Digital Commons Network^™

Determining Knowledge From Student Performance Prediction Using Machine Learning, Wala El Rashied Mohamed

Theses

Recent years have seen a rapid development in the field of educational data mining (EDM), enhancing the ability to trace student knowledge. Data from intelligent tutoring systems (ITS) have been analyzed and interpreted by multiple researchers seeking to measure students’ knowledge as it evolves. Human nature, as well as other factors, makes it difficult to determine whether or not students are knowledgeable. This thesis sets out to examine the level of students’ knowledge by predicting their current and future academic performance based on records of their historical interactions. By restructuring data and considering a student perspective, we can gain insight …

A Multi-Criteria Decision-Making (Mcdm) Approach For Data-Driven Distance Learning Recommendations, Aysha Meshaal Alshamsi

Theses

Distance learning has been adopted as an alternative learning strategy to the dominant face-to-face teaching methodology. It has been largely implemented by many governments worldwide due to the spread of the COVID-19 pandemic and the implication in enforcing lockdown and social distancing. In emergency situations distance learning is referred to as Emergency Remote Teaching (ERT). Due to this dynamic, sudden shift, and scaling demand in distance learning, many challenges have been accentuated. These include technological adoption, student commitments, parent involvement, and teacher extra burden management, changes in the organization methodology, in addition to government development of new guidelines and regulations …

Quantifying The Effects Of Customer Predictability On Battery Energy Storage System Cost And Emissions, Mudit Bhadresh Purohit

Theses

Electricity providers are using variable pricing to encourage customers to shift energy consumption from “peak” times. This presents a great opportunity for the customers to reduce their bills using this variable pricing strategy coupled with a battery energy storage system (BESS). The schedule of charging and discharging the BESS depends on the forecasted customer demand data. Forecasts are bound to have a certain degree of error associated with them, and hence it becomes important to understand the effect of these forecasting errors on the cost and the emissions associated with scheduling of the BESS. In this work, a method has …

Un-Fair Trojan: Targeted Backdoor Attacks Against Model Fairness, Nicholas Furth

Theses

Machine learning models have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a single global model communicating only using local gradients, the issue of attacks become more prevalent and complex. Previously published works revolve around solving these issues both individually and jointly. However, there has been little study on the effects of attacks against model fairness. Demonstrated in this work, a flexible attack, which we call Un-Fair …

A Detailed Parameter Study Into The Dermal Absorption Of Chemical Warfare Agents And The Effects Of Pharmacokinetics, Koko Lear

Theses

Chemical warfare agents (CWAs) are substances of varying toxicity profiles. These chemicals exhibit complex dynamics and pose a serious health risk when released into the environment. A mathematical model based on Fick’s second law of diffusion was developed to comprehend how these compounds were absorbed into the skin. The analysis applied to both small and large doses and, successfully, predicted experimental results. This work also includes the effects of CWA physicochemical properties on evaporation and dermal absorption through the stratum corneum. A sensitivity analysis was conducted to assess the impacts of small variations in the initial dose, environmental conditions, and …

The Interconnection Of The Vestibular And Oculomotor Systems Analyzed In Healthy Young Adults By Examining Postural Sway, Cassandra Martin

Theses

In order to study the human brain in a non-invasive way, the vestibular and oculomotor systems have been analyzed simultaneously. To achieve this, an eye movement and balance assessment was conducted for 29 (23 male; 21.6 ± 3.8 years) healthy participants with no history of concussions, brain injuries, vertigo, migraines, brain surgeries, eye surgeries, or amblyopia. The tasks consisted of eyes open, eyes closed, horizontal saccades, vertical saccades, vergence jumps, horizontal vestibulo-ocular reflex (VOR), and vertical VOR. Each task was completed in two stances: feet shoulder width apart and feet together. Distance, velocity, sway area, center of pressure (COP) frequency, …

Smart City Operation System An Innovative Approach For A Collaborative Smart City Platform, Mohamed Gaber Abouelkassem

Theses

Command and Control Centers (CCCs) are an essential building block in the structure of smart cities. Typically, in most developed cities, CCCs are built to serve a certain function or application as a dedicated and standalone center that belongs to a certain entity or city department, such as transportation, police and security, utilities, or municipal operations departments, etc. The integrated command and control center (ICCC) has a central platform that integrates some of the city systems. The ICCC output is a sophisticated dashboard that acts as an interface to display and analyze collected data with the objective to help operators …

Low-Rank Clustering Via Lp1-Pca, Matt Krol

Theses

In recent years, subspace clustering has found many practical use cases which include, for example, image segmentation, motion segmentation, and facial clustering. The image and video data that is common to these types of applications often has high dimensionality. Rather than viewing high dimensionality as a drawback, we propose a novel algorithm for subspace clustering that takes advantage of the high dimensional nature of such data. We call this algorithm LP1-PCA Spectral Clustering. Specifically, we introduce a concept that we call cluster-ID sparsity, and we propose an algorithm called LP1-PCA to attain this in low data dimensions. Our novel LP1-PCA …

Using An Agent Based Model And Deep Learning To Simulate And Infer Market Behavior On Networks, Benjamin Weir

Theses

The financial markets have been affected by the recent advancements in social media. Retail traders often use social media as a source of financial information. This thesis provides a mathematical proof of concept for how retail traders on social media can cause a large change in market price and that it is possible to identify the factors that drive the price change before it is seen in the market. An Agent Based Model is used to simulate a self-contained artificial market on a network. Traders gather pricing information from social media posts created by traders on the network and their …

Exploring Digital Checking: Evolution, Technology, And Future Directions, Mohammed Hasan Saleh Bamasood

Theses

This capstone project sought to explore the evolution of digital/electronic checking, assess how technology and other factors fueled the development of digital electronic checking, evaluate if the sampled research literature indicate that the desirable attributes of a payment instrument have been fully addressed; and analyze issues that deter the digital/electronic checking system to fully integrate the six most desirable attributes for a payment instrument in order to recommend possible directions for future research and design implementation. The project utilized integrative review as its methodology and adopted a theoretical framework based on the input-process-output model to guide the analysis and presentation …

Opinion Mining Of Phone Sitting Feature, Atiq Yousuf Ahmad

Theses

This report aims to evaluate opinion mining of customers about phone sitting features in cell phones in different brands across the world by using data mining techniques. Therefore, Data for the report has been collected from data scrapping in Qoura which collects opinion of customers. The collected information from the data base has evaluated by using sentiment analysis. The collected information from Qoura transforms the content and extracts data from API’s. In relation to this, information obtains from the research contributed for providing useful information for these features. The collected information from application scrapping has been analysed through sentiment analysis. …

The Power Of Mind Control, Ali Adnan Majed

Theses

Electroencephalogram (EEG) is a technology that has been used for so long to read and record neurological activity in the brain. EEG recordings are widely used nowadays for different neurological applications. Emerging technologies that can detect and analyze eye focus using EEG based technology are now are developing quickly. At a relatively affordable cost one can own an EEG kit. With the help of predisposed algorithms or the help of developers, new algorithms for different commands are being worked on. Along with other technologies EEG eye tracking can be beneficial in many domains such as, psychology, marketing, automotive industry, and …

The Effect Of Different Feeding Regimes On Recent Nutritional And Growth Measurements In Juvenile California Killifish (Fundulus Parvipinnis), Emily Parks

Theses

Gaining a deeper understanding of in-situ growth approximations for juvenile fishes is one way to understand how food consumption may affect fish growth. If variations in growth rate are strongly mirrored by past food status, then the condition (degree of well-being) of fish can be potentially used as a reference for relative prey availability. Furthermore, confirming that there is a positive relationship between food availability and fish growth rate is a critical first step to deepen our understanding of growth rate variation as well as examining if growth can be a proxy for habitat quality.

The California killifish (Fundulus …

Supply Chain Disruption: A Conceptual Framework On Decision Making Using Neuroscience, Sadiya Siddique

Theses

The simplest definition of supply chain is the delivering of goods and/or services to the consumers required by the organization. In the late 1950s it was identified that the supply chain system was becoming more uncertain due to the changes in demands and inventory. Due to globalization and other business factors, supply chain has become more complex now due to which the likelihood and impact of disruption has increased. These disruptions can vary between known-unknowns and controllable to unknown-unknowns and uncontrollable ones. In recent years, the major disruptions happening in the supply chain and its effects on bottom line of …

Finding The Meaning In Ceramic Patterns From A Chaco Canyon Burial, Michael Lucero

Theses

The focus of this research considers the culture of the Ancestral Puebloans from the American Southwest region. This project reflects and examines the cultural arts and practices in relation to funerary aspects of the ancient Puebloan society that flourished in Chaco Canyon, located in present-day New Mexico. While investigations of historians and archaeologists have concentrated on findings within the Great House of Pueblo Bonito in Chaco Canyon, research focused on the structures and objects within rooms. The base of this research examines a collective set of vessels from burial room 33, excavated from the original exhibition of George H. Pepper, …

Intelligent Relaxation System For Information Anxiety, Xiuyu Shi

Theses

The development of information technology has brought a lot of convenience to people's lives and changed the way we work. There are many people who use cell phones and computers every day, which has caused many health problems, and information anxiety is one of them. This paper discusses a project that proposed to help with the problem of information anxiety among workers and investigates the root causes of information anxiety among IT workers. After user testing and design, this project gives a potential design solution that uses sensory feedback. In addition, this paper gives some insights into the negative effects …

Steam Toys: Empowering The Next Generation Of Women In Stem, Grace Newman-Lapinski

Theses

Even in 2022, STEM (science, technology, engineering, and mathematics) fields continue to be dominated by men. Starting from an early age, women are systematically pushed out of STEM fields. Three main reasons contribute to this – gender bias, lack of role models, and a lack of opportunity for skill building at an early age. This paper proposes that STEAM (STEM + Art) toys are critical to empowering the next generation of women in STEM. By mixing art with STEM, STEAM toys provide kids with the opportunity to explore these complex fields of study in creative ways. By making use of …

Sku Time Series Forecasting Methods For Fmcgs, Mohammad Al Orbani

Theses

This research aims at using forecasting algorithm that predicts the demand that is to be needed on a monthly basis while factoring in occasional inconsistent patterns, seasonality, and non-stationary and cyclical patterns of the data. The prediction is to predict around 3000 SKUs in 19 end markets and since the data is necessary for marketing enhancement and strategies, the Forecasting accuracy must be high. Since market strategies will be based on those predictions and revenue will be lost in the case of an error. Hence, we need to keep in mind that the model is not overfitted and that it …

Modeling Intra-Patient Planned Dose Change To Better Understand Dose Response In Cancer, Lauren Burke, Lin Hui Jiang, Tyler Frediani, Drew Haiber, James Winger

Theses

In this paper, we attempt to find the most efficient trial design to determine the optimal dose of cancer treatment. The two trial designs being evaluated are a standard trial design and intra-patient dose-switching trial. The optimal dose is the lowest dose that still causes a decrease in the tumor size. The most efficient trial is defined as the trial in which the distribution of parameters from the data set mostly closely matches the distribution from a simulated trial. We developed an ordinary differential equation to model the change in the sum of the length of tumor diameters over time. …

Creating Better Musicians Through Musicality: A Guide To Building An Instructional Unit, Shelby Leo

Theses

This project provides an in depth focus on how to strengthen an ensemble's approach to musicality through lesson plans, assessments, and activities. The primary focus group of this project is high school aged performance based classes including band and choir. The aim of the project is to provide a music educator with a detailed curriculum to teach musicality that is adjustable to any size ensemble and any score. Furthermore, this project is not a study but instead an explanation to the approach of developing the curriculum unit. The project consists of a four unit curriculum with two to three lessons …

Effect Of Simultaneous Application Of The Two Horizontal Orthogonal Ground Motion Components On The Seismic Behavior Of Buildings (Case Of Four-Story Steel Frame), Joel Mondo Kisekini

Theses

Joel Mondo Kisekini, for the Master of Science degree in Civil Engineering, presented on March 25, 2022, at Southern Illinois University Carbondale.TITLE: EFFECT OF SIMULTANEOUS APPLICATION OF THE TWO HORIZONTAL ORTHOGONAL GROUND MOTION COMPONENTS ON THE SEISMIC BEHAVIOR OF BUILDINGSMAJOR PROFESSOR: Dr. JALE TEZCAN During an earthquake, buildings are simultaneously excited by two horizontal and one vertical ground motion components. Modern seismic codes and guidelines such as ASCE/SEI 41-06 (Seismic rehabilitation of existing buildings, American Society of Civil Engineers), EUROCODE 8 (1998-1) (Design provisions for earthquake resistance of structures, European Committee for Standardization, 2003), FEMA 356 (Prestandard and Commentary for …

Why Did You Clone These Identifiers? Using Grounded Theory To Understand Identifier Clones, Luis Angel Gutierrez Galaviz

Theses

Developers spend most of their time comprehending source code, with some studies estimating this activity takes between 58% to 70% of a developer’s time. To improve the readability of source code, and therefore the productivity of developers, it is important to understand what aspects of static code analysis and syntactic code structure hinder the understandability of code. Identifiers are a main source of code comprehension due to their large volume and their role as implicit documentation of a developer’s intent when writing code. Despite the critical role that identifiers play during program comprehension, there are no regulated naming standards for …

Desalination Waste Revitalization Using Carbon Capture: Process Optimization Using Machine Learning, Ahmed Mohamed Elsayed

Theses

Over the next five to ten years, desalination will play an ever-important role in our society. Developing nations will look at desalination from the point of water scarcity, while developed nations will consider the perspective of the Water-Energy-Food nexus. With current technology, for every liter of freshwater produced, one and a half liters is thrown away as waste. This body of research proposes to employ chemical precipitation in ammoniated brine solutions, that have reasonably high ionic concentrations. CO2 absorption in Bubble Column Reactors can reduce sodium ions by precipitating NaHCO3. Also, the absorbed CO2 can reduce chloride ions and induce …

An Intelligent Passive Islanding Detection And Classification Scheme For A Radial Distribution System, Mohannad Khaleel Subhi Suleiman

Theses

Distributed generation (DG) provides users with a dependable and cost-effective source of electricity. These are directly connected to the distribution system at customer load locations. Integration of DG units into an existing system has significantly high importance due to its innumerable advantages. The high penetration level of distributed generation (DG) provides vast techno-economic and environmental benefits, such as high reliability, reduced total system losses, efficiency, low capital cost, abundant in nature, and low carbon emissions. However, one of the most challenges in microgrids (MG) is the island mode operations of DGs. the effective detection of islanding and rapid DG disconnection …

Fabrication And Characterization Of Germanium Telluride Nanowires, Shaikha Saeed Alketbi

Theses

Random access memories (RAMs) made from phase change materials (PCMs) are a promising alternative for flash memory technology currently dominating the memory market owing to its many appealing traits such as non-volatility, fast read/write performance, excellent scalability, and compatibility with complementary metal-oxide-semiconductor (CMOS) architectures. In fact, the scalability of PCMs is driving this class of materials to be the successor in the memory industry in the near future, and germanium telluride (GeTe) is one of the most viable PCMs in this context. In this study the phase change material GeTe nanowires, is fabricated using the vapor–liquid–solid (VLS) growth method. GeTe …

Addressing Energy Efficiency In Rental Units: A Preliminary Cost Assessment Of Minimum Energy Standards And Policy Alternatives For Rochester, Ny, Bryn Stricker

Theses

With the rising concern for climate change and energy consumption, global, national, and local policies attempt to reduce carbon emission and energy usage. Starting in 2010, the city of Rochester established a climate action plan which aims to reduce greenhouse gas emissions by 40% in the year 2030 (City of Rochester, NY, 2017). The city recognizes rental homes are a promising source to mitigate energy consumption and carbon emissions, a type of greenhouse gas. Minimum energy standards for rentals (MESR) are a relatively new type of policy which can help achieve energy and carbon reduction goals. By using an existing …

Quantum Solutions For Training A Single Layer Binary Neural Network, Sabrina Ly

Theses

Quantum computing is a relatively new field starting in the early 1980s when a physicist named Paul Benioff proposed a quantum mechanical model of the Turing machine, introducing quantum computers. Previously, the focus of most quantum computers was in the study of quantum applications instead of broad applications due to the fact that quantum technology is a newer field with many technology constraints, such as limited qubits and noisy environments. However, quantum computers are still capable of using quantum mechanics to solve specific algorithms with an exponential speed-up in comparison to their classical counterparts. One key algorithm is the HHL …

Sku Time Series Forecasting Methods For Fmcgs, Mohammad Al Orbani

Theses

This research aims at using forecasting algorithm that predicts the demand that is to be needed on a monthly basis while factoring in occasional inconsistent patterns, seasonality, and non-stationary and cyclical patterns of the data. The prediction is to predict around 3000 SKUs in 19 end markets and since the data is necessary for marketing enhancement and strategies, the Forecasting accuracy must be high. Since market strategies will be based on those predictions and revenue will be lost in the case of an error. Hence, we need to keep in mind that the model is not overfitted and that it …

Predicting Hepatotoxicity In Patients Receiving T-Dm1 Treatment Using Alt Blood Concentrations, Nick Fidalgo, Chris Gatesman, Phillip Lee, Brett Peters, Samantha Sandwick, Alex Shetler

Theses

During cancer treatments, it is imperative to keep a close eye on the side effects of whatever drug you are using to target the infected cells. For example, many drugs will target cancerous cells by attaching themselves onto different receptors on the membranes of the cells. However, these treatments are not always exact in affecting only the cancerous cells. One of the major side effects of these drugs is that different types of non-cancerous cells are accidentally killed during the process of cancer treatments when the drug latches onto the similar receptors of those cells. For example, when the antibody-drug …

Design And Evaluation Of A Machine Learning Based Model For Optimization Of Residential Battery Energy Storage System Scheduling For Cost And Emissions Reductions, Kevin George

Theses

Usage of battery energy storage system (BESS) to facilitate demand response (DR) programs such as time of use (TOU) pricing can reduce utility bills for residential customers. However, using such a system for minimizing electric bills under these rate structures has the potential to cause an increase in emissions from the grid system. The increased emissions were majorly due to bulk energy storage of electricity produced by off-peak generators with higher emission rates and excess energy consumption due to battery inefficiency. BESS operating to optimize competing objectives to minimize utility cost and minimize CO2 emissions requires complex models that require …