Digital Commons Network^™

Adaptive Crop Switching For Irrigated Agriculture In Response To Climate Change In The Western U.S., Shahryar Fazli, Wenzhao Li, Surendra Maharjan, Rejoice Thomas, Aqil Tariq, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Adaptive irrigation strategies are crucial for balancing water use, economic viability, and food security in the arid Western United States. However, as a key indicator vital in regulating agricultural productivity and crop irrigation, water use efficiency (WUEc) is becoming increasingly complex to estimate due to climate change. This study explores the critical role of key meteorological drivers, such as maximum temperature (tmax) and vapor pressure deficit (vpd), and their impacts on crop-specific WUEc. Future impacts are also assessed through integrating machine learning models with climate projections from the CMIP6 framework under SSP2–4.5 and SSP5–8.5 scenarios to forecast WUEc trends from …

A Novel, Metal-Based Approach To Identify Residences With Lead Service Lines, Danielle Land, Grant D. Brown, David M. Cwiertny, Marc A. Edwards, Mona Hanna, Drew E. Latta, Michelle M. Scherer

Michigan Tech Publications

There is an urgent need for rapid, cost-effective approaches to identify residences with lead service lines (LSLs). We evaluated whether analyzing water for corrosion-related metals could accurately identify residences with LSLs without relying on potentially inaccurate property records. We applied principal component analysis logistic regression (PCA-LR) and classification tree models using 28 analytes per bottle (including Pb, Cu, Zn, Fe, Al, and others) measured in 216 water samples collected in Flint, Michigan, in August 2015. The PCA-LR model achieved 87% accuracy (AUROC = 0.93) with 81% sensitivity and 90% specificity, while the classification tree model achieved 80% accuracy (AUROC = …

Gene Regulatory Network Prediction Using Machine Learning, Deep Learning, And Hybrid Approaches, Sai Teja Mummadi, Md Khairul Islam, Victor Busov, Hairong Wei

Michigan Tech Publications

Construction of gene regulatory networks (GRNs) is essential for elucidating the regulatory mechanisms underlying metabolic pathways, biological processes, and complex traits. In this study, we developed and evaluated machine learning, deep learning, and hybrid approaches for constructing GRNs by integrating prior knowledge and large-scale transcriptomic data from Arabidopsis thaliana, poplar, and maize. Among these, hybrid models that combined convolutional neural networks and machine learning consistently outperformed traditional machine learning and statistical methods, achieving over 95% accuracy on the holdout test datasets. These models not only identified a greater number of known transcription factors regulating the lignin biosynthesis pathway but also …

The Problem With Consumer Affordability Of Prescription Medications In The United States, Valerie E. Bell

Walden Dissertations and Doctoral Studies

Consumer affordability of prescription drugs is an ongoing problem in the United States. This study was undertaken to research the financial, physical, and economic effects of drug prices on consumers and the methods used by consumers to address such effects. Rational choice and power and politics theories were used to explain the decisions consumers make when they could not afford their medications and the role policies and politics play in drug pricing. The research questions concerned the relationship between consumers’ perceptions of drug pricing and their ability to purchase medications. The quantitative nonexperimental study involved the administration of a survey …

Associations Between School-Based Arrests And High School Graduation Status Of African American Female Students In Florida, Rannisha Missick

Walden Dissertations and Doctoral Studies

Zero tolerance school discipline policies, originally intended to address serious threats such as weapon and drug possession, have increasingly been applied to minor behavioral infractions, disproportionately affecting African American students, particularly females. These exclusionary practices, including school-based arrests, have been linked to adverse educational outcomes. The purpose of this quantitative correlational study was to examine associations between school-based arrests due to zero tolerance policy violations and high school graduation status of African American female students in Florida. The study was guided by the intersectionality theory, which posits individuals who belong to multiple marginalized groups experience compounded forms of discrimination. Archival …

A Survey Of Image Forensics: Exploring Forgery Detection In Image Colorization, Saurabh Agarwal, Deepak Sharma, Nancy Girdhar, Cheonshik Kim, Ki-Hyun Jung

School of Engineering, Computing and Mathematics

In today’s digital era, the rapid evolution of image editing technologies has brought about a significant simplification of image manipulation. Unfortunately, this progress has also given rise to the misuse of manipulated images across various domains. One of the pressing challenges stemming from this advancement is the increasing difficulty in discerning between unaltered and manipulated images. This paper offers a comprehensive survey of existing methodologies for detecting image tampering, shedding light on the diverse approaches employed in the field of contemporary image forensics. The methods used to identify image forgery can be broadly classified into two primary categories: classical machine …

Low-Energy Multi-Photon Scattering At Tree-Level And One-Loop Order In A Homogeneous Electromagnetic Field, Ivan Ahumada, Patrick Copinger, James P. Edwards

School of Engineering, Computing and Mathematics

We study low energy photons coupled to scalar and spinor matter in the presence of an arbitrary homogeneous electromagnetic field in a first-quantised (worldline) approach. Utilising a Fock-Schwinger gauge for both the scattering photons and homogeneous background, simple compact expressions are found for both the photon- and background-dressed effective action and propagator in scalar and spinor quantum electrodynamics. The low-energy limit allows identification of the coupling of the scattering photons as one of an effective homogeneous superposition of their field strengths, with amplitudes following from application of a suitable linearisation operator. To treat the linearisation, several techniques are employed, including …

A Comprehensive Review On Machine Learning-Based Job Recommendation Systems, Shaymaa Al-Juboori, Su-Cheng Haw, Rui Ern Yap

School of Engineering, Computing and Mathematics

A dynamic, constantly shifting labor market creates enormous job postings, overwhelming candidates and making it difficult for businesses to find quality candidates. It is also hard for job seekers to find suitable jobs. Addressing these issues, machine learning-driven job recommender systems have recently become an essential tool using predictivemodels to improve the match between jobs and candidates. A hybrid design that combine scollaborative filtering with content-based filtering andadds contextual information like geographic location,industry trends, and user behavioural data can enhance the accuracy and relevance of recommendations. This paper reviews and critically analyzes contemporary jobre commender system techniques. The focus is …

Cowboy Narrative - Neal S. Watts, Sheldon F. Gauthier, Neal S. Watts

Writers' Program of the Work Projects Administration in the State of Texas, Fort Worth City Guide and History Draft Records

A transcript of a Cowboy Narrative, or Rangelore, interview conducted by Sheldon Gauthier for the Works Progress Administration's Federal Writers' Project in the 1930s with former cowboy Neal S. Watts. Watts was born in 1859 on his father's farm in Shelby County, Texas and moved to present-day Mansfield, Texas in 1868. In his interview, he describes the abundance of wild game and farming methods in Shelby County. He later began working as a cowhand for L. H. Stevens in Tarrant County, and describes roping cattle, applying a salve to injured cattle, roundups, stampedes, rustlers, and the roles of each cowhand …

Selected Prose And Poetry, Ralph Waldo Emerson

Hannah Arendt Marginalia - All

New York, Rinehart [1950]

Call #: PS1602 .C6

Contains light underlining

PDF Information: 18 pages – 797KB

The Complete Poetry And Selected Prose Of John Donne & The Complete Poetry Of William Blake, John Donne, William Blake

Hannah Arendt Marginalia - All

New York, Modern Library [1946]

Call #: PR2245.A5 H3 1946

Contains gift inscription by “Arthur Lapa?”

PDF Information: 13 pages – 948 KB

The Possessed, Fyodor Dostoyevsky

Hannah Arendt Marginalia - All

New York : The Modern Library, 1963

Call #: PG3326 .B6 1963

Contains marginalia, underlining, marginal lining and endpaper notes

PDF Information: 170 pages – 12.7 MB

Problems Of Men, John Dewey

Hannah Arendt Marginalia - All

New York, Philosophical library, 1946

Call #: B945.D43 P7

Contains underlining and endpaper notes.

PDF Information: 26 pages – 10.9mb

Using A Layered Ensemble Of Physics-Guided Graph Attention Networks To Predict Covid-19 Trends, Connie Sun, Vijayalakshmi Kumarasamy, Yu Liang, Dalei Wu, Yingfeng Wang

UTC Spring Research and Arts Conference

The COVID-19 pandemic has rapidly disseminated worldwide, profoundly impacting numerous nations. Accurately forecasting the trajectory of COVID-19 across various scales is crucial for informing public health decisions. However, existing forecasting models primarily operate at the state or country level. Conventional mathematical models face limitations due to oversimplified assumptions, while machine learning algorithms struggle to extrapolate novel trends. This underscores the necessity for hybrid machine learning models that amalgamate domain expertise to enable precise long-term predictions. In response, we propose a sophisticated three-layered ensemble, tailored to geographical insights and fostering extensive peer learning. Our framework aims to forecast COVID-19 trends at …

Sustaining Smart Cities: Benchmarking Success Factors For High School Education, Lora Taylor

UTC Spring Research and Arts Conference

As Chattanooga strides towards becoming a thriving Smart City, it is imperative to evaluate the academic achievement and graduation rates of Hamilton County students. Chattanooga's Smart City growth relies on assessing Hamilton County schools' academic and graduation outcomes. This research project focuses on benchmark data gathered from two magnet schools - STEM School and Tyner Academy - to understand high school achievement drivers. The research aims to guide policymakers, educators, and stakeholders to enhance graduation rates and educational quality. Ultimately, the goal is to prepare students for success in a tech-centric economy, supporting Chattanooga's sustainable development through informed educational strategies.

Advancements In Gunshot Detection: Ai, Iot, And Deep Learning For Real-Time Response, Vijayalakshmi K Kumarasamy, Anitha Anandhan, Yu Liang, Dalei Wu

UTC Spring Research and Arts Conference

Gun violence is a growing public safety concern, highlighting the need for fast and accurate gunshot detection systems (GDS) to support real-time law enforcement response. This review explores the integration of deep learning (DL), artificial intelligence (AI), and the Internet of Things (IoT) in enhancing GDS performance. It summarizes recent advances ranging from physics-based acoustic modeling to data-driven methods like CNNs, RNNs, and hybrid neural networks, along with edge-based IoT frameworks for low-latency alerts. The review also examines challenges such as differentiating gunshots from similar sounds, ensuring robustness across environments, and addressing surveillance-related privacy concerns. Case studies from urban, indoor, …

A Comparative Study On Viral Fitness Among Influenza Virus Strains Across Different Periods And Locations, J M Imtinan Uddin, Hong Qin

UTC Spring Research and Arts Conference

Influenza viruses, in 1918, 1957, 1968, and 2009 causing pandemics of contagious respiratory illnesses, have taken away millions of lives worldwide [1][2]. Still, many influenza virus strains are circulating worldwide, infecting people in the USA and other countries [3]. Furthermore, influenza viruses are constantly changing, called "antigenic drift"[4]. These circulating influenza virus strains in humans present a potential threat to another pandemic, like the SARS-CoV-2 pandemic. For this reason, We must revise our risk assessment and preparedness plans to mitigate the risk of another pandemic and should continue to put surveillance on influenza virus strains on different hosts [5]. For …

A Combination Of Modified Stacking Method With Voting Ensemble Technique For Binary Classification, J M Imtinan Uddin, Hong Qin

UTC Spring Research and Arts Conference

Binary classification is a frequently encountered machine learning problems. Many machine learning algorithms are used to solve binary classification problems. However, all machine learning algorithms are not suited or efficient for solving binary classification problems.

In this paper, authors has proposed a approach. The proposed approach is a machine learning algorithm, to solve binary classification problems. Authors has combined modified stacking and voting ensemble machine learning techniques for binary classification problems. Before combining the ensemble techniques, authors has modified the stacking ensemble technique for making the proposed method more robust.

This proposed method was applied on two different binary class …

Machine Learning For Reparameterization Of Molecular Dynamics Water Model To Accurately Capture Electrical And Thermal Behavior, Khowshik Dey, Murat Barisik, Yu Liang

UTC Spring Research and Arts Conference

Water is an important component in many scientific and engineering applications, but precisely modeling its thermal, electrical, and physical properties remains difficult in molecular dynamics (MD) simulations. The widely used TIP4P water model, while useful in many circumstances, requires parameterization to better agreement with experimental results under various conditions. In this study, interpretable machine learning techniques were used to systematically tune the TIP4P model parameters where mathematical relationship between features and targets has been developed using deep symbolic optimization (DSO), resulting in a more accurate depiction of water behavior in molecular dynamics simulation. A data-driven approach was created to optimize …

Quantum Mechanical Insights Into Heterogeneous Surface Reactions In Chemical Vapor Infiltration, Atal Bhowmik

UTC Spring Research and Arts Conference

This study investigates the decomposition mechanism of Methyl trichlorosilane during Silicon Carbide (SiC) deposition during Chemical Vapor Infiltration (CVI). High-performance applications require SiC-based ceramic matrix composites (CMCs); however, producing them presents difficulties due to limited deposition rates, high energy consumption, and uneven coatings. To overcome these challenges, the mechanism of SiC formation must be understood completely. Modeling surface reactions of MTS decomposition on the SiC substrate using density functional theory (DFT) calculations with the Vienna Ab initio Simulation Package (VASP) is the key point of current research. By focusing on the adsorption, reaction, and desorption mechanisms that control SiC development, …

Artificial Wetlands Provide Hope For Municipal Sewage Effluent Treatment And Biodiversity Declines, William T. Bryant

UTC Spring Research and Arts Conference

Wetlands provide habitat for a multitude of species worldwide and exist on almost every continent. They act as water filtration systems, cycle organic and inorganic nutrients, prevent flooding and mitigate storm damage. As the human population continues to expand and cities continue expanding, more infrastructure is needed for water treatment and providing green spaces for citizens to enjoy. This literature review analyzes the current data on the effectiveness of constructed wetlands in the treatment of sewage effluent and how they impact the biodiversity of the local ecosystem. The databases Web of Science, ProQuest and Agriculture, Ecosystems and Environment were utilized. …

Forced Labor In Soviet Russia, David J. Dallin, Boris I. Nikolaevsky

Hannah Arendt Marginalia - All

New Haven, Yale University Press, 1947

Call #: HV8931.R8 D3

contains underlining, marginal lining and endpaper notes (front of book)

PDF information: 35 pages – 3.1 MB

Cowboy Narrative - Dr. A. S. Rattan, Woody Phipps, S. A. Rattan

Writers' Program of the Work Projects Administration in the State of Texas, Fort Worth City Guide and History Draft Records

A transcript of a Cowboy Narrative, or Rangelore, interview conducted by Woody Phipps for the Works Progress Administration's Federal Writers' Project in the 1930s with former cowboy Dr. A. S. Rattan. Rattan was born on his father's stock ranch in Greenville, Texas. He began working as a cowhand on his family's ranch, which moved to West Texas during his adolescence. He describes roundups, riding horses, and working with cattle. After his father moved back to Fort Worth, he attended school and became a saddlebag doctor.

Cowboy Narrative - John Raines, Sheldon F. Gauthier, John Raines

Writers' Program of the Work Projects Administration in the State of Texas, Fort Worth City Guide and History Draft Records

A transcript of a Cowboy Narrative, or Rangelore, interview conducted by Sheldon F. Gauthier for the Works Progress Administration's Federal Writers' Project in the 1930s with former cowboy John Raines. Raines was born in Logan County, Kentucky in 1863 and moved to Fort Worth, Texas in 1875 with his father. As a young boy, he worked as an errand boy and then as a waterboy when the railroad came to Fort Worth. He describes the political situation surrounding the railroad's arrival. When he turned 17, he went to work as a cowhand for the Steve Russell outfit north of Fort …

Cowboy Narrative - W. E. Oglesby, Sheldon F. Gauthier, W. E. Oglesby

Writers' Program of the Work Projects Administration in the State of Texas, Fort Worth City Guide and History Draft Records

A transcript of a Cowboy Narrative, or Rangelore, interview conducted by Sheldon F. Gauthier for the Works Progress Administration's Federal Writers' Project in the 1930s with former cowboy W. E. Oglesby. Oglesby was born in 1863 on his father's farm in Lincoln County, Tennessee and migrated to Fort Worth, Texas in his youth. In his interview, he describes the process of migrating in a caravan with several other families, as well as the conditions in Fort Worth during his youth. He discusses Fort Worth history, including the coming of the railroad, the outmigration of Native Americans from Possum Ridge (present-day …

Tusculan Disputation, Marcus Tullius Cicero

Hannah Arendt Marginalia - All

Cambridge, Mass., Harvard University Press, 1950

Call #: PA6156.C6 T6 1950

Contains underlining, marginal lining and endpaper notes.

PDF Information: 27 pages – 6 MB

The Russian Enigma, Anne Ciligia

Hannah Arendt Marginalia - All

London : Labour Book Service, [1940]

Call #: DK267 .C5543 1940

Contains endpaper notes

PDF Information: 23 pages – 1.5 MB

Unless Peace Comes; A Scientific Forecast Of New Weapons, Nigel Calder

Hannah Arendt Marginalia - All

New York, Viking Press, 1968

Call #: U104 .C155 1968

Contains underlining and marginal lining.

PDF Information: 48 pages – 19mb

Wireless Sensor Networks In Renewable Energy Monitoring: A Comprehensive Survey Of Protocols And Applications, Atheer Yousif Oudah, Lina M. Shaker

AUIQ Technical Engineering Science

The global shift to sustainable energy has heightened the demand for smart, robust, and efficient monitoring systems. Wireless Sensor Networks (WSNs) play a key role by enabling real-time data collection, decentralized control, and flexible communication in renewable energy applications. This review presents a comprehensive analysis of WSN architectures, routing protocols, and deployment strategies tailored to photovoltaic (PV) arrays, wind energy systems, hydroelectric plants, and smart microgrids. Core operational challenges are examined through a critical evaluation of energy-aware routing protocols including LEACH, PEGASIS, TEEN, ZRP, and advanced variants like EE-OLEACH and PT-Hybrid. Real-world applications, such as offshore wind farms, rooftop PV …

Comparative Analysis Of Linear And Non-Linear Feature Selection For Breast Cancer Detection With Shap Analysis, Hamza Sabo Maccido

AUIQ Technical Engineering Science

Breast cancer remains one of the leading causes of mortality worldwide, emphasizing the critical need for accurate and efficient diagnostic tools. This study investigates the effectiveness of combining linear and non-linear feature selection methods-Principal Component Analysis (PCA), Pearson Correlation Coefficient (PCC), and Backpropagation Neural Networks (BNN) to improve breast cancer classification using machine learning models. We utilized the Wisconsin Breast Cancer Dataset to evaluate the performance of five classifiers-Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Naïve Bayes (NB) and Artificial Neural Network (ANN). The results demonstrated that BNN-selected features consistently outperformed PCA and PCC …