Digital Commons Network^™

Insights Into Employees’ Attrition Causes: Data Analytics, Sumayah Abdulla Al Heloo, Naela Nasser Al Koudah

Theses

Many employers are currently facing the costly challenge of employee attrition. This project study aims to present a prediction model that predicts employees’ erosion. To ensure project completion, the author scrutinized the Dubai Government’s employee data, which we obtained from its Human Resources Department. The employee data helped me determine the statistically essential factors that are associated with an employee’s decision to quit and understand the types of occupations where this model can be applied. The data gathered included information about employees’ specific demographics, seniority, income, and satisfaction. The dataset consists of 35 variables, with an Attrition category that entails …

Financial Fraud Detection Using Machine Learning Techniques, Matar Al Marri, Ahmad Alali

Theses

Payments related fraud is a key aspect of cyber-crime agencies and recent research has shown that machine learning techniques can be applied successfully to detect fraudulent transactions in large amounts of payments data. Such techniques have the ability to detect fraudulent transactions that human auditors may not be able to catch and also do this on a real time basis. In this project, we apply multiple supervised machine learning techniques to the problem of fraud detection using a publicly available simulated payment transactions data. We aim to demonstrate how supervised ML techniques can be used to classify data with high …

Forensic Memory Classification Using Deep Recurrent Neural Networks, Aishwarya Afzulpurkar

Theses

The goal of this project is to advance the application of machine learning frameworks and tools in the process of malware detection. Specifically, a deep neural network architecture is proposed to classify application modules as benign or malicious, using the lower level memory block patterns that make up these modules. The modules correspond to blocks of functionality within files used in kernel and OS level processes as well as user level applications. The learned model is proposed to reside in an isolated core with strict communication restrictions to achieve incorruptibility as well as efficiency, therefore providing a probabilistic memory-level view …

Design Of Dsp Guitar Effects With Fpga Implementation, Connor William Blasie

Theses

The face of music has been drastically evolving over the past century starting with the advent of the electric guitar. The emergence of digital signal processing in guitar audio applications has constantly been driven by the ability to diversify tonalities from experimenting with instrument materials, pick-ups, amplifiers, and effects. This paper demonstrates an alternative approach to guitar effects by using FPGA implementation, in lieu of DSP cores or analog components, to perform digital signal processing intended for alteration of guitar audio signals. The audio processing of the multiple effects were developed on a Zedboard incorporated with a Xilinx Zynq®-7000 SOC …

Design Of Hardware Cnn Accelerators For Audio And Image Classification, Rohini Jayachandre Gillela

Theses

Ever wondered how the world was before the internet was invented? You might soon wonder how the world would survive without self-driving cars and Advanced Driver Assistance Systems (ADAS). The extensive research taking place in this rapidly evolving field is making self-driving cars futuristic and more reliable. The goal of this research is to design and develop hardware Convolutional Neural Network (CNN) accelerators for self-driving cars, that can process audio and visual sensory information. The idea is to imitate a human brain that takes audio and visual data as input while driving. To achieve a single die that can process …

Divide And Conquer In Neural Style Transfer For Video, Paul Galatic

Theses

Neural Style Transfer is a class of neural algorithms designed to redraw a given image in the style of another image, traditionally a famous painting, while preserving the underlying details. Applying this process to a video requires stylizing each of its component frames, and the stylized frames must have temporal consistency between them to prevent flickering and other undesirable features. Current algorithms accommodate these constraints at the expense of speed.

We propose an algorithm called Distributed Artistic Videos and demonstrate its capacity to produce stylized videos over ten times faster than the current state-of-the-art with no reduction in output quality. …

Elucidating The Effect Of Temperature And Concentration On The Rotational Diffusion Of Yb– Crystallin To Elucidate Inter-Protein Interactions, Olivia Fraser

Theses

γB – crystallin is a 21 kDa protein found in the lens of the bovine eye, existing without turnover. It shares 76% sequence identity with a human lens protein, γD – crystallin, with a structural RMSD of 0.8 Å by Dali (174 residues, Cα atoms only). Damages to and abnormalities on crystallin proteins can lead to phase separation and aggregation in the lens, resulting from aberrant inter-protein interactions, which can lead to partial or total blindness by cataract. The purpose of this work is to elucidate global inter-protein interactions of wild-type γB – crystallin by T1 and T2 relaxation NMR …

Gait Generation For Damaged Hexapods Using Genetic Algorithm, Justin Kon

Theses

This paper discusses the design and implementation of a Genetic Algorithm for the generation of gaits compensating for system damage on the joint level of a hexapod system. The hexapod base used for this algorithm consists of six three degree of freedom legs on a rectangular body. The purpose of this algorithm is to generate a gait such that when N motors become inoperable, as detected by the robot’s internal software, the system is able to continue moving about its environment. While algorithms like this have been implemented before, the generated gaits are a sequence of discrete foot positions. This …

Detecting Performance Regression Inducing Code Changes Using Static And Dynamic Metrics, Hiten Gupta

Theses

Performance regression testing is a cost-intensive task as it delays the system development. The process, if performed in Iterations, significantly slows down the developer’s pace. Hence, it is essential to execute the performance tests only on the new commit and not the whole system, as regression is induced by a newly made change to the system. This work presents a novel contribution to the detection of performance regression inducing code changes to solve the optimization problem. In this study, we combine the static and dynamic metrics as features to train classifiers to predict the performance regression if introduced by the …

All-Passive Composite Right/Left-Handed (Crlh) Antenna Array For Sum And Difference Patterns, Vu James Le

Theses

Monopulse tracker is a system that uses the sum and difference radiation patterns to track. If there is a target in the beam, the tracker receives an echo from it following each transmitted pulse. The target range or distance is readily determined by multiplying half the time delay between the transmitted and received pulses by the speed of light. Typically, the sum and difference patterns are obtained by adding and subtracting individual beam patterns electronically or using RF components, such as: hybrid junctions, directional couplers. However, RF components are frequency dependent. Once they are used to realize the sum pattern …

The Design Of A Custom 32-Bit Risc Cpu And Port To Gcc Compiler Backend, Danielle Megan Fischer

Theses

This paper presents the design of a 32-bit RISC processor, which is then mapped to the backend of GCC so basic C code can be compiled successfully to the processor. There are many design decisions that go into the construction of a processor. The instruction set architecture gives away a lot of information regarding the individual instructions that the processor will have, the memory architecture, as well as how I/O peripherals will be handled. Additionally, the hardware implementation of the processor needs to be kept in mind when crating the design. Pipelining can often help with processor speed, while cache …

Design And Production Of 3d Animation Short Film “Memories Of The Post-80s”, Hui Shen

Theses

“The memories of the post-80s” is a 2minutes and 8 seconds 3D animated short film which tells a story of a young man named Kai who born in the post-80s in China, living in a modern, high-tech environment, but falling into a fantasy dream and reminiscing about his simple and happy life as a child. The most important question expressed in this short film is whether a more convenient, high-tech, fast-paced modern life is proportional to people's happiness index. The main reasons for this problem are multiple, such as working pressure, stressful life, repayment of loans, health, and so on. …

High-Capacity Directional Graph Networks, Miguel Dominguez

Theses

Deep Neural Networks (DNN) have proven themselves to be a useful tool in many computer vision problems. One of the most popular forms of the DNN is the Convolutional Neural Network (CNN). The CNN effectively learns features on images by learning a weighted sum of local neighborhoods of pixels, creating filtered versions of the image. Point cloud analysis seems like it would benefit from this useful model. However, point clouds are much less structured than images. Many analogues to CNNs for point clouds have been proposed in the literature, but they are often much more constrained networks than the typical …

Neural Network Architectures And Ensembles For Packet Classification: Addressing Visibility, Security And Quality Of Service Challenges In Communication Networks, Bruce Hartpence

Theses

Increasingly researchers are turning to machine learning techniques such as artificial neural networks (ANN) to address communication network research challenges in the areas of enhanced security, quality of service, visibility and control. Central to each is the need to classify packets. Determining an effective architecture for the artificial neural network is more difficult because traditional techniques such as principal component analysis (PCA) show reduced effectiveness. Presented are the techniques for preprocessing datasets and selecting input traffic features for the multi-layer perceptron (MLP) architecture. This methodology achieves classification accuracy above 99%.

An investigation into neural network architectures revealed the optimal structure …

Parallelized Robustness Computation For Cyber Physicalsystems Verification, Joseph Cralley

Theses

Failures in cyber physical systems can be costly in terms of money and lives. The marsclimate orbiter alone had a mission cost of 327.6 million USD which was almostcompletely wasted do to an uncaught design flaw. This shows the importance of beingable to define formal requirements as well as being able to test the design against theserequirements. One way to define requirements is in Metric Temporal Logic (MTL), whichallows for constraints that also have a time component. MTL can also have a distancemetric defined that allows for the calculation of how close the MTL constraint is to beingfalsified. This is …

Posits: An Alternative To Floating Point Calculations, Matt Wagner

Theses

Floating point arithmetic is one of several methods of performing computations in digital designs; others include integer and fixed point computations. Fixed point utilizes a method comparable to scientific notation in the binary domain. In terms of computations, floating point is by far the most prevalent in today’s digital designs. Between the support offered by compilers, as well as for ready-to-use IP blocks, floating point units (FPU’s) are a de-facto standard for most processors. Despite its prevalence in modern designs, floating point has many flaws. One of the most common is the use of not-a-numbers (NaN’s). These are meant to …

Ar Comic Chat, Dylan Bowald

Theses

Live speech transcription and captioning are important for the accessibility of deaf and hard of hearing individuals, especially in situations with no visible ASL translators. If live captioning is available at all, it is typically rendered in the style of closed captions on a display such as a phone screen or TV and away from the real conversation. This can potentially divide the focus of the viewer and detract from the experience. This paper proposes an investigation into an alternative, Augmented Reality driven approach to the display of these captions, using deep neural networks to compute, track and associate deep …

Exploration Of The Process Of Building Brand Equity As A Digital Painter, Andrew Lim

Theses

The mainstream debut of the World Wide Web in the 20th century has increased the use of branding from its simple origins of being a visual marker into a multi-faceted entity. Branding has evolved to become a multi-faceted effort that creates rational and emotional attributes and can foster interactions and develop and deepen relationships with customers (Rubinstein, 2002).

The boom of the Internet brought forth new inventions and software that affected many industries, particularly the arts. A new emergent form of art known as digital painting emerged where a drawing tablet, stylus and digital image rendering software such as Adobe …

Have Objects, Will Travel: Object-Based Outreach To Solstice Independent Living At Fairport, New York, Taylor Carpenter

Theses

This thesis details my process in designing and delivering a program, “The Evolution of the Erie Canal,” to residents of the Solstice Senior Living at Fairport, New York, utilizing objects from the Rochester Museum & Science Center’s teaching collection. Given the ever-increasing population of American adults aged 55 and older, it is more important than ever for museums to create engaging programs aimed at this sector of the population. The goal of this project was to create a meaningful object-based experience for participants through discussion and reminiscence. My sources include findings from similar projects, literature on working with adult audiences, …

Conceptions Of Refactoring: An Investigation Of Stack Overflow Posts, Steven David Simmons

Theses

Refactoring is a common activity in software development. Developers make changes in the code in order to achieve a desired effect such as better performance, conformance to new business rules, or the removal of code anti-patterns such as code smells. However, refactoring operations often fail to achieve the results that are expected of them. There have been many studies conducted to assess their impact and effectiveness in different scenarios, but they have not returned consistent results. At times, studies have even shown decreasing and increasing in code quality from the same operation.

This study investigated whether a common set of …

Improving Omnidirectional Camera-Based Robot Localization Through Self-Supervised Learning, Robert Relyea

Theses

Autonomous agents in any environment require accurate and reliable position and motion estimation to complete their required tasks. Many different sensor modalities have been utilized for this task such as GPS, ultra-wide band, visual simultaneous localization and mapping (SLAM), and light detection and ranging (LiDAR) SLAM. Many of the traditional positioning systems do not take advantage of the recent advances in the machine learning field. In this work, an omnidirectional camera position estimation system relying primarily on a learned model is presented. The positioning system benefits from the wide field of view provided by an omnidirectional camera. Recent developments in …

Led Selection For Spectral (Multispectral) Imaging, Jenibel N. Paray

Theses

Research was performed to design an LED-based spectral imaging system having channels, commonly referred to as a multispectral imaging system. The first part tackled the evaluation of a camera model in predicting the signals of a 10 LED LEDmotive Technologies Spectra Tunelab coupled with a Finger Lakes Instrumentation panchromatic camera. The camera model was shown to be valid and effective in predicting the camera signal taking into account the color transformation noise. The second part involved the computational selection of 10 LEDs in order to determine the optimum combination for a custom Spectra Tunelab. The computational selection used the spectral …

Implementation Of A Digital Asset Management System Using Human-Centered Design, Lynne Tseng

Theses

With all the people and activities involved, modern marketing and strategic communications departments are complex organizations. This complexity can lead to longer lead times to complete projects within specific and deadline-driven timeframes. Therefore, companies are turning to digital asset management (DAM) systems to streamline their workflows and become more efficient. However, without a comprehensive and strategic implementation plan, DAM systems are significantly less likely to be adopted by their end-users. This paper describes how a DAM system was selected and implemented in the marketing and strategic communications department of a large health system. By using a human-centered design methodology to …

An Assessment Of Media Consumers’ Ability To Distinguish The Level Of Post-Processing In Journalistic Images, Emily Shriver

Theses

Photojournalists are held to a high degree of ethics because of the importance and impact of their work. To address this, several professional photojournalist organizations and publishers have created guidelines on how to appropriately post-process an image. Today the average media consumer is exposed to a diverse news landscape, and there is a tendency for consumers to trust photojournalistic images as being representative of the truth (Farid, 2006). This research considers to what extent can the average media consumer distinguish between ethically and unethically post-processed images.

This study aimed to discover how well people can distinguish between three categories of …

An Interactive Medication Reminder To Bond Senior Citizens And Their Family Members, Bei Liu

Theses

This project is about assisting seniors in their daily life. More and more senior citizens in the world are facing the problem of living alone. After research, I find that medication is a very important part of seniors’ life. My design is about medication reminder that can also connect the seniors with their family members. At first, I focused on the social relationship of senior citizens and started to research medication reminders in the market. I also read many books and magazines about the medication of senior citizens and try to figure out the size and volume of my design. …

Breathing Pacer Device For Stress And Anxiety Relief, Maria Grazia Guerrero Bejarano

Theses

Stress and stress-related physical and mental diseases are increasing and affecting more people every day. There have been many approaches to try to solve this issue. Many of them are based on the idea that meditation and mindfulness breathing could improve these conditions. The problem is that not everyone can achieve those levels of meditation for that to work. Another issue is that those solutions are relying on a particular way of breathing to help all.

In contrast, this project developed under research that shows that the amount of CO₂ in a person's exhaled breath could be an indicator of …

Self-Supervised Learning For Segmentation Using Image Reconstruction, Srivallabha Karnam

Theses

Deep learning is the engine that is piloting tremendous growth in various segments of the industry by consuming valuable fuel called data. We are witnessing many businesses adopting this technology be it healthcare, transportation, defense, semiconductor, or retail. But most of the accomplishments that we see now rely on supervised learning. Supervised learning needs a substantial volume of labeled data which are usually annotated by humans- an arduous and expensive task often leading to datasets that are insufficient in size or human labeling errors. The performance of deep learning models is only as good as the data. Self-supervised learning minimizes …

Radar-Aware Transmission And Scheduling For Cognitive Radio Dynamic Spectrum Access In The Cbrs Radio Band, Dennis P. Bleier

Theses

Use of the wireless spectrum is increasing. In order to meet the throughput requirements, Dynamic Spectrum Access is a popular technique to maximize spectrum usage. This can be applied to the Citizen Broadband Radio Service (3550-3700MHz), a band recently opened by the Federal Communications Commission for opportunistic access. This radio band can be accessed as long as no higher priority users are interfered with. The top priority users are called incumbents, which are commonly naval radar. Naval radars transmit a focused beam that can be modelled as a periodic function. Lower tier users are prohibited from transmitting when their transmissions …

Identifying Performance Regression From The Commit Phase Utilizing Machine Learning Techniques, Max Mendelson

Theses

Over the lifespan of a software application, it is inevitable that changes to the source code will be made that causes unintended slowdowns in functionality. These slowdowns are referred to as performance regression. Typically projects who are particularly concerned about performance have performance testing that are run to identify if a performance regression is introduced into the code. This is difficult however due to how time consuming and resource intensive running performance tests are when trying to simulate a realistic scenario.

The study of De Oliveira et. al. (Perphecy) [4] suggests a technique to predict the likelihood that a commit …

Exploring The Role Of Direct Phonemic Awareness Instruction Of Decoding And Letter Naming On Reading Abilities Of Uae Kindergarteners, Eiman Abdulla Alkhlaifi

Theses

This study aimed at exploring the role of direct phonemic awareness of letter naming and decoding in the reading abilities of Emirati kindergartners. The mixed-method was adopted to achieve the purpose of this study. In the first phase of the study quantitative means were used by conducting a pre and post-test after implementation of the program for six weeks. The second phase of the study featured a collection of qualitative data means of document analysis which was randomly selected from the participant's performance during the program. The participants in this study were KG1 students who were selected conveniently (n=40) and …