Physical Sciences and Mathematics Commons^™

Customer Churn Prediction, Deepshikha Wadikar

Dissertations

Churned customers identification plays an essential role for the functioning and growth of any business. Identification of churned customers can help the business to know the reasons for the churn and they can plan their market strategies accordingly to enhance the growth of a business. This research is aimed at developing a machine learning model that can precisely predict the churned customers from the total customers of a Credit Union financial institution. A quantitative and deductive research strategies are employed to build a supervised machine learning model that addresses the class imbalance problem handled feature selection and efficiently predict the …

Metal Ions Impact On Shewanella Oneidensis Mr-1 Adhesion To Ito Electrode And The Enhancement Of Current Output, Aisha Awad Alshahrani

Dissertations

The goal of this study is to enhance the efficiency of bacterial extracellular electron transfer (EET) in Shewanella oneidensis MR-1 by enhancing adhesion to the electrode's surface. Our results clearly show a major difference in the attachment and behavior of Shewanella oneidensis MR-1 for Ca2+, Pb2+, Cd2+, and Mg2+, compared to the control. the final microbial coverage, as measured by confocal microscopy and cathodic peak charge in cyclic voltammetry (Qpc), increases with increasing metal ion concentrations. We found the cells attached to the electrode increased more with the addition of metal ion concentrations in the following order of metals: Ca2+ …

Optimization Of Microbial Fuel Cells, Norberto M. Gonzalez

Dissertations

Optimization of microbial fuel cells is investigated by utilizing Shewanella oneidensis as a model microorganism. the microbe's ability to grow and use glucose as a carbon source is explored under varying oxygen environments through an offline PMP derivatization method and HPLC analysis. Shewanella growth and glucose utilization is enhanced under aerobic environments; however, under microaerobic environments the addition of ferric iron results in a faster exponential growth initialization. a flavin mononucleotide modified indium tin oxide electrode is prepared and characterized for its usefulness in microbial fuel cells by controlled potential electrolysis, cyclic voltammetry, and electrochemical impedance spectroscopy studies. the electrode …

Lewis Acid-Carbonyl Solution Interactions And Their Implications In Catalytic Systems, Carly Soren Hanson

Dissertations

The utilization of Lewis acids to activate substrates containing carbonyls is ubiquitous in organic synthetic methods. in order to facilitate the development of novel reaction pathways and understand existing methods, it is necessary to determine the solution interactions between Lewis acids and Lewis bases. Historically, the characterization of the interactions of Lewis pairs has relied on solid state infrared (IR) spectroscopy and X-ray crystallography, as well as in situ NMR. I have developed a method utilizing in situ IR spectroscopy and solution conductivity towards the identification of the solution structures formed when a range of carbonyl compounds are combined with …

Development Of Methods For The Removal Of Selected Pollutants From Several Matrices And Identification Of Unknown Pollutants Adsorbed Onto Plastics Collected From Freshwater, Kathryn Marie Renyer

Dissertations

Plastic pollution represents one of greatest anthropogenic threats to the environment. Five to ten billion tons of plastic are manufactured every year. Currently, Earth's ecosystem is contaminated with billions of tons of plastic debris, much of which cannot be recycled. Over time, this plastic debris decomposes into small particles. Small plastic particles are known to adsorb toxic compounds in marine environments. My research is concerned with creating novel methods for the detection and quantification of selected persistent organic pollutants from several media. Specifically, I developed methods for the detection and quantification of endosulfan sulfate (ESS) from Lumbricus terrestris tissue and …

Electron Transfer Of Shewanella Oneidensis Mr-1 At Clay-Modified Ito Electrode, Reem Faez Alshehri

Dissertations

Various strategies have been established to enhance the extracellular electron transfer and energy output capability of microbial fuel cells, with the majority being aimed at anode modification. The anode has a significant impact on the electricity generation performance of MFCs because it is in direct contact with the microorganisms. The materials of the anode should be favorable for the bacterial cell and capable to facilitate the electron transfer. Developing of an electrode using low-cost and effective materials assists to enhance the bacterial cell attachment and extracellular electron transfer. This provides a significant improvement in MFC performance. In this study, clay …

Brain Disease Detection From Eegs: Comparing Spiking And Recurrent Neural Networks For Non-Stationary Time Series Classification, Hristo Stoev

Dissertations

Modeling non-stationary time series data is a difficult problem area in AI, due to the fact that the statistical properties of the data change as the time series progresses. This complicates the classification of non-stationary time series, which is a method used in the detection of brain diseases from EEGs. Various techniques have been developed in the field of deep learning for tackling this problem, with recurrent neural networks (RNN) approaches utilising Long short-term memory (LSTM) architectures achieving a high degree of success. This study implements a new, spiking neural network-based approach to time series classification for the purpose of …

Content-Based Filtering Recommendation Approach To Label Irish Legal Judgements, Sandesh Gangadhar

Dissertations

Machine learning approaches are applied across several domains to either simplify or automate tasks which directly result in saved time or cost. Text document labelling is one such task that requires immense human knowledge about the domain and efforts to review, understand and label the documents. The company Stare Decisis summarises legal judgements and labels them as they are made available on Irish public legal source www.courts.ie. This research presents a recommendation-based approach to reduce the time for solicitors at Stare Decisis by reducing many numbers of available labels to pick from to a concentrated few that potentially contains the …

Convex Relaxations Of A Continuum Aggregation Model, And Their Efficient Numerical Solution, Mahdi Bandegi

Dissertations

In this dissertation, the global minimization of a large deviations rate function (the Helmholtz free energy functional) for the Boltzmann distribution is discussed. The Helmholtz functional arises in large systems of interacting particles — which are widely used as models in computational chemistry and molecular dynamics. Global minimizers of the rate function (Helmholtz functional) characterize the asymptotics of the partition function and thereby determine many important physical properties such as self-assembly, or phase transitions. Finding and verifying local minima to the Helmholtz free energy functional is relatively straightforward. However, finding and verifying global minima is much more difficult since the …

Quantitative Metrics For Mutation Testing, Amani M. Ayad

Dissertations

Program mutation is the process of generating versions of a base program by applying elementary syntactic modifications; this technique has been used in program testing in a variety of applications, most notably to assess the quality of a test data set. A good test set will discover the difference between the original program and mutant except if the mutant is semantically equivalent to the original program, despite being syntactically distinct.

Equivalent mutants are a major nuisance in the practice of mutation testing, because they introduce a significant amount of bias and uncertainty in the analysis of test results; indeed, mutants …

Dimension Reduction Techniques For High Dimensional And Ultra-High Dimensional Data, Subha Datta

Dissertations

This dissertation introduces two statistical techniques to tackle high-dimensional data, which is very commonplace nowadays. It consists of two topics which are inter-related by a common link, dimension reduction.

The first topic is a recently introduced classification technique, the weighted principal support vector machine (WPSVM), which is incorporated into a spatial point process framework. The WPSVM possesses an additional parameter, a weight parameter, besides the regularization parameter. Most statistical techniques, including WPSVM, have an inherent assumption of independence, which means the data points are not connected with each other in any manner. But spatial data violates this assumption. Correlation between …

Early Detection Of Fake News On Social Media, Yang Liu

Dissertations

The ever-increasing popularity and convenience of social media enable the rapid widespread of fake news, which can cause a series of negative impacts both on individuals and society. Early detection of fake news is essential to minimize its social harm. Existing machine learning approaches are incapable of detecting a fake news story soon after it starts to spread, because they require certain amounts of data to reach decent effectiveness which take time to accumulate. To solve this problem, this research first analyzes and finds that, on social media, the user characteristics of fake news spreaders distribute significantly differently from those …

Investigation Of Small-Scale Energy Release And Transfer Processes In The Solar Atmosphere With High-Resolution Observations In Infrared, Xu Yang

Dissertations

Solar spectrum in the infrared (IR) contains abundant information of solar activities, however, it has not spectral lines in the solar IR spectrum provide different tools to probe the solar atmosphere in various heights. This radiation band in such relatively long wavelength includes various atom and molecule spectral lines that are generated by relatively small energy level transitions. The temperature-sensitive and highly dynamic spectral lines could reveal the energy transmission process more easily than those in the visible wavelength of solar emission. Moreover, the better magnetic sensitivities for the infrared lines resulting from their longer wavelength make them detect the …

Bio-Inspired Learning And Hardware Acceleration With Emerging Memories, Shruti R. Kulkarni

Dissertations

Machine Learning has permeated many aspects of engineering, ranging from the Internet of Things (IoT) applications to big data analytics. While computing resources available to implement these algorithms have become more powerful, both in terms of the complexity of problems that can be solved and the overall computing speed, the huge energy costs involved remains a significant challenge. The human brain, which has evolved over millions of years, is widely accepted as the most efficient control and cognitive processing platform. Neuro-biological studies have established that information processing in the human brain relies on impulse like signals emitted by neurons called …

Amyloid Proteins And Fibrils Stability, Farbod Mahmoudinobar

Dissertations

Compared to globular proteins that have a stable native structure, intrinsically disordered peptides (IDP) sample an ensemble of structures without folding into a native conformation.One example of IDP is the amyloid-beta(Abeta) protein which is the main constituent of senile plaques in the brain of Alzheimer's patients.Understanding the process by which IDPs undergo structural changes to form oligomers that eventually aggregate into senile plaques/amyloid fibrils may significantly advance the development of novel therapeutic methods to treat neurodegenerative diseases, for which there is no cure to date. This dissertation has two main objectives. The first one is to investigate and identify structural …

Mitochondria Imaging And Targeted Cancer Treatment, Tinghan Zhao

Dissertations

Mitochondria are essential organelles as the site of respiration in eukaryotic cells and are involved in many crucial functions in cell life. Dysfunction of mitochondrial metabolism and irregular morphology have been frequently found in human cancers. The capability of imaging mitochondria as well as regulating their microenvironment is important both scientifically and clinically. Mitochondria penetrating peptides (MPPs), certain peptides that are composed of cationic and hydrophobic amino acids, are good candidates for mitochondria targeting. Herein, a novel MPP, D-argine-phenylalanine-D-argine-phenylalanine-D-argine-phenylalanine-NH₂ (rFrFrF), is conjugated with a rhodamine-based fluorescent chromophore (TAMRA). The TAMRA-rFrFrF probe exhibits advantageous properties for long-term mitochondria tracking of …

Topics On High Dimensional Selective Inference, Yan Zhang

Dissertations

In such applications as identifying differentially expressed genes in micro-array experiments or assessing safety and efficacy of drugs in clinical trials, researchers often report confidence intervals (CIs) and p-values only for the selected parameters, which is called selective inference. While constructing multiple CIs for the selected parameters, it is common practice to ignore issue of selection and multiplicity. Although protection against the effect of selection is sufficient in some cases, simultaneous coverage should be also needed in real applications. For example, in clinical trials, multiple endpoints are considered to assess effects of a drug and the ultimate decision often depends …

Cancer Risk Prediction With Whole Exome Sequencing And Machine Learning, Abdulrhman Fahad M Aljouie

Dissertations

Accurate cancer risk and survival time prediction are important problems in personalized medicine, where disease diagnosis and prognosis are tuned to individuals based on their genetic material. Cancer risk prediction provides an informed decision about making regular screening that helps to detect disease at the early stage and therefore increases the probability of successful treatments. Cancer risk prediction is a challenging problem. Lifestyle, environment, family history, and genetic predisposition are some factors that influence the disease onset. Cancer risk prediction based on predisposing genetic variants has been studied extensively. Most studies have examined the predictive ability of variants in known …

Reduction In Salt Deposition On Carbon Nano-Tube Immobilized Membrane During Desalination Via Membrane Distillation, Madihah Saud Humoud

Dissertations

As water scarcity increases globally under the stresses of increasing demand, aquifer depletion, and climate change, the market for efficient desalination technologies has grown rapidly to fill the void. One such developing technology, membrane distillation (MD), has found much interest in the scientific community. MD has also been powered by solar energy and waste heat resources because it can be operated at relatively low temperatures. Recent studies indicate that MD could potentially achieve the efficiencies of state-of-the-art mature thermal desalination technologies, although additional engineering and scientific challenges must first be overcome.

MD can be used to treat high salinity water …

Using Machine Learning Classification Methods To Detect The Presence Of Heart Disease, Nestor Pereira

Dissertations

Cardiovascular disease (CVD) is the most common cause of death in Ireland, and probably, worldwide. According to the Health Service Executive (HSE) cardiovascular disease accounting for 36% of all deaths, and one important fact, 22% of premature deaths (under age 65) are from CVD.

Using data from the Heart Disease UCI Data Set (UCI Machine Learning), we use machine learning techniques to detect the presence or absence of heart disease in the patient according to 14 features provide for this dataset. The different results are compared based on accuracy performance, confusion matrix and area under the Receiver Operating Characteristics (ROC) …

Factor Analysis Of Mixed Data (Famd) And Multiple Linear Regression In R, Nestor Pereira

Dissertations

In the previous projects, it has been worked to statistically analysis of the factors to impact the score of the subjects of Mathematics and Portuguese for several groups of the student from secondary school from Portugal.

In this project will be interested in finding a model, hypothetically multiple linear regression, to predict the final score, dependent variable G3, of the student according to some features divide into two groups. One group, analyses the features or predictors which impact in the final score more related to the performance of the students, means variables like study time or past failures. The second …

Adsorption Of Polyisobutylene-Based Dispersants Onto Carbon Black, Travis Paul Holbrook

Dissertations

The formation of carbonaceous by-products (e.g. soot) during the operation of an internal combustion engine is unavoidable and the aggregation of this soot leads to deleterious effects including abrasive wear of the engine, increased oil viscosities, and sludge deposition. Dispersants, which are composed of a hydrophobic tail and a polar headgroup, are used as oil additives to aid in the suspension and stabilization of the soot particles. Polyisobutylene succinimide (PIBSI) is the most well-studied class of dispersants and is characterized by a linear architecture and polyamine headgroup that interacts with soot by acid-base and dipole-dipole interactions. As such, there remains …

The Antimicrobial Activity And Cellular Targets Of Plant Derived Aldehydes And Degradable Pro-Antimicrobial Networks In Pseudomonas Aeruginosa, Yetunde Adewunmi

Dissertations

Essential oils (EOs) are plant-derived products that have been long exploited for their antimicrobial activities in medicine, agriculture, and food preservation. EOs represent a promising alternative to conventional antibiotics due to the broad-range antimicrobial activity, low toxicity to human commensal bacteria, and the capacity to kill microorganisms without promoting resistance. Despite the progress in the understanding of the biological activity of EOs, many aspects of their mode of action remain inconclusive. The overarching aim of this work was to address these gaps by studying molecular interactions between antimicrobial plant aldehydes and the opportunistic human pathogen Pseudomonas aeruginosa. We initiated …

Developing A Computational Framework For A Construction Scheduling Decision Support Web Based Expert System, Feroz Ahmed

Dissertations

Decision-making is one of the basic cognitive processes of human behaviors by which a preferred option or a course of action is chosen from among a set of alternatives based on certain criteria. Decision-making is the thought process of selecting a logical choice from the available options. When trying to make a good decision, all the positives and negatives of each option should be evaluated. This decision-making process is particularly challenging during the preparation of a construction schedule, where it is difficult for a human to analyze all possible outcomes of each and every situation because, construction of a project …

Social Media Sentiment Analysis With A Deep Neural Network: An Enhanced Approach Using User Behavioral Information, Ahmed Sulaiman M. Alharbi

Dissertations

Sentiment analysis on social media such as Twitter has become a very important and challenging task. Due to the characteristics of such data (including tweet length, spelling errors, abbreviations, and special characters), the sentiment analysis task in such an environment requires a non-traditional approach. Moreover, social media sentiment analysis constitutes a fundamental problem with many interesting applications, such as for Business Intelligence, Medical Monitoring, and National Security. Most current social media sentiment classification methods judge the sentiment polarity primarily according to textual content and neglect other information on these platforms. In this research, we propose deep learning based frameworks that …

Embedded Silver Nanoparticles For Metal Enhanced Photoluminescence, Shahid Iqbal

Dissertations

Imaging of biologically significant molecules using plasmons of Metal Nanoparticles (MNPs) is gaining attention in the research community. Localized Surface Plasmon Resonance (LSPR) is the coherent oscillation of conduction electrons of MNPs. The biologically significant molecule is labeled with the fluorophore molecule to get the image. This approach is widely used in clinical practices, however, low intensity light emission from the labeled molecule makes it difficult to image the biologically significant material. One way to improve the weak intensities of fluorophore is to enhance the brightness using a process called Metal Enhanced Photoluminescence (MEP). This phenomenon occurs in the close …

Establishing The Role Of The Mississippi-Alabama Barrier Islands In Mississippi Sound And Bight Circulation Using Observational Data Analysis And A Coastal Model, Laura Hode

Dissertations

The Mississippi-Alabama barrier islands restrict exchange between the Mississippi Sound and Mississippi Bight in the northern Gulf of Mexico. The islands also act as storm breaks for tropical cyclones, so their continued existence sustains marine ecosystems and protects coastal communities. However, the chain has undergone extensive segmentation, erosion, and westward migration in the past two hundred years. The islands are now more susceptible to further erosion (Pendleton et al., 2013; Morton, 2007). Additional reduction in island subaerial land extent would alter circulation in the Mississippi Sound and Bight.

Consequently, this study targeted the two most vulnerable barrier islands in the …

Ultrafast Relaxation Dynamics In Graphene Oxide-Dye And Perovskites Nanocomposites, Abubkr A. Arzaq Abuhagr

Dissertations

Novel materials such as graphene oxide (GO), reduced graphene oxide (RGO), and Perovskites nanocomposites nanosheets have shown interesting electrical and optical properties. These materials have shown prominence in research regarding optical sensing applications. The interaction of different fluorescent molecules like dye molecules with GO, and RGO have been studied recently to develop novel optical sensors, photo-catalysts, and light-harvesting agents. In this study, we have monitored the excited state interactions of dyes covalently attached to GO and RGO nanosheets. Three amine derivatives of anthracene, pyrene, and coumarin were covalently bound to different systems via amide bonds and diazotization. Characterization of different …

Scalable Algorithms And Hybrid Parallelization Strategies For Multivariate Integration With Paradapt And Cuda, Omofolakunmi Elizabeth Olagbemi

Dissertations

The evaluation of numerical integrals finds applications in fields such as High Energy Physics, Bayesian Statistics, Stochastic Geometry, Molecular Modeling and Medical Physics. The erratic behavior of some integrands due to singularities, peaks, or ridges in the integration region suggests the need for reliable algorithms and software that not only provide an estimation of the integral with a level of accuracy acceptable to the user, but also perform this task in a timely manner. We developed ParAdapt, a numerical integration software based on a classic global adaptive strategy, which employs Graphical Processing Units (GPUs) in providing integral evaluations. Specifically, ParAdapt …

Smart Sensors With Dual Modes Of Signal Transduction For Monitoring Molecules Pertinent To Health And The Environment, Jared T. Wabeke

Dissertations

The dissertation focuses on the design and synthesis of smart materials for the detection of molecules pertinent to environmental protection and healthcare. The use of computational simulations is pivotal toward advancing molecular design for targeted applications. Research was conducted to investigate the use of simulations to develop novel sensors with dual modes of signal transduction. The molecular properties were determined using computational modelling, and then used to elucidate the binding mechanism of the corresponding sensor complexes. Several molecules were produced that respond to important organic analytes, such as glucose and fenthion, an organophosphorus pesticide. Glucose is an exceedingly important biological …