Physical Sciences and Mathematics Commons^™

The Vulnerabilities Of Artificial Intelligence Models And Potential Defenses, Felix Iov

Cybersecurity Undergraduate Research Showcase

The rapid integration of artificial intelligence (AI) into various commercial products has raised concerns about the security risks posed by adversarial attacks. These attacks manipulate input data to disrupt the functioning of AI models, potentially leading to severe consequences such as self-driving car crashes, financial losses, or data breaches. We will explore neural networks, their weaknesses, and potential defenses. We will discuss adversarial attacks including data poisoning, backdoor attacks, evasion attacks, and prompt injection. Then, we will explore defense strategies such as data protection, input sanitization, and adversarial training. By understanding how adversarial attacks work and the defenses against them, …

Improving Educational Delivery And Content In Juvenile Detention Centers, Yomna Elmousalami

Undergraduate Research Symposium

Students in juvenile detention centers have the greatest need to receive improvements in educational delivery and content; however, they are one of the “truly disadvantaged” populations in terms of receiving those improvements. This work presents a qualitative data analysis based on a focus group meeting with stakeholders at a local Juvenile Detention Center. The current educational system in juvenile detention centers is based on paper worksheets, single-room style teaching methods, outdated technology, and a shortage of textbooks and teachers. In addition, detained students typically have behavioral challenges that are deemed "undesired" in society. As a result, many students miss classes …

Learning Optimal Inter-Class Margin Adaptively For Few-Shot Class-Incremental Learning Via Neural Collapse-Based Meta-Learning, Hang Ran, Weijun Li, Lusi Li, Songsong Tian, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot …

Osfs-Vague: Online Streaming Feature Selection Algorithm Based On A Vague Set, Jie Yang, Zhijun Wang, Guoyin Wang, Yanmin Liu, Yi He, Di Wu

Computer Science Faculty Publications

Online streaming feature selection (OSFS), as an online learning manner to handle streaming features, is critical in addressing high-dimensional data. In real big data-related applications, the patterns and distributions of streaming features constantly change over time due to dynamic data generation environments. However, existing OSFS methods rely on presented and fixed hyperparameters, which undoubtedly lead to poor selection performance when encountering dynamic features. To make up for the existing shortcomings, the authors propose a novel OSFS algorithm based on vague set, named OSFS-Vague. Its main idea is to combine uncertainty and three-way decision theories to improve feature selection from the …

Quantification Of Landside Congestion In Ports: An Analysis Based On Gps Data, Kumushini Thennakoon, Namal Bandaranayake, Senevi Kiridena, Asela K. Kulatunga

Computer Science Faculty Publications

Hinterland transport is a critical segment in maritime cross-border logistics, which links the end-users of global supply chains to the maritime segment. Truck-based hinterland transport is known to cause congestion in and around ports. This study aimed to quantify the congestion caused by trucks at the Port of Colombo, which has not been a subject of a systematic study. To this end, the study makes use of GPS data. In addition to revealing heavy congestion within the port, the study also reveals significant variations in congestion during different times of the day with the duration of journeys peaking from 1200hrs …

A Benchmark Framework For Data Visualization And Explainable Ai (Xai), Murat Kuzlu, Gokcen Ozdemir, Umut Ozdemir

Engineering Technology Faculty Publications

This research introduces a benchmark framework, called EDUMX, designed for machine learning (ML)- based forecasting and XAI tasks, leveraging the Streamlit open-source Python library. The framework offers a comprehensive suite of functionalities, including data loading, feature selection, relationship analysis, data preprocessing, model selection, metric evaluation, training, and real-time monitoring. Users can easily upload data in diverse formats, explore relationships between variables, preprocess data using various techniques, and assess the performance of the ML model using customizable metrics. With its user-friendly interface, this framework offers invaluable insights for forecasting tasks in various domains, catering to the evolving needs of predictive analytics. …

Data Science In Finance: Challenges And Opportunities, Xianrong Zheng, Elizabeth Gildea, Sheng Chai, Tongxiao Zhang, Shuxi Wang

Information Technology & Decision Sciences Faculty Publications

Data science has become increasingly popular due to emerging technologies, including generative AI, big data, deep learning, etc. It can provide insights from data that are hard to determine from a human perspective. Data science in finance helps to provide more personal and safer experiences for customers and develop cutting-edge solutions for a company. This paper surveys the challenges and opportunities in applying data science to finance. It provides a state-of-the-art review of financial technologies, algorithmic trading, and fraud detection. Also, the paper identifies two research topics. One is how to use generative AI in algorithmic trading. The other is …

In Pursuit Of Consumption-Based Forecasting, Charles Chase, Kenneth B. Kahn

Marketing Faculty Publications

[Introduction] Today's most mature, most sophisticated, best-in-class forecasting is what we call consumption-based forecasting (CBF). In contrast, the least sophisticated companies typically do not forecast at all, but rather set financial targets based on management expectations. Companies beginning to use statistical forecasting techniques usually take a supply-centric orientation, relying on time series techniques applied to shipment and/or order history. The next stage of progression is to incorporate promotions data, economic data, and market data alongside supply-centric data so that regression and other advanced analytics can be used. Companies pursing CBF utilize even more advanced capabilities to capture, examine, and understand …

Methods That Support The Validation Of Agent-Based Models: An Overview And Discussion, Andrew Collins, Matthew Koehler, Christopher Lynch

Engineering Management & Systems Engineering Faculty Publications

Validation is the process of determining if a model adequately represents the system under study for the model’s intended purpose. Validation is a critical component in building the credibility of a simulation model with its end-users. Effectively conducting validation can be a daunting task for both novice and experienced simulation developers. Further compounding the difficult task of conducting validation is that there is no universally accepted approach for assessing a simulation. These challenges are particularly relevant to the paradigm of Agent-Based Modeling and Simulation (ABMS) because of the complexity found in these models’ mechanisms and in the real-world situations they …

Teaching Analytics Online: A Self-Study Of Professional Practice, Andrew J. Collins, Brandon Butler, James F. Leathrum Jr., Christopher J. Lynch

Engineering Management & Systems Engineering Faculty Publications

As the COVID-19 pandemic caused severe disruption to education enterprises throughout the world, the main response by educational institutions was to move to online learning environments. The purpose of this study was to understand better how instructors could improve online learning for a professional-level week-long short course in a highly technical area (data analytics), which had, pre-COVID, been a hands-on computer, laboratory-based learning experience. The authors used self-study of professional practice to elicit and understand the major issues and concerns of the transition to an online learning environment. Under the guidance of a colleague in teacher education, three course instructors …

The Effect Of Sustainability Information Disclosure On The Cost Of Equity Capital: An Empirical Analysis Based On Gartner Top 50 Supply Chain Rankings, Lingyu Li, Xianrong Zheng, Shuxi Wang

Information Technology & Decision Sciences Faculty Publications

While disclosing financial information has been widely proved to reduce the financing cost of a company, the impact of non-financial information, such as sustainability information, disclosing on the financing cost of the company is still in debate. The goal of this paper is to explore the impact of disclosing sustainability-related information on the cost of equity for firms. The paper first introduces the concept of sustainability information disclosure, and then exhibits its benefit through exploring its impact on reducing a firm’s financing cost. It uses the Gartner supply chain top 50 rankings to construct the experiment environment to test for …

Assessing The Frequency And Severity Of Malware Attacks: An Exploratory Analysis Of The Advisen Cyber Loss Dataset, Ahmed M. Abdelmagid, Farshid Javadnejad, C. Ariel Pinto, Michael K. Mcshane, Rafael Diaz, Elijah Gartell

Modeling, Simulation and Visualization Student Capstone Conference

In today's business landscape, cyberattacks present a significant threat that can lead to severe financial losses and damage to a company's reputation. To mitigate this risk, it is essential for stakeholders to have an understanding of the latest types and patterns of cyberattacks. The primary objective of this research is to provide this knowledge by utilizing the Advisen cyber loss dataset, which comprises over 137,000 cyber incidents that occurred across various industry sectors from 2013 to 2020. By using text mining techniques, this paper will conduct an exploratory data analysis to identify the most common types of malware, including ransomware. …

Extracting Information From Twitter Screenshots, Tarannum Zaki, Michael L. Nelson, Michele C. Weigle

Modeling, Simulation and Visualization Student Capstone Conference

Screenshots are prevalent on social media as a common approach for information sharing. Users rarely verify before sharing screenshots whether they are fake or real. Information sharing through fake screenshots can be highly responsible for misinformation and disinformation spread on social media. There are services of the live web and web archives that could be used to validate the content of a screenshot. We are going to develop a tool that would automatically provide a probability whether a screenshot is fake by using the services of the live web and web archives.

The Legacy Of Colonization And Civil Societies In South Africa, Erika Frydenlund, Melissa Miller-Felton, Bolu Ayankojo

Modeling, Simulation and Visualization Student Capstone Conference

This research analyzes the unique ways that civil societies operate in Sub-Saharan Africa in the context of post-apartheid Cape Town, South Africa. Decades after the demise of apartheid, remnants of inequality remain without the promise of actionable change. We used a computational modeling approach to understand the dynamics of migrants in the receiving community as derived from qualitative interviews conducted with 24 stakeholders in Cape Town, South Africa between 2020 and 2021. Our findings show that the presence of NGOs can promote access to resources and reduce xenophobia if they can have the right influence on government policies.

Gpu Utilization: Predictive Sarimax Time Series Analysis, Dorothy Dorie Parry

Modeling, Simulation and Visualization Student Capstone Conference

This work explores collecting performance metrics and leveraging the output for prediction on a memory-intensive parallel image classification algorithm - Inception v3 (or "Inception3"). Experimental results were collected by nvidia-smi on a computational node DGX-1, equipped with eight Tesla V100 Graphic Processing Units (GPUs). Time series analysis was performed on the GPU utilization data taken, for multiple runs, of Inception3’s image classification algorithm (see Figure 1). The time series model applied was Seasonal Autoregressive Integrated Moving Average Exogenous (SARIMAX).

Assessing Frustration Towards Venezuelan Migrants In Columbia: Path Analysis On Newspaper Coded Data, Brian Llinás, Guljannat Huseynli, Erika Frydenlund, Katherine Palacia, Jose Padilla

Modeling, Simulation and Visualization Student Capstone Conference

This study analyzes the impact of Venezuelan migrants on local frustration levels in Colombia. The study found a relationship between the influx of Venezuelan migrants and the level of frustration among locals towards migrants, infrastructure, government, and geopolitics. Additionally, we identified that frustration types have an impact on other frustrations. The study used articles from a national newspaper in Colombia from 2015 to 2020. News articles were coded during a previous study qualitatively and categorized into frustration types. The code frequencies were then used as variables in this study. We used path modeling to statistically study the relationship between dependent …

The Effectiveness Of Visualization Techniques For Supporting Decision-Making, Cansu Yalim, Holly A. H. Handley

Modeling, Simulation and Visualization Student Capstone Conference

Although visualization is beneficial for evaluating and communicating data, the efficiency of various visualization approaches for different data types is not always evident. This research aims to address this issue by investigating the usefulness of several visualization techniques for various data kinds, including continuous, categorical, and time-series data. The qualitative appraisal of each technique's strengths, weaknesses, and interpretation of the dataset is investigated. The research questions include: which visualization approaches perform best for different data types, and what factors impact their usefulness? The absence of clear directions for both researchers and practitioners on how to identify the most effective visualization …

Behind Derogatory Migrants' Terms For Venezuelan Migrants: Xenophobia And Sexism Identification With Twitter Data And Nlp, Joseph Martínez, Melissa Miller-Felton, Jose Padilla, Erika Frydenlund

Modeling, Simulation and Visualization Student Capstone Conference

The sudden arrival of many migrants can present new challenges for host communities and create negative attitudes that reflect that tension. In the case of Colombia, with the influx of over 2.5 million Venezuelan migrants, such tensions arose. Our research objective is to investigate how those sentiments arise in social media. We focused on monitoring derogatory terms for Venezuelans, specifically veneco and veneca. Using a dataset of 5.7 million tweets from Colombian users between 2015 and 2021, we determined the proportion of tweets containing those terms. We observed a high prevalence of xenophobic and defamatory language correlated with the …

The Shortfalls Of Vulnerability Indexes For Public Health Decision-Making In The Face Of Emergent Crises: The Case Of Covid-19 Vaccine Uptake In Virginia, Lydia Cleveland Sa, Erika Frydenlund

VMASC Publications

Equitable and effective vaccine uptake is a key issue in addressing COVID-19. To achieve this, we must comprehensively characterize the context-specific socio-behavioral and structural determinants of vaccine uptake. However, to quickly focus public health interventions, state agencies and planners often rely on already existing indexes of "vulnerability." Many such "vulnerability indexes" exist and become benchmarks for targeting interventions in wide ranging scenarios, but they vary considerably in the factors and themes that they cover. Some are even uncritical of the use of the word "vulnerable," which should take on different meanings in different contexts. The objective of this study is …

Deeppatent2: A Large-Scale Benchmarking Corpus For Technical Drawing Understanding, Kehinde Ajayi, Xin Wei, Martin Gryder, Winston Shields, Jian Wu, Shawn M. Jones, Michal Kucer, Diane Oyen

Computer Science Faculty Publications

Recent advances in computer vision (CV) and natural language processing have been driven by exploiting big data on practical applications. However, these research fields are still limited by the sheer volume, versatility, and diversity of the available datasets. CV tasks, such as image captioning, which has primarily been carried out on natural images, still struggle to produce accurate and meaningful captions on sketched images often included in scientific and technical documents. The advancement of other tasks such as 3D reconstruction from 2D images requires larger datasets with multiple viewpoints. We introduce DeepPatent2, a large-scale dataset, providing more than 2.7 million …

Development Of A Data Science Curriculum For An Engineering Technology Program, Salih Sarp, Murat Kuzlu, Otilia Popescu, Vukica M. Jovanovic, Zafer Acar

Engineering Technology Faculty Publications

Data science has gained the attention of various industries, educators, parents, and students thinking about their future careers. Statistics departments have traditionally offered data science courses for a long time. The main objective of these courses is to examine the fundamental concepts and theories. However, teaching data science courses has also expanded to other disciplines due to the vast amount of data being collected by numerous modern applications. Also, someone needs to learn how to collect and process data, especially from industrial devices, because of the recent development of Internet of Things (IoT) technologies. Hence, integrating data science into the …

Biodiversity Of Philippine Marine Fishes: A Dna Barcode Reference Library Based On Voucher Specimens, Katherine E. Bemis, Matthew G. Girard, Mudjekeewis D. Santos, Kent E. Carpenter, Jonathan R. Deeds, Diane E. Pitassy, Nicko Amor L. Flores, Elizabeth S. Hunter, Amy C. Driskell, Kenneth S. Macdonald Iii, Lee A. Weigt, Jeffrey T. Williams

Biological Sciences Faculty Publications

Accurate identification of fishes is essential for understanding their biology and to ensure food safety for consumers. DNA barcoding is an important tool because it can verify identifications of both whole and processed fishes that have had key morphological characters removed (e.g., filets, fish meal); however, DNA reference libraries are incomplete, and public repositories for sequence data contain incorrectly identified sequences. During a nine-year sampling program in the Philippines, a global biodiversity hotspot for marine fishes, we developed a verified reference library of cytochrome c oxidase subunit I (COI) sequences for 2,525 specimens representing 984 species. Specimens were primarily purchased …

Metaenhance: Metadata Quality Improvement For Electronic Theses And Dissertations, Muntabir H. Choudhury, Lamia Salsabil, Himarsha R. Jayanetti, Jian Wu

College of Sciences Posters

Metadata quality is crucial for digital objects to be discovered through digital library interfaces. Although DL systems have adopted Dublin Core to standardize metadata formats (e.g., ETD-MS v1.1¹), the metadata of digital objects may contain incomplete, inconsistent, and incorrect values [1]. Most existing frameworks to improve metadata quality rely on crowdsourced correction approaches, e.g., [2]. Such methods are usually slow and biased toward documents that are more discoverable by users. Artificial intelligence (AI) based methods can be adopted to overcome this limit by automatically detecting, correcting, and canonicalizing the metadata, featuring quick and unbiased responses to document metadata. …

X-Disetrac: Distributed Eye-Tracking With Extended Realities, Bhanuka Mahanama, Sampath Jayarathna

College of Sciences Posters

Humans use heterogeneous collaboration mediums such as in-person, online, and extended realities for day-to-day activities. Identifying patterns in viewpoints and pupillary responses (a.k.a eye-tracking data) provide informative cues on individual and collective behavior during collaborative tasks. Despite the increasing ubiquity of these different mediums, the aggregation and analysis of eye-tracking data in heterogeneous collaborative environments remain unexplored. Our study proposes X-DisETrac: Extended Distributed Eye Tracking, a versatile framework for eye tracking in heterogeneous environments. Our approach tackles the complexity by establishing a platform-agnostic communication protocol encompassing three data streams to simplify data aggregation and …

Blockchain And Puf-Based Secure Key Establishment Protocol For Cross-Domain Digital Twins In Industrial Internet Of Things Architecture, Khalid Mahmood, Salman Shamshad, Muhammad Asad Saleem, Rupak Kharel, Ashok Kumar Das, Sachin Shetty, Joel J. P. C. Rodrigues

VMASC Publications

Introduction:: The Industrial Internet of Things (IIoT) is a technology that connects devices to collect data and conduct in-depth analysis to provide value-added services to industries. The integration of the physical and digital domains is crucial for unlocking the full potential of the IIoT, and digital twins can facilitate this integration by providing a virtual representation of real-world entities.

Objectives:: By combining digital twins with the IIoT, industries can simulate, predict, and control physical behaviors, enabling them to achieve broader value and support industry 4.0 and 5.0. Constituents of cooperative IIoT domains tend to interact and collaborate during their complicated …

Assessing Spurious Correlations In Big Search Data, Jesse T. Richman, Ryan J. Roberts

Political Science & Geography Faculty Publications

Big search data offers the opportunity to identify new and potentially real-time measures and predictors of important political, geographic, social, cultural, economic, and epidemiological phenomena, measures that might serve an important role as leading indicators in forecasts and nowcasts. However, it also presents vast new risks that scientists or the public will identify meaningless and totally spurious ‘relationships’ between variables. This study is the first to quantify that risk in the context of search data. We find that spurious correlations arise at exceptionally high frequencies among probability distributions examined for random variables based upon gamma (1, 1) and Gaussian random …

Tenvr: Matlab-Based Toolbox For Environmental Research, Aleksandar I. Goranov, Rachel L. Sleighter, Dobromir A. Yordanov, Patrick G. Hatcher

Chemistry & Biochemistry Faculty Publications

With the advancements in science and technology, datasets become larger and more multivariate, which warrants the need for programming tools for fast data processing and multivariate statistical analysis. Here, the MATLAB-based Toolbox for Environmental Research "TEnvR" (pronounced "ten-ver") is introduced. This novel toolbox includes 44 open-source codes for automated data analysis from a multitude of techniques, such as ultraviolet-visible, fluorescence, and nuclear magnetic resonance spectroscopies, as well as from ultrahigh resolution mass spectrometry. Provided are codes for processing data (e.g., spectral corrections, formula assignment), visualization of figures, calculation of metrics, multivariate statistics, and automated work-up of large datasets. TEnvR allows …

Fitting Time Series Models To Fisheries Data To Ascertain Age, Kathleen S. Kirch, Norou Diawara, Cynthia M. Jones

OES Faculty Publications

The ability of government agencies to assign accurate ages of fish is important to fisheries management. Accurate ageing allows for most reliable age-based models to be used to support sustainability and maximize economic benefit. Assigning age relies on validating putative annual marks by evaluating accretional material laid down in patterns in fish ear bones, typically by marginal increment analysis. These patterns often take the shape of a sawtooth wave with an abrupt drop in accretion yearly to form an annual band and are typically validated qualitatively. Researchers have shown key interest in modeling marginal increments to verify the marks do, …

Assessing Univariate And Multivariate Normality In Pls-Sem, Kathy Qing Ma, Weiyong Zhang

Information Technology & Decision Sciences Faculty Publications

Partial least squares structural equation modeling (PLS-SEM) has gained popularity among researchers in part due to its relaxed requirement for multivariate normality. One important step in performing structural equation modeling (SEM) is to test the normality assumption. In this paper, we illustrate how to assess univariate and multivariate normality in PLS-SEM using WarpPLS.

Generalized Sparse Bayesian Learning And Application To Image Reconstruction, Jan Glaubitz, Anne Gelb, Guohui Song

Mathematics & Statistics Faculty Publications

Image reconstruction based on indirect, noisy, or incomplete data remains an important yet challenging task. While methods such as compressive sensing have demonstrated high-resolution image recovery in various settings, there remain issues of robustness due to parameter tuning. Moreover, since the recovery is limited to a point estimate, it is impossible to quantify the uncertainty, which is often desirable. Due to these inherent limitations, a sparse Bayesian learning approach is sometimes adopted to recover a posterior distribution of the unknown. Sparse Bayesian learning assumes that some linear transformation of the unknown is sparse. However, most of the methods developed are …