Digital Commons Network^™

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 …

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 …

Turn And Orientation Sensitive A* For Autonomous Vehicles In Intelligent Material Handling Systems, Rashmi Ballamajalu

Theses

Autonomous mobile robots are taking on more tasks in warehouses, speeding up operations and reducing accidents that claim many lives each year. This work proposes a dynamic path planning algorithm, based on A* search method for large autonomous mobile robots such as forklifts, and generates an optimized, time-efficient path. Simulation results of the proposed turn and orientation sensitive A* algorithm show that it has a 94% success rate of computing a better or similar path compared to that of default A*. The generated paths are smoother, have fewer turns, resulting in faster execution of tasks. The method also robustly handles …

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. …

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 …

Aggregation As An Efficiency Driver In Bulk Heterojunction Devices Measured Through Mixed Squaraines In Ternary Blends, Soumya Gupta

Theses

While OPV offers great promise as a low-cost renewable energy source, the relatively low efficiency still challenges its commercialization potential. SQ dyes offer significant potential as a light-absorbing layer in OPV because of their high extinction coefficient, broad spectral absorption, and ease of tuning the chemical structure and packing motif. Devices incorporating SQ dyes, however, have shown low PCE. In this preliminary work, we seek to explore the relationship between low power conversion efficiency (PCE) of Squaraine (SQ) related Organic Photovoltaics (OPV) systems and the formation of aggregates with the help of mixed SQs in ternary blends. Four aniline based …

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 …

Probability Of Naturalism And Metanormative Realism, Curtis Howd

Theses

Darwin’s Theory of Evolution can be mobilized to provide epistemological challenges to metanormative realism. It is argued that, since natural selection selects for behaviors adequate for survival and fecundity, our psychologies must be shaped by this same process. A-type challenges point to the improbability of the vast number of true normative beliefs given that they evolved to track survival and fecundity, not truth. B-type debunking arguments point to the improbability of the hypothesis that evolution would track truth given that there are a multitude of defeaters for this hypothesis. I will argue that both a-type and b-type arguments fail to …

Attitude Control For Circumnavigating The Sun With Diffractive Solar Sails, Amber Dubill

Theses

A solar sail making use of the physics of diffracted light enables the transfer of optical to mechanical momentum for in-space propulsion. In this thesis we describe advantages of diffractive solar sailing for trajectory and attitude control. In particular, a high inclination angle heliophysics mission is examined. A simple roll maneuver of a diffractive sail is described to attain an inclination angle of 60º. A comparison of idealized diffractive and reflective sails for a five-year solar polar orbiter mission, showing higher inclination angles and a smaller orbital radius for the former is performed. As a result, a constellation of diffractive …

Automated Brain Segmentation Methods For Clinical Quality Mri And Ct Images, Viraj Reddy Adduru

Theses

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder associated with brain tissue loss. Accurate estimation of this loss is critical for the diagnosis, prognosis, and tracking the progression of AD. Structural magnetic resonance imaging (sMRI) and X-ray computed tomography (CT) are widely used imaging modalities that help to in vivo map brain tissue distributions. As manual image segmentations are tedious and time-consuming, automated segmentation methods are increasingly applied to head MRI and head CT images to estimate brain tissue volumes. However, existing automated methods can be applied only to images that have high spatial resolution and their accuracy on heterogeneous …

Deep Convolutional Networks Without Learning The Classifier Layer, Zhongchao Qian

Theses

Deep convolutional neural networks (CNNs) are effective and popularly used in a wide variety of computer vision tasks, especially in image classification. Conventionally, they consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to produce the final output in image classification tasks. This design descends from traditional image classification machine learning models which use engineered feature extractors followed by a classifier, before the widespread application of deep CNNs. While this has been successful, in models trained for classifying datasets with a large number of categories, the fully connected layers often account …

Deepmind’S Protein Folding Quality Process Analysis, Amro Oussama Noueihed

Theses

Proteins are the building blocks of life and are responsible for the vast majority of our cellular activity. For decades, the major method of producing acceptable protein structures was laboratory testing. Scientists have been perplexed by how the components of a protein, which are made up of a string of different amino acids, come together to produce a complex twisting and folding pattern. Following that, scientists started developing computer algorithms for predicting protein structure from amino acid sequence. To test the anticipated structural accuracy, data from multiple prediction models were compared with CASP entries in this research. Later, the experiment …

Comparison Of Statistical Models For Imputation Of Missing Data In Clinical Trials, Vaishnavi Purandare

Theses

Missing data is an integral part of clinical trials and its analysis. This study discusses the downsides of having missing values in clinical data, traditional methods used to resolve this issue and some techniques which can be implemented to remedy the same.

The data used for the study is simulated from Theophylline data from Pinheiro and Bates (1995). The simulated data measures the Theophylline drug concentration in the body of 10 Subjects over 24 hours. There are three cases considered with increasing number of randomly created missing values for the Concentration variable. Subsets are created to fit linear and quadratic …

Crafting Adversarial Examples Using Particle Swarm Optimization, Rayan Mosli

Theses

Machine learning models have been found to be vulnerable to adversarial attacks that apply small perturbations to input samples to get them misclassified. Attacks that search for and apply the perturbations are performed in both white-box and black-box settings, depending on the information available to the attacker about the target. For black-box attacks, the attacker can only query the target with specially crafted inputs and observing the outputs returned by the model. These outputs are used to guide the perturbations and create adversarial examples that are then misclassified.

Current black-box attacks on API-based malware classifiers rely solely on feature insertion …

Kaizen Programming With Enhanced Feature Discovery: An Automated Approach To Feature Selection And Feature Discovery For Prediction Models, John Stelmack

Theses

Feature selection (FS) is the process of finding an ideal set of features for a prediction model from a set of candidate features. A key step in designing a prediction model is reducing the size of the input feature set while increasing its usefulness. This reduces the complexity of a model, making the model run more quickly while allowing one to explain the usefulness of each individual feature more easily. Despite the desire to determine an ideal feature set, the process of FS can be time consuming and yield mixed results. FS is often partially automated with the use of …

Reducing Global Demand On Conflict Minerals In Consumer Electronics And Lithium-Ion Batteries, Mosunmola Odulate

Theses

Advances in technology have led to increasing demand for more sophisticated electronic products, which, in turn, induces demand for raw materials essential for product performance. A class of such materials is mined in places in the world that are politically unstable – they are called Conflict Minerals (CMs) because profits from their mining and trade support human rights violations in their places of origin. They include Tantalum, Tin, Tungsten, and Gold (3TG). To reduce global reliance on 3TG, government policies from local and international communities are the only works in place, but what is still unclear is their efficacy towards …

Detecting Malicious Websites Using Machine Learning, Saeed Ahmad Al Tamimi

Theses

The growing use of the internet resulted in emerging of new websites every day (Total number of Websites - Internet Live Stats, 2020). Web surfing has become important for everyone regardless of their occupation, age or location. However, as the use of the internet is increasing so is the vulnerability to malware attacks through malicious websites (Softpedia, 2016). Identifying and dealing with such malicious website has been quite difficult in the past as it is quite challenging to separate good websites from bad websites. However, by using machine learning algorithms on large datasets it is now possible to detect such …

For The Sensing Of Viral Dna: An Integrated Polydimethylsiloxane Accurate Crispr Detection (Impact) System, Kenneth N. Hass

Theses

Infectious disease outbreaks have become more frequent and extreme in recent years, and as populations continue to grow and the world becomes more interconnected, they show no signs of stopping. The current COVID-19 pandemic affecting the world and grinding economies to a halt was known about months ago but could not be contained. One of the largest issues facing the containment of infectious disease is a lack of real-time, point-of-care detection devices which can accurately and effectively identify those who are infected so they can be treated and quarantined. Here, an Integrated Micropillar Polydimethylsiloxane Accurate CRISPR Detection (IMPACT) system is …

Design And Simulation Analysis Of Deep Learning Based Approaches And Multi-Attribute Algorithms For Warehouse Task Selection, Prashant Sankaran

Theses

With the growth and adoption of global supply chains and internet technologies, warehouse operations have become more demanding. Particularly, the number of orders being processed over a given time frame is drastically increasing, leading to more work content. This makes operational tasks, such as material retrieval and storage, done manually more inefficient. To improve system-level warehouse efficiency, collaborating Autonomous Vehicles (AVs) are needed. Several design challenges encompass an AV, some critical aspects are navigation, path planning, obstacle avoidance, task selection decisions, communication, and control systems. The current study addresses the warehouse task selection problem given a dynamic pending task list …

Effects Of Heterogeneity, Technological Progress And Interaction On Carbon Mitigation Costs, Saptarshi Das

Theses

As many societal needs compete with sustainability for a finite pool of public resources, understanding the cost of mitigating greenhouse gas emissions has become a critical sustainability question. The Marginal Abatement Cost Curve (MACC) is a widely used approach to characterize mitigation costs. It is constructed by ordering technological and other interventions to mitigating an emission from lowest to highest cost, indicating the cumulative mitigation possible for each intervention. It is clearly a simplification of a complex techno-economic system and has been criticized for neglecting factors such as dynamics, consumer behavior, non-cost barriers to adoption, and interactions between technologies. However, …

Visualization & Automation Of Shams Dubai Report, Noora Ibrahim Alblooshi

Theses

Dubai’s Smart Grid strategy includes the implementation of Distributed Energy Resources and Distribution Automation (DA) facilities to continuous monitoring and remote control from DEWA’s Distribution Control Center (DCC) , and, in some cases, automatic control of electric distribution assets operated at 33kV or lower. The increase level of telemetry and automation in the field imposes a greater challenge in monitoring and live data visualization for establishing a decision support system that empowers distribution system operators and enables optimal control of existing and planned assets. This challenge can be overcome through introducing data science tools in the sector of energy. Through …

Applying Systems Pharmacology To The Treatment Of Chronic Illness Using Novel Scoring And Translational Methods, Spencer Richman

Theses

Chronic illnesses are poorly understood diseases that are often highly resistant to treatment. The prevalence and severity of these illnesses necessitates new methods for treatment development that diverge from the paradigm of one drug, one illness. Instead, multidrug interventions that utilize repurposable, previously approved drugs could be far more advantageous. In order to support this, a novel scoring framework and accompanying set of tools, collectively termed DrugAble, have been developed. DrugAble scores proposed, model-based treatment target solutions by analyzing drug-target interaction data and addressing the network complexity of these solutions. Actionability scores that summarize the likelihood of a proposed target …

Data Representation For Motor Imagery Classification, Andrew Festa

Theses

While much progress has been made towards the advancement of brain-controlled interfaces (BCI), there remains an information gap between the various domains involved in progressing this area of research. Thus, this research seeks to address this gap through creation of a method of representing brainwave signals in a manner that is intuitive and easy to interpret for both neuroscientists and computer scientists. This method of data representation was evaluated on the ability of the model to accurately classify motor imagery events in a timely manner.

The proposed data representation of electroencephalographic signals in the form of signal images was found …

Efficient Algorithms For Unrelated Parallel Machine Scheduling Considering Time Of Use Pricing And Demand Charges, Brady Collea

Theses

There is an ever-increasing focus on sustainability and energy consumption worldwide. Manufacturing is one of the major areas where energy reduction is not only environmentally beneficial, but also incredibly financially beneficial. These industrial consumers pay for their electricity according to prices that fluctuate throughout the day. These price fluctuations are in place to shift consumption away from “peak” times, when electricity is in the highest demand. In addition to this consumption cost, industrial consumers are charged according to their highest level of demand in a given window of time in the form of demand charges. This paper presents multiple solution …

Impact Analysis Of Electric Vehicle Demand On Demand Profile, Electricity Charges And System Emissions Of Rochester Institute Of Technology, Akshata Shanbhag

Theses

In view of growing concerns of greenhouse gas emissions, electrification in the transportation fleet is expected to increase globally. To accommodate the incoming increase in energy demand from vehicle charging, the existing electrical network should be managed in a way that the load is operated with no electrical instability. Peak demand occurrences which could be measured daily, annually, weekly, monthly or annually should be avoided in order to maintain the health of the electrical network and reduce demand charges billed to the end energy user. Moreover, depending on the emissions factor of the fuel mix used in a region for …

Randomizable Phenology-Dependent Corn Canopy For Simulated Remote Sensing Of Agricultural Scenes, M Grady Saunders

Theses

Crop health assessment and yield prediction from multi-spectral remote sensing imagery are ongoing areas of interest in precision agriculture. It is in these contexts that simulation-based techniques are useful to investigate system parameters, perform preliminary experiments, etc., because remote sensing systems can be prohibitively expensive to design, deploy, and operate. However, such techniques require realistic and reliable models of the real world. We thus present a randomizable time-dependent model of corn (Zea mays L.) canopy, which is suitable for procedural generation of high-fidelity virtual corn fields at any time in the vegetative growth phase, with application to simulated remote sensing …

Representations And Representation Learning For Image Aesthetics Prediction And Image Enhancement, Michal Kucer

Theses

With the continual improvement in cell phone cameras and improvements in the connectivity of mobile devices, we have seen an exponential increase in the images that are captured, stored and shared on social media. For example, as of July 1st 2017 Instagram had over 715 million registered users which had posted just shy of 35 billion images. This represented approximately seven and nine-fold increase in the number of users and photos present on Instagram since 2012. Whether the images are stored on personal computers or reside on social networks (e.g. Instagram, Flickr), the sheer number of images calls for methods …

Exploring Students Mental Behaviors Using Unsupervised Learning Algorithms And Graph Theory, Abdullah Hussein Mohsen

Theses

With the high amount of mentally seeking behaviors among students nationwide according to Healthy minds network survey (2019) and lack of related studies to students mental health in the Gulf region, a gap is created Fatima Al-Darmaki et al. (2015) this project is executed to fill the gap by utilizing data analytics techniques to generate insights that can be used to support future decisions. Students who suffer from mental disorders are most likely to disengage from university which can be translated into a dropout. Many organizations are conducting periodically to capture as many insights to tackle those behaviors. This project …