Computer Sciences Commons^™

Improving Matching And Classification Through Deep Learning Of Structure And Varying Illumination, Sarah Braeger

Electronic Theses and Dissertations, 2020-2023

Convolutional networks have driven major advances in computer vision in recent years. The design of deep architectures, loss functions, and the curation of large, diverse datasets have furthered progress in many applied computer vision tasks. How data is represented to a network guides feature discovery and must be carefully considered in order to maximize performance on any applied task. We introduce novel input representations and associated architectural techniques to better utilize them such as complementary loss terms and network structure. We demonstrate the impact of these approaches on classification and matching tasks which involve shape and varied illumination. We show …

Contextual Understanding Of Sequential Data Across Multiple Modalities, Sangwoo Cho

Electronic Theses and Dissertations, 2020-2023

In recent years, progress in computing and networking has made it possible to collect large volumes of data for various different applications in data mining and data analytics using machine learning methods. Data may come from different sources and in different shapes and forms depending on their inherent nature and the acquisition process. In this dissertation, we focus specifically on sequential data, which have been exponentially growing in recent years on platforms such as YouTube, social media, news agency sites, and other platforms. An important characteristic of sequential data is the inherent causal structure with latent patterns that can be …

Fine-Grained Lower Bounds For Problems On Strings And Graphs, Gary Thomas Hoppenworth

Honors Undergraduate Theses

The motivation of this thesis is to present new lower bounds for important computational problems on strings and graphs, conditioned on plausible conjectures in theoretical computer science. These lower bounds, called conditional lower bounds, are a topic of immense interest in the field of fine-grained complexity, which aims to develop a better understanding of the hardness of problems that can be solved in polynomial time. In this thesis, we give new conditional lower bounds for four interesting computational problems: the median and center string edit distance problems, the pattern matching on labeled graphs problem, and the subtree isomorphism problem. These …

Deployment Of Causal Effect Estimation In Live Games Of Dota 2, Anders Harboell Christiansen, Emil Gensby, Bryan S. Weber

Publications and Research

In this paper, we provide an application that produces consistent in-game estimates of win probabilities in Dota 2. Previous work shows that common methods of identifying the effect of in-game features are strongly inconsistent, which we corroborate here with a large data set. We further provide an in-game application for players to see these estimates during the game as a training tool, along with displaying the estimated marginal impact of the primary actions (kills, last hits, and tower damage), which are previously known only by intuition. In a double-blind setting, we are the first to identify that users observe a …

Family Communication: Examining The Differing Perceptions Of Parents And Teens Regarding Online Safety Communication, Tara Rutkowski

Honors Undergraduate Theses

The opportunity for online engagement increases possible exposure to potentially risky behaviors for teens, which may have significant negative consequences (Hair et al., 2009). Effective family communication about online safety can help reduce the risky adolescent behavior and limit the consequences after it occurs. This paper contributes a theory of communication factors that positively influence teen and parent perception of communication about online safety and provides design implications based on those findings. Previous work identified gaps in family communication, however, this study seeks to empirically identify factors that would close the communication gap from the perspective of both teens and …

Predictive Modeling Of Critical Temperatures In Superconducting Materials, Markus Hofmann, Natalia Sizochenko

Articles

n this study, we have investigated quantitative relationships between critical temperaturesof superconductive inorganic materials and the basic physicochemical attributes of these materials(also called quantitative structure-property relationships). We demonstrated that one of the mostrecent studies (titled "A data-driven statistical model for predicting the critical temperature of asuperconductor” and published in Computational Materials Science by K. Hamidieh in 2018) reportson models that were based on the dataset that contains 27% of duplicate entries. We aimed todeliver stable models for a properly cleaned dataset using the same modeling techniques (multiplelinear regression, MLR, and gradient boosting decision trees, XGBoost). The predictive ability ofour best …

Detection Of Freezing Of Gait Using Unsupervised Convolutional Denoising Autoencoder, Mohd Halim Mohd Noor, Amril Nazir, Mohd Nadhir Ab Wahab, Jodene Ooi Yen Ling

All Works

At the advanced stage of Parkinson’s disease, patients may suffer from ‘freezing of gait’ episodes: a debilitating condition wherein a patient’s “feet feel as though they are glued to the floor”. The objective, continuous monitoring of the gait of Parkinson’s disease patients with wearable devices has led to the development of many freezing of gait detection models involving the automatic cueing of a rhythmic auditory stimulus to shorten or prevent episodes. The use of thresholding and manually extracted features or feature engineering returned promising results. However, these approaches are subjective, time-consuming, and prone to error. Furthermore, their performance varied when …

Applications Of Machine Learning To Facilitate Software Engineering And Scientific Computing, Natalie Best

Computational and Data Sciences (PhD) Dissertations

The use of machine learning has risen in recent years, though many areas remain unexplored due to lack of data or lack of computational tools. This dissertation explores machine learning approaches in case studies involving image classification and natural language processing. In addition, a software library in the form of two-way bridge connecting deep learning models in Keras with ones available in the Fortran programming language is also presented.

In Chapter 2, we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software unified modeling language diagrams where data is …

Utilizing Resonant Scattering Signal Characteristics Via Deep Learning For Improvedclassification Of Complex Targets, Tuğçe Toprak, Mustafa Alper Selver, Mustafa Seçmen, Emi̇ne Yeşi̇m Zoral

Turkish Journal of Electrical Engineering and Computer Sciences

Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties, spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover, existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and …

The Effect Of Demand Response Control On Stability Delay Margins Of Loadfrequency Control Systems With Communication Time-Delays, Deni̇z Kati̇poğlu, Şahi̇n Sönmez, Saffet Ayasun, Ausnain Naveed

Turkish Journal of Electrical Engineering and Computer Sciences

This paper studies the effect of dynamic demand response (DR) control on stability delay margins of load frequency control (LFC) systems including communication time-delays. A DR control loop is included in each control area, called as LFC-DR system and Rekasius substitution is utilized to identify stability margins for various proportionalintegral (PI) gains and participation ratios of the secondary and DR control loops. The purpose of Rekasius substitution technique is to obtain purely complex roots on the imaginary axis of the time-delayed LFC-DR system. This substitution first converts the characteristic equation of the LFC-DR system including delay-dependent exponential terms into an …

An Improved Version Of Multi-View K-Nearest Neighbors (Mvknn) For Multipleview Learning, Eli̇fe Öztürk Kiyak, Derya Bi̇rant, Kökten Ulaş Bi̇rant

Turkish Journal of Electrical Engineering and Computer Sciences

Multi-view learning (MVL) is a special type of machine learning that utilizes more than one views, where views include various descriptions of a given sample. Traditionally, classification algorithms such as k-nearest neighbors (KNN) are designed for learning from single-view data. However, many real-world applications involve datasets with multiple views and each view may contain different and partly independent information, which makes the traditional single-view classification approaches ineffective. Therefore, this article proposes an improved MVL algorithm, called multi-view k-nearest neighbors (MVKNN), based on the existing KNN algorithm. The experimental results conducted in this research show that a significant improvement is achieved …

Classification Of Neonatal Jaundice In Mobile Application With Noninvasive Imageprocessing Methods, Firat Hardalaç, Mustafa Aydin, Uğurhan Kutbay, Kubi̇lay Ayturan, Anil Akyel, Ati̇ka Çağlar, Bo Hai̇, Fati̇h Mert

Turkish Journal of Electrical Engineering and Computer Sciences

This study aims a mobile support system to aid health care professionals in hospitals or in regions far away from hospitals to utilize noninvasive image processing methods for classification of neonatal jaundice. A considerably low processing cost is aimed to be attained by developing an algorithm that could work on a mobile device with low-end camera and processor capabilities within this study. In this context, an algorithm with low cost is developed performing detection of most meaningful parameters by a multiple input single output regression model and correlation.The advantage of the proposed method is that it can estimate bilirubin with …

Building A Competitive Platform For Cyber Security And Computer Science Technical Challenges, Zachariah Pelletier

Senior Honors Theses and Projects

To answer the question of whether creating a competitive environment drives students’ engagement while completing class objectives, two EMU Honors students designed and built a web application that creates such an environment. This system allows students to complete assignments that are weighted on a point system and compare scores on an anonymous “Leaderboard”. This system attempts to emulate a competition environment for objective-based learning and is designed to be used for Information Security lab assignments similar to a Security competition environment. Although the primary proof-of-concept labs for this project for this project are in the Computer Science and Information Security …

Building A Secure Web Application For Gamified Technical Labs, Kevin Higman

Senior Honors Theses and Projects

In order to improve upon existing online lab platforms, in an attempt to increase student motivation, gamification has been used to create a new gamified web application. Departmental research has shown gamification to provide significant improvement to student’s self-efficacy and motivation. Neuralabs, a web application created by two Eastern Michigan Honors Students, uses techniques often found in popular video games in order to create a more appealing learning experience. Building a public web application designed towards Cybersecurity students creates many technical security challenges. Neuralabs goal is to create a secure competitive learning experience where students can create and take labs …

Proposed Data Governance Framework For Small And Medium Scale Enterprises (Smes), Rejoice Okoro

All Graduate Theses, Dissertations, and Other Capstone Projects

Data governance is not a one size fits all, instead, it should be an evolutionary process that can be started small and measurable along the way. This research aims at proposing a data governance framework by ensuring data management processes, data security and control are compliant with laws and policies. This article also presents the first results of a comparative analysis between three data privacy laws and outlines five components which together form a data governance framework for SMEs. The data governance model documents data quality roles and their type of interaction with data quality management activities exploring how data …

Exploiting Semantic Embedding And Visual Feature For Facial Action Unit Detection, Huiyuan Yang, Lijun Yin, Yi Zhou, Jiuxiang Gu

Computer Science Faculty Research & Creative Works

Recent study on detecting facial action units (AU) has utilized auxiliary information (i.e., facial landmarks, relationship among AUs and expressions, web facial images, etc.), in order to improve the AU detection performance. As of now, no semantic information of AUs has yet been explored for such a task. As a matter of fact, AU semantic descriptions provide much more information than the binary AU labels alone, thus we propose to exploit the Semantic Embedding and Visual feature (SEV-Net) for AU detection. More specifically, AU semantic embeddings are obtained through both Intra-AU and Inter-AU attention modules, where the Intra-AU attention module …

Preface, Zhe Liu, Fan Wu, Sajal K. Das

Computer Science Faculty Research & Creative Works

No abstract provided.

Optimizing Error-Bounded Lossy Compression For Scientific Data On Gpus, Jiannan Tian, Sheng Di, Xiaodong Yu, Cody Rivera, Kai Zhao, Sian Jin, Yunhe Feng, Xin Liang, Dingwen Tao, Franck Cappello

Computer Science Faculty Research & Creative Works

Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes. With ever-emerging heterogeneous high-performance computing (HPC) architecture, GPU-accelerated error-bounded compressors (such as CUSZ and cuZFP) have been developed. However, they suffer from either low performance or low compression ratios. To this end, we propose CUSZ+ to target both high compression ratios and throughputs. We identify that data sparsity and data smoothness are key factors for high compression throughputs. Our key contributions in this work are fourfold: (1) We propose an efficient compression workflow to adaptively perform run-length encoding and/or variable-length encoding. (2) We derive Lorenzo reconstruction in …

Synchronization And Analysis Of Multimodal Medical Data, Nafisa N. Mostofa

Honors Undergraduate Theses

The United States suffers from a significant disparity in the availability of the medical resources and expertise among different regions of the country. Patients in rural areas may not have the opportunity to consult with a physician until their disease progresses to later stages, resulting in a considerable decrease in quality of life. Advances in telemedicine systems that can provide remote communication, medical data acquisition, and medical data analysis promise a significant improvement to early access to medical care and diagnoses for disadvantaged individuals.

In this thesis, we make several contributions on topics that contribute to the improvement of telemedicine …

A Monte-Carlo Analysis Of Monetary Impact Of Mega Data Breaches, Mustafa Canan, Omer Ilker Poyraz, Anthony Akil

Engineering Management & Systems Engineering Faculty Publications

The monetary impact of mega data breaches has been a significant concern for enterprises. The study of data breach risk assessment is a necessity for organizations to have effective cybersecurity risk management. Due to the lack of available data, it is not easy to obtain a comprehensive understanding of the interactions among factors that affect the cost of mega data breaches. The Monte Carlo analysis results were used to explicate the interactions among independent variables and emerging patterns in the variation of the total data breach cost. The findings of this study are as follows: The total data breach cost …

Enhancing Cyberweapon Effectiveness Methodology With Se Modeling Techniques: Both For Offense And Defense, C. Ariel Pinto, Matthew Zurasky, Fatine Elakramine, Safae El Amrani, Raed M. Jaradat, Chad Kerr, Vidanelage L. Dayarathna

Engineering Management & Systems Engineering Faculty Publications

A recent cyberweapons effectiveness methodology clearly provides a parallel but distinct process from that of kinetic weapons – both for defense and offense purposes. This methodology promotes consistency and improves cyberweapon system evaluation accuracy – for both offensive and defensive postures. However, integrating this cyberweapons effectiveness methodology into the design phase and operations phase of weapons systems development is still a challenge. The paper explores several systems engineering modeling techniques (e.g., SysML) and how they can be leveraged towards an enhanced effectiveness methodology. It highlights how failure mode analyses (e.g., FMEA) can facilitate cyber damage determination and target assessment, how …

A Blockchain-Enabled Model To Enhance Disaster Aids Network Resilience, Farinaz Sabz Ali Pour, Paul Niculescu-Mizil Gheorghe

Engineering Management & Systems Engineering Faculty Publications

The disaster area is a true dynamic environment. Lack of accurate information from the affected area create several challenges in distributing the supplies. The success of a disaster response network is based on collaboration, coordination, sovereignty, and equality in relief distribution. Therefore, a trust-based dynamic communication system is required to facilitate the interactions, enhance the knowledge for the relief operation, prioritize, and coordinate the goods distribution. One of the promising innovative technologies is blockchain technology which enables transparent, secure, and real-time information exchange and automation through smart contracts in a distributed technological ecosystem. This study aims to analyze the application …

Siguria Kibernetike Gjatë Punës Nga Distanca, Agon Daci

Theses and Dissertations

Në çdo pjesë të përditshmërisë dhe jetës tonë kemi vendosur përdorimin e teknologjisë së informacionit dhe sistemet e informacionit në përgjithësi. Jeta e jonë është e plotësuar me Internetin e gjërave (IoT), ku shtëpitë tona tani janë shtëpi të mençura.

Mundësitë për të thjeshtësuar dhe lehtësuar punën tonë janë shumë të mëdha dhe tani në këtë realitet që jetojmë, kemi mundësi të përfundojmë detyrat tona edhe pa prezencën fizike, nga distanca.

Puna nga distanca ka shumë përparësi sa i përket anës ekonomike sikurse të punonjësit ashtu edhe të punëdhënësit që mund të kursejmë në hapësirë (qira, objekt, udhëtim), më tepër …

Access Control For The Internet Of Things, Yllka Bahtiri

Theses and Dissertations

Access control for the internet of things controlli i qasjes ne koncept është siguria që minimizon rrezikun për biznes apo organizata të ndryshme të qasjes së paautorizuar në sistemet fizike dhe logjike.

Ndryshe mundemi të themi se është një teknik që rregullon cilët persona çfarë munden te

shikojnë dhe çfarë munden të perdorin në një mjedis informatikë.

Interneti i gjerave mundëson shërbime që do ta përmisojnë jetën e përditshme të njerzëve, do të

krijojnë biznese të reja dhe do të bëjnë ndërtesa, qytete dhe transportin më te zgjuar. Internet of

things ka ardhur për të përshkruar një numer të teknologjive …

Classification Of Pedagogical Content: Review And Research Challenges, Vedat Apuk

Theses and Dissertations

The advent of the Internet and a large number of digital technologies has brought with it many different challenges. A large amount of data is found on the web, which in most cases is unstructured and unorganized, and this contributes to the fact that the use and manipulation of this data is quite a difficult process. Due to this fact, the usage of different machine learning techniques for Text Classification has gained its importance, which improved this discipline and made it more interesting for scientists and researchers for further study. These techniques bring a lot of advantages, as they are …

Ndikimi I Sulmeve Kibernetike Në Sektorin Bankar Dhe Shëndetësor Gjatë Vitit 2020, Triflona Tolaj

Theses and Dissertations

- Punimi im i temës së diplomës është një hulumtim shkencor rreth sulmeve kibernetike dhe ndikimit të tyre në dy sektorët më të rrezikuar, sektorin bankar dhe atë shëndetësor. Tema është përzgjedhur e tillë pasi që çdo ditë përballemi me risi të reja në fushën e teknologjisë. Kjo gjë ka ndikuar edhe në rritjen e sulmeve kibernetike, e numri i tyre është shtuar edhe më shumë gjatë periudhës së po këtij viti, pandemisë së koronavirusit. Në kapitujt e parë të projektit është shtjelluar fillimisht koncepti i sigurisë kibernetike dhe masat që duhet të merren për mbrojtjen ndaj sulmeve të mundshme, …

Testimi I Përformances Së Web Aplikacioneve, Nita Belegu

Theses and Dissertations

Meqenëse numri i web aplikacioneve është në rritje dhe këto web aplikacione gjithnjë e më tepër po bëhen më komplekse, atëherë edhe kërkesat për performancë të avancuar rriten njëkohësisht. Padyshim, nga çdo web aplikacion secili nga ne kërkon që të jetë mjaft i shpejtë, por në të njëjtën kohë edhe të ketë siguri. Me një klikim në një faqe në web, dëshirojmë që ajo të ngarkohet mjaftë shpejtë ashtu që të përfundojmë punët e caktuara dhe t’i dedikohemi punës tjetër. Në të kundërtën, nëse faqja ngarkohet shumë ngadalë, njeriu është i prirur që të dorëzohet për atë punë që ka …

Testimi I Java Dhe Node.Js Aplikacioneve, Nderim Bytyçi

Theses and Dissertations

Testimi është njëra nga fazat e ciklit të zhvillimit të një softueri. Se sa ai softuer është i besueshëm dhe konsistent ndaj përdoruesit, vlerësohet me anë të shumë testeve qofshin ato automatike apo manuale nga një tester i kualifikuar. Shpeshherë eksperienca e dobët e testerit, shkakton probleme dhe vonesa në lëshim (release) të aplikacionit dhe kjo ndikon në reputacionin e kompanisë si dhe pakënaqësinë e përdoruesit. Në mënyrë që të evitojmë raste të tilla, aplikacioni duhet testuar. Testimi i një produkti ka shumë benefite, dhe njëra nga më të rëndësishmet është efikasiteti dhe kursimi i buxhetit, sepse nëse gabimet (bugs) …

Hardware Hacking, Purpleair – Rast Studimi, Pajtim Cakaj

Theses and Dissertations

Gajtë këtij punimi unë do të trajtoj temën Hardware Hacking, ma konkretisht hakimi i paisjes PurpleAir. Do të analizojë sistematikisht mekanizmat e përditësimit të firmware-it të pajisjeve të njohura të monitorimit të cilësisë së ajrit PurpleAir dhe paraqes sulme (fizike) harduerike dhe sulme nga distanca kundër këtyre pajisjeve, cilat janë dobësit që një haker i shfrytëzon për të hakuar këto paisje, cilat janë pasojat e hakimit të këtyre paisjeje si dhe do të tregohet projektimi dhe implementimi për një sistem të sigurt të përditësimit të firmware-it të këtyre paisjeve e që si rast studimi është marr paisja PurpleAir.

Interneti I Gjerave Ne Shendetesi, Mihrije Morina

Theses and Dissertations

Me avancimin e teknologjive të komunikimit të informacionit, evolucioni i Internetit ka krijuar një rrjet të kudogjendur, i përbërë nga objekte (ose gjëra) të ndërlidhura, të quajtur Interneti i Gjërave (IoT). Kohët e fundit, komuniteti akademik ka bërë përparime të mëdha në kërkimin dhe zhvillimin e sigurisë për aplikacionet e bazuara në IoT, duke u përqëndruar, në veçanti, në sistemet e kujdesit shëndetësor të bazuar në rrjetet e IoT. Interneti i Gjërave (IoT) është i pajisur me çdo proces kompjuterik, mikrokontrolluesit dhe marrësit për fuqizimin e komunikimit dhe është ndërtuar me pirgje të përshtatshme protokolli që i ndihmojnë ata të …