Computer Sciences Commons^™

Active Learning With Cybersecurity, Carole Shook

TFSC Publications and Presentations

A global campus grant was obtained in Spring 2020 to develop modules for Cybersecurity. This presentation encompasses the use of Cyberciege and case studies that require active learning of students.

A Machine Learning And Deep Learning Framework For Binary, Ternary, And Multiclass Emotion Classification Of Covid-19 Vaccine-Related Tweets, Aditya Dubey

Honors Scholar Theses

My research mines public emotion toward the Covid-19 vaccine based on Twitter data collected over the past 6-12 months. This project is centered around building and developing machine learning and deep learning models to perform natural language processing of short-form text, which in our case tweets. These tweets are all vaccine-related tweets and the goal of the classification task is for our models to accurately classify a tweet into one of four emotion groups: Apprehension/Anticipation, Sadness/Anger/Frustration, Joy/Humor/Sarcasm, and Gratitude/Relief. Given this data and the goal of the paper, we aim to answer the following questions: (1) Can a framework be …

Pervasive Machine Learning For Smart Radio Environments Enabled By Reconfigurable Intelligent Surfaces, George C. Alexandropoulos, Kyriakos Stylianopoulos, Chongwen Huang, Chau Yuen, Mehdi Bennis, Mérouane Debbah

Machine Learning Faculty Publications

The emerging technology of Reconfigurable Intelligent Surfaces (RISs) is provisioned as an enabler of smart wireless environments, offering a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for dynamic control of the propagation of electromagnetic signals over the wireless medium, ultimately providing increased environmental intelligence for diverse operation objectives. One of the major challenges with the envisioned dense deployment of RISs in such reconfigurable radio environments is the efficient configuration of multiple metasurfaces with limited, or even the absence of, computing hardware. In this paper, we consider multi-user and multi-RIS-empowered wireless systems, and present a thorough survey of the online …

Computational Investigations Into Astrochemical Inorganic Oxides, Ammonia Borane, And Genetic Algorithms, E. Michael Valencia

Honors Theses

The formulations of quantum mechanics in the early 1900s were exciting theoretical discoveries, but were not practical to apply until the advent of computers and the subsequent computational methods in 1951. With the introduction of tractable simplifications, procedures such as Hartree-Fock allowed for determination of properties of non-trivial systems. Presently, huge leads of computational power have allowed for extremely precise, quantitative work that can be applied to the human body, synthesis, or even astrochemical processes. This thesis presents works concerning 1) the history of quantum mechanics; 2) a brief primer on computational chemistry and its methods; 3) inorganic oxides in …

Building An Artificial Intelligence Framework For Hypertension Diagnosis: A Use Case Of The Problem List Curation, Ketemwabi Yves Shamavu

Theses & Dissertations

Hypertension is the world's leading factor in cardiovascular disease. Forty-seven percent or close to one in two Americans aged 18 and older are affected. It predicts approximately a thousand deaths per day. Based on recent statistics from the Centers for Disease Control and Prevention, one in three patients with hypertension does not know they are hypertensive. Seventy-five percent of hypertensive patients have uncontrolled hypertension - meaning that they are not treated to target. While there is extensive literature on hypertension diagnosis and management, there is an apparent gap in understanding and acknowledging that a person is hypertensive. Moreover, blood pressure …

Increasing Perceived Realism Of Objects In A Mixed Reality Environment Using 'Diminished Virtual Reality', Logan Scott Parker

Honors Theses

With the recent explosion of popularity of virtual and mixed reality, an important question has arisen: “Is there a way to create a better blend of real and virtual worlds in a mixed reality experience?” This research attempts to determine whether a visual filter can be created and applied to virtual objects to better convince the brain into interpreting a composite of virtual and real views as one seamless view. The method devised in this thesis is being called 'Diminished Virtual Reality'. The results found in this study show that when presented with a scene composed of a combination of …

The Understanding Of Mycorrhizae Networks: A Historical Approach, Jake Sun

The Confluence

The growth of mycorrhizal fungi into plant roots used to be viewed as a parasitic relationship between plants and fungi, where the fungal symbiont benefits and the plant host is harmed. Current research elucidates a mutualistic relationship. The mycorrhizae network assists the plants by increasing the capabilities for nutrient absorption in the soil. In exchange, the fungi receive carbon supply from the photosynthetic plants for growth. Our scientific understanding of other topics like species specificity, seed germination, and co-evolutionary influence of mycorrhizae and plants has also progressed. Additionally, we now understand that the mycorrhizal mutualism is not limited to the …

Jlootbox: An Agent-Based Model Of Social Influence And Gambling In Online Video Games, Lila Zayed

Honors Capstones

Loot boxes are digital treasure chests that players spend real money to purchase, wherein the contents are randomly generated. Since players spend money on the pretense they might receive something valuable, many comparisons have been drawn to gambling behavior as the reward is up to chance. To explore this phenomenon, agent-based modeling will be used to simulate this behavior. Agent-based modeling allows us to create heterogenous agents who follow simple rules so that we may observe emergent behavior in a population. An agent-based model was created using Repast Simphony for this end.

Parameters included the player’s internal decision strategy around …

Indexer++: Workload-Aware Online Index Tuning With Transformers And Reinforcement Learning, Vishal Sharma, Curtis Dyreson

Computer Science Student Research

With the increasing workload complexity in modern databases, the manual process of index selection is a challenging task. There is a growing need for a database with an ability to learn and adapt to evolving workloads. This paper proposes Indexer++, an autonomous, workload-aware, online index tuner. Unlike existing approaches, Indexer++ imposes low overhead on the DBMS, is responsive to changes in query workloads and swiftly selects indexes. Our approach uses a combination of text analytic techniques and reinforcement learning. Indexer++ consist of two phases: Phase (i) learns workload trends using a novel trend detection technique based on a pre-trained …

Read This: A Content Analysis Framework For Book Recommendation Applications, Cypress S. Payne

Honors Projects

Book recommendation applications combine word-of-mouth recommendations with algorithms that can suggest books based on a user’s account activity, creating a robust system for finding new books to read. Current research on recommendation systems is purely quantitative, focusing on the efficacy of the system, and content analyses are only just beginning to be performed on mobile applications. I use previous content analyses on applications as a basis for creating a content analysis framework for book recommendation applications. This framework can be used to analyze what users find important in book recommendation apps and inform app creators about their users’ wants and …

A Machine Learning Based Approach To Detect The Ethereum Fraud Transactions With Limited Attributes, Rabia Musheer Aziz, Mohammed Farhan Baluch, Sarthak Patel, Pavan Kumar

Karbala International Journal of Modern Science

Ethereum smart contracts have recently received new commercial applications and a lot of attention from the scientific community. Ethereum eliminates the requirement for a trusted third party by allowing untrusted parties to expose contract details in computer code. Nonetheless, as online commerce grows, plenty of fraudulent activities, such as money laundering, bribery, and phishing, emerge as major threats to trade security. For correctly recognizing fraudulent transactions, this paper developed a Light Gradient Boosting Machine (LGBM) technique-based model. The modified LGBM model optimized the parameters of Light GBM using the Euclidean distant structured estimation approach. This paper also examines the performance …

A Bi-Level Data Lowering Method To Minimize Transferring Big Data In The Sensors Of Iot Applications, Ali Kadhum M. Al-Qurabat, Ali Kadhum Idrees, Abdallah Makhoul, Chady Abou Jaoude

Karbala International Journal of Modern Science

In the IoT era, the number of devices connected to it continues to grow significantly. This can lead to an increase in the amount of reported data by these IoT devices. The reported data by the Sensor Nodes (SNs) to the Gateway (GW) drives these IoT sensors to consume their energy and storage. These problems can be solved by reducing the amount of data in the source nodes in order to reduce both the amount of energy consumed and the amount of storage required. Energy consumption represents one aspect of the Quality of Service (QoS) in the sensor nodes of …

An Economical Source For Peroxidase: Maize Cobs, Hathama Razooki Hasan, Ali Waleed Al- Ani

Karbala International Journal of Modern Science

According to the current situation of peroxidase (POD), the relevant studies on this enzyme indicated its importance as a tool in clinical biochemistry and different industrial fields. Most of these studies used the fruits and vegetables as source of this enzyme. So that in order to couple the growing requirements for POD with the recent demands for reduc-ing disposal volume by recycling the plant waste, the aim of the present study was to extract POD through management of municipal bio-waste of Iraqi maize species. A simple, green and economical method was used to extract this enzyme. Our results revealed that …

Efficient Removal Of Common Organic Pollutants From Water By Zn-Doped Tio2 Nanoparticles With Different Applications, Khaled Elgendy, Ibrahim Elmehasseb, Saleh Kandil

Karbala International Journal of Modern Science

Water purification via adsorption without energy consumption was considered a green process. Zn-doped TiO2 nanoparticles were fabricated by the Sol-gel method and characterized by different analysis techniques. Zinc doping of TiO2 increases the surface area to 26.7m2g-1 with adsorption results, 75.1%, 71.1%, and 68.2% for methylene blue, ofloxacin, and SLS, respectively. Variable affecting factors on adsorption have been studied. The adsorption behavior fitted with Langmuir and Freundlich equations than Temkin isotherm, indicating the preferred heterogeneous adsorption at equivalent adsorbent sites. The application of nanoparticles in many synthetic specimens of pollutants gave excellent removal results, which exceeded 75% of detoxification.

Synthesis Of Cuo/Zno And Mgo/Zno Core/Shell Nanoparticles With Plasma Jets And Study Of Their Structural And Optical Properties, Raghad S. Mohammed, Kadhim A. Aadim, Khalid A. Ahmed

Karbala International Journal of Modern Science

This paper reports the synthesis of CuO/ZnO and MgO/ZnO core/shell nanoparticles using atmospheric plasma jets. The characterization of the synthesized CuO/ZnO and MgO/ZnO core/shell nanoparticles were confirmed by a series of techniques, including X-ray diffraction (XRD), scanning electron microscopy (SEM), X-ray dispersive spectroscopy (EDS), transmission electron microscopy (TEM), and UV–Vis spectroscopy. The XRD analysis confirmed no other peaks related to the secondary phases for CuO, MgO, or ZnO, indicating the purity of these nanoparticles. Additionally, EDX analysis confirmed the formation of high purity CuO/ZnO and MgO/ZnO core/shell nanoparticles. The surface morphology, which represented the high agglomeration rate, was investigated using …

Numerical Analysis Of A Silicon-Based Electro-Optic Modulator, Mario Alberto García-Ramírez, Orfil González-Reynoso, Everardo Vargas-Rodríguez, Miguel Angel Bello-Jiménez, Abel García-Barrientos

Karbala International Journal of Modern Science

A phase shift electro-optic semiconductor structure that features a Mach-Zehnder Interferometer (MZI) is numerically analyzed. The interferometer structure considers a highly-doped Si-based waveguide that can control the phase shift by varying the refractive index through the carrier concentration while applying a control voltage. To analyze the structure, Kramers-Kronig dispersion relations, the effective index method and the Drude model are implemented within a finite element software. As a result, for an optical waveguide structure with a 9 mm length and 10 V, it is possible to obtain a phase shift by that allows, at the output of the MZI, total interference …

Partial Pseudo-Random Hashing For Transactional Memory Read/Write Data Processing And Validation, G M Sridevi, Ashoka D V, B V Ajay Prakash

Karbala International Journal of Modern Science

Development of a bypass parallel processing block is one of the emerging and interesting research areas in memory read/write application domain. Many Random Number Generation (RNG) techniques have been introduced for processing the data in storage memory. But the limitations include reduced efficiency, increased computational complexity, high area consumption and higher cost. This paper presents a novel dynamic memory register with optimal XOR design based on partial pseudo-random hashing to process transactional memory read/write data. Transfer characteristics of the current are analysed based on the pseudo differential pair for proficient memory utilization. A memory window is then created and adjusted …

A Content-Based File Identification Dataset: Collection, Construction, And Evaluation, Saja Dheyaa Khudhur, Hassan Awheed Jeiad

Karbala International Journal of Modern Science

File-Type Identification (FTI) is one of the essential functions that can be performed by examining the data blocks' magic numbers. However, this examination leads to a challenge when a file is corrupt, or these magic numbers are missing. Content-based analytics is the best way for file type identification when the magic numbers are not available. This paper prepares and presents a content-based dataset for eight common types of files based on twelve features. We designed our dataset to be used for supervised and unsupervised machine learning models. It provides the ability to classify and cluster these types into two levels, …

Nigella Sativa Methanol Extract Inhibits Pc-3 Cell Line Colonization, Induced Apoptosis, And Modulated Lc3-Based Autophagy, Yusuf Toy, Merve Kivrik, Marwa H. Alkhafaji, Aryan M. Faraj, Ibrahim H. Gecibesler, Can A. Ağca

Karbala International Journal of Modern Science

Nigella sativa has various pharmacological properties and has been used throughout history for a variety of reasons. However, there is limited data about the effects of Nigella sativa (NS) on human cancer cells. This study aimed at observing the roles of methanolic extract of N. sativa on apoptosis and autophagy pathway in the Human PC3 (prostate cancer) cell line. The cell viability was checked by MTT assay. Clonogenic assay was performed to demonstrate clonogenicity and Western blot was used to check caspase-3, TIGAR, p53, and LC3 protein expression. The results demonstrated that PC3 cell proliferation was inhibited, caspase-3 and p53 …

Ultrasound-Assisted Dibutyl Phthalate Nanocapsules Preparation And Its Application As Corrosion Inhibition Coatings, Uday Bagale, Ammar Kadi, Irina Potoroko, Vinay Rangari, Minakshi Mahale

Karbala International Journal of Modern Science

The current research employs an encapsulation of dibutyl phthalate (DBP) as a corrosion inhibitor in situ polymerization using a sonochemical method to form nanocapsules. The prepared nanocapsules were characterization by using Malvern particle size, Fouri-er transforms infrared spectroscopy (FTIR), Scanning electron microscope (SEM) and Transmission electron microscope (TEM), and thermal and mechanical test to check particle size, morphology, and stability of nanocapsules. Later prepared DBP nanocapsules were incorporated in standard epoxy coating to check its corrosion inhibition resistance. The results show that nanocapsules are spherical, with an average particle size of 337 nm. Scratch nanocapsules epoxy coating shows improves coating …

Heterogeneous Catalytic Degradation Of Dye By Fenton-Like Oxidation Over A Continuous System Based On Box–Behnken Design And Traditional Batch Experiments, Imad M. Luaibi, Mohammed A. Atiya, Ahmed K. Hassan, Zainab A. Mahmoud

Karbala International Journal of Modern Science

In this study, iron was coupled with copper to form a bimetallic compound through a biosynthetic method, which was then used as a catalyst in the Fenton-like processes for removing direct Blue 15 dye (DB15) from aqueous solution. Characterization techniques were applied on the resultant nanoparticles such as SEM, BET, EDAX, FT-IR, XRD, and zeta potential. Specifically, the rounded and shaped as spherical nanoparticles were found for green synthesized iron/copper nanoparticles (G-Fe/Cu NPs) with the size ranging from 32-59 nm, and the surface area was 4.452 m2/g. The effect of different experimental factors was studied in both batch and continuous …

Optical Measurement And Performance Prediction Of Solar Pv System In Al-Khidhir Zone/Iraq, Faten Sh. Zainulabdeen, Jaber O. Dahloos, Ahmed F. Atwan, Naseer K. Kasim

Karbala International Journal of Modern Science

People have tended for investing the sources of renewable energy, especially solar energy, as they are clean and environmentally friendly sources. The present work aims to invest the measured data of solar irradiance, maximum ambient temperatures and wind speed provided by Al Khidhir Meteorological Station to predict the minimum performance of photovoltaic solar systems (NT-R0E3E-SHARP) for electric power generation. The single diode model is used to calculate the minimum output power produced by solar module and its minimum conversion efficiency based on soalr irradiance, maximum ambient temperatures and wind speed throughout 2020. The results indicate that the annual solar irradiance …

Segmentation With Super Images: A New 2d Perspective On 3d Medical Image Analysis, Ikboljon Sobirov, Numan Saeed, Mohammad Yaqub

Computer Vision Faculty Publications

Deep learning is showing an increasing number of audience in medical imaging research. In the segmentation task of medical images, we oftentimes rely on volumetric data, and thus require the use of 3D architectures which are praised for their ability to capture more features from the depth dimension. Yet, these architectures are generally more ineffective in time and compute compared to their 2D counterpart on account of 3D convolutions, max pooling, up-convolutions, and other operations used in these networks. Moreover, there are limited to no 3D pretrained model weights, and pretraining is generally challenging. To alleviate these issues, we propose …

Pluto In Hand: Design And Implementation Of A Location-Based Mobile Augmented Reality Application For Viewing Open Data, Matthew O. Ward

Theses and Dissertations

Immersive mobile augmented reality (AR) technology has improved while geolocational data volume has grown. City governments can utilize this technology to share their geospatial data with the public, promoting smart city aims. This research describes the design and implementation of a novel open-source ARGIS application to view property tax lot information in New York City. This proof-of-technology demonstrates web-based AR can visualize location-based spatial data.

The Applications Of The Internet Of Things In The Medical Field, Cody Repass

Theses and Dissertations

The Internet of Things (IoT) paradigm promises to make “things” include a more generic set of entities such as smart devices, sensors, human beings, and any other IoT objects to be accessible at anytime and anywhere. IoT varies widely in its applications, and one of its most beneficial uses is in the medical field. However, the large attack surface and vulnerabilities of IoT systems needs to be secured and protected. Security is a requirement for IoT systems in the medical field where the Health Insurance Portability and Accountability Act (HIPAA) applies.

This work investigates various applications of IoT in healthcare …

The Power Of The Collective: A Multi Agent-Based Modeling Approach To Nuclear Radiation Localization, Benjamin Totten, Christof Teuscher

Student Research Symposium

Gamma radiation is a very high frequency, very dangerous electromagnetic wave that has a chance of being emitted after radioactive decay. Radiation source localization, or locating the previously unknown source of nuclear radiation, in a rapid and efficient manner is critically important, but challenging. We aim to create an architecture for multiple, fully independent agents that cooperate to localize sources faster than existing single-agent architectures, without compromising accuracy. Using Agent-Based Modeling and Deep Reinforcement Learning, agents are enabled to make decisions based on other agents' behaviors while maintaining programmatic autonomy. We hypothesize that radiation sources can be localized faster using …

Growing Reservoir Networks Using The Genetic Algorithm Deep Hyperneat, Nancy L. Mackenzie

Student Research Symposium

Typical Artificial Neural Networks (ANNs) have static architectures. The number of nodes and their organization must be chosen and tuned for each task. Choosing these values, or hyperparameters, is a bit of a guessing game, and optimizing must be repeated for each task. If the model is larger than necessary, this leads to more training time and computational cost. The goal of this project is to evolve networks that grow according to the task at hand. By gradually increasing the size and complexity of the network to the extent that the task requires, we will build networks that are more …

Privacy Assessment Breakthrough: A Design Science Approach To Creating A Unified Methodology, Lisa Mckee

Masters Theses & Doctoral Dissertations

Recent changes have increased the need for and awareness of privacy assessments. Organizations focus primarily on Privacy Impact Assessments (PIA) and Data Protection Impact Assessments (DPIA) but rarely take a comprehensive approach to assessments or integrate the results into a privacy risk program. There are numerous industry standards and regulations for privacy assessments, but the industry lacks a simple unified methodology with steps to perform privacy assessments. The objectives of this research project are to create a new privacy assessment methodology model using the design science methodology, update industry standards and present training for conducting privacy assessments that can be …

Factored Beliefs For Machine Agents In Decentralized Partially Observable Markov Decision Processes, Joshua A. Lapso, Gilbert L. Peterson

Faculty Publications

A shared mental model (SMM) is a foundational structure in high performing, task-oriented teams and aid humans in determining their teammate's goals and intentions. Higher levels of mental alignment between teammates can reduce the direct dialogue required for team success. For decision-making teams, a transactive memory system (TMS) offers team members a map of specialized knowledge, indicating source of knowledge and the source's credibility. SMM and TMS formulations aid human-agent team performance in their intended team types. However, neither improve team performance with a project team--one that requires both behavioral and knowledge integration. We present a hybrid cognitive model (HCM) …

A Few-Shot Learning Model Based On A Triplet Network For The Prediction Of Energy Coincident Peak Days, Jinxiang Liu, Laura Brown

Michigan Tech Publications, Part 1

In an electricity system, a coincident peak (CP) is defined as the highest daily power demand in a year, which plays an important role in keeping the balance between power supply and its demand. Advanced information about the time of coincident peaks would be helpful for both utility companies and their customers. This work addresses the prediction of the five coincident peak days (5CP) in a year. We present a few-shot learning model to classify a day as a 5CP day or a non-5CP day 24-hours ahead. A triplet network is implemented for the 2-way-5-shot classifications on six different historical …