Physical Sciences and Mathematics Commons^™

Metalearning By Exploiting Granular Machine Learning Pipeline Metadata, Brandon J. Schoenfeld

Theses and Dissertations

Automatic machine learning (AutoML) systems have been shown to perform better when they use metamodels trained offline. Existing offline metalearning approaches treat ML models as black boxes. However, modern ML models often compose multiple ML algorithms into ML pipelines. We expand previous metalearning work on estimating the performance and ranking of ML models by exploiting the metadata about which ML algorithms are used in a given pipeline. We propose a dynamically assembled neural network with the potential to model arbitrary DAG structures. We compare our proposed metamodel against reasonable baselines that exploit varying amounts of pipeline metadata, including metamodels used …

Implementimi I Devops Strategjisë Në Kompani Të Vogla Dhe Të Mesme, Diellza Shabani

Theses and Dissertations

DevOps është një kornizë konceptuale për riintegrimin e zhvillimit dhe funksionimit të Sistemeve të Informacionit. Unë kam kryer një studim për strategjitë e ndryshme të implementimit të DevOps në kompani të ndryshme. Unë vërejta se DevOps nuk është studiuar në mënyrë adekuate në literaturën shkencore. Ekzistojnë relativisht pak kërkime në dispozicion në DevOps dhe studimet shpesh janë me cilësi të ulët. Unë gjithashtu vërejta që DevOps mbështetet nga një kulturë e bashkëpunimit, automatizimi, matje, shkëmbimi i informacionit dhe përdorimi i shërbimit në internet. DevOps përfiton nga SI dhe zhvillimi i operacioneve. Ajo gjithashtu ka efekte pozitive në zhvillimin e shërbimit …

Ndërtimi I Një "To-Do" Aplikacioni Me Teknologjinë Flutter, Emnolina Brahimi

Theses and Dissertations

Aplikacionet për telefon mobil viteve të fundit kanë filluar të zëvendësojnë shumë veprimtari që në të shkuarën i kemi bërë në mënyrë primitive te themi. Nevoja për të kursyer sa më shumë kohë, energji dhe para ka bërë që të krijohen aplikacione të ndryshme, inovative dhe mbi të gjitha aplikacione që ofrojnë zgjidhje të problemeve.

Smartphone-ët por edhe shumë pajisje të tjera elektronike si tabletet dhe smartwatch janë bërë aq të nevojshme sa që pothuajse secili person i rritur mund të posedoj një të tillë.

Duke parë kërkesën dhe nevojën në tregun tonë për zgjidhje të problemeve përmes aplikacioneve, si …

Vitrina Virtuale E Librit, Genti Sheholli

Theses and Dissertations

Zhvillimi i aplikacioneve moderne në ditët e sotme nuk është vetëm proces i ndërtimit të aplikacionit. Procesi përfshin zhvillimin e shërbimeve në anën e serverit dhe aplikacionit në anën e klientit. Teknologjitë dhe opsionet për të zhvilluar një web aplikacion janë të shumta dhe varësisht se cfarë web aplikacioni duhet të zhvillohet mund të vendosim edhe për teknologjitë në secilin aspekt.

Qëllimi i këtij web aplikacioni është hulmtimi në teknologjit të kohës që kanë marrë hov të zhvillimit në aplikacionet moderne dhe hulumtim në zhvillimin e aplikacionit me struktura moderne.

Ky web aplikacion është një sintezë e proceseve, procedurave dhe …

Analiza E Efekteve Shëndetsore Gjatë Përdorimit Të Rrjetave Pa Tela Në Kushtet E Jetës Reale, Hashim Sahiti

Theses and Dissertations

Teknologjia Wireless u ideua në 1880 nga Alexander Graham Bell dhe Sumner Tainted kur u zbulua telefoni fotografik. Në ditët e sotme, ka shumë lloje të pajisjeve pa tela që përdoren për të komunikuar. Telefoni celular dhe Rrjeti Wireless janë pjesa e jetës sonë të përditshme në të gjithë botën. Pajisja Wi-Fi lejon shkëmbimin (marrjen dhe dërgimin) e të dhënave përmes pajisjeve pa tela dhe Wi-Fi lëshojnë valë radio. Pajisjet që përdorin Wi-Fi janë kompjuterët, tabletat, celularët, audio player, aparatet fotografikë digjital si dhe pajisjet përcjellëse te kompjuterit si printerët, tastiera, miu e etj. Pajisjet pa tela janë të bazuara …

Analizimi Dhe Zhvillimi I Sistemit Për Komunikim Në Telemjekësi Duke Përdorur Teknologjinë Webrtc, Fitim Mehmeti

Theses and Dissertations

Sistemet softuerike për komunikim në përgjithësi e në veçanti telemedicina që për qëllim ka ofrimin e kujdesit shëndetsor në distancë janë duke u bërë aset i rëndësishëm në shtetet e zhvilluara. Kufizimet në kohë, vendndodhja, kushtet atmosferike, tash së fundmi edhe pandemia COVID-19 janë ndër arsyet kryesore për zhvillimin e sistemeve të tilla. Ky punim është përqëndruar në hulumtimin, analizimin dhe krahasimin e sistemeve për komunikim online, mënyra se si funksionojnë këto sisteme, gjithashtu është fokusuar në zhvillimin e një aplikacioni për komunikim me video për pacientët dhe mjekët duke përdorur teknologjinë webRTC, ky projekt do të zhvillohet në bazë …

Ndikimi I Ueb Aplikacionit Dhe Aplikacionit Për Telefonë Në Menaxhimin Dhe Shperndarjen E Informacionit Në Ditët E Sotme, Jetmir Feka

Theses and Dissertations

Në kohën tonë teknologjia po ecën me hapa shumë të shpejtë, sidomos në fushën e pajisjeve elektronike si: kompjuterët, tabletat, telefonat e mençur etj. Numri i përdoruesve të internetit dhe pajisjeve elektronike është shumë i madh dhe është në rritje të vazhdueshme. Qëllimi i këtij hulumtimi është identifikimi efektiv i strategjisë për zhvillimin e sistemit të menaxhimeve të portaleve online, si dhe efikasitetin në shpërndarjen e tyre. Një kompanie i nevojitet një sistem për menaxhim të lajmeve i cili është një element kryesor në zhvillimin e kompanisë. Shumica e kompanive mediatike sot kanë krijuar ueb-sajte online në mënyrë që punën …

Cross Dataset Evaluation For Iot Network Intrusion Detection, Anjum Farah

Theses and Dissertations

With the advent of Internet of Things (IOT) technology, the need to ensure the security of an IOT network has become important. There are several intrusion detection systems (IDS) that are available for analyzing and predicting network anomalies and threats. However, it is challenging to evaluate them to realistically estimate their performance when deployed. A lot of research has been conducted where the training and testing is done using the same simulated dataset. However, realistically, a network on which an intrusion detection model is deployed will be very different from the network on which it was trained. The aim of …

Deep Learning-Based Reconstruction Of Volumetric Ct Images Of Vertebrae From A Single View X-Ray Image, Mingren Xiang

Theses and Dissertations

Computed tomography is often used in medical fields today because it creates more detailed information for doctors than regular X-ray images. However, one major side effect is that patients may be exposed to a large dose of radiation because it takes hundreds of X-ray images to compute a CT scan. Another shortcoming is that patients are required to lay down on the CT machine for the scan, which is usually not the ideal position when diagnosing spine related issues such as cervical spondylosis and lumbar disc herniation. The prime motivation for this study is to reconstruct CT images using only …

The Design And Validation Of A Discrete-Event Simulator For Carbohydrate Metabolism In Humans, Husam Ghazaleh

Theses and Dissertations

CarbMetSim is a discrete event simulator that tracks the changes of blood glucose level of a human subject after a timed series of diet and exercises activities. CarbMetSim implements wider aspects of carbohydrate metabolism in individuals to capture the average effect of various diet/exercise routines on the blood glucose level of diabetic patients. The simulator is implemented in an object-oriented paradigm, where key organs are represented as classes in the CarbMetSim. Key organs (stomach, intestine, portal vein, liver, kidney, muscles, adipose tissue, brain and heart) are implemented to the extent necessary to simulate their impact on the production and consumption …

Intelligent Therapeutic Robot: Design, Development, And Control, Asif Al Zubayer Swapnil

Theses and Dissertations

This research contributes to developing an Intelligent Therapeutic Robot (iTbot) designed to provide therapy to patients with upper limb impairment due to stroke, injury, and other trauma. This robot aims to implement robotic rehabilitation based on principles of motor rehabilitation and Neuroplasticity. The iTbot, as developed in this research, can provide end-effector type rehabilitation exercises in various configurations, including motion in the vertical and horizontal plane. It can provide passive, active, and active-assisted rehabilitation therapies to patients with limited upper limb mobility.

The iTbot has been designed with simplicity in mind with a minimum viability approach. With a minimum amount …

Proactive Management In Academic Libraries: Promoting Improved Communication And Inclusion Of Academic Librarians And Archivists In Cybersecurity Policy Creation, Paul J. Luft

Theses and Dissertations

Although increasing cybersecurity threats continue in libraries, not many studies are available which examine surrounding cybersecurity policies. Even less has been done on specific types of libraries such as academic and archives. When it comes to academic libraries, cybersecurity policies take a top-down approach to managing and creating policies. The problem is that both academic libraries and archives are unique areas within a university setting. Some of the general policies do not always handle specific issues dealt with in an academic library or archives. This paper investigates if an actual gap or void in policy exists which could create issues …

Empowering People With Cognitive Disabilities To Live Independently By Supporting Their Self-Management Of Food And Related Expenses, Apoorv Prasad

Theses and Dissertations

People with ADHD (attention deficit hyperactivity disorder) often have difficulty in planning and organization that can impact their eating habits and lifestyle. We have created a novel mobile software application to support choosing meals and making healthy food purchases that meet dietary preferences within a specified budget. The core functions allow 1) Managing user profiles to support personalization 2) Obtaining recipe recommendations to fit profile, budget, and foods-on-hand 3) Planning food purchases, and 4) Reviewing foods-on-hand, budget and the nutritional balance of recent meals and food purchases.The application supports self-introspection to help people with ADHD review their history of food …

Trace: A Differentiable Approach To Line-Level Stroke Recovery For Offline Handwritten Text, Taylor Neil Archibald

Theses and Dissertations

Stroke order and velocity are helpful features in the fields of signature verification, handwriting recognition, and handwriting synthesis. Recovering these features from offline handwritten text is a challenging and well-studied problem. We propose a new model called TRACE (Trajectory Recovery by an Adaptively-trained Convolutional Encoder). TRACE is a differentiable approach using a convolutional recurrent neural network (CRNN) to infer temporal stroke information from long lines of offline handwritten text with many characters. TRACE is perhaps the first system to be trained end-to-end on entire lines of text of arbitrary width and does not require the use of dynamic exemplars. Moreover, …

A Machine Learning Approach To Forecasting Sep Events With Solar Activities, Jesse Scott Torres

Theses and Dissertations

Solar energetic particles (SEPs) are fast-moving events which can cause severe damage to astronauts and their equipment, and can disrupt communications on Earth. There are no clear patterns in solar activities which indicate whether an SEP is about to occur, making physics-based methods inaccurate for SEP forecasting. Therefore, in order to provide an advance warning so that astronauts are able to get to safety, we apply neural networks to the problems of forecasting SEP occurrence and intensity. Our algorithm for predicting SEP occurrence uses a combination of observed CME properties and derived features and achieves a TSS of 0.846 and …

A Fast And Exact Motif Enumeration Algorithm For Dynamic Networks, Abbas Al-Thaedan

Theses and Dissertations

From social to biological networks, prior research in complex networks have demonstrated the importance of the frequency and distribution of different types of motifs to important network functions and properties. A network motif (or graphlet) is defined as a small connected sub-pattern which is over-represented in a network. Network motifs have been widely applied in a wide range of applications, namely biological, social, and technical networks. The counting of the network motif involves expensive enumeration of graph sub-patterns along with the detection of graph isomorphism. In general, network motif detection algorithms are computationally expensive and often designed to operate over …

Real-Time Full Face Closed Eyes Detection, Lucas De Morais Tramasso

Theses and Dissertations

Intelligent systems based on machine-learning techniques are becoming a common way of solving problems in many different areas. In this thesis, our goal is to apply machine learning to a computer vision problem. We propose a new solution to detect closed eyes in full-face images. Accurate detection of closed eyes can be used in many problems such as driver drowsiness detection, human-computer interaction, and computer user monitoring. Most algorithms used to detect blinks or closed eyes follow a similar workflow. They require detection of a region of interest that is then used with different algorithms and techniques to determine if …

Refinements Of The Concept Of Privacy In Distributed Computing, Entisar Seedi Alshammry

Theses and Dissertations

In light of the tremendous development of technology in the modern world in which we live, privacy concerns are increasing, especially after the massive spread of distributed computing systems and the technologies that depend on it, whether in personal devices or public services. Hence, this research proposes refinements on the concept of privacy for enhancing the development of privacy-related strategies in distributed computing systems to address the elements of privacy. In particular, the study introduces the new concept of Privacy Appetite to describe and model the nature of the relationship between the intended disclosure of private information and gained value …

Real-Time Action Classification Using Intermediate Skeletal Pose Estimation, Kleanthis Zisis Tegos

Theses and Dissertations

The topic of Human Action Classification has attracted significant interest these past years, which can be attributed to the advancements in deep learning methodologies. Its applications range from robotics to surveillance and automated video categorization, as well as in the healthcare industry. The literature, however, has primarily focused on offline action classification, without significant attention being given to the constraints of an online real-time classifier. Using an intermediate skeletal representation of humans, while convoluted, provides a scalable means of tackling the action classification problem. This project discusses the existing literature, and adapts two of the state-of-the-art approaches for real-time analysis. …

Biometric Face Skintone Data Augmentation Using A Generative Adversarial Network, Rosalin Dash

Theses and Dissertations

Researchers seek methods to increase the accuracy and efficiency in identifying an individual using facial biometric systems. Factors like skin color, which may affect the accuracy of facial recognition, need to be investigated further. To analyze the impact of race with respect to skin color of face on biometric systems, we focused on generating a dataset with uniformly distributed images of different skin tones while preserving identities. Deep learning neural network architectures like the generative adversarial network (GAN) focus on modifying only certain features of the face like the color of the skin. In our experimental approach, we implemented a …

In-Depth Analysis Of College Students’ Data Privacy Awareness, Vernon D. Andrews

Theses and Dissertations

While attending university, college students need to be aware of issues related to data privacy. Regardless of the age, gender, race, or education level of college students, every student can relate to the advancement of the internet within the last decades. The internet has completely transformed the way the world receives and stores messages. Positively, the internet allows messages to be sent across the globe within the fraction of a second and provides students with access to potentially unlimited information on a variety of subjects. On the downside, there are issues on the internet that can cause more harm than …

Neural Network Development In An Artificial Intelligence Gomoku Program, David Garcia

Theses and Dissertations

The game of Gomoku, also called Five in a Row, is an abstract strategy board game. The Gomoku program is constructed upon an algebraic monomial theory to aid values for each possible move and estimate chances for the artificial intelligence program to accomplish a winning path for each move and rounds. With the utilization of the monomial theory, winning configurations are successfully converted into monomials of variables which are represented on board positions. In the artificial intelligence program, an arduous task is how to perform the present configuration of the Gomoku game along with the past moves of the two …

Artificial Intelligence In A Main Warehouse In Panasonic: Los Indios, Texas, Edison Antonio Trejo Hernandez

Theses and Dissertations

The Panasonic Company warehouse is located in Los Indios Texas. The warehouse presents the limitation of the great distances between its headquarters and the Main Warehouse for supplying the branches and main customers, which requires a considerable amount of time to maintain effective communication in the inventory area. In addition, during an online review, it can be confirmed that the website is disabled, contradicting its corporate policy.

The structure of the thesis proposal is arranged in four chapters from the Introduction, Statement of the Problem and Purposes; Previous Studies and Definition of the literature; the Research Methodology and the resources …

A Targeted Adversarial Attack On Support Vector Machine Using The Boundary Line, Yessenia Rodriguez

Theses and Dissertations

In this thesis, a targeted adversarial attack is explored on a Support Vector Machine (SVM). SVM is defined by creating a separating boundary between two classes. Using a target class, any input can be modified to cross the “boundary line,” making the model predict the target class. To limit the modification, a percentage of an image of the target class is used to get several random sections. Using these sections, the input will be moved in small steps closer to the boundary point. The section that took the least number of steps to cause the model to predict the target …

Reinforcement Learning Environment For Orbital Station-Keeping, Armando Herrera Iii

Theses and Dissertations

In this thesis, a Reinforcement Learning Environment for orbital station-keeping is created and tested against one of the most used Reinforcement Learning algorithm called Proximal Policy Optimization (PPO). This thesis also explores the foundations of Reinforcement Learning, from the taxonomy to a description of PPO, and shows a thorough explanation of the physics required to make the RL environment. Optuna optimizes PPO's hyper-parameters for the created environment via distributed computing. This thesis then shows and analysis the results from training a PPO agent six times.

Deep Learning-Based, Passive Fault Tolerant Control Facilitated By A Taxonomy Of Cyber-Attack Effects, Dean C. Wardell

Theses and Dissertations

In the interest of improving the resilience of cyber-physical control systems to better operate in the presence of various cyber-attacks and/or faults, this dissertation presents a novel controller design based on deep-learning networks. This research lays out a controller design that does not rely on fault or cyber-attack detection. Being passive, the controller’s routine operating process is to take in data from the various components of the physical system, holistically assess the state of the physical system using deep-learning networks and decide the subsequent round of commands from the controller. This use of deep-learning methods in passive fault tolerant control …

Electro-Optic Satellite Constellation Design Using Multi-Objective Genetic Algorithm, Yasin Tamer

Theses and Dissertations

Satellite constellation design is a complex, highly constrained, and multidisciplinary problem. Unless optimization tools are used, tradeoffs must be conducted at the subsystem level resulting in feasible, but not necessarily optimal, system designs. As satellite technology advances, new methods to optimize the system objectives are developed. This study is based on the development of a representative regional remote sensing constellation design. This thesis analyses the design process of an electrooptic satellite constellation with regional coverage considerations using system-level optimization tools. A multi objective genetic algorithm method is used to optimize the constellation design by utilizing MATLAB and STK integration. Cost, …

Moving Target Network Steganography, Tapan Soni

Theses and Dissertations

A branch of information hiding that has gained traction in recent years is network steganography. Network steganography uses network protocols are carriers to hide and transmit data. Storage channel network steganography manipulates values in protocol header and data fields and stores covert data inside them. The timing channel modulates the timing of events in the protocol to transfer covert information. Many current storage channel network steganography methods have low bandwidths and they hide covert data directly into the protocol which allows discoverers of the channel to read the confidential information. A new type of storage channel network steganography method is …

Barriers And Drivers Influencing The Growth Of E-Commerce In Uzbekistan, Madinakhon Tursunboeva

Theses and Dissertations

Electronic commerce (e-commerce) has become a major retail channel for businesses in developed countries. However, it is still considered an innovation in developing countries. Specifically, e-commerce in Uzbekistan is in the early stages of emergence despite its advance in recent years in terms of Internet penetration, a strong retail sector, new national regulations, and a young population. The study aimed to identify barriers and drivers influencing e-commerce growth in Uzbekistan. A Delphi research design was utilized to answer the research questions of the study, which categorized and ranked factors that Uzbekistani entrepreneurs are facing when engaging in e-commerce processes. A …

Privacy And The Digital Divide: Investigating Strategies For Digital Safety By People Of Color, Denavious Hoover

Theses and Dissertations

People of color are becoming increasingly concerned with digital privacy. They are concerned about the obfuscated data collection and sharing practices of major social media plat- forms and the strong entitlement of other users in the online space to their content. This study examines how people of color conceptualize and behave to produce safety in the online space, or, in other words, digital privacy. This study challenges notions that people are not purposeful about privacy in the online space and highlights the voices of people of color, whom are not of- ten included in theorizing or decision making about the …