Digital Commons Network^™

Why Kolmolgorov-Arnold Networks (Kan) Work So Well: A Qualitative Explanation, Hung T. Nguyen, Vladik Kreinovich, Olga Kosheleva

Departmental Technical Reports (CS)

In the usual deep neural network, weights are adjusted during training, but the activation function remains the same. Lately, it was experimentally shown that if, instead of using the same activation function always, we train the activation functions as well, we get a much better results -- i.e., for the networks with the same number of parameters, we get a much better accuracy. Such networks are called Kolmogorov-Arnold networks. In this paper, we provide a general explanation of why these new networks work so well.

Three Applications Of Geometric Reasoning: Why Metastasis Is Mostly Caused By Elongated Cancer Cells? How Body Shape Affects Curiosity? Why Ring Fractures In Ice?, Julio C. Urenda, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In this paper, we describe three applications of geometric reasoning to important practical problems ranging from micro- to macro-level. Specifically, we use geometric reasoning to explain why metastasis is mostly caused by elongated cancer cell, why curiosity in fish is strongly correlated with body shape, and why ring-shaped fractures appear in Antarctica.

Development And Validation Of A Chemistry Laboratory Safety Knowledge, Attitudes, Practices, And Mindset Questionnaire, Claudine Garcia, Genejane Adarlo, Anna Carissa San Esteban, Armando M. Guidote

Health Sciences Faculty Publications

Accidents in chemistry laboratories can be prevented by fostering a safety culture - the institution’s knowledge, attitudes, practices (KAP), and mindset regarding laboratory safety. To effectively promote a safety culture, robust tools are essential for evaluating safety KAP and mindset. Hence, this study developed and validated a questionnaire that can rapidly measure laboratory safety KAP and mindset to guide targeted interventions aimed at enhancing the safety culture in chemistry laboratories. The study was drawn from existing validated questionnaires in constructing a tool comprising 40 items that can measure the safety KAP and mindset in chemistry laboratories. Using a cross-sectional design, …

Root Lesion And Burrowing Nematodes And Their Management, Department Of Primary Industries And Regional Development, Western Australia

Grains and other field crops factsheets

Nematodes are common soil pests that feed on the roots of a wide range of crops in all agricultural areas of Western Australia, resulting in significant crop yield loss. Root lesion nematode can be managed but not eradicated.

This factsheet summarises the biology of the root lesion nematode (RLN, Pratylenchus spp.) and burrowing nematode (Radopholus spp.) species that damage Western Australian (WA) crops, and their diagnosis and management.

Why Green Wavelength Is Closer To Blue Than To Red And How It Is Related To Computations: Information-Based Explanation, Victor L. Timchenko, Yury P. Kondratenko, Olga Kosheleva, Vladik Kreinovich, Nguyen Hoang Phuong

Departmental Technical Reports (CS)

In our previous papers, we analyzed the idea of using light signals of three basic color -- red, green, and blue -- to speed up computations, in particular fuzzy-related computations. A natural question is: why red, green, and blue? Why not select some other colors: e.g., from the wavelength viewpoint, green is much closer to blue than to green, so why not select colors whose distribution is more even? In this paper, we show that if we consider this problem from the information viewpoint, then the corresponding equal-information criterion indeed implies that the intermediate wavelength should be closer to the …

Roly Poly And Its Management, Department Of Primary Industries And Regional Development, Western Australia

Grains and other field crops factsheets

Roly poly, also known as prickly saltwort or tumbleweed (Salsola australis), is a native species found throughout Australia. The dead plants can break off at ground level, forming the ‘tumbleweeds’ seen in movies.

Like most summer weeds, roly poly uses soil moisture and nutrients that would otherwise be available to the following crop. The time taken to clear uncontrolled plants can delay seeding.

Livestock will graze the young plants; however, they will not eat the mature plants and are injured by the prickly leaves.

Nitrate Removal By Floating Treatment Wetlands Under Aerated And Unaerated Conditions: Field And Laboratory Results, Jenna Mccoy, Matt Chaffee, Aaron Mittelstet, Tiffany L. Messer, Steve Comfort

Earth and Environmental Sciences Faculty Publications

Urban and storm water retention ponds eventually become eutrophic after years of receiving runoff water. In 2020, a novel biological and chemical treatment was initiated to remove accumulated nutrients from an urban retention pond that had severe algae and weed growth. Our approach installed two 6.1 m × 6.1 m floating treatment wetlands (FTWs) and two airlift pumps that contained slow-release lanthanum composites, which facilitated phosphate precipitation. Four years of treatment (2020–2023) resulted in median nitrate-N concentrations decreasing from 23 μg L−1 in 2020 to 1.3 μg L−1 in 2023, while PO4-P decreased from 42 μg L−1 to 19 μg …

A Convenient Synthesis Of Short Α-/Β-Mixed Peptides As Potential Α-Amylase Inhibitors, Naeem Ahmed, Fakhira Razzaq, Muhammad Arfan, Mansour K. Gatasheh, Hammad Nasir, Joham Sarfraz Ali, Hamna Hafeez

Michigan Tech Publications

Over the last decades, the increased incidence of metabolic disorders, such as type two diabetes and obesity, has motivated researchers to investigate new enzyme inhibitors. Inhibition of the α-amylase enzyme is one therapeutic approach in lowering glucose levels in the blood to manage diabetes mellitus. The objective of this study was to synthesize short α-/β-mixed peptides in the solution phase. The Boc-protected α-L-leucine was converted to β-analogue by using Arndt–Eistert synthesis with the advantage of no racemization and retention of configuration. Three novel short peptides were successfully synthesized: N(Boc)-Gly-β-Leu–OCH3(14), N(Boc)-O(Bz)α-Ser-β-Leu–OCH3(16), and N(Boc)-O(Bz)-α-Tyr-α-Gly-β-Leu–OCH3(17), characterized by FTIR and 1H NMR analysis. The …

Contemplating Existence: Ai And The Meaning Of Life, Emily Barnes, James Hutson

Faculty Scholarship

This article explores the intersection of artificial intelligence (AI) with existential philosophy, examining how AI technologies influence human conceptualizations of purpose and meaning. Despite rapid advancements in AI, the domain's implications for existential thought remain underexplored. By integrating interdisciplinary perspectives from psychology, philosophy, and AI ethics, this study elucidates how AI can shape, challenge, or enhance our understanding of life's purpose. It investigates theoretical frameworks and practical implementations of AI engaging in existential questions, analyzing both the capabilities and limitations of AI systems such as ChatGPT in simulating human existential thought. The ethical implications of AI's role in existential inquiries …

Growing Oaten Hay On Frost Prone Paddocks, Department Of Primary Industries And Regional Development, Western Australia

Grains and other field crops factsheets

Growing oaten hay on frost-prone paddocks minimises the frost risk because it is cut soon after flowering, avoiding the frost sensitive period. If severe frost damage occurs to other crops, baling them for hay may reduce economic loss.

Oats are much more tolerant than other cereals to frost events that occur during vegetative growth and flowering.

Fleabane And Its Management, Department Of Primary Industries And Regional Development, Western Australia

Grains and other field crops factsheets

Flaxleaf and tall fleabane (Conyza spp.) are emerging weeds in Western Australia (WA), germinating in spring and becoming major weeds in summer. Fleabane is now considered an important weed of reduced tillage farming systems.

Historically, fleabane was primarily a weed of roadsides, particularly if the road shoulders were sprayed with glyphosate, leaving bare soil on which the fleabane could germinate and flourish.

Coal Ash Triggers An Elevated Temperature Landfill Development: Lessons From The Bristol Virginia Solid Waste Landfill Neighboring Community, Reagan Patton Witt, Marcelo I. Guzman

UK CARES Faculty Publications

Landfills for disposing of solid waste are designed, located, managed, and monitored facili- ties expected to comply with government regulations to prevent contamination of the surrounding environment. After the average life expectancy of a typical landfill (30 to 50 years), a large investment in the construction, operation, final closure, and 30-year monitoring of a new site is needed. In this case study, we provide a holistic explanation of the unexpected development of elevated temperature landfills (ETLFs), such as that in the city of Bristol (United States) on the border of the states of Virginia and Tennessee, including the initial role …

History & Evolution Of Plastic Mulching Technology: An Ethnography Of California Strawberry Plasticulture, Kalea Conrad

Master's Theses

This ethnography draws on key informant interviews and participant observation to produce a case study about plastic mulching as an important industry standard in specialty crop production. It documents the historic adoption and present role of plastic mulching technology in California strawberry production and addresses the characteristics of commercial standard management that inhibit the adoption of alternative mulching practices. It complements extensive research on strawberry pathology and fumigation, breeding innovations, fertilizer and pesticide treatments, and maximization of yields to incorporate participants’ lived experiences and knowledge of mulch origins, the technology adoption process, mulch benefits and drawbacks, the state of agricultural …

An Artificial Intelligence Report Card For Judicial Review, Zoe E. Niesel

Michigan Journal of Environmental & Administrative Law

The rapid advancement of technology, including artificial intelligence (AI), is creating new challenges for judicial review under the Administrative Procedure Act (APA). In late 2023, federal administrative agencies publicly disclosed over 700 use cases of AI that employ sophisticated techniques like machine learning and natural language processing. While the APA's flexible judicial review framework certainly allows agencies to utilize new technologies, the APA also requires explainability of agency decisions; thus, agencies must be able to articulate the reasoning and methodology behind AI-enabled decisions for the purpose of judicial review. This Article examines APA judicial review as it applies to agency …

Design, Fabrication, And Spectroscopy Of Photocatalytic Materials In Visible Spectrum, Yamuna Paudel

Dissertations, Theses, and Capstone Projects

Heterogeneous photocatalysis has attracted research interest in sustainable energy technologies. However, achieving high photocatalytic efficiency from visible light-absorbing semiconductors is challenging due to their weak absorption, transport losses, and low activity. While multilayer approaches have been developed to enhance the surface reactivity and stability independent of electronic factors, a comprehensive framework for optimizing light-matter interactions has not yet been established. Here, we introduce a photonic strategy using semiconductor metasurfaces, which is highly effective in enhancing the photocatalytic activity of GaAs, a high-performance semiconductor with a near-infrared bandgap. Our engineered pillar arrays with heights of ~150 nm exhibit Mie resonances near …

Advancing Affective Computing: Emotion Recognition And Tracking Across Diverse Contexts (Varied Environments), Shao Liu

Dissertations, Theses, and Capstone Projects

Affective Computing (AC) is an interdisciplinary field that recognizes, interprets, and processes human emotions. Emotions are complex, involving consciousness, physical sensations, and behavioral expressions, and are significant in various domains like mental health, human-computer interaction, and social security. Real-world applications of AC include monitoring drivers’ emotional states to improve road safety and understanding the emotions expressed by artists in visual arts. Traditional methods relying on facial expressions often fall short due to the nuanced nature of emotions, which vary across individuals, cultures, and contexts. Accurate AC systems require sophisticated, multimodal models to handle these variations and external factors like noise …

Synthesis Of C-Di- And C-Tri- Saccharides From Glycosyl Crotylating Agents, Steven Truong

Dissertations, Theses, and Capstone Projects

The involvement of carbohydrates in a plethora of fundamental biological pathways, including disease related processes, has created a demand for molecular probes for elucidating these mechanisms. Accordingly, synthesis of tailored and diverse carbohydrate-like molecules, commonly referred to as glycomimetics, is a very active area of research. Among the more popular classes of glycomimetics are C-glycosides, analogues in which the anomeric carbon of a parent sugar is attached to a carbon substituent. C-glycosides have attracted attention in the medicinal chemistry community as there are several naturally occurring examples with interesting pharmacologically activity. C-glycosides are also of interest because in …

Drying Techniques For Precooked Hybrid Rice To Ensure Quality Of Instantized Rice, Anne Adhiambo Okeyo, Kaushik Luthra, Justin Siebenmorgen, Alan R. Vazquez, Griffiths Atungulu

Food Science Faculty Publications and Presentations

Background and Objectives

Due to the emergence of new hybrid rice cultivars, rice processors must refine their processing protocols to maintain the production of high-quality products. This is crucial for the instant rice processing industry. Therefore, this study aims to refine current convective heated air-drying processing methods to suit the new hybrid rice cultivars intended for instant rice production. New strategies to dry cooked rice were investigated. These included drying in a stepwise manner with high (230–200°C) and medium (190–160°C) air temperatures and drying at constant high (200°C) and medium (160°C) air temperatures. Changes in quality attributes of two new …

Developing Empathetic Ai: Exploring The Potential Of Artificial Intelligence To Understand And Simulate Family Dynamics And Cultural Identity, Emily Barnes, James Hutson

Faculty Scholarship

The rapid advancement of Artificial Intelligence (AI) has significantly impacted various domains. Yet, the exploration of AI's potential to develop a deep understanding of family culture and identity remains underexplored. This study introduces the concept of "a love of grandma and apple pie" to symbolize the potential of various AI to internalize and appreciate familial relationships, cultural traditions, and personal identity. The proposed study would investigate how an advanced deep learning model, trained on diverse unstructured datasets—including multimedia data from 100 families-could learn and reflect human-like emotions, values, and cultural understanding. Utilizing Convolutional Neural Networks (CNNs) for visual data processing …

Incorporating Solvation Thermodynamic Mapping In Computer-Aided Drug Design, Yeonji Ji

Dissertations, Theses, and Capstone Projects

Advancements in computational techniques have revolutionized structure-based drug design, substantially improving the efficiency and effectiveness of the drug discovery process by reducing time, costs, and labor requirements. These advancements include various methods, such as investigating small molecule ligands binding to proteins, exploring alternative protein conformations, and solvation mapping on the protein surfaces. Among these methods, understanding the correlation between protein-ligand binding and the role of solvation is important.

A fundamental concept in protein-ligand binding is shape and electrostatic complementarity, which is complicated by the inherent flexibility of proteins. In the absence of small molecule ligands, proteins are complementary to surface …

Protein And Water Modeling In Computer-Aided Drug Discovery, Mossa Ghattas

Dissertations, Theses, and Capstone Projects

The field of Computer-Aided Drug Design (CADD) is continuously evolving to improve protein modeling, a crucial step in the drug discovery process. However, limitations exist in how CADD accounts for the various configurations a protein can adopt due to different rotamer and protonation states of its residues. This thesis explores advancements in CADD to address this challenge, focusing on protein modeling and water interactions.

In Chapter 1, I introduce the drug discovery process with a brief overview of its history, the purpose of FDA clinical trials, and the cost and time duration for bringing a drug to the market. I …

From Stars To Moons: Investigating Stellar Rotations, Planetary Interactions, And Exoplanetary Prospects, Rosario Cecilio-Flores-Elie

Dissertations, Theses, and Capstone Projects

The thesis is divided into two key sections. The first chapter presents the results of analyzing TESS light curves for 99 targets within the Carina-Near moving group. By deriving rotational periods, this analysis supports stellar age estimation, contributing to the broader efforts of the Backyard Worlds: Planet 9 citizen project in determining age parameters for 89 newly identified systems, including ultracool dwarf companions. These findings enhance our understanding of stellar rotation and evolution, offering new insights into the development of secondary co-moving objects like brown dwarfs.

The second chapter investigates planet-moon interactions within our solar system by examining mass ratios, …

44ti/44sc Generator Development And Radiolabeling Optimization For Medical Applications, Christine E. Schmidt-Kennelty

Dissertations, Theses, and Capstone Projects

In recent years, there has been a growing interest in scandium-44 (⁴⁴Sc) for medical applications due to its favorable decay properties. With a relatively short half-life of 3.97 hours and high positron branching ratio of 94.3%, ⁴⁴Sc is an ideal candidate for positron emission tomography (PET) imaging. However, producing ⁴⁴Sc without an on-site cyclotron limits access, as its short half-life makes it impractical to ship to more remote locations.

To address this issue, ⁴⁴Ti/⁴⁴Sc generators have become a focal point of research, providing an onsite source of⁴⁴Sc. Despite their potential, current …

Design And Characterization Of De Novo Photoactivated Charge Separating Proteins, Paul M. Molinaro

Dissertations, Theses, and Capstone Projects

Light activate charge separation can provide high energy electrons for a variety of chemical processes. Reaction center proteins serve as a scaffold for small molecules that serve as “hopping” sites for electrons. Previous reaction center designs are four helix bundles that bind at minimum two metalloporphyrin’s: a zinc porphyrin serves as a light activated electron donor, mimicking chlorophyl, and a heme molecule serving as the acceptor. The efficiency of these designs is hampered by the enhanced relaxation of the singlet excited state of zinc porphyrin molecules due to spin-orbit coupling with the paramagnetic heme acceptor. The optimal design would contain …

Dirt/Μ: Automated Extraction Of Root Hair Traits Using Combinatorial Optimization, Peter Pietrzyk, Neen Phan-Udom, Chartinun Chutoe, Lise Pingault, Ankita Roy, Marc Libault, Patompong Johns Saengwilai, Alexander Bucksch

Department of Entomology: Faculty Publications

As with phenotyping of any microscopic appendages, such as cilia or antennae, phenotyping of root hairs has been a challenge due to their complex intersecting arrangements in two-dimensional images and the technical limitations of automated measurements. Digital Imaging of Root Traits at Microscale (DIRT/μ) is a newly developed algorithm that addresses this issue by computationally resolving intersections and extracting individual root hairs from two-dimensional microscopy images. This solution enables automatic and precise trait measurements of individual root hairs. DIRT/μ rigorously defines a set of rules to resolve intersecting root hairs and minimizes a newly designed cost function to combinatorically identify …

Ensemble Pretrained Language Models To Extract Biomedical Knowledge From Literature, Zhao Li, Qiang Wei, Liang-Chin Huang, Jianfu Li, Yan Hu, Yao-Shun Chuang, Jianping He, Avisha Das, Vipina Kuttichi Keloth, Yuntao Yang, Chiamaka S Diala, Kirk E Roberts, Cui Tao, Xiaoqian Jiang, W Jim Zheng, Hua Xu

Faculty, Staff and Student Publications

OBJECTIVES: The rapid expansion of biomedical literature necessitates automated techniques to discern relationships between biomedical concepts from extensive free text. Such techniques facilitate the development of detailed knowledge bases and highlight research deficiencies. The LitCoin Natural Language Processing (NLP) challenge, organized by the National Center for Advancing Translational Science, aims to evaluate such potential and provides a manually annotated corpus for methodology development and benchmarking.

MATERIALS AND METHODS: For the named entity recognition (NER) task, we utilized ensemble learning to merge predictions from three domain-specific models, namely BioBERT, PubMedBERT, and BioM-ELECTRA, devised a rule-driven detection method for cell line and …

Improving Large Language Models For Clinical Named Entity Recognition Via Prompt Engineering, Yan Hu, Qingyu Chen, Jingcheng Du, Xueqing Peng, Vipina Kuttichi Keloth, Xu Zuo, Yujia Zhou, Zehan Li, Xiaoqian Jiang, Zhiyong Lu, Kirk Roberts, Hua Xu

Faculty, Staff and Student Publications

IMPORTANCE: The study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets.

OBJECTIVES: This study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance.

MATERIALS AND METHODS: We evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, …

Putting Gpt-4o To The Sword: A Comprehensive Evaluation Of Language, Vision, Speech, And Multimodal Proficiency, Sakib Shahriar, Brady D. Lund, Nishith Reddy Mannuru, Muhammad Arbab Arshad, Kadhim Hayawi, Ravi Varma Kumar Bevara, Aashrith Mannuru, Laiba Batool

All Works

As large language models (LLMs) continue to advance, evaluating their comprehensive capabilities becomes significant for their application in various fields. This research study comprehensively evaluates the language, vision, speech, and multimodal capabilities of GPT-4o. The study employs standardized exam questions, reasoning tasks, and translation assessments to assess the model’s language capability. Additionally, GPT-4o’s vision and speech capabilities are tested through image classification and object-recognition tasks, as well as accent classification. The multimodal evaluation assesses the model’s performance in integrating visual and linguistic data. Our findings reveal that GPT-4o demonstrates high accuracy and efficiency across multiple domains in language and reasoning …

Paper-Recorded Ecg Digitization Method With Automatic Reference Voltage Selection For Telemonitoring And Diagnosis, Liang Hung Wang, Chao Xin Xie, Tao Yang, Hong Xin Tan, Ming Hui Fan, I. Chun Kuo, Zne Jung Lee, Tsung Yi Chen, Pao Cheng Huang, Shih Lun Chen, Patricia Angela R. Abu

Department of Information Systems & Computer Science Faculty Publications

In electrocardiograms (ECGs), multiple forms of encryption and preservation formats create difficulties for data sharing and retrospective disease analysis. Additionally, photography and storage using mobile devices are convenient, but the images acquired contain different noise interferences. To address this problem, a suite of novel methodologies was proposed for converting paper-recorded ECGs into digital data. Firstly, this study ingeniously removed gridlines by utilizing the Hue Saturation Value (HSV) spatial properties of ECGs. Moreover, this study introduced an innovative adaptive local thresholding method with high robustness for foreground–background separation. Subsequently, an algorithm for the automatic recognition of calibration square waves was proposed …

Deciphering The Interdomain Coupling In A Gram-Negative Bacterial Membrane Insertase, Adithya Polasa, Shadi A. Badiee, Mahmoud Moradi

Chemistry & Biochemistry Faculty Publications and Presentations

YidC is a membrane protein that plays an important role in inserting newly generated proteins into lipid membranes. The Sec-dependent complex is responsible for inserting proteins into the lipid bilayer in bacteria. YidC facilitates the insertion and folding of membrane proteins, both in conjunction with the Sec complex and independently. Additionally, YidC acts as a chaperone during the folding of proteins. Multiple investigations have conclusively shown that Gram-positive bacterial YidC has Sec-independent insertion mechanisms. Through the use of microsecond-level all-atom molecular dynamics (MD) simulations, we have carried out an in-depth investigation of the YidC protein originating from Gram-negative bacteria. This …