)

---

The Controller Area Network (CAN) bus is a crucial communication backbone in modern vehicles, connecting various Electronic Control Units (ECUs). However, inherent design weaknesses such as the lack of encryption and authentication make CAN networks vulnerable to cyber-attacks, including spoofing, Denial of Service (DoS), and fuzzing attacks. This thesis thoroughly evaluates these vulnerabilities and the limitations of existing security frameworks like Message Authentication Codes (MACs) and encryption, advocating for the adoption of Intrusion Detection Systems (IDS) as a more practical solution for CAN bus security. The proposed IDS leverages advanced machine learning techniques to accurately detect intrusions, even under complex …

---

The Right To A Glass Box: Rethinking The Use Of Artificial Intelligence In Criminal Justice, Brandon L. Garrett, Cynthia Rudin

Faculty Scholarship

---

Artificial intelligence (“AI”) increasingly is used to make important decisions that affect individuals and society. As governments and corporations use AI more pervasively, one of the most troubling trends is that developers so often design it to be a “black box.” Designers create AI models too complex for people to understand or they conceal how AI functions. Policymakers and the public increasingly sound alarms about black box AI. A particularly pressing area of concern has been criminal cases, in which a person’s life, liberty, and public safety can be at stake. In the United States and globally, despite concerns that …

---

Machine Learning Based Three-Limb Core-Type Transformer Core Aspect Ratios Identification, Ananta Bijoy Bhadra

College of Graduate Studies: Theses & Dissertations

---

Power transformers are considered one of the key elements of electric grids. Transient studies include transformer transient analysis which is required for the continuous power supply. However, to perform the transient analysis, the details of the internal structure of the transformer are required which are unobtainable and considered as confidential information. Therefore, the application of topological-based transformer models is limited although the models can accurately represent the transformers. To address this concern, a novel approach utilizing Machine Learning (ML) to identify the core aspect ratios of the three-limb core-type transformer is introduced. The proposed approach, using only the voltage and …

---

Exploring Hedonic And Utilitarian Aspects Through Perceived Warmth In Human-Designed Vs. Ai-Generated Fashion, Dooyoung Choi, Ha Kyung Lee

Educational Leadership & Workforce Development Faculty Publications

---

Among various ways in which artificial intelligence (AI) is used in the fashion industry, its utilization in design has sparked public discussion about the potential replacement of human designers by AI. Along with this critical question, it is imminent to examine how consumers would respond to designs by AI. The purpose of this study is to explore consumers’ perceptions toward a fashion product labeled as generated by an AI system, comparing it to the same product labeled as designed by a human designer. Specifically, drawing from existing literature, we examine if the design source affects consumers’ perceptions of a product …

---

Enhancing Community College Leadership Development Through Ai: Enriching The Andragogical Approach, James Bartlett, Michelle Bartlett

Educational Leadership & Workforce Development Faculty Publications

---

This proposal is for a work-in-progress that proposes a study to explore the innovative use of Artificial Intelligence (AI), specifically ChatGPT, in advancing the development of training for leadership skills within community college settings. It aims to investigate how AI can be leveraged to provide a personalized and effective learning experience, aligning with the principles of andragogy to cater to adult learners in leadership roles. The study, currently in the data collection phase, anticipates revealing significant insights into the effectiveness of AI in professional development. It seeks to highlight the innovative aspects of AI integration in educational leadership, focusing on …

---