Digital Commons Network^™

From Biased Data Inputs To Your Discriminatory Diagnosis Outputs: A Review Of Legal Liability For Artificial Intelligence In Healthcare, Amber Bolden

Michigan Technology Law Review

While health disparities in America occur due to non-medical circumstances, certain protected classes experience healthcare disparities due to the biases of medical professionals. Biased diagnoses, both intentional or unintentional, have existed throughout the history of the medical profession. That those biases are becoming data for training algorithms raises concerns as the medical field increasingly incorporates and standardizes artificial and augmented intelligence in patient diagnosis and treatment. Currently unregulated but with lifedetermining potential, artificial intelligence (AI) when used in patient treatment leads to important questions: should the doctor, the provider, or the AI developers be liable, and for what? Section II …

Left, Then Right Internal Carotid Artery Dissection: A Case Report, Jeffrey M. Kalczynski, John Douds, Michael E. Silverman

SKMC Student Presentations and Publications

INTRODUCTION: We present a unique case of a patient who presented to the emergency department with stroke-like symptoms found to have a spontaneous, left-sided internal carotid artery dissection (ICAD).

CASE REPORT: The patient was treated successfully with thrombectomy and subsequently developed contralateral symptoms caused by a right-sided ICAD. This was managed with a second contra-lateral thrombectomy. The patient's course was complicated by persistent and mild hypotension, postulated to be secondary to bilateral carotid baroreceptor trauma from the dissections.

CONCLUSION: This case highlights the importance of close neurological monitoring for patients, preferably in a neurologic critical care setting, during and after …

Large Language Models For Software Engineering: A Systematic Literature Review, Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, Haoyu Wang

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have significantly impacted numerous domains, including Software Engineering (SE). Many recent publications have explored LLMs applied to various SE tasks. Nevertheless, a comprehensive understanding of the application, effects, and possible limitations of LLMs on SE is still in its early stages. To bridge this gap, we conducted a Systematic Literature Review (SLR) on LLM4SE, with a particular focus on understanding how LLMs can be exploited to optimize processes and outcomes. We selected and analyzed 395 research articles from January 2017 to January 2024 to answer four key Research Questions (RQs). In RQ1, we categorize different LLMs …

Defending Large Language Models Against Jailbreak Attacks Via Layer-Specific Editing, Wei Zhao, Zhe Li, Yige Li, Jun Sun, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) are increasingly being adopted in a wide range of realworld applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts even when aligned via Reinforcement Learning from Human Feedback or supervised fine-tuning. While existing defense methods focus on either detecting harmful prompts or reducing the likelihood of harmful responses through various means, defending LLMs against jailbreak attacks based on the inner mechanisms of LLMs remains largely unexplored. In this work, we investigate how LLMs respond to harmful prompts and propose a novel defense method termed Layer-specific Editing (LED) …

Please Understand My Disability: An Analysis Of Youtubers’ Discourse On Disability Challenges, Shuo Niu

Computer Science

Video-sharing platforms offer a unique avenue for people with disabilities (PWDs) to highlight their experiences, including the challenges and accessibility barriers they face. While creators with disabilities effectively use these platforms to share their life struggles and advocate for societal changes, the scope of research exploring the nature of the discourse activities related to disability challenges remains limited. Our study addresses this gap by conducting a comprehensive qualitative content analysis of 468 videos posted by YouTubers with a range of disabilities, including vision, speech, mobility, hearing, and cognitive and neural impairments. Our findings reveal a predominant discussion on stigma and …

Unlocking Potential: Analyzing The Content, Style, Structure, And Interactivity Of Mesonets As Operational Dashboards, Savannah Olivas, Jeannette Sutton, Michele K. Olson

Emergency Preparedness, Homeland Security, and Cybersecurity Faculty Scholarship

Emergency managers need data and information to make life-saving decisions on behalf of the public. Operational dashboards, if designed appropriately, can provide this information in a central location and reduce cognitive demands during decision-making. Mesonet websites can serve as a type of operational dashboard that has the potential to provide the meteorological data necessary for emergency managers to make decisions. In this study, we use quantitative content analysis to examine the content, style, structure, and interactivity of 18 Mesonet websites from across the contiguous United States. We find that Mesonet websites vary in the type and amount of content they …

Cirp: Cross‑Item Relational Pre‑Training For Multimodal Product Bundling, Yunshan Ma, Yingzhi He, Wenjun Zhong, Xiang Wang, Roger Zimmermann, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Product bundling has been a prevailing marketing strategy that is beneficial in the online shopping scenario. Effective product bundling methods depend on high-quality item representations capturing both the individual items' semantics and cross-item relations. However, previous item representation learning methods, either feature fusion or graph learning, suffer from inadequate cross-modal alignment and struggle to capture the cross-item relations for cold-start items. Multimodal pre-train models could be the potential solutions given their promising performance on various multimodal downstream tasks. However, the cross-item relations have been under-explored in the current multimodal pre-train models.To bridge this gap, we propose a novel and simple …

Ultra-High Resolution Image Segmentation Via Locality-Aware Context Fusion And Alternating Local Enhancement, Wenxi Liu, Qi Li, Xindai Lin, Weixiang Yang, Shengfeng He, Yuanlong Yu

Research Collection School Of Computing and Information Systems

Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultra-high resolution image is partitioned into regular patches for local segmentation and then the local results are merged into a high-resolution semantic mask. In particular, we introduce a novel locality-aware context fusion based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations. Additionally, we present the alternating local enhancement …

Lr-Auth: Towards Practical Implementation Of Implicit User Authentication On Earbuds, Changshuo Hu, Xiao Ma, Xinger Huang, Yiran Shen, Dong Ma

Research Collection School Of Computing and Information Systems

The increasing use of earbuds in applications like immersive entertainment and health monitoring necessitates effective implicit user authentication systems to preserve the privacy of sensitive data and provide personalized experiences. Existing approaches, which leverage physiological cues (e.g., jawbone structure) and behavioral cues (e.g., gait), face challenges such as limited usability, high delay and energy overhead, and significant computational demands, rendering them impractical for resource-constrained earbuds. To address these issues, we present LR-Auth, a lightweight, user-friendly implicit authentication system designed for various earbud usage scenarios. LR-Auth utilizes the modulation of sound frequencies by the user's unique occluded ear canal, generating user-specific …

Multimodal Misinformation Detection By Learning From Synthetic Data With Multimodal Llms, Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang

Research Collection School Of Computing and Information Systems

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even …

Thoughts To Target: Enhance Planning For Target-Driven Conversation, Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie

Research Collection School Of Computing and Information Systems

In conversational AI, large-scale models excel in various tasks but struggle with target-driven conversation planning. Current methods, such as chain-of-thought reasoning and tree-search policy learning techniques, either neglect plan rationality or require extensive human simulation procedures. Addressing this, we propose a novel two-stage framework, named EnPL, to improve the LLMs’ capability in planning conversations towards designated targets, including (1) distilling natural language plans from target-driven conversation corpus and (2) generating new plans with demonstration-guided in-context learning. Specifically, we first propose a filter approach to distill a high-quality plan dataset, ConvPlan1. With the aid of corresponding conversational data and support from …

Selective Annotation Via Data Allocation: These Data Should Be Triaged To Experts For Annotation Rather Than The Model, Chen Huang, Yang Deng, Wenqiang Lei, Jiancheng Lv, Ido Dagan

Research Collection School Of Computing and Information Systems

To obtain high-quality annotations under limited budget, semi-automatic annotation methods are commonly used, where a portion of the data is annotated by experts and a model is then trained to complete the annotations for the remaining data. However, these methods mainly focus on selecting informative data for expert annotations to improve the model predictive ability (i.e., triage-to-human data), while the rest of the data is indiscriminately assigned to model annotation (i.e., triage-to-model data). This may lead to inefficiencies in budget allocation for annotations, as easy data that the model could accurately annotate may be unnecessarily assigned to the expert, and …

Navigating Weight Prediction With Diet Diary, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Current research in food analysis primarily concentrates on tasks such as food recognition, recipe retrieval and nutrition estimation from a single image. Nevertheless, there is a significant gap in exploring the impact of food intake on physiological indicators (e.g., weight) over time. This paper addresses this gap by introducing the DietDiary dataset, which encompasses daily dietary diaries and corresponding weight measurements of real users. Furthermore, we propose a novel task of weight prediction with a dietary diary that aims to leverage historical food intake and weight to predict future weights. To tackle this task, we propose a model-agnostic time series …

Ai And Creativity: Effects Of Culture And Task Emotiveness In Human-Ai Collaboration, Choon Ngee Tan

Dissertations and Theses Collection (Open Access)

Creativity is the driving force behind innovation, propelling individuals and societies toward progress by generating novel ideas and groundbreaking solutions. The emergence of generative AI models, exemplified by GPT-3, offers opportunities to enhance human creativity. This paper explores the potential for unprecedented breakthroughs through the synergy between human intuition and AI-driven creativity, providing practical guidance on leveraging AI to amplify creative capacities. Study 1 finds that AI models trained on data from the U.S. and Chinese cultures exhibit cultural norms, values and cognition of those cultures. Study 2 finds that when humans and AI models of the same culture collaborate …

Tackling Toxicity And Harassment In Online Environments Through The Use Of Artificial Intelligence, Heba Saleous

Dissertations

With the increase in popularity of online communities, such as social media platforms, online games, and chatroom servers, there is a need to improve chat and content moderation. Platforms have reported an increase in the prevalence of toxic behavior and hate speech. Meanwhile, moderators are reporting difficulties in keeping up with the amount of data to check as well and the type of content they are exposed to, which further harms their own mental health. The main objective of this work is to address the challenges that exist within online communities with the rising prevalence of hate speech. Additionally, some …

Towards Trustworthy Recommendation Systems: Beyond Collaborative Filtering, Zhongzhou Liu, Zhongzhou

Dissertations and Theses Collection (Open Access)

Recommendation systems have been widely deployed in various scenarios and applications, such as e-commerce, social media, and streaming services. Recommendation systems have significantly influenced how we interact with various items in a wide range of platforms. They help users discover their preferred items and provide efficient and enjoyable experiences. They also help item providers and platforms to quickly find their potential customers, thus increasing the total revenue and user engagement.

The majority of existing recommendation systems merely focus on the matching between users and items, aiming for higher recommendation accuracy. Collaborative filtering is regarded as one of the most successful …

Effect Of Virtual Reality Technology On Computer Science/Engineering Based Laboratories Education – A Case Study, Saeed Salem Al Shebli

Theses

The rapid growth in mobile applications raises critical concerns about the security of apps and users' privacy, especially in permission control. Mobile apps access sensitive information of users, and the current cybersecurity landscape faces a huge challenge in ensuring the least required permissions are granted. This research focuses on designing an advanced permission recommendation system that couples the strengths of Natural Language Processing (NLP) and Machine Learning (ML) in solving most of the existing gaps in permission management, thus guiding which permissions are mostly needed by Android applications.

The research thus follows a multi-classification approach, integrating state-of-the-art ML techniques with …

Enhancedbert: A Python Software Tailored For Arabic Word Sense Disambiguation, Sanaa Kaddoura, Reem Nassar

All Works

EnhancedBERT is a software framework designed to disambiguate Arabic polysemous terms using advanced natural language processing techniques. It integrates transformer architectures with ensemble methods to achieve high performance in understanding and processing Arabic text. The framework provides a flexible pipeline that can be directly utilized or fine-tuned according to specific needs. EnhancedBERT stands out for its ease of use, leveraging transformer-based models combined with ensemble strategies to provide superior contextual understanding. This contextual awareness makes it an invaluable tool for researchers and practitioners tackling complexities in Arabic language processing.

Unveiling Scientic Articles From Paper Mills With Provenance Analysis, João Phillipe Cardenuto, Daniel Moreira, Anderson Rocha

Computer Science: Faculty Publications and Other Works

The increasing prevalence of fake publications created by paper mills poses a significant challenge to maintaining scientific integrity. While integrity analysts typically rely on textual and visual clues to identify fake articles, determining which papers merit further investigation can be akin to searching for a needle in a haystack, as these fake publications have non-related authors and are published on non-related venues. To address this challenge, we developed a new methodology for provenance analysis, which automatically tracks and groups suspicious figures and documents. Our approach groups manuscripts from the same paper mill by analyzing their figures and identifying duplicated and …

Unveiling Scientific Articles From Paper Mills With Provenance Analysis, João Phillipe Cardenuto, Daniel Moreira, Anderson Rocha

Computer Science: Faculty Publications and Other Works

The increasing prevalence of fake publications created by paper mills poses a significant challenge to maintaining scientific integrity. While integrity analysts typically rely on textual and visual clues to identify fake articles, determining which papers merit further investigation can be akin to searching for a needle in a haystack, as these fake publications have non-related authors and are published on non-related venues. To address this challenge, we developed a new methodology for provenance analysis, which automatically tracks and groups suspicious figures and documents. Our approach groups manuscripts from the same paper mill by analyzing their figures and identifying duplicated and …

Bridging The Protection Gap: Innovative Approaches To Shield Older Adults From Ai-Enhanced Scams, Ld Herrera, London Van Sickle, Ashley L. Podhradsky

Research & Publications

Artificial Intelligence (AI) is rapidly gaining popularity as individuals, groups, and organizations discover and apply its expanding capabilities. Generative AI creates or alters various content types including text, image, audio, and video that are realistic and challenging to identify as AI-generated constructs. However, guardrails preventing malicious use of AI are easily bypassed. Numerous indications suggest that scammers are already using AI to enhance already successful scams, improving scam effectiveness, speed and credibility, while reducing detectability of scams that target older adults, who are known to be slow to adopt new technologies. Through hypothetical cases analysis of two leading scams, the …

Learning Peer Support Interactions Via Bi-Lstm Graph Neural Networks For Suicide Risk Prediction, Harikrishna Marampelly

USF Tampa Graduate Theses and Dissertations

Suicide prevention through early detection using social media data has been widely studied. However, the critical role of peer support interactions among individuals with similar mental disorders has not been deeply investigated or explored. In this study, we explore peer interactions in online communities for individuals with bipolar disorder and leverage this information to predict suicide risk levels. We propose a model that uses contextualized posts and comments along with their sentiment features. By embedding these features into a peer support network, our model captures peer interactions and predicts suicide risk levels using the bidirectional LSTM Graph Neural Networks (Bi-LSTM …

Vulnerability Discovery On Broadcom Devices With Qemu, Christian Shane Douglas Little

USF Tampa Graduate Theses and Dissertations

System-on-chip (SoC) devices in the form of routers, access points, and smart appliances have become an increasingly prevalent aspect of our infrastructure. Performing vulnerability research on these devices may be exceptionally difficult given the on-hardware limitations, inability to guarantee certain aspects of the system, and lack of information when the appliance’s source code is not available.In this thesis, we present Broadfeather, a QEMU-based emulation target, and framework for dynamic analysis and instrumentation. While Broadfeather supports data types shared across many chips under the Broadcom umbrella, it is primarily geared towards the BCM6755 Wi-Fi 6E capable chipset. Broadfeather also features the …

Photoluminescence Intensity Enhancement And Stability In Cdte/Sio2 Quantum Dots Through Water Molecule Adsorption And Trap Passivation, Daniil S. Daibagya, Ivan A. Zakharchuk, Sergei A. Ambrozevich, Mikhail S. Smirnov, Anna V. Osadchenko, Oleg V. Ovchinnikov, Alexandr S. Selyukov

Karbala International Journal of Modern Science

The study of the luminescence photostability for colloidal nanocrystals is an important task since the understanding of the corresponding physical processes advances new electronic devices based on semiconductor nanoparticles as well as other important applications such as biomarkers. In this paper, we provide the first study and comprehensive analysis of the photostability of the luminescent properties for colloidal CdTe/SiO₂ core/shell quantum dots prepared by an aqueous-based method. The quantum dots were exposed to continuous laser radiation during two time intervals with prolonged break in between. The photoluminescence intensity of the quantum dots increased over time under continuous laser irradiation. …

Removal Of Selenium Ions From Contaminated Aqueous Solutions By Adsorption Using Lemon Peels As A Non-Conventional Medium, Alanood A. Alsarayreh, Suha Anwer Ibrahim, Salem Jawad Alhamd, Thekra Atta Ibrahim, Mohammed Nsaif Abbas

Karbala International Journal of Modern Science

The disposal of heavy metals from various activities has become a pervasive issue. The investigation of sustain-able, low-cost adsorbents for the remediation of these hazardous pollutants has been widely disregarded. This research emphasizes the recovery of selenium ions from contaminated water using lemon peels as a cost-effective adsorbent. The adsorption was explored in a batch unit under various operational parameters, including initial selenium concentration (1-90 ppm), pH (1-11), agitation speed (100-500 rpm), adsorbent dose (0.4-5.5 g), contact time (5-180 minutes), and temperature (25-55 °C). The BET surface area of the lemon peels was found to be 27.86 m²/g before adsorption …

Challenges, Countermeasures, And Forward-Looking Technologies For Cyber Society Governance From System Security Perspective, Hongbin Pei, Jingxin Hai, Pinghui Wang, Xiaohong Guan

Bulletin of Chinese Academy of Sciences (Chinese Version)

With the rapid development and widespread application of artificial intelligence and information technologies, the cyber society has evolved into a new form featuring human-machine integration, mass interaction, and intelligent interconnection. While transforming human life and production, it has also brought security risks such as cyberattacks, privacy breaches, online rumors, and information cocoons, posing serious challenges to social order. Cyber society governance has thus become a key component of national governance modernization. This study proposes the STC governance paradigm from a system security perspective, covering three key dimensions: security (cyber infrastructure security), trustworthiness (credibility of cyber entity identities), and controllability (content …

The Evolution Of Community Engagement Strategies In The Context Of Advancements In Artificial Intelligence Technologies, Erika Grodzki, Stefanie Powers, Gary Carlin, Hung Chum Kao

Faculty and Staff Publications & Presentations

As the AI landscape continues to evolve, the need for communities to nurture, inform, and challenge these technologies becomes paramount. This panel addresses the importance of traditional and AI driven strategies in terms of community engagement. Four case studies are reviewed to show how AI technologies are being implemented in communities. While AI offers numerous benefits, it is important not to overlook the value of human interaction in building and maintaining thriving community engagement. AI cannot replicate emotional intelligence and authentic relationship building - critical components of community engagement.

Personalized Learning Path Problem Variations: Computational Complexity And Ai Approaches, Sean A. Mochocki, Mark Reith, Brett J. Borghetti, Gilbert L. Peterson, John Jasper, Laurence D. Merkle

Faculty Publications

E-learning courses often suffer from high dropout rates and low student satisfaction. One way to address this issue is to use personalized learning paths (PLPs), which are sequences of learning materials that meet the individual needs of students. However, creating PLPs is difficult and often involves combining knowledge graphs (KGs), student profiles, and learning materials. Researchers typically assume that the problem of creating PLPs belong to the nondeterministic polynomial (NP)-hard class of computational problems. However, previous research in this field has neither defined the different variations of the PLP problem nor formally established their computational complexity. Without clear definitions of …

Tradeoffs Of Generalization, Kyra M. Abrams, Peter T. Darch

I-GUIDE Forum

Models used in geospatial data science are often built and optimized for a specific local context, such as a particular location at a point in time. However, upon publication, these models may be generalized beyond this context, reused in research simulating or predicting other times and places. Without sufficient information or documentation, bias embedded in these models can in turn result in bias in the reuser’s research outputs. Drawing on a long-term qualitative case study of aging dams researchers and developers of models used by these researchers, we find significant documentation gaps. We combine a literature-based genealogy with interviews with …

Treatment Recommendation Using Bert Personalization, J Jayapradha, Yukta Kulkarni, Lakshmi Vadhanie G, Palanichamy Naveen, Elham Abdulwahab Anaam

Journal of Informatics and Web Engineering

This research work develops a new framework that combines patient feedback with evidence-based best practices across disease states to improve drug recommendations. It employs BERT as its free-text processing engine to deal with sentiment judgment and classification. The functionality of the system, named `PharmaBERT`, includes acceptance of drug review data as a comprehensive input, drug categorization when dealing with a wide range of treatments and fine-tuning the BERT-based model for gaining positive or negative sentiment towards specific medications. PharmaBERT categorizes various drugs and fine-tunes the BERT structure to perceive lots of possible sentiments for specific medications. Consequently, PharmaBERT brings all …