Digital Commons Network^™

Doctor Or Ai? Efficient Neural Network For Response Classification In Health Consultations, Olumide E. Ojo, Olaronke O. Adebanji, Hiram Calvo, Alexander Gelbukh, Anna Feldman, Ofir Ben Shoham

School of Computing Faculty Scholarship and Creative Works

Patients seek quality healthcare because they trust their doctors and the healthcare system. However, the use of AI models in medical consultations has undermined this trust. AI systems typically depend on accurate and large volumes of data for training, but in cases of insufficient or incorrect data, this can lead to incomplete or flawed outputs. The inaccuracies in the response generated by AI systems may result in biased outcomes, compromising patient care and further eroding the trust patients place in the healthcare system. In this paper, we describe an innovative approach to distinguishing between responses generated by AI and those …

Report On The Multilingual Euphemism Detection Task, Patrick Lee, Anna Feldman

School of Computing Faculty Scholarship and Creative Works

This paper presents the Multilingual Euphemism Detection Shared Task for the Fourth Workshop on Figurative Language Processing (FigLang 2024) held in conjunction with NAACL 2024. Participants were invited to attempt the euphemism detection task on four different languages (American English, global Spanish, Yorùbá, and Mandarin Chinese): given input text containing a potentially euphemistic term (PET), determine if its use is euphemistic or not. We present the expanded datasets used for the shared task, summarize each team’s methods and findings, and analyze potential implications for future research.

Mining Satellite Imagery For Offshore Wind Energy, Cristian C.Noriega Monsalve, Aparna S. Varde

School of Computing Faculty Scholarship and Creative Works

This work mines big data in Sentinel-1 satellite images to unveil geographical patterns in offshore wind energy. We leverage unsupervised machine learning to extract insights from a 44GB open access dataset for decision support in wind farm orientations to guide stakeholders. It has broader impacts of overcoming climate change by enhancing renewable energy.

Empirical-Likelihood-Based Inference For Partially Linear Models, Haiyan Su, Linlin Chen

School of Computing Faculty Scholarship and Creative Works

Partially linear models find extensive application in biometrics, econometrics, social sciences, and various other fields due to their versatility in accommodating both parametric and nonparametric elements. This study aims to establish statistical inference for the parametric component effects within these models, employing a nonparametric empirical likelihood approach. The proposed method involves a projection step to eliminate the nuisance nonparametric component and utilizes an empirical-likelihood-based technique, along with the Bartlett correction, to enhance the coverage probability of the confidence interval for the parameter of interest. This method demonstrates robustness in handling normally and non-normally distributed errors. The proposed empirical likelihood ratio …

Facilitating Covid Recognition From X-Rays With Computer Vision Models And Transfer Learning, Aparna S. Varde, Divydharshini Karthikeyan, Weitian Wang

School of Computing Faculty Scholarship and Creative Works

Multimedia data plays an important role in medicine and healthcare since EHR (Electronic Health Records) entail complex images and videos for analyzing patient data. In this article, we hypothesize that transfer learning with computer vision can be adequately harnessed on such data, more specifically chest X-rays, to learn from a few images for assisting accurate, efficient recognition of COVID. While researchers have analyzed medical data (including COVID data) using computer vision models, the main contributions of our study entail the following. Firstly, we conduct transfer learning using a few images from publicly available big data on chest X-rays, suitably adapting …

Predictive Analysis Of Bank Marketing For Financial Decision Support And Smart Economy, Hiral Vashi, Jyoti Yadav, Aparna S. Varde

School of Computing Faculty Scholarship and Creative Works

An active purpose of financial organizations is to preserve existing customers and accomplish imminent long-term ones. Bank marketing campaigns often depend on huge electronic data from a plethora of customers. Given the enormous and ever-growing data, it is not feasible for human analysts to procure interesting information and derive inferences for financial decision support. This motivates us to build a software tool for predictive analysis of bank marketing based on data mining from customer profiles. The success of telemarketing depends on various factors such the customers’ age, job, loan status etc. Hence, these factors constitute various features analyzed by data …

Ai-Based Modeling For Textual Data On Solar Policies In Smart Energy Applications, Sarahana Shrestha, Isabele Bittencourt, Aparna S. Varde, Pankaj Lal

School of Computing Faculty Scholarship and Creative Works

This study aims to examine sentiments and themes in deploying solar energy, after the recent enactment of the Clean Energy Act. It uses text on solar energy from public dockets and open access social media platforms to fathom mass opinion. It is crucial for policymakers / stakeholders in smart and renewable energy to address challenges of energy efficiency and equity. While we deal with solar energy, many claims here are valid for other sources such as offshore wind. We propose to harness the AI-based models of VADER, SentiWordNet and TextBlob for sentiment analysis, and Latent Dirichlet Allocation (LDA) for topic …

Audiovisual Multimodal Cough Data Analysis For Tuberculosis Detection, Jyoti Yadav, Aparna S. Varde, Hao Liu, George Antoniou, Lei Xie

School of Computing Faculty Scholarship and Creative Works

Early detection of tuberculosis (TB) remains a critical challenge. This research presents a novel approach leveraging audio information from cough recordings for predicting TB. We move beyond traditional image-based methods (such as sputum smear microscopy and chest X-rays) and explore the feasibility of leveraging cough recordings for differentiating TB cases. Two main audio processing techniques, i.e. Mel-Spectrograms and Mel-Frequency Cepstral Coefficients (MFCCs), are utilized to feature encoding audio recording into deep learning models for TB classification. Our proposed methods leverage a large challenge dataset encompassing clinical data from over 1,105 participants and over 502,252 cough recordings. Notably, a simple 1D …

A Speech And Facial Information Based Emotion Recognition System Of Collaborative Robot For Empathic Human-Robot Collaboration, Jianna Loor, Jordan Murphy, Rui Li

School of Computing Faculty Scholarship and Creative Works

A robot's ability to effectively recognize human emotions is critical in human-robot collaboration. However, most of the current collaborative robots were designed to improve productivity. Few of these robots consider human emotions. This situation would cause humans to be unwilling to work with robots for a long time. Motivated by this gap, this research developed a human emotion recognition system for enhancing the interaction abilities of collaborative robots. In this project, both speech and facial information were analyzed for robust human emotion recognition in complex working environments like manufacturing assembly environments. In the experiment, the developed system has been tested …

A Survey: Emerging Cybersecurity Threats In Driverless Cars, Vaibhavi Tiwari, Dharshana Rajasekar, Jiayin Wang

School of Computing Faculty Scholarship and Creative Works

In light of the increasing adoption of autonomous vehicles in our transportation networks, it is crucial to emphasize the significance of implementing strong cybersecurity protocols. These self-driving cars, which heavily depend on state-of-the-art sensors, artificial intelligence (AI), and complex communication networks, represent a remarkable advancement in technology. However, they also bring about new vulnerabilities. While it is true that autonomous vehicles have been shown to be statistically safer than traditional cars, it is important to acknowledge the growing concern surrounding cyber threats and their potential impact on the safety and reliability of these vehicles. This paper provides a thorough examination …

Using Generative Large Language Models For Hierarchical Relationship Prediction In Medical Ontologies, Hao Liu, Shuxin Zhou, Zhehuan Chen, Yehoshua Perl, Jiayin Wang

School of Computing Faculty Scholarship and Creative Works

This study extends the exploration of ontology enrichment by evaluating the performance of various open-sourced Large Language Models (LLMs) on the task of predicting hierarchical relationships (IS-A) in medical ontologies including SNOMED CT Clinical Finding and Procedure hierarchies and the human Disease Ontology. With the previous finetuned BERT models for hierarchical relationship prediction as the baseline, we assessed eight open-source generative LLMs for the same task. We observed only three models, without finetuning, demonstrated comparable or superior performance compared to the baseline BERT -based models. The best performance model OpenChat achieved a macro average F1 score of 0.96 (0.95) on …

Using Software Metrics For Predicting Vulnerable Classes In Java And Python Based Systems, Kazi Zakia Sultana, Vaibhav Anu, Tai Yin Chong

School of Computing Faculty Scholarship and Creative Works

[Context:] Failure to predict vulnerability in the earlier stage of development can cause vulnerable code being written and deployed in the final software product. Vulnerability prediction using software metrics as features can support the discovery process by localizing vulnerable code. Existing studies have successfully employed metrics for vulnerability prediction for some platforms (C/C++ or Java projects). We propose that a comparative evaluation of how these metrics perform in projects of different languages can help the developers in deciding whether metrics-based prediction approach can be effective in their own project’s context. [Objective:] The purpose of this research is to analyze/compare the …

Turkish Delights: A Dataset On Turkish Euphemisms, Hasan Can Biyik, Patrick Lee, Anna Feldman

School of Computing Faculty Scholarship and Creative Works

Euphemisms are a form of figurative language relatively understudied in natural language processing. This research extends the current computational work on potentially euphemistic terms (PETs) to Turkish. We introduce the Turkish PET dataset, the first available of its kind in the field. By creating a list of euphemisms in Turkish, collecting example contexts, and annotating them, we provide both euphemistic and non-euphemistic examples of PETs in Turkish. We describe the dataset and methodologies, and also experiment with transformer-based models on Turkish euphemism detection by using our dataset for binary classification. We compare performances across models using F1, accuracy, and precision …

Securing Bystander Privacy In Mixed Reality While Protecting The User Experience, Matthew Corbett, Brendan David-John, Jiacheng Shang, Y. Charlie Hu, Bo Ji

School of Computing Faculty Scholarship and Creative Works

The modern mixed-reality devices that make the Metaverse viable require vast information about the physical world and can also violate the privacy of unsuspecting or unwilling bystanders. We provide an introduction to the problem, existing solutions, and avenues for future research.

Personalizing Text-To-Image Diffusion Models By Fine-Tuning Classification For Ai Applications, Rafael Hidalgo, Nesreen Salah, Rajiv Chandra Jetty, Anupama Jetty, Aparna S. Varde

School of Computing Faculty Scholarship and Creative Works

Stable Diffusion is a captivating text-to-image model that generates images based on text input. However, a major challenge is that it is pretrained on a specific dataset, limiting its ability to generate images outside of the given data. In this paper, we propose to harness two models based on neural networks, Hypernetworks and DreamBooth, to allow the introduction of any image into Stable Diffusion, addressing versatility with minimal additional training data. This work targets AI applications such as augmenting next-generation multipurpose robots, enhancing human-robot collaboration, feeding intelligent tutoring systems, training autonomous cars, injecting subjects for photo personalization, producing high quality …

Uni Scholarworks Readership Snapshot, December 2023, Bepress

Library Documents & Reports (entire collection)

No abstract provided.

Why Do Judges Compete For Cases?, Jonas Anderson, Paul R. Gugliuzza

Utah Law Faculty Scholarship

It’s not just parties to litigation who forum shop. Sometimes judges forum sell by trying to attract cases to their courts. This judicial competition for cases has been documented in areas ranging from bankruptcy to antitrust to, most infamously, patent law. Despite the ubiquity of judicial case-seeking behavior, one important question remains unanswered: why? Why do judges—particularly federal district judges, who enjoy life tenure and are paid fixed salaries—seek out more work, especially in cases that can be quite complex?

This article answers that question by developing a first-of-its-kind model of judicial behavior in the context of court competition. The …

Forensic Genetics In The Shadows, Teneille R. Brown, Sarah Duensing, Bob Wong

Utah Law Faculty Scholarship

This article examines the controversial and growing practice of law enforcement agencies searching clinical and public health genetic databases—without a warrant or consent. While police have previously used online public genealogy databases for this purpose, our article describes how they are secretly accessing private genetic information from newborn screening programs and medical tests. We argue this raises serious ethical and legal concerns, blurring the line between healthcare and law enforcement and infecting clinical encounters with the goals of prosecution. This in turn may discourage people from seeking important medical care due to distrust and privacy concerns.

To explore public attitudes …

Health Law And Bigotry Distractions, Daniel G. Aaron, Leslie Francis

Utah Law Faculty Scholarship

Bigotry distractions are strategic invocations of racism, transphobia, or negative stigma toward other marginalized groups to shape political discourse. Although the vast majority of Americans agree on large policy issues ranging from reducing air pollution to prosecuting corporate crime, bigotry distractions divert attention from areas of agreement toward divisive identity issues. This article explores how the nefarious targeting of identity groups through bigotry distractions may be the tallest barrier to health reform, and social change more broadly. The discussion extends the literature on dog whistles, strategic racism, and scapegoating.

Exploring The Impact Of Diabetes On Feet: Analysis Of Foot Ulcers With A Focus On Eczema-Related Considerations, Namlhun Jachung

Pitzer Senior Theses

Diabetes mellitus, a chronic metabolic disorder, has far-reaching consequences on various organ systems, with the lower extremities being particularly susceptible to complications. This study delves into the profound effects of diabetes on the feet, specifically examining the interplay between diabetes-induced foot ulcers, and potential complications arising from coexisting eczema. Two distinct experiments were designed to investigate critical aspects of this complex relationship.

The first experiment aims to compare Transepidermal Water Loss (TEWL) levels among diabetic patients with and without eczema. The study involves a cohort of diabetic patients, stratified based on the presence or absence of eczema, and measured TEWL …

Can Litigation Analytics Tell Us What Became Of The 2015 Proportionality Amendments To The Federal Rules Of Civil Procedure?, Patricia W. Moore

Faculty Articles

In 2015, the Federal Rules of Civil Procedure pertaining to discovery were amended for the seventh time in 40 years–part of a cyclic effort to address the so-called “cost and delay” of litigation. The centerpiece of the amendments was the reconfigured requirement that requested discovery be “proportional to the needs of the case,” in addition to being relevant and nonprivileged. The concept of “proportionality” crystallized the 2015 amendments in a single mantra. The proposed amendments inspired passionate and polarized public reactions. Plaintiffs’ attorneys opposed them as an impediment to obtaining the discovery they needed to prove their case, particularly in …

A Haven For Traffickers: How The United States Provides A Legal Safe Haven For Businesses That Rely On Forced Labor In The International Supply Chain, Ramona L. Lampley

Faculty Articles

Congress enacted the Trafficking Victims Protection Act ("TVPRA" or "Act") in 2000, which, through its amendments, gives victims of human trafficking, including forced labor or slave labor, a private right of action against those who knowingly benefit from the abusive labor practices perpetrated on them. Even though slave labor, particularly child labor, is a perceived evil in the foreign supply chains of many domestic companies, courts appear uncomfortable with the some of the civil-liability provisions of the TVPRA. This Article examines recent cases brought under the TVPRA, and how, in some cases, courts have eviscerated the private right of action …

Moral Panic And The First Amendment, Michael L. Smith

Faculty Articles

Debates over free speech in the United States frequently see advocates of strong, broad protections at odds with those who argue that unfettered free speech tends to harm society's most vulnerable. Free speech advocates invoke the marketplace of ideas and argue that the antidote to false or harmful speech is more speech. In response, critics contend that speech itself causes harm and chills counter-speech effectively excluding marginalized groups, including women and LGBTQ people, from discourse altogether. These critics support limitations on robust free speech doctrine targeting speech that harms marginalized communities.

This Article identifies a significant wrinkle in this narrative: …

Oil & Gas And Corpus Linguistics, Chad J. Pomeroy

Faculty Articles

Oil and gas law focuses on the subsurface mineral estate, which is just what it sounds like: the estate that entitles one to the subsurface, to the stuff that is underground. That, of course, includes the minerals under a given piece of property, and the value associated with that is enormous. So, it is a big deal to have the right to minerals, and, if I convey to you "the mineral estate" of Blackacre or "the minerals under Blackacre" or something similar, then I have given you something very significant, indeed. As such, it is critical to know just what …

Arbitrary And Capricious X Artificial Intelligence, Zoe Niesel

Faculty Articles

The "arbitrary and capricious" review standard has been interpreted to govern the judicial review of agency factual findings that are produced through informal rulemaking or informal adjudication. In contrast, agency factual findings that are produced through formal rulemaking or adjudication will be reviewed under the Administrative Procedure Act, Section 706(2)(E), which states that such findings can be set aside if they are "unsupported by substantial evidence." While the standards technically vary-factual findings that are the product of informal procedures will warrant arbitrary and capricious review, while factual findings that are the product of formal procedures will warrant substantial evidence review …

Enhancing Health Education: The Role Of Social Emotional Learning In Prek-12 Students' Well-Being, Elena Saldutti, Joseph Donnelly, Judy Lobianco, Mary Connolly

Department of Public Health Scholarship and Creative Works

Purpose: This commentary delves into the profound impact of Social Emotional Learning (SEL), particularly through the lens of the Collaborative for Academic, Social, and Emotional Learning (CASEL), on Health Education, elucidating its potential to nurture the well-being of PreK-12 students. Results: Students experiencing comprehensive skills-based health/SEL education gain knowledge, skills, and competencies that are used within and beyond the classroom, fostering the development of healthier decision-making, bolstering self-esteem, and enriching the emotional and mental wellness of students. Health educators have the opportunity to utilize CASEL's SEL Competencies in conjunction with the National Health Education Standards, as both are mutually aligned …

Milk Tooth, 2024, Bemidji State University, Eddie Anderson, Caroline Bender, Connor Brahms, Kendra Carriere, Shawn Cruze, Madelyn Dakken, Liz Fisher, Donovan Floyd, Brooke Froehle, Eve Gwendolyn Hansen, Gordon Hess, Sadie House, Iris Jensen, Lacey Lacey, Hannah Lewis, Marissa Marxhausen, Izzy Mcclintic, Jenika Moen, Emma Niessink, Grace Roecker, Lauren Winkelman, Nicholas Wolter

Milk Tooth

"Writings by Bemidji State University Students."  Sponsored by the Bemidji State University English Department.

Chicago Must End The Use Of Shotspotter To Protect Human Rights, Sarah Dávila

Faculty White Papers

No abstract provided.

Why Should Early-Career Scientists Publish In Society Journals, Stephen K. Dolan, Lori D. Banks, Wenqi Yu

Molecular Biosciences Faculty Publications

In this editorial, written by early-career scientists, we advocate for the invaluable role of society journals in our scientific community. By choosing to support these journals as authors, peer reviewers, and as editors, we can reinforce our academic growth and benefit from their re-investment back into the scientific ecosystem. Considering the numerous clear merits of this system for future generations of microbiologists and more broadly, society, we argue that early-career researchers should publish our high-quality research in society journals to shape the future of science and scientific publishing landscape.

The Inaugural Mbio Junior Editorial Board—Lessons Learned And The Path Forward Toward Improving The Peer Review Process, Cynthia Ayefoumi Adinortey, Stephen K. Dolan, Sarah Doore, Rebeccah Lijek, Diana Priscila Pires, Wenqi Yu, Elizabeth B. Draganova, Lennart Schada Von Borzyskowski

Molecular Biosciences Faculty Publications

The inaugural Junior Editorial Board (JEB) of mBio consisted of 64 early-career researchers active from 2022 to 2023. The goal of the JEB was to train early-career researchers in the art of peer review under the guidance of experienced editors. JEB members gained hands-on experience in peer review by participating in modules detailing the publishing process through the lenses of the journal, editor, and reviewer. Ultimately, JEB members applied this new knowledge by reviewing mBio manuscripts. Here, we summarize the background, the mission, and the achievements of the first mBio JEB. We also include possible trajectories for the future editions …