Digital Commons Network^™

Explaining Time Series Classifiers Through Post-Hoc Xai Methods Capturing Temporal Dependencies, Ephrem Tibebe Mekonnen

Conference papers

Time series classification is essential in domains such as healthcare and finance, where accurate predictions can have significant real-world consequences. However, in many high-stakes applications, understanding why a model makes a certain decision is just as important as the prediction itself. While deep learning models excel at capturing complex temporal patterns, their black-box nature limits transparency, making it difficult to trust and interpret their decisions. Although eXplainable AI (XAI) methods have advanced considerably for image and tabular data, applying them to time series remains challenging due to the intricate temporal dependencies and high dimensionality of the data. Post-hoc model-agnostic XAI …

Geochemical Characteristics And Genesis Of Element Enrichment Of Niobium-Rich-Rare Earth Metal Layer In Longtan Formation Of Zhina Coalfield, Ding Yunlong, Wang Fangfa, Li Bi, Tang Lifang, Yang Yi, Li Shangyuan, Wang Xiaofang, Zou Yinhong, Wang Yang

Coal Geology & Exploration

Background With the increasing demand for strategic metals and the gradual depletion of traditional metal deposit resources, coal and coal-bearing rock series are considered to be potential sources of rare metals, and coal series associated has become one of the main directions of current mineral exploration. A set of coal measure strata rich in niobium (Nb) and rare earth elements (REE) has been found in Zhina coalfield, western Guizhou and the contents of Nb and REE are as high as 334.89 μg/g and 1014.51 μg/g, respectively. This discovery is of great significance to the theoretical study of coal measure metal …

Advances In Research On The Activation And Recovery Of Strategic And Critical Valuable Metals From Coal Fly Ash, Wang Yuhao, Dong Zhongbing

Coal Geology & Exploration

Background Coal fly ash, a bulk solid waste byproduct from coal-fired power generation, has a global annual output exceeding 0.75 billion tons. Its disordered piling poses severe environmental risks, such as the generation of heavy metal leachate and PM_2.5 emissions. However, coal fly ash is rich in aluminum (Al 100‒200 mg/g), gallium (Ga 10‒300 μg/g), lithium (Li 1 300‒3 700 μg/g), and rare earth elements (REEs 200‒800 μg/g), establishing it as a potential alternative resource of strategic metals. Methods By analyzing the current domestic and international technologies for metal recovery from coal fly ash, this study expatiates on the …

An Investigation Of Hydro-Morphological Changes At The Estuarine Outlet Of Kitchener Drain, Northern Coast Of Egypt, Nada Mansour, Karim Nassar, Mahmoud El-Gamal, Tharwat Sarhan

Mansoura Engineering Journal

In recent years, sedimentation and coastline erosion have occurred in the Kitchener Drain, where its outflow meets the Mediterranean Sea. Several measures have been taken to mitigate the impact of these problems. Excavation continues toward the drain's outlet, and there have been multiple stages of hard protection work, such as groins along the drain's eastern and western banks. What would happen if the working near the drain was kept, where accretion and erosion are most severe. The Coastal Modelling System (CMS) was used to find it out. The two-dimensional hydrodynamic circulation model known as the CMS is outfitted with modules …

Electrical Energy Consumption Forecasting Based On Conventional And Artificial Intelligence Methods: A Comparison, Haya H. Binsalim, Jana Kamal, Salma Badaam, Danah Milyani, Ghadah S. Alyami, Aziza I. Hussein

Effat Undergraduate Research Journal

Artificial Intelligence (AI)-based models have been widely applied for energy consumption forecasting over the past decades. The purpose of this paper is to review and compare the classical techniques and the emerging new AI-based techniques used for forecasting electrical energy consumption in buildings. The findings revealed that the Artificial Neural Network (ANN) model achieved the lowest Mean Absolute Percentage Error (MAPE) of 0.928%. AI-based techniques have many advantages over classical techniques, such as their ability to handle a large amount of data and provide accurate and fast results.

Electrical Energy Consumption Forecasting Analysis Based On Conventional And Artificial Intelligence Methods: A Comparison, Aziza I. Hussein

Effat Undergraduate Research Journal

Artificial intelligence (AI)-based models have been widely applied for energy consumption forecasting over the past decades. The purpose of this paper is to review the classical techniques and the emerging new techniques based on AI of the building electrical energy consumption forecasting. The advantages of AI-based techniques over the classical are that AI methods can handle a large amount of data yet gives accurate results, the results can be found very quickly, in addition to AI having the ability to solve complex nonlinear patterns of raw data. This paper will discuss several studies using different models of forecasting based on …

Influence Of Obesity On Knee Joint Mechanics: A Subject-Specific Musculoskeletal Modeling Approach, Ryan C. Knowles

Electronic Theses and Dissertations

Obesity has been consistently linked to knee osteoarthritis (KOA), a debilitating joint disease. While prior work has shown that obese individuals often walk with altered biomechanics compared to normal-weight (NW) individuals, which may accelerate KOA progression, less is known about how these mechanics affect load distribution between the medial and lateral tibiofemoral (TF) compartments, particularly during higher-demand activities. This study developed subject-specific musculoskeletal models of five obese and five NW individuals, incorporating CT-based bone measurements and individualized joint contact points. Simulations were driven by six degree-of-freedom (6DOF) kinematics obtained from high-speed stereo radiography (HSSR) to predict TF loading and associated …

From Infection To Restoration: A Case Study On Dental Extraction In The Maxilla Anterior, Melanie Ramirez

Mako: NSU Undergraduate Student Journal

A dental implant is a restorative surgical procedure that serves as a solution to replace missing teeth that imitate the function, sensation, and appearance of natural teeth. The objective of this dental case study is to examine the diagnosis, treatment, and post-operation of a patient with a history of tooth loss and infection in the anterior maxilla. This case follows a 55-year-old patient, Jorge Marquez, name changed for confidentiality, who presented a severe tooth abscess on tooth #10 on the anterior maxilla which had previously undergone root canal treatment (Figure 1B). Radiographic evaluations illustrated the severity of the abscess the …

Detection Of Bacterial Genomic Dna Fragments Using The Mxene Crispr-Cas9 Field-Effect Transistor, Jiaoli Li, Ali Taheri, Weijia Liu, Ying Zhuo, Pengfei Ma, Chenglin Wu

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Clustered regularly interspaced short palindromic repeats (CRISPR)-based field-effect transistor (FET) sensors provide a promising platform for highly specific and amplification-free nucleic acid detection. However, their direct application in identifying target sequences within intact genomic DNA remains underexplored. We developed a CRISPR-Cas9 FET sensor for detecting DNA sequences by immobilizing Cas9 onto a graphene-MXene sensing interface via (3-aminopropyl)triethoxysilane (APTES) functionalization. The sensor targeted Stx1, a 440 bp laboratory-amplified fragment associated with Shiga toxin production in pathogenic E. coli. Gel electrophoresis confirmed the precise cleavage of Stx1, while the nontarget sequence Stx2 remained undetected. FET measurements further validated the sensor's specificity, showing …

Cost-Effectiveness Model For Reservoir Sediment Management Economics, Connor Ronald Hale

Theses and Dissertations

Reservoir sediment deposition poses a challenge to sustainable water supplies around the world. Sediment management has proven to be an expensive endeavor. Two models have been developed to guide economic analysis for reservoir sediment management, namely the Reservoir Sediment Economics Model (RSEM) and the Reservoir Conservation Model 2 (RESCON 2). While these are helpful tools for benefit-cost prefeasibility studies, they rely heavily on sometimes elusive estimations of the benefits of water supply. In this study, a new method for economic analysis is proposed that foregoes benefit-cost analysis in favor of a cost-effectiveness approach. The Sediment Management Cost-Effectiveness Model ranks sediment …

Research Synthesis Of Predicting Part 135 Accident Probability In Aviation: How The Bayesian Brain Ignores Declining Safety Standards, Jonathan R. Clarke

Journal of Aviation Technology and Engineering

Technological innovation has had an enormous effect on safety in aviation. However, in Part 135 operations, where technology is not as ubiquitous, the accident rates have plateaued. Human error is constantly misrepresented as being responsible for 70–80 percent of accidents, when it is clearly only one of several contributing factors. In commercial aviation, all accidents should be considered organizational failures, because by definition all defensive layers have been breached. Organizational failure, as it affects safety, should be identifiable and predictable from organizational behavior. Inevitably, in the aftermath of accidents the warning signs of poor behavior are seemingly obvious, yet there …

Assessing Cascaded Op-Amp And Pre-Current Amplifier Configurations In Transimpedance Amplifier Interfacing Circuits For Nano-Scale Current-Based Sensor Applications, Mohamed Mamdouh, Sameh O. Abdellatif

Electrical Engineering

This study provides a comprehensive analysis of two proposed configurations for current-to-voltage converters tailored for nano-scale current-based sensor applications, focusing on key performance metrics such as linearity, dynamic range, DC noise immunity, and power losses. The evaluation employed frequency-dependent analyses, including transient response, step response, input impedance, and frequency-dependent noise spectra, to compare a cascaded double output configuration with a pre-current amplifier design. The results indicate a trade-off between dynamic range and linearity, with the pre-current amplifier demonstrating a higher dynamic range but lower linearity compared to the cascaded configuration. Additionally, the current amplifier configuration exhibited advantages in power consumption …

Investigating Resilience Of Cyberattack Detection Using Lyapunov-Based Economic Model Predictive Control To Data Poisoning, Helen Durand, Akkarakaran Francis Leonard

Chemical Engineering and Materials Science Faculty Research Publications

Cyberattacks may be performed on process control systems due to their integration of networking and computing with physical systems. Prior work in our group has developed detection strategies for nonlinear systems under sensor, actuator, and combined sensor and actuator attacks which can ensure, under characterizable conditions, that attacks can be detected before they cause safety issues. However, this work did not take into account the potential that an attacker could attempt to provide data to a process that causes an attack to remain undetected but that also is consistent with different process dynamics than those which the process has. This …

Köppen-Geiger Climate Effects On F-15 Readiness Spares Package Parts, Maximus A. Fan

Theses and Dissertations

Readiness Spares Packages (RSP) are critical to deployed operations. Future demands of the Air Force require squadrons to operate in different climate environments from home stations. RSPs can sustain aircraft maintenance operations for up to 30 days. Currently, failure rates of parts within the RSP are assumed to be constant. This research aims to explore whether there is a difference in F-15 RSP failure rates when Koeppen climate classifications are taken into effect. The Koeppen-Geiger system classifies area climates based on the geography, elevation, and location. The history of operations and diversity of F-15 locations make the aircraft an ideal …

Polymeric Nanocarriers Functionalized With Peptides For Improved Glioblastoma Targeting And Blood–Brain Barrier Permeability, Cristian Antonio Wieczorek Villas Boas, Aaron Priester, Buck E. Rogers, Anthony J. Convertine

Materials Science and Engineering Faculty Research & Creative Works

We report the synthesis of polymeric conjugates designed to penetrate the blood–brain barrier (BBB) and selectively bind glioblastoma (GBM) cells through reversible addition–fragmentation chain transfer (RAFT) polymerization. The resulting materials were engineered to contain peptide macromonomers for cell-specific targeting and integrated DOTA units to facilitate radiolabeling with copper-64 (⁶⁴Cu), yielding radiolabeled conjugates with greater than 95% radiochemical purity. In biodistribution assessments conducted in mice, C1C2 peptide-conjugated polymers showed significantly improved accumulation in brain tissue, supported by brain perfusion analyses confirming efficient BBB penetration. Additionally, flow cytometry evaluations demonstrated specific affinity of GBM-targeted polymer formulations toward U87 glioblastoma cells. …

U.S News & World Report 2025 Graduate Program Rankings, Unlv & Unr, Dre Boyd-Weatherly, Caitlin J. Saladino, William E. Brown Jr.

Higher Education

This fact sheet presents 2025 graduate program rankings for the University of Nevada, Las Vegas (UNLV) and for the University of Nevada, Reno (UNR) based on the data published in spring 2025 by U.S. News & World Report. The graduate program categories reported include business, education, engineering, fine arts, law, medicine and health care, sciences and mathematics, and social sciences and humanities.

Re-Engaging Driver Attention Using Chatgpt: A Multimodal Study On Stress Impact And Driving Performance, Alaa Zaki Elfiqi

Theses and Dissertations

Driving is considered a complex task that requires continuous focus and attention from the driver. Driving performance can also be impacted by changes in the driver’s stress level. However, limited research explores methods to address this challenge. With the current advances in Large Language Models (LLMs) and their ability to engage in human-like interaction, this study investigates the potential of using ChatGPT, designed to speak Egyptian Arabic, in re-engaging driver attention under different driving scenarios for low-stress and high-stress conditions within a virtual reality (VR) environment driving simulator. Drivers were asked to follow a leading car into two scenarios with …

Investigation Of A Divergent Triangle Construct For Internal Fixation Of Vertical Femoral Neck Fractures Using Experimental And Finite Element Analysis Methods, Hannah Rainey

Masters Theses

Hip fractures are a significant public health issue as they are a commonly encountered problem and have a high rate of mortality. The fracture of the femoral neck is difficult to treat due to the geometry of the proximal femur and the weight-bearing capacity that the structure must comply with. Internal fixation of the femoral neck is often accomplished with three screws inserted along the axis of the femoral neck. The optimal configuration and number of these screws is not agreed upon in the literature. The purpose of this study was to conduct a pilot investigation on the biomechanical performance …

Early Detection Of Oak Wilt Using Unmanned Aerial Vehicles (Uav) & Computer Vision, Muttaki I. Bismoy

Masters Theses

Forests are critical ecosystems, delivering services such as biodiversity conservation, climate regulation, timber production, and recreation. However, they face increasing threats from pathogens like Bretziella fagacearum, which causes Oak Wilt, a lethal disease that disrupts water transport in oak trees, leading to canopy dieback and eventual death. Traditional detection methods rely on manual ground surveys, which are labor-intensive, time-consuming, and prone to error, particularly in early disease stages.

This research presents an automated, scalable, high-precision Oak Wilt detection system using Unmanned Aerial Vehicles (UAVs) combined with deep learning-based computer vision. Expanding on earlier work with a lightweight CNN achieving an …

Correlations Between Hemodynamics And Radiomic Features In Thrombosed Intracranial Aneurysms, Zonghan Lyu, Andres Gudino, Navami Shenoy, Carlos Dier, Elena Sagues, Jingfeng Jiang, Edgar A. Samaniego

Michigan Tech Publications

Purpose: Evaluating intracranial aneurysm (IA) rupture risk is essential for guiding management. Although intrasaccular thrombosis (IST) is less common, it can contribute to aneurysm growth, mass effect, and rupture. Aneurysm wall enhancement (AWE) on high-resolution MRI (HR-MRI) offers valuable insight into IST and IA progression. Using radiomics, we extracted spatial information of the aneurysm wall to characterize AWE. This study aimed to explore correlations between radiomics-based AWE profiles and gross hemodynamic parameters, integrating imaging and flow dynamics to better understand IST. Methods: Radiomic analysis was conducted on a cohort of 3T HR-MRI scans from IA with IST. Three-dimensional vascular reconstructions …

Palpation Characteristics Of An Instrumented Virtual Cricothyroidotomy Simulator, Melih Turkseven, Trudi Di Qi, Ganesh Sankaranarayanan, Suvranu De

Engineering Faculty Articles and Research

Cricothyroidotomy (CCT) is a critical, life-saving procedure requiring the identification of key neck landmarks through palpation. Interactive virtual simulation offers a promising, cost-effective approach to CCT training with high visual realism. However, developing the palpation skills necessary for CCT requires a haptic interface with tactile sensitivity comparable to human fingers. Such interfaces are often represented by plastic partial mannequins, which require further adaptation to integrate into virtual environments. This study introduces an instrumented physical palpation interface for CCT, integrated into a virtual surgical simulator, and tested on 10 surgeons who practiced the procedure over a training period. Data on haptic …

Moment Ensemble Approaches For Estimation And Robust Quantum Control, Andre Luiz Paes De Lima

McKelvey School of Engineering Graduate Student Theses & Dissertations

Large-scale population dynamics governed by ensemble systems present significant challenges due to their inherently high dimensionality. Recent advances have demonstrated the effectiveness of moment-based methods (particularly those employing polynomial bases such as Legendre and Chebyshev polynomials) when integrated with optimization techniques for control design in ensemble systems. However, these methods have not been extensively explored for enhancing robustness against systematic noise, nor have they been widely applied to complex quantum systems involving multi-parameter configurations and entanglement phenomena. In this work, we extend the application of moment methods in ensemble systems through two projects. Initially by developing a Kalman filter analogue, …

A Contemporary Approach For Exploring The Influence Of Detoxification And Standardization Of Traditional Metallopharmaceutical Product Pharmacological And Toxicological Aspects, Malarvizhi K

Theses and Dissertations

Polyherbomineral formulation possess unique medicinal properties due to the presence of metals and minerals as integral part, as processed in addition to specific herbals. There is an increased interest in metallopharmaceuticals in clinical and research areas, because of their immense therapeutic efficiency towards multiple diseases and evidence for non-toxic claim. Sivanar Amirtham is one of the polyherbomineral Siddha medicine recommended for the treatment of various respiratory diseases and other ailments including antidote therapy for poisonous bites. The present research work attempted for standardization of Sivanar Amirtham preparation as per the traditional standard protocols (including the detoxification process of raw materials) …

Magnetic Molecularly Imprinted Polymers For Quercetin Adsorption: Fabrication, Characterization, And Application, Vinitha Ug

Theses and Dissertations

A highly selective Magnetic Molecularly Imprinted Polymer (MMIP) was developed for the detection and purification of Quercetin. The Density Functional Theory was utilized for the selection of suitable monomers based on binding energy interaction between quercetin and monomers (Acrylamide, Acrylonitrile, Methacrylic Acid). From computational studies, Acrylamide was selected as a suitable monomer for the synthesis of MMIP. Under ultrasound irradiation both quercetin and naringin imprinted materials MMIP-Q and MMIP-N were fabricated.

Compared to ultrasound-assisted synthesis, Microwave Synthesis provides uniform heat transfer throughout the reaction solution, which enables uniformity in the size of synthesised material, increases the yield of material and …

Facile Fabrication Of Protein-Polysaccharide Conjugate Multifilament Nerve Guidance Conduit For Peripheral Nerve Regeneration, Preethy Amruthavarshini R

Theses and Dissertations

Long segmental defects in peripheral nerves impair sensory and motor function by disrupting neural impulse transmission. End-to-end autologous grafting with proper fascicular complementation has demonstrated functional recovery per the Medical Research Council Classification (MRCC). However, obtaining donor nerve tissue exceeding 30 mm remains a significant challenge. Artificial hollow conduits serve as an alternative but are limited to defects smaller than 30 mm due to inadequate innervation across the lumen.

Multichannel nerve guidance conduits (mNGCs) have emerged as a promising solution by enhancing fascicular complementation similar to autografts. This study presents a two-step approach for fabricating nerve conduits with precise fascicular …

Impact Of Ionic Liquids On The Treatment Of Various Derivatives Of Prosopis Juliflora For Removing Toxic Pollutants From Wastewater, Karthikeyan A

Theses and Dissertations

Water resources are increasingly contaminated by toxic pollutants, particularly industrial effluents, posing significant environmental concerns. Addressing the toxicity of these pollutants, especially those released from textile industries, presents challenges due to their harmful effects on living organisms. Various treatment methods are employed to mitigate this issue, including coagulation, flocculation, membrane filtration, photocatalytic degradation, adsorption, anaerobic processes, and chemical oxidation. Among these, adsorption emerges as an effective and economical method due to its minimal secondary contamination, negligible sludge production, and the use of inexpensive agricultural and marine waste materials.

This study examines the ability of Prosopis juliflora treated with imidazolium-based ionic …

Ai Based Early Detection Of Hormonal Imbalance And Poly-Cystic Ovary Syndrome In Young Women, Reka S

Theses and Dissertations

A hormonal disorder, Poly-Cystic Ovary Syndrome (PCOS) usually affects women during the reproductive age. It is characterised by imbalances in hormones, particularly a rise in the female body's androgen level (male hormone) and enlarged ovaries with small cysts. PCOS can cause ovarian cysts, weight gain, acne, excessive hair growth, insulin resistance, and irregular menstrual cycles along with other health problems. While the exact origin of PCOS is uncertain and its symptoms are unclear, diagnosing PCOS in real-world conditions is a difficult task. Therefore, prompt and precise PCOS diagnosis is essential for efficient treatment and for averting long-term issues.

Clinicians typically …

Bioprospecting Of Wheat Straw Pyrolysis Aqueous Phase To Combat Multi-Drug Resistant Pathogens, Srividhya K

Theses and Dissertations

Hospital-acquired infections (HAIs) significantly contribute to the emergence and spread of antimicrobial resistance (AMR), primarily through the contamination of high-touch surfaces. Current disinfectants have drawbacks like high environmental persistence, ecotoxicity, and resistance development, prompting the need for environmentally friendly alternatives.

One potential approach is pyrolysis, during which the biomass components are broken down into solid, liquid, and pyro-gas. The aqueous phase of the liquid fraction is usually discarded as waste, but it contains a variety of organic compounds that have the potential for antibacterial and antifungal activity. The present study assessed the anti-infective and anti-biofilm properties of wheat straw pyrolysis …

Design And Investigation Of Deep Eutectic Solvent-Assisted Extractive Fermentation Of Biomolecules, Ramya M

Theses and Dissertations

The increasing demand for sustainable and efficient bioprocessing techniques has prompted the development of novel separation strategies integrating bioproduction with downstream processing. Extractive fermentation has emerged as a promising process intensification to overcome product inhibition and enhance productivity by constantly removing target biomolecules from the fermentation medium. Although the extractive fermentation of acids and alcohols has been extensively studied, less attention has been focused on green solvents and their compatibility, phase-forming abilities, and reactor configurations.

Therefore, advancing extractive fermentation technology necessitates comprehensive studies on solvent systems and the development of modified bioreactor configurations to aid future optimization. Initially, 22 DESs …

Investigation Of Dependency Parsing Techniques For Digital Document Analysis Through Deep Learning Approach, Rekah D Ms

Theses and Dissertations

Digital document dependency parsing is a significant task in natural language processing. Dependency parsing supports verification of the grammatical correctness of a sentence besides enabling extraction of relevant documents. Inappropriate extraction of features may result in falsely parsing a document, leading to decreased accuracy. Machine learning methods have been employed to perform feature extraction. However, selecting pertinent features was never achieved which minimizes the time consumption and overhead.

Hence, novel machine learning and deep learning techniques have been designed in our work for accurate and computationally efficient digital document analytics through dependency parsing. Four different contributions have been proposed for …