Digital Commons Network^™

Robot Navigation In Cluttered Environments With Deep Reinforcement Learning, Ryan Weideman

Master's Theses

The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. The system is designed such that a real robot could be placed in an unmapped, cluttered environment and be able to navigate in a desired direction with no prior knowledge. Deep Q-learning, coupled with the innovations of double Q-learning and dueling Q-networks, is applied. Two modifications of this architecture are presented to incorporate direction heading information that …

Viewpoint Optimization For Autonomous Strawberry Harvesting With Deep Reinforcement Learning, Jonathon J. Sather

Master's Theses

Autonomous harvesting may provide a viable solution to mounting labor pressures in the United States' strawberry industry. However, due to bottlenecks in machine perception and economic viability, a profitable and commercially adopted strawberry harvesting system remains elusive. In this research, we explore the feasibility of using deep reinforcement learning to overcome these bottlenecks and develop a practical algorithm to address the sub-objective of viewpoint optimization, or the development of a control policy to direct a camera to favorable vantage points for autonomous harvesting. We evaluate the algorithm's performance in a custom, open-source simulated environment and observe affirmative results. Our trained …

Evaluating Projections And Developing Projection Models For Daily Fantasy Basketball, Eric C. Evangelista

Master's Theses

Daily fantasy sports (DFS) has grown in popularity with millions of participants throughout the world. However, studies have shown that most profits from DFS contests are won by only a small percentage of players. This thesis addresses the challenges faced by DFS participants by evaluating sources that provide player projections for NBA DFS contests and by developing machine learning models that produce competitive player projections.

External sources are evaluated by constructing daily lineups based on the projections offered and evaluating those lineups in the context of all potential lineups, as well as those submitted by participants in competitive FanDuel DFS …

A Case Study Examining The Structure Of The Event Process At California Polytechnic State University, Ryan R. Baker

Master's Theses

The purpose of this study was to examine the structure of the event process on Cal Poly’s campus. An intrinsic case study method was used, and data were collected and analyzed using triangulation from three sources of information: documents, interviews, and participation research. Overall, the structure of the event management process on campus was found to be stable, but could use improvement. Cal Poly should consider establishing a specific, designated organization that would help centralize the event management process at Cal Poly. This organization could be in charge of training and updating event managers, approving events, monitoring volume of events …

Carbonate Chemistry Characterization In A Low-Inflow Estuary With Recent Seagrass Loss, Jolie Higgins

Master's Theses

Estuaries are dynamic environments that are strongly affected by natural variability, as well as direct and indirect anthropogenic impacts. A better understanding of the drivers of carbon fluxes and biogeochemical variability in estuarine systems is needed, particularly with the increasing threat of ocean acidification. Morro Bay in Central California is a small nationally protected estuary, with seasonally low freshwater inputs. Since 2007, the bay has experienced a significant loss of native seagrass, Zostera marina, which is an important component of the marine ecosystem. Because seagrass photosynthesis decreases carbon dioxide and increases oxygen in the water column, the loss of seagrass …

A Predictive Modeling Approach For Assessing Seismic Soil Liquefaction Potential Using Cpt Data, Jonathan Paul Schmidt

Master's Theses

Soil liquefaction, or loss of strength due to excess pore water pressures generated during dynamic loading, is a main cause of damage during earthquakes. When a soil liquefies (referred to as triggering), it may lose its ability to support overlying structures, deform vertically or laterally, or cause buoyant uplift of buried utilities. Empirical liquefaction models, used to predict liquefaction potential based upon in-situ soil index property measurements and anticipated level of seismic loading, are the standard of practice for assessing liquefaction triggering. However, many current models do not incorporate predictor variable uncertainty or do so in a limited fashion. Additionally, …

Designing A Simulator For An Electrically-Pumped Organic Laser Diode, Robert Hulbert

Master's Theses

Organic semiconductors provide an alternative set of basis materials to fabricate electronic devices like PN Junctions, LEDs, and FETs. These materials have several benefits over traditional inorganic semiconductors including their mechanical flexibility, reliance on renewable resources, and inexpensive large-scale manufacturability. Despite the contemporary device implementations with organic semiconductors, a solid-state electrically-pumped organic laser diode does not exist. However, organically-based lasers do exist by utilizing the organic material strictly for optical gain. The challenge occurs when charge carriers appear in the organic material. The charge carriers must reach a concentration such that population inversion occurs producing optical gain. However, between the …

A Homegrown Dsmc-Pic Model For Electric Propulsion, Dominic Charles Lunde

Master's Theses

Powering spacecraft with electric propulsion is becoming more common, especially in CubeSat-class satellites. On account of the risk of spacecraft interactions, it is important to have robust analysis and modeling tools of electric propulsion engines, particularly of the plasma plume. The Navier-Stokes equations used in classic continuum computational fluid dynamics do not apply to the rarefied plasma, and therefore another method must be used to model the flow. A good solution is to use the DSMC method, which uses a combination of particle modeling and statistical methods for modeling the simulated molecules. A DSMC simulation known as SINATRA has been …

A 3-Dimensional In Silico Test Bed For Radiofrequency Ablation Catheter Design Evaluation And Optimization, Carolyn Teng

Master's Theses

Atrial fibrillation (AF) is the disordered activation of the atrial myocardium, which is a major cause of stroke. Currently, the most effective, minimally traumatic treatment for AF is percutaneous catheter ablation to isolate arrhythmogenic areas from the rest of the atrium. The standard in vitro evaluation of ablation catheters through lesion studies is a resource intensive effort due to tissue variability and visual measurement methods, necessitating large sample sizes and multiple prototype builds. A computational test bed for ablation catheter evaluation was built in SolidWorks® using the morphology and dimensions of the left atrium adjacent structures. From this geometry, the …

Observations Of The Copenhagen Networks Study, Michael A. Cantrell

Master's Theses

Attribute-rich longitudinal datasets of any kind are extremely rare. In 2012 and 2013, the SensibleDTU project created such a dataset using approximately 1,000 university students. Since then, a large number of studies have been performed using this dataset to ask various questions about social dynamics. This thesis delves into this dataset in an effort to explore previously unanswered questions. First, we define and identify social encounters in order to ask questions about face-to-face interaction networks. Next, we isolate students who send and receive disproportionately high numbers of phone calls and text messages to see how these groups compare to the …

Dynamic Response Validation Of Cubesats Through Testing And Finite Element Analysis, Peter Rivera

Master's Theses

During a rocket launch, satellites withstand large dynamic forces due to vibrations that are transmitted from the launch vehicle. As such, they must undergo testing to ensure that their function is not impaired by such forces. CubeSats are cost-effective nanosatellites, and like their larger counterparts, undergo dynamic testing for launch qualification. While dynamic analysis can done on a CubeSat alone, other assembly constituents also affect the response, and including them in the analysis can provide insight on the true dynamic behavior of CubeSats. To show this, the work presented here recreates a vibration test setup using Finite Element Analysis (FEA) …

Development Of A Model And Imbalance Detection System For The Cal Poly Wind Turbine, Ryan Miki Takatsuka

Master's Theses

This thesis develops a model of the Cal Poly Wind Turbine that is used to determine if there is an imbalance in the turbine rotor. A theoretical model is derived to estimate the expected vibrations when there is an imbalance in the rotor. Vibration and acceleration data are collected from the turbine tower during operation to confirm the model is useful and accurate for determining imbalances in the turbine.

Digital signal processing techniques for analyzing the vibration data are explored and tested with simulation data. This includes frequency shifts, lock-in amplifiers, phase-locked loops, discrete Fourier transforms, and decimation filters. The …

Snoring: A Noise Defect Prediction Datasets, Aalok Ahluwalia

Master's Theses

Defect prediction aims at identifying software artifacts that are likely to exhibit a defect. The main purpose of defect prediction is to reduce the cost of testing and code review, by letting developers focus on specific artifacts. Several researchers have worked on improving the accuracy of defect estimation models using techniques such as tuning, re-balancing, or feature selection. Ultimately, the reliability of a prediction model depends on the quality of the dataset. Therefore effort has been spent in identifying sources of noise in the datasets, and how to deal with them, including defect misclassification and defect origin. A key component …

Confronting Retainage And Its Disruptive Effects On The Business Practices Of Commercial Concrete Subcontractors, Arlen Karl Hartoonian

Construction Management

This paper aims to explore the extent of the damage that retainage is capable of inflicting on the financial health of commercial concrete subcontractors and strategies which can be utilized to mitigate or avoid damage to their financial health. The methodology implemented to conduct this exploration is a series of interviews with commercial concrete subcontractors. An analysis of these interviews in conjunction with a thorough literature review demonstrates that retainage does indeed impact financial health of commercial concrete subcontractor though the scale of the operation does make a difference in the severity of this impact. Whether or not the construction …

Academic Senate - Agenda, 05/21/2019, Academic Senate

Academic Senate Agendas

No abstract provided.

As-879-19 Resolution On Subject Area Guidelines (I) For General Education 2020, General Education Governance Board

Academic Senate Resolutions

Cal Poly’s Academic Senate has approved the Template for General Education 2020; and Implementation of the new Template requires the establishment of course criteria and educational objectives for all General Education courses; therefore, be it that the Academic Senate of Cal Poly approve the attached Subject Area Guidelines covering Areas A and B in the Template for General Education 2020; and be it further that these Guidelines be used for the review and implementation of pre-existing and proposed General Education courses from Areas A and B within the 2020-2021 and subsequent catalogs.

Executive Committee - Agenda, 5/14/2019, Academic Senate

Academic Senate Agendas

No abstract provided.

Graduate Internship Report- Dinuba High School, Nicole R. Borba

Agricultural Education: Graduate Internship Reports

This graduate internship report includes the documentation required in meeting the quality criteria for secondary-level programs of instruction in agriculture. The documents are concurrently used for the Agriculture Incentive Grant review process at Dinuba High School conducted by representatives of the California Department of Education. The supporting material includes information to receive state and local funding, outline the goals and objectives of the program, along with an overview of Dinuba High School, the agriculture program and the community.

Dynamic Shifting Of Virtual Network Topologies For Network Attack Prevention, Lenoy Avidan

Master's Theses

Computer networks were not designed with security in mind, making research into the subject of network security vital. Virtual Networks are similar to computer networks, except the components of a Virtual Network are in software rather than hardware. With the constant threat of attacks on networks, security is always a big concern, and Virtual Networks are no different. Virtual Networks have many potential attack vectors similar to physical networks, making research into Virtual Network security of great importance. Virtual Networks, since they are composed of virtualized network components, have the ability to dynamically change topologies. In this paper, we explore …

Autonomous Vehicles Operating Collaboratively To Avoid Debris And Obstructions, Toan T. Le, Cole W. Oppenheim, James H. Gildart, Kyle M. Bybee

Mechanical Engineering

The purpose of this project is to demonstrate the safety and increased fuel efficiency of an automated collision avoidance system in collaborative vehicle platooning. This project was cosponsored by Daimler Trucks North America headquartered in Portland, Oregon, as well as Dr. Birdsong, and Dr. DeBruhl of Cal Poly. The mechanical engineering team consists of Cole Oppenheim, James Gildart, Toan Le, and Kyle Bybee who worked in coordination with a team of computer engineers. Vehicle platooning is a driving technique to increase the fuel efficiency of a group of vehicles by following a lead vehicle closely to reduce the drag experienced …

Solar-Powered Fountain, Byungyu Andy Kim, Jun Kim, Kota Ozawa, Joseph Ciolino

Mechanical Engineering

This Final Design Review (FDR) document outlines the senior design project started by four mechanical engineering students from California Polytechnic State University, San Luis Obispo for Dr. Gary Epstein, a retired Cal Poly mathematics professor and avid gardener. This project entails created a solar-powered fountain for his backyard that has two buckets, a top bucket that will pour into a bottom bucket and then finally into a basin. The goal is to create a fountain that includes the tipping motion of the buckets powered fully by photovoltaic panels. In order to tackle the bucket tipping motion, formulas were derived to …

Graduate Internship Report - Fowler High School, Victor Evans

Agricultural Education: Graduate Internship Reports

This internship/project report includes validation documents required in meeting the quality criteria for secondary-level programs of instruction in agriculture. The documents are concurrently used for the Agriculture Incentive Grant review process at Fowler High School conducted by representatives of the California Department of Education. The internship included the construction of a facility to house and care for fair livestock. Accompanying the project report are photos illustrating the construction steps and educational processes utilized to complete the project.

Left Atrial Model, Borna Sobati, Sarah Porello, Tess Pate

Biomedical Engineering

The objective is to produce an electrophysiological model of an adult human left atrium. This model will be used to test mapping probe catheters used for locating cardiac arrhythmias against current technology used in practice. Dr. Chris Porterfield requested this model and other physicians or probe catheter manufacturers may also use this product in the future. Dr. Porterfield also discussed the possibility of future senior project groups using the model as a bench test for designing new catheter tips. The model will precisely simulate electrical behaviors of the heart in normal as well as arrhythmic conditions. Ideally, the model will …

Tropicalization Of Canonical Curves, Adhitya Saran Mohan

Master's Theses

A fundamental result in the classification of nonsingular projective curves is the canonical embedding. Our goal is to investigate how this canonical embedding interacts with the process of tropicalization. We first give an overview of classical algebraic geometry, beginning with affine varieties. We highlight several important tools used for the construction of maps from algebraic varieties to projective space, namely divisors and differentials, extracting the main properties necessary for the canonical embedding. For illustration, we explicitly describe the image of a certain genus six curve under the canonical embedding. We then transition to tropical geometry, with a brief overview of …

Comparison Of Lqr And Lqr-Mrac For Linear Tractor-Trailer Model, Kevin Richard Gasik

Master's Theses

The United States trucking industry is immense. Employing over three million drivers and traveling to every city in the country. Semi-Trucks travel millions of miles each week and encompass roads that civilians travel on. These vehicles should be safe and allow efficient travel for all. Autonomous vehicles have been discussed in controls for many decades. Now fleets of autonomous vehicles are beginning their integration into society. The ability to create an autonomous system requires domain and system specific knowledge. Approaches to implement a fully autonomous vehicle have been developed using different techniques in control systems such as Kalman Filters, Neural …

Feature Identification In Time Series Data Sets, Justin Shaw, Marek Stastna, Aaron Coutino, Ryan K. Walter, Eduard Reinhardt

Physics

We present a computationally inexpensive, flexible feature identification method which uses a comparison of time series to identify a rank-ordered set of features in geophysically-sourced data sets. Many physical phenomena perturb multiple physical variables nearly simultaneously, and so features are identified as time periods in which there are local maxima of absolute deviation in all time series. Unlike other available methods, this method allows the analyst to tune the method using their knowledge of the physical context. The method is applied to a data set from a moored array of instruments deployed in the coastal environment of Monterey Bay, California, …

Academic Senate - Agenda, 4/30/2019, Academic Senate

Academic Senate Agendas

No abstract provided.

Academic Senate - Agenda, 4/16/2019, Academic Senate

Academic Senate Agendas

No abstract provided.

As-873-19 Resolution On Template For General Education 2020, General Education Governance Board

Academic Senate Resolutions

Cal Poly’s current General Education template was created over two decades ago; and Executive Order 1100-Revised, imposed on the CSU campuses in August 2017, mandates modification of Cal Poly’s current General Education template; therefore, be it that the Academic Senate of Cal Poly approve the attached Template for General Education 2020; and be it further that it be implemented for all students following the 2020–2021 and subsequent catalogs.

Academic Senate - Agenda, 4/09/2019, Academic Senate

Academic Senate Agendas

No abstract provided.