Digital Commons Network^™

Application Of Machine Learning Techniques To Forecast Harmful Algal Blooms In Gulf Of Mexico, Bala Tripura Sundari Yerrapothu

Master's Theses

The Harmful Algal Blooms (HABs) forecast is crucial for the mitigation of health hazards and to inform actions for the protection of ecosystems and fisheries in the Gulf of Mexico (GoM). For the sake of simplicity of our application we assume ocean color satellite imagery from the National Oceanic and Atmospheric Administration as a proxy for HABs.

In this study we use a deep neural network trained on the 2-Dimensional time series proxy data to provide a forecast of the HABs’ manifestations in the GoM.Our approach analyzes between both spatial and temporal features simultaneously. In addition, the network also helps …

Neural Network For Monitoring Infant Feeding Process In The Smartbottle Device, Jiajun Guan

Master's Theses

To research the relationship between Childhood obesity and infant feeding patterns, the Electrical Engineering Department at California Polytechnic State University has designed a SmartBottle device attaching to the bottom of a baby bottle to monitor the infant feeding process. This project mainly focuses on the software and firmware design, as well as the neural network design of the SmartBottle device. The SmartBottle device is designed to identify infant feeding activities and to record related data for overweight and obesity research on children. This device includes a 6-dimensional inertial sensor that contains a 3-axis digital accelerometer and a 3-axis digital gyroscope. …

Structural Re-Orientation Of Magmatic Fabrics And Layering In The Lower Oceanic Crust: Hole Gt1, Wadi Tayin Massif, Samail Ophiolite, Justin Guillot

Master's Theses

This thesis aims to re-orient borehole images of layered gabbros sampled beneath Hole GT1 in the Wadi Tayin massif of the Oman ophiolite by the Oman Drilling Project to better constrain models of crustal accretion. The gabbro glacier model proposes that crystallized basalt flows down and away from the crystallization site to form the lower crust while the sheeted sill model proposes that basaltic melt crystallizes at multiple levels in the crust through sills. Hole GT1 provides an unprecedented 400 m, 100% recovery, look at the lower oceanic crust. Cores lose their geographic orientation when drilled, requiring use of the …

A Deep Learning-Based Automatic Object Detection Method For Autonomous Driving Ships, Ojonoka Erika Atawodi

Master's Theses

An important feature of an Autonomous Surface Vehicles (ASV) is its capability of automatic object detection to avoid collisions, obstacles and navigate on their own.

Deep learning has made some significant headway in solving fundamental challenges associated with object detection and computer vision. With tremendous demand and advancement in the technologies associated with ASVs, a growing interest in applying deep learning techniques in handling challenges pertaining to autonomous ship driving has substantially increased over the years.

In this thesis, we study, design, and implement an object recognition framework that detects and recognizes objects found in the sea. We first curated …

Design Of An Ultra-Wideband Frequency-Modulated Continuous Wave Short Range Radar System For Extending Independent Living, Toai-Chi Nguyen

Master's Theses

Falls in the disabled and elderly people have been a cause of concern as they can be immobilized by the fall and have no way to contact others and seek assistance. The proposed frequency modulated continuous wave (FMCW) short range radar (SRR) system, which uses ultra-wideband (UWB) signals can provide immediate assistance by monitoring and detecting fall events. The unique characteristics of this system allow for a frequency-based modulation system to carry out triangulation and sense the location of the fall through the usage of a continuous chirp signal that linearly sweeps frequency. This project focuses on the development, design …

Physics Engine On The Gpu With Opengl Compute Shaders, Quan Huy Minh Bui

Master's Theses

Any kind of graphics simulation can be thought of like a fancy flipbook. This notion is, of course, nothing new. For instance, in a game, the central computing unit (CPU) needs to process frame by frame, figuring out what is happening, and then finally issues draw calls to the graphics processing unit (GPU) to render the frame and display it onto the monitor. Traditionally, the CPU has to process a lot of things: from the creation of the window environment for the processed frames to be displayed, handling game logic, processing artificial intelligence (AI) for non-player characters (NPC), to the …

Natural And Experimental Noise Affects Acoustic Communication In Songbirds, Veronica Arlene Reed

Master's Theses

Background noise is ubiquitous and can impair acoustic communication and influence signaling behavior in animals. Despite evidence demonstrating myriad effects of anthropogenic noise on animal communication, precisely how natural background noise influences communication and behavior remains unclear. Yet, natural sources of background noise, such as rushing rivers or crashing ocean surf, share similar power spectra to sources of anthropogenic noise and can occur at high amplitudes, potentially masking acoustic signals.

To investigate the effects of water-generated noise on songbird behavior, we experimentally broadcast landscape-level playbacks of ocean surf and river noise in coastal California, USA, and riparian habitat in Idaho, …

Associations Between Parenting Stress, Feeding Practices, And Child Eating Behaviors During The Covid-19 Pandemic, Maria G. Gonzalez

Master's Theses

The COVID-19 pandemic provides an important opportunity to understand how parenting stress during social crisis may predict child feeding practices and perceptions of child mealtime behaviors. The objective of the present study was to explore whether parents’ perceived increases in and overall levels of parenting stress during the pandemic were associated with controlling feeding practices and perceptions of child eating behaviors. Parents (n = 284) of 4–6-year-old children completed a cross-sectional online survey between March and April 2020. The survey assessed parents’ perceived change in parenting stress during the onset of the pandemic and levels of parenting stress during …

Gpu High-Performance Framework For Pic-Like Simulation Methods Using The Vulkan® Explicit Api, Kolton Jacob Yager

Master's Theses

Within computational continuum mechanics there exists a large category of simulation methods which operate by tracking Lagrangian particles over an Eulerian background grid. These Lagrangian/Eulerian hybrid methods, descendants of the Particle-In-Cell method (PIC), have proven highly effective at simulating a broad range of materials and mechanics including fluids, solids, granular materials, and plasma. These methods remain an area of active research after several decades, and their applications can be found across scientific, engineering, and entertainment disciplines.

This thesis presents a GPU driven PIC-like simulation framework created using the Vulkan® API. Vulkan is a cross-platform and open-standard explicit API for graphics …

Comparing Radiation Shielding Potential Of Liquid Propellants To Water For Application In Space, John Czaplewski

Master's Theses

The radiation environment in space is a threat that engineers and astronauts need to mitigate as exploration into the solar system expands. Passive shielding involves placing as much material between critical components and the radiation environment as possible. However, with mass and size budgets, it is important to select efficient materials to provide shielding. Currently, NASA and other space agencies plan on using water as a shield against radiation since it is already necessary for human missions. Water has been tested thoroughly and has been proven to be effective. Liquid propellants are needed for every mission and also share similar …

Node Classification On Relational Graphs Using Deep-Rgcns, Nagasai Chandra

Master's Theses

Knowledge Graphs are fascinating concepts in machine learning as they can hold usefully structured information in the form of entities and their relations. Despite the valuable applications of such graphs, most knowledge bases remain incomplete. This missing information harms downstream applications such as information retrieval and opens a window for research in statistical relational learning tasks such as node classification and link prediction. This work proposes a deep learning framework based on existing relational convolutional (R-GCN) layers to learn on highly multi-relational data characteristic of realistic knowledge graphs for node property classification tasks. We propose a deep and improved variant, …

A Method For Visualizing The Structural Complexity Of Organizational Architectures, Jacob Michael B. King

Master's Theses

To achieve a high level of performance and efficiency, contemporary aerospace systems must become increasingly complex. While complexity management traditionally focuses on a product’s components and their interconnectedness, organizational representation in complexity analysis is just as essential. This thesis addresses this organizational aspect of complexity through an Organizational Complexity Metric (OCM) to aid complexity management. The OCM augments Sinha’s structural complexity metric for product architectures into a metric that can be applied to organizations. Utilizing nested numerical design structure matrices (DSMs), a compact visual representation of organizational complexity was developed. Within the nested numerical DSM are existing organizational datasets used …

Development Of An Infrared Thermography System To Measure Boundary Layer Transition In A Low Speed Wind Tunnel Testing Environment, Damien Horton

Master's Theses

The use of infrared thermography for boundary layer detection was evaluated for use in the Cal Poly Low Speed Wind Tunnel (LSWT) and recommendations for the successful use of this technique were developed. In cooperation with Joby Aviation, an infinite wing model was designed, manufactured and tested for use in the LSWT. The wing was designed around a custom airfoil profile specific for this project, where the nearly-flat pressure gradient at a zero pitch angle would delay the chordwise onset of boundary layer transition. Steady-state, RANS numerical simulations predicted the onset of transition to occur at 0.75 x/c for the …

Computational Bone Mechanics Modeling With Frequency Dependent Rheological Properties And Crosslinking, Timothy G. Moreno

Master's Theses

Bone is a largely bipartite viscoelastic composite. Its mechanical behavior is determined by strain rate and the relative proportions of its principal constituent elements, hydroxyapatite and collagen, but is also largely dictated by their geometry and topology. Collagen fibrils include many segments of tropocollagen in staggered, parallel sequences. The physical staggering of this tropocollagen allows for gaps known as hole-zones, which serve as nucleation points for apatite mineral. The distance between adjacent repeat units of tropocollagen is known as D-Spacing and can be measured by Atomic Force Microscopy (AFM). This D-Spacing can vary in length slightly within a bundle, but …

Biological Semantic Segmentation On Ct Medical Images For Kidney Tumor Detection Using Nnu-Net Framework, Andres Bergsneider

Master's Theses

Healthcare systems are constantly challenged with bottlenecks due to human-reliant operations, such as analyzing medical images. High precision and repeatability is necessary when performing a diagnostics on patients with tumors. Throughout the years an increasing number of advancements have been made using various machine learning algorithms for the detection of tumors helping to fast track diagnosis and treatment decisions. “Black Box” systems such as the complex deep learning networks discussed in this paper rely heavily on hyperparameter optimization in order to obtain the most ideal performance. This requires a significant time investment in the tuning of such networks to acquire …

Clustering Web Users By Mouse Movement To Detect Bots And Botnet Attacks, Justin L. Morgan

Master's Theses

The need for website administrators to efficiently and accurately detect the presence of web bots has shown to be a challenging problem. As the sophistication of modern web bots increases, specifically their ability to more closely mimic the behavior of humans, web bot detection schemes are more quickly becoming obsolete by failing to maintain effectiveness. Though machine learning-based detection schemes have been a successful approach to recent implementations, web bots are able to apply similar machine learning tactics to mimic human users, thus bypassing such detection schemes. This work seeks to address the issue of machine learning based bots bypassing …

Characteristics And Management Implications Of Mollic Soils In Forest Versus Grassland Settings In Central California, Brian Charles Clark

Master's Theses

Efforts to sequester soil carbon (C) should consider soils intrinsically capable at C retention. Of the mineral soil orders, Mollisols have minimum requirements for soil organic C (SOC; over 0.06 %) and basic saturation (over 50 %). In the U.S., grasslands comprise 93% of the vegetation mapped above Mollisols. Soils beneath the southern extent of Sequoia sempervirens (redwood) forests in central California are mapped as Molliols. It widely accepted that redwood forests harbor considerable biomass C, but the extent to which aboveground C is retained in the soil is not well understood. This study aimed to: (i) to gather baseline …

The Response Of Marine Synechococcus To A Landscape Of Environmental Stressors: A Proteomic Exploration, Dana E. Michels

Master's Theses

In the field of marine microbial ecology, many questions remain unanswered with regards to the physiological trade-offs made by phytoplankton to maximize growth (e.g., nutrient acquisition) and minimize loss (e.g., predation defenses). These tradeoffs, which occur at the cellular level, have wide reaching impacts on food web dynamics and global biogeochemical cycles. In the first chapter, we explored the use of a non-canonical amino acid (NCAA) technique, bioorthogonal non-canonical amino-acid tagging (BONCAT), in phytoplankton model systems. This technique has potential to work well in natural systems by enabling isolation of only newly synthesized proteins during an incubation period with the …

The Effect Of Focused Ultrasound On Altering The Diameter Class Of Nerve Fibers Contributing To A Compound Evoked Potential, Analyzed Using A Perturbative Decomposition Technique., Megan Wurden

Master's Theses

Peripheral neuropathies are disorders that involve the damage of peripheral nerve fibers, affecting the ability of different parts of the body to communicate. A differentiating factor in diagnosis between various clinical conditions can be which size class of nerve fibers are affected. A nerve conduction velocity test can be used to assess the viability of the nerve but is a single-parameter test and gives no information about the population characteristics of the remaining active fibers. A method developed and previously reported by Szlavik (2016) utilizes a mathematical perturbed decomposition to determine the normalized frequency of each size class of fiber …

Towards A Complete Formal Semantics Of Rust, Alexa White

Master's Theses

Rust is a relatively new programming language with a unique memory model designed to provide the ease of use of a high-level language as well as the power and control of a low-level language while preserving memory safety. In order to prove the safety and correctness of Rust and to provide analysis tools for its use cases, it is necessary to construct a formal semantics of the language. Existing efforts to construct such a semantic model are limited in their scope and none to date have successfully captured the complete functionality of the language. This thesis focuses on the K-Rust …

Brain Tumor Detection And Classification From Mri Images, Anjaneya Teja Sarma Kalvakolanu

Master's Theses

A brain tumor is detected and classified by biopsy that is conducted after the brain surgery. Advancement in technology and machine learning techniques could help radiologists in the diagnosis of tumors without any invasive measures. We utilized a deep learning-based approach to detect and classify the tumor into Meningioma, Glioma, Pituitary tumors. We used registration and segmentation-based skull stripping mechanism to remove the skull from the MRI images and the grab cut method to verify whether the skull stripped MRI masks retained the features of the tumor for accurate classification. In this research, we proposed a transfer learning based approach …

Development Of Novel Hardware And Software For Wind Turbine Condition Monitoring, Ryan A. Zhan

Master's Theses

With the increased use of wind turbines as sources of energy, maintenance of these devices becomes more and more important. Utility scale wind turbines can be time consuming and expensive to repair so an intelligent method of monitoring these devices is important. Commercial solutions for condition monitoring exist but are expensive and can be difficult to implement. In this project a novel condition monitoring system is developed. The priority of this system, dubbed the LifeLine, is to provide reliable condition monitoring through an easy-to-install and low-cost system. This system utilizes a microcontroller to collect acceleration data to detect imbalances on …

A Single-Stage Passive Vibration Isolation System For Scanning Tunneling Microscopy, Toan T. Le

Master's Theses

Scanning Tunneling Microscopy (STM) uses quantum tunneling effect to study the surfaces of materials on an atomic scale. Since the probe of the microscope is on the order of nanometers away from the surface, the device is prone to noises due to vibrations from the surroundings. To minimize the random noises and floor vibrations, passive vibration isolation is a commonly used technique due to its low cost and simpler design compared to active vibration isolation, especially when the entire vibration isolation system (VIS) stays inside an Ultra High Vacuum (UHV) environment. This research aims to analyze and build a single-stage …

Of The Wide-Eyed In Uncertain Times: The Education Of Girls During The Third Reich, Ingmar D. Clausing

Master's Theses

The aim of this thesis is to describe how both the state school system and the Hitler Youth educated girls during the Third Reich. Conventional theories have suggested a number of ideological suppositions regarding the overall curricular emphasis, but this study contends that such simplistic determinations do not capture the full spread of the educational experience. This thesis asks if girls in Nazi Germany were truly just indoctrinated or if schooling had legitimate academic purposes. Based on actual textbooks that were studied by girls for every subject area, at different grade levels, and in different types of schools, as well …

Exposing The Effects Of Reaction Cavity In Solid-Phase Reaction Kinetics, Michael Carr

Master's Theses

Reactivity of molecular solids is governed by topochemical considerations, where minimizedmolecular movement dictates both product identity and kinetics. This Thesis explores the central role reaction cavity plays in the topochemical principle by using the highly varied cavities formed by the different facets of a tetracene crystal. The relative rates for ten different reaction cavities were measured via energy dispersive X-ray spectroscopy for the reaction of tetracene with vapors of maleic anhydride. Variance in cavities resulted in Diels-Alder reaction rates that differed by as much as a factor of 2.6. Effects were understood via molecular dynamic simulations which modeled the approach …

An Efficient Design Methodology For Complex Sequential Asynchronous Digital Circuits, Tomasz Chadzynski

Master's Theses

Asynchronous digital logic as a design alternative offers a smaller circuit area and lower power consumption but suffers from increased complexity and difficulties related to logic hazards and elements synchronization. The presented work proposes a design methodology based on the speed-independent sequential logic theory, oriented toward asynchronous hardware implementation of complex multi-step algorithms. Targeting controller-centric devices that perform data-driven non-linear execution, the methodology offers a CSP language-based controller workflow description approach and the specification of a project implementation template supported by a two-stage design process. First, the CSP layer describes complex speed-independent controller behavior offering better scalability and maintainability than …

Influence Of Social Circles On User Recommendations, Chaitanya Krishna Kasaraneni

Master's Theses

Recommender systems are powerful tools that filter and recommend content relevant to a user. One of the most popular techniques used in recommender systems is collaborative filtering. Collaborative filtering has been successfully incorporated in many applications. However, these recommendation systems require a minimum number of users, items, and ratings in order to provide effective recommendations. This results in the infamous cold start problem where the system is not able to produce effective recommendations for new users. In recent times, with escalation in the popularity and usage of social networks, people tend to share their experiences in the form of reviews …

Transfer Learning For Hyperspectral Images Utilizing Channel Selection Techniques And Ensemble Methods, Scott Daniel Vogel

Master's Theses

Hyperspectral images contain information from a wider range of the electromagnetic spectrum than natural images which gives them potential for better classification ability. However, hyperspectral datasets are typically small due to the expensive equipment needed to obtain the images, which can limit classification performance. One solution to this problem is transfer learning, in which a model trained on one dataset is reused for a separate dataset. Research has shown that transfer learning between hyperspectral datasets can give improved performance over models without transfer learning when training data are limited. Since extra hyperspectral data are not always available, the solution proposed …

Lstm-Enabled Level Curve Tracking In Scalar Fields Using Multiple Mobile Robots, Kunj J. Parikh

Master's Theses

Autonomous mobile sensor networks are ideal candidates for exploring large-scaleunknown fields with tasks ranging from source seeking, level curve tracking, mapping an unknown field, and many more. In this work, we investigate the problem of level curve tracking in unknown scalar fields using a limited number of mobile sensors. The level curve tracking problem has been studied in many applications such as monitoring the propagation of fire boundaries and the algae blooms. We design and implement a long short term memory (LSTM) enabled control strategy for a mobile sensor network to detect and track the desired level curve. We develop …

Deep Reinforcement Learning Based Path-Planning For Multi-Agent Systems In Advection-Diffusion Field Reconstruction Tasks, Deepak Talwar

Master's Theses

Many environmental processes can be represented mathematically using spatial-temporal varying partial-differential equations. Timely estimation and prediction of processes such as wildfires is critical for disaster management response, but is difficult to accomplish without the availability of a dense network of stationary sensors. In this work, we propose a deep reinforcement learning-based real-time path-planning algorithm for mobile sensor networks traveling in a formation through a spatial-temporal varying advection-diffusion field for the task of field reconstruction. A deep Q-network (DQN) agent is trained on simulated advection-diffusion fields to direct the mobile sensor network to travel along information-rich trajectories. The field measurements made …