My RoleAdvising sinceFull nameThesis Titlegraduation dateThesis abstract
Thesis AdvisorFall 2016Radhika SoodComparative Data Analytic Approach for detection of DiabetesFall 2018The purpose of this study is to create a framework for detecting diabetes existence based on the using the attributes available in the PimaIndiansDiabetes2 dataset. After performing model training practice on various models, we decided to do a comparative study of logistic regression (LR) model, random forest method (RF) and support vector machine (SVM) methods using five-fold cross validation technique. The data is of imbalanced nature, so to overcome this issue Synthetic Minority Over-sampling Technique (SMOTE) is used. This model can be used as a decision support tool by medical practitioners which in turn will not just expedite the decision-making process but will also help to reduce the cost of services by decreasing the usage of time-consuming processes.
Thesis AdvisorFall 2016Bhanu Sai Kishore Puvvala3-D Simulation of Multi Cells and Growth Model - A Case Study In CompuCell3DFall 2018Computer simulation and modeling have become vital in the field of biology to study the growth and behavior of cell/ multi cells. Simulations of multi cell growth are mathematically complex and lack software that allows creating and running biological experiments without the knowledge of programming. To address this problem, we present a flexible, scalable problem solving environment for cell simulations called CompuCell3D that is based on object oriented programming. This paper studies the simulation framework CompuCell3D and Python code base within CompuCell3D that allows users to build, test and run simulations.
Thesis AdvisorSpring 2017Deepika RameshAddressing Older Adults' Social Media Mobile Interface NeedsSpring 2019In our research, we present findings from an online study focused on addressing older adults’ (age 65 & above) social media interactions using a smartphone, identify challenges and make usability recommendations to social media companies to better attract and engage older adults. We identified participants using a snowball sampling method. The participants who are of the age 65 years and above through email with a link to the survey and instructions to perform tasks related to the survey. Results from the survey and feedback from participants were analyzed across three broader categories impacting user adoption. Then, a prototype was designed based on results from the survey. A pilot study was conducted to capture feedback around the newly designed prototype and to understand if the prototype design could potentially help social media-based companies drive towards an increase in adoption of social media apps among all age groups.
Thesis AdvisorSpring 2017Sai Nikhil BheemanathiniA Systematic Review of Blockchain Technology: Privacy Concerns, Security Challenges, and SolutionsSummer 2019Blockchain technology is described as the technology that enables digital information to be shared online without creating copies using the basis of digital currency. It acts as a public ledger that grants access to all people without necessarily having a central authority as a control point. This thesis uses literature review methodology to explore blockchain technology in terms of privacy concerns, security challenges and associated solutions in the modern-day business. The purpose of the review is to give an overview of the sources used during the examination of the topic and to show the readers how the research corresponds to a larger scope of research.
Thesis AdvisorFall 2016Badri JimaleE-loox, A Hybrid Learning ManagementFall 2019E-loox is an educational software application that has been designed specifically for students located in areas with limited Internet access. Unlike the majority of existing educational applications, E-loox is a “hybrid app”– meaning it can function both on and offline. As a hybrid app, E-loox allows students to complete assignments, access course materials, and conduct research in places where there is no Internet access. E-loox seeks to bridge the gap for the millions of students who have internet in the classroom but lack a home connection.
Thesis AdvisorFall 2019Yusuf Lanre LawalAnomaly Detection in Ethereum Transactions Using Network Science AnalyticsSummer 2020Since the introduction of Bitcoin, the rate of adoption of blockchain technology has exponentially increased. Consequently, numerous other types of cryptocurrencies, such as Ethereum, have been introduced. The high rate of adoption of cryptocurrencies has resulted in the generation of enormous amounts of data. In this paper, we focus on detecting anomaly or outliner in the daily Ethereum network using network properties. We were able to use the network properties and data mining in getting the required results. Wallets or accounts acting on the blockchain are represented as nodes, while interactions between wallets or accounts are represented as links or edges. Based on the explanation, we were able to discover how the network properties have an impact on transaction behavior within the network. we propose how this analysis would be useful in real-life events.
Thesis AdvisorSpring 2019Rishika KapoorMalaria Detection using Deep Convolutional Neural NetworkFall 2020Malaria is a female Anopheles mosquito-borne disease. In severe cases may lead to coma and death. In this research, we used deep neural networks to detect the malaria virus in human blood cells. The dataset used in this research was taken from the National Institute of Health (NIH) Malaria Dataset. Data Preprocessing techniques like data segmentation and normalization are applied to maximize the model performance. In this research, two deep Convolutional Neural Networks, VGG-19, and ResNet-50, are experimented on to analyze and compare the best performing model on the malaria dataset. Our results showed that the ResNet-50 outperforms the VGG-19 by achieving an accuracy of 97 percent.
Thesis AdvisorFall 2020Sanith DhanpalBlockchainFall 2021 (Expected)
Thesis AdvisorFall 2020Victor AdewopoScraping The Deep Web : A 3-Dimensional Framework For Cyber-Threat IntelligenceSummer 2021 (Expected)The cyberspace is one of the most complex systems ever built by humans, the utilization of cyber-technology resources are used ubiquitously by many, but sparsely understood by majority of the users. In the past, cyber attacks were usually orchestrated in a random pattern of attack to lure unsuspecting targets. More evidence has demonstrated that cyber attack knowledge is shared among individuals using social media and hacker forums in the virtual ecosystem. This paper proposes using open source intelligence from the surface web (Twitter) and deep web hacker forums to identify texts related to cyber threats. The proposed methodology combines information extracted from the deep web and technical indicators of threats from the surface web.
Thesis AdvisorFall 2020Marina KlaiberIT interoperability concepts standardization in connected healthFall 2021 (Expected)Assessment of a workplace is important to control occupational safety for injuries, incidents prevention, and promotion of a healthy workforce. The aim of this study is to provide the insights into occupational injuries using Machine Learning algorithms to predict days away from work. This will allow business organizations to project operational hours, strategize the occupational safety procedure and ultimately reduce the costly injuries. In this research, the data analytics involves collection, evaluation of data, and application of an algorithms capable to identify and predict future outcomes. After data normalization phase, multiple supervised machine learning algorithms will be used for predictive outcomes and compared to each other based on accuracy, precision and recall. Among are Decision Tree, Grid Search CV, MLP Repressor, Linear Regression, Ridge and Lasso. Models will be compared for performance. The utilized dataset is the historic OSHA dataset, which consist of 30 original attributes.
Thesis committee member (Advisor: Dr. Murat Ozer)Fall 2019Daniel AddaiPrediction of Cyber Attack in Social NetworkSummer 2020
Thesis committee member (Advisor: Dr. Murat Ozer)Summer 2020Nesibe KaratasAnalysis of Ransomware Attacks to Government OrganizationsSpring 2021 (Expected)
Thesis committee member (Advisor: Dr. Kijung Lee)Fall 2019Bander AlyamiInterpreting Visual Scenes by Augmented-Reality Approach for People with Retinitis PigmentosaSpring 2021 (Expected)The goal of this study is to determine the possible technology solution of augmented reality (AR) for people who are affected by retinitis pigmentosa (RP). AR technology via wearable glasses might improve their safety, which is negatively influenced by their loss of peripheral vision and night blindness. AR smart glasses are considered to use for backing the limited visual field. This research is proposed to study the potential and feasibility of augmented reality via smart glasses at improving social life and keeping both indoor and outdoor environments safe for people who are living with RP.
Thesis committee member (Advisor: Dr. Kijung Lee)Fall 2017Renuka AroraEvaluating User’s Perceived Credibility of Health Information on Facebook – based on Elaboration Likelihood ModelSummer 2018The study investigates the factors that influence user’s perception of credibility of health care information on Facebook. The study builds upon the findings of Elaboration Likelihood Model (ELM) of Information Processing. This research extends the ELM model and makes an initial contribution towards evaluating credibility of health care information present on Facebook.
Thesis committee member (Advisor: Dr. Hazem Said)Fall 2019Adeyinka BakareIntegrating FAIR into NIST framework for Quantitative Risk Assessment of Cyber threatsSpring 2020We proposed using an organization’s maturity level towards the implementation of NIST controls as a replacement of expert opinion in defining the organization’s resistance strength to a cyber threat. This hybrid risk analysis approach will help stakeholders make better-informed decisions on improving security measures and provide accurate values that represent the current security state of their organization.
Thesis committee member (Advisor: Dr. Chengcheng Li)Spring 2020Efosa Michael OgbomoDetecting Zero-day Attacks (ZED-IDS): Botnet as a Case StudyFall 2020 (Expected)
Thesis committee member (Advisor: Dr. Chengcheng Li)Fall 2019Nitin MathurIntrusion Detection SystemsFall 2020
Thesis committee member (Advisor: Dr. Kijung Lee)Spring 2020Mian WangApplying Uses and Gratifications Theory to Investigate Social Media User’s Motivations for MastodonSpring 2021
Thesis committee member (Advisor: Dr. Chengcheng Li)Fall 2019Ozioma UwakwehCybersecurity Concerns with Third-Party Vendors in the Retail IndustrySummer 2020
Thesis committee member (Advisor: Dr. Carla Purdy)Spring 2017Khaled AlrawashdehToward a Hardware-assisted Online Intrusion Detection System Based on Deep Learning Algorithms for Resource-limited Embedded SystemsSummer 2018Real-time scenarios of deep learning algorithms are challenged by two less frequently addressed issues. The first is data inefficiency, i.e., the model requires several epochs of trial and error to converge which makes it impractical to be applied to real-time applications. The second is the high precision computation load of the deep learning algorithms to achieve high accuracy during training and inference. To address the first issue, we propose a compressed training model for the contrastive divergence algorithm (CD) in the Deep Belief Network (DBN). The goal is to dynamically adjust the training vector according to the feedback from the free energy and the reconstruction error, which allows for better generalization.
Independent Study in ITSpring 2019Dipali SawantSignificance of Agile software development and SQA powered by automationMany businesses including software industries are trying to embrace Agile method for software development and its maintenance. Agile has its own limitations and challenges, there is no one proper solution for all types of industries and hence improving agile is necessity. In this research paper, we discuss how agile process can be improved by applying automation and agile quality assurance techniques.
Independent Study in ITFall 2019Hari Priya PonnakantiRelative Importance of Blockchain in Cryptocurrency, Banking & Health CareThis paper looks at the opportunities and challenges of implementing blockchain technology across medical, finance and banking sectors, and provides a clear view which can enable Blockchain for more extents. Few drawbacks that we encountered are using Power of Work (POW) in medical sector which is destroying the computing ability at a stage when system is getting bigger and eventually which is wasting lots of resources. One study over conceptual proposal on blockchain is the idea of using trade credit as the value of transactions, and this trade credit is in the scope of trade secret which improves trade confidentiality and makes it more secure. Moreover, centralization systems have few risks owing to their dependence on a high scale which could tamper the data or can even block access, change the rules and might even completely shut down the system. Few more drawbacks are designing and building a secure blockchain system is much more difficult on large-scale of banking sector with large database. To address these challenges, recent developments in blockchain technology are enabling novel opportunities in every possible sector by using Trust-worthy cloud, IoT and artificial intelligence, which makes it more powerful and secure. After analysing Blockchain implementations and identifying their limitations, we conclude with several promising directions for future research.
Independent Study in ITSpring 2019Himanshu AjmeraVirtual Reality in Health CareThis paper presents a prime aspect of Augmented and Virtual Reality development in the field of healthcare. We explored several recent works and articles and a comparison between generic application development and immersive technology-based application is included. The paper talks about more practical approaches that can be taken to enhance the effectiveness of the application. The resources (infrastructure) to complete this study are provided by the University of Cincinnati’s Center for Simulation and Virtual Environment Research (UCSIM). And several experiments and projects in the field of health care are used as a reference to make conclusions.
Independent Study in ITFall 2018Sriveni NamaniSmart Agriculture Based on IoT and Cloud ComputingThe improvement in new technologies in this modern era has resulted to miniaturization of sensors and the attempts to utilize them in various areas are getting succeeded. Also, adoption of Internet of Things (IoT) and Cloud Computing in any area are leading them to a notion of "Smart" like Smart Health Care systems, Smart Cities, Smart Mobility, Smart Grid, Smart Home and Smart Metering etc. One such area of research that has also seen this adoption is agriculture and thus making it a Smart Agriculture. Agriculture is one of the major sources for any of the largest population countries like India, China etc. to earn money and carry out the livelihood. Involvement of IoT and Cloud Computing in the agricultural sector would result in the better production of crops by controlling the cost, monitoring performance and maintenance, thereby benefiting the farmers and the overall nation. This paper focuses on introduction of a Smart Drone for crop management where the real-time Drone data coupled with IoT and Cloud Computing technologies help in building a sustainable Smart Agriculture.
Independent Study in ITFall 2019Tek DhitalA Comparative Review of Botnet Roles on Web Security
Independent Study in ITFall 2019Victor AdewopoPlunge into the Underworld: A survey on Emergence of DarknetWe studied relevant literature reviews to help researchers to better understand the darknet technologies, identify future areas of research on the darknet and ultimately to optimize how data-driven insights can be utilized to support governmental agencies in unraveling the depths of darknet technologies. This paper focuses on the use of internet for crimes, deanonymization of TOR-services, darknet a new digital street for illicit drugs, research questions and hypothesis to guide researchers in further studies. Finally, in this study, we propose a model to examine and investigate anonymous online illicit markets.
Independent Study in ITSpring 2021Jones YeboahThe Opioid Crisis: A Data Analytics FrameworkPrescription opioid misuse and opioid use disorder (OUD) are significant health problems in the US and impact stakeholders across the healthcare sector. The Center for Medicare and Medicaid Services’(CMS’s) paper summarizes these issues and outlines strategies to handle the crisis and reduce impacts of this epidemic. Although there are several initiatives at the federal, state, and local level to combat this problem, proactively identifying fraudulent and risky behaviors of various healthcare entities can help with preventive measures. This thesis propose a framework for healthcare data analytics platform using Cloud, Artificial Intelligence (AI) and Machine Learning (ML) technologies to enable real time/predictive analytics and gather deep insights into collecting preliminary data to investigate opioid crisis.