Engineering Commons^™

Predicting Suicide Risk Among Youths Using Machine Learning Methods, Saswati Bhattacharjee

Master's Theses

Suicide is the second leading cause of death among youths in the USA. Although machine learning approaches have provided great potential for predicting suicide risk using survey data, prediction accuracy may not meet the need for clinical diagnosis due to the intrinsic characteristics of datasets. In this study, I perform a comparative study of six classification algorithms including naïve Bayes (NB), logistic regression (LR), multilayer perceptron (MLP), AdaBoost (Ada), random forest (RF), and bagging using YRBSS dataset and investigate the effectiveness of several data handling techniques to improve the overall performance of suicide risk prediction.

The dataset consists of 76 …

Implementation Of Methods For Cell Therapy Research And Assessment Of The Impact Of Cryopreservation, Samantha Lynes

Master's Theses

Cell therapy is the administration of living cells into a patient to prevent or treat a variety of diseases and illnesses. The cell therapy industry is rapidly expanding, and continued research is necessary for manufacturing safe and effective therapies. Although cell therapy manufacturing generally involves cryopreservation processes for storage, there are limited standards for cryopreservation processes and assays required to evaluate cell therapies post-thaw, and limited understanding exists about how a recovery period post-thaw could impact cell health. The overall goal of this thesis was to evaluate the effect of cryopreservation and potential subsequent recovery time on cell viability.

Because …

A Proof Of Concept For Detection Of Palato-Lingual Contact Without Intraoral Electrodes In A Human Participant, Amitava Biswas

Master's Theses

The author of this thesis conceived and investigated an unexpected electrical signal that may not be noticed during regular electroglottography (EGG) when electrodes are conventionally placed on the anterior surface of the throat. It appears that there is a measurable electrical signal from the EGG equipment when electrodes are placed over the frontal cheek (belly of zygomatic muscle), and the tongue is elevated to contact the hard palate, or the tongue is lowered to break the contact. Therefore, this phenomenon is designated as unconventional electroglottography (UEGG, Dr. Steven Cloud, private communication, July 17, 2022).

Two distinctive patterns of waveforms were …

Trace Dna Detection Using Diamond Dye: A Recovery Technique To Yield More Dna, Leah Davis

Master's Theses

This study aspires to find a new screening approach to trace DNA recovery techniques to yield a higher quantity of trace DNA from larger items of evidence. It takes the path of visualizing trace DNA on items of evidence with potential DNA so analysts can swab a more localized area rather than attempting to recover trace DNA through the general swabbing technique currently used for trace DNA recovery. The first and second parts consisted of observing trace DNA interaction with Diamond Dye on porous and non-porous surfaces.

The third part involved applying the Diamond Dye solution by spraying it onto …

Rattus Norvegicus As A Biological Detector Of Clandestine Remains And The Use Of Ultrasonic Vocalizations As A Locating Mechanism, Gabrielle M. Johnston

Master's Theses

In investigations, locating missing persons and clandestine remains are imperative. One way that first responder and police agencies can search for the remains is by using cadaver dogs as biological detectors. Cadaver dogs are typically used due to their olfactory sensitivity and ability to detect low concentrations of volatile organic compounds produced by biological remains. Cadaver dogs are typically chosen for their stamina, agility, and olfactory sensitivity. However, what is not taken into account often is the size of the animal and the expense of maintaining and training the animal. Cadaver dogs are typically large breeds that cannot fit in …

Serviceability Analysis And Feasibility Study Of Rooftop Pv System On Commercial Buildings In New York City, Daniel A. Shedo

Master's Theses

Concrete Masonry Unit (CMU) blocks (Ballasts) to counterbalance an uplift wind pressure on Photovoltaic (PV) panels have been used widely. In contrast to mechanically attaching PV panels through penetration of a roof slab, the use of CMU blocks is preferred by many building owners, as penetrating and attaching the panels to a roof slab will pose a serious threat to the warranty of roof membranes, which typically last for 30 years. On the other hand, placing CMU blocks along with PV panels and other system components on a rooftop slab adds additional dead load, which may raise a concern regarding …

Development Of Mirror Flexures For Use In The Muvi Instrument, Colin W. Harrop

Master's Theses

The Miniaturized Ultraviolet Imager (MUVI), is a compact wide field UV imaging instrument in development at UC Berkeley Space Sciences Laboratory and Cal Poly, San Luis Obispo. MUVI is designed to fit in a 2U CubeSat form factor and provide wide field, high resolution images of the ionosphere at far ultraviolet wavelengths. This thesis details the design and analyses of MUVI’s deployable cover mirror mounting flexures. Three different flexure geometries were evaluated, an optimal candidate was determined based on a number of criteria including isolation of vibration and stress to the mirrors, manufacturability and cost. The design of the flexure …

Solar Farm Utilizing A Battery Energy Storage System, Hannah Nicole Bonderov

Master's Theses

According to the US Energy and Information Administration, between 2022-2023 60% of planned new electricity generation consists of solar farms with a battery energy storage system [1]. The demand for these paired systems has increased since batteries can be charged during the day with the energy captured from the solar farm then released to the customer in the evening during peak energy demand. This achieves peak load shaving which reduces the cost of electricity for the customer and is ecologically friendly.

This thesis aims to create an efficient solar farm with a battery energy storage system for a farmer in …

Shelfaware: Accelerating Collaborative Awareness With Shelf Crdt, John C. Waidhofer

Master's Theses

Collaboration has become a key feature of modern software, allowing teams to work together effectively in real-time while in different locations. In order for a user to communicate their intention to several distributed peers, computing devices must exchange high-frequency updates with transient metadata like mouse position, text range highlights, and temporary comments. Current peer-to-peer awareness solutions have high time and space complexity due to the ever-expanding logs that each client must maintain in order to ensure robust collaboration in eventually consistent environments. This paper proposes an awareness Conflict-Free Replicated Data Type (CRDT) library that provides the tooling to support an …

Time-Domain Evaluation Of Atmospheric Ducting Effects On X-Band Propagation Over Water, Jack A. Gallegos

Master's Theses

The marine atmospheric boundary layer (MABL) is the region of atmosphere that interacts with the ocean surface. The atmospheric variability (i.e. temperature and relative humidity) in this region can result in rapid changes in the refractive index with increasing height from the sea surface. The complex region can result in non-standard propagation of electromagnetic (EM) waves beyond the horizon under atmospheric ducting conditions. However, when ducting layers are not present, EM waves are limited to line-of-sight transmission. Atmospheric ducting research is typically conducted using radio frequencies in the X-band (around 8-12 GHz) due to its impact on performance of marine …

Reinforcement Learning Framework For The Unreal Engine, Justin B. Wheeler

Master's Theses

This dissertation addresses the need for using machine learning-based methods rather than traditional rule-based methods for controlling non-playable characters (NPCs). The goal of the Reinforcement Learning Framework for the Unreal Engine is to enable game development studios to create, train, and more easily implement smarter, more compelling AI characters in major video game releases. The framework contains three distinct software libraries: an Unreal Engine reinforcement learning library whose purpose is to enable Unreal Engine levels to act as reinforcement learning environments, a python library which provides convenient abstractions and implementations to the reinforcement learning process, and a flexible connection system …

Racketframes: A Dataframe Implementation For The Racket Programming Language, Shubham Kahal

Master's Theses

The DataFrame is a powerful table-like data structure used frequently in Data Science, the in-demand and innovative field focused on the extraction of valuable insights from data. Typically, datasets are not perfect upon collection and need to be prepared so that the resulting dataset is useful for statistical analysis. A DataFrame API supports optimized methods such as, selecting, aggregating and filtering rows, columns, and cells as well as renaming row and column labels. It also supports methods for normalizing data, merging data, adding new columns and labelling missing data among numerous other features. An API to work with tabular data …

Analysis And Usage Of Natural Language Features In Success Prediction Of Legislative Testimonies, Marine Cossoul

Master's Theses

Committee meetings are a fundamental part of the legislative process in which
constituents, lobbyists, and legislators alike can speak on proposed bills at the
local and state level. Oftentimes, unspoken “rules” or standards are at play in
political processes that can influence the trajectory of a bill, leaving constituents
without a political background at an inherent disadvantage when engaging with
the legislative process. The work done in this thesis aims to explore the extent to
which the language and phraseology of a general public testimony can influence a
vote, and examine how this information can be used to promote civic …

Trajectory-Tracking Control Of The Ball-And-Plate System, Dominic E. Riccoboni

Master's Theses

The Mechatronics group in the Mechanical Engineering department of Cal Poly is interested in creating a demonstration of a ball-and-plate trajectory tracking controller on hardware. The display piece will serve to inspire engineering students to pursue Mechatronics and control theory as an area of study. The ball-and-plate system is open-loop unstable, underactuated, and has complicated, nonlinear equations of motion. These features present substantial challenges for control - especially if the objective is trajectory tracking. Because the system is underactuated, common nonlinear trajectory tracking control techniques are ineffective. This thesis lays out a theoretical foundation for controlling the hardware.

Several important …

Simple Open-Source Formal Verification Of Industrial Programs, Christopher Disney Peterson

Master's Theses

Industrial programs written on Programmable Logic Controllers (PLCs) have become an essential component of many modern industries, including automotive, aerospace, manufacturing, infrastructure, and even amusement parks. As these safety-critical systems become larger and more complex, ensuring their continuous error-free operation has become a significant and important challenge. Formal methods are a potential solution to this issue but have traditionally required substantial time and expertise to deploy. This usability issue is compounded by the fact that PLCs are highly proprietary and have substantial licensing costs, making it difficult to learn about or deploy formal methods on them.

This thesis presents the …

Deep Learning In Ai Medical Imaging For Stroke Diagnosis, James Mario Guzman

Master's Theses

Enhancing medical imaging stroke diagnosis applications with artificial intelligence (AI) tools to determine lesion volume, location and clinical metadata is vital toward guiding patient treatment and procedure. A major hardship in developing stroke diagnosis AI tools is the scarcity of publicly available clinical 3D stroke datasets. Through working with Johns Hopkins University, University of Michigan’s ICPSR data repository and SJSU research, we gained access to potentially the largest 3D MRI stroke dataset with clinical metadata annotated by neuroradiologists known as ICPSR 38464. With the ICPSR 38464 dataset recently being available through institutional review board (IRB) approval or exemption, we were …

Group-Invariant Reinforcement Learning, Fnu Ankur

Master's Theses

Our work introduces a way to learn an optimal reinforcement learning agent accompanied by intrinsic properties of the environment. The extracted properties helps the agent to extrapolate the learning to unseen states efficiently. Out of all the various types of properties, we are intrigued towards equivariant and invariant properties, which essentially translates to symmetry. Contrary to many approaches, we do not assume the symmetry, rather learn them, making the approach agnostic to the environment and the property. The learned properties offers multiple perspective of the environment to exploit it to benefit decision making while interacting with the environment. By building …

Automatic Presentation Slide Generation Using Llms, Tanya Gupta

Master's Theses

Presentation slides are widely used for conveying information in academic and professional contexts. However, manual slide creation can be time-consuming. Our research focuses on automated slide generation, specifically for scientific research papers. Automating the creation of presentation slides for scientific documents is a rather novel task and hence, there’s limited training data available and there also exists the token constraints of language models like BERT, with a maximum sequence length of 512 tokens. In this study, we fine-tune large language models, including Longformer-Encoder-Decoder (supporting sequences up to 16,834 tokens) and BIGBIRD-Pegasus (supporting sequences up to 4,096 tokens). We tackle this …

Detecting The Onion Routing Traffic In Real-Time By Using Reinforcement Learning, Dazhou Liu

Master's Theses

Anonymous networks have been popularly utilized to protect user anonymity and facilitate network security for a decade. However, such networks have been a platform for adversarial affairs and various network attacks including suspicious traffic generators. As a result, detecting anonymous network traffic is one critical task to defend a network against unpredictable attacks. Many new methods using machine learning and deep learning techniques have been proposed. However, many of them rely heavily on a vast amount of labeled data and have complicated architectures. Since network traffic always fluctuates under different network environments, those techniques may degrade in performance due to …

Intrinsic Motivation By The Principles Of Non-Linear Dynamical Systems, Phu C. Nguyen

Master's Theses

The design of appropriate control rules for the stabilization of dynamical systems can require quite substantial domain knowledge. Modern AI methodologies, such as Reinforcement Learning, are often used to mitigate the need for such knowledge. However, these can be slow and often rely on at least some hand-designed reward structure, and thus human input, to be more effective. Here, we propose an alternative route to construct rewards requiring only minimal domain knowledge, essentially relying on the structure of the dynamical system itself. For this, we use truncated Lyapunov exponents as rewards to calculate the stabilizing controller from samples. Concretely, the …

Interdependence Of Salt Concentration And Filler Particles On Crystallinity And Mechanical Behavior Of Peo-Litfsi Electrolytes For Lithium-Ion Batteries, Valeria Perez

Master's Theses

Developing composite polymer electrolytes is crucial for enhancing the safety, energy density, and performance of lithium-ion batteries. While it is widely accepted that introducing filler particles in PEO-based electrolytes can reduce crystallinity and enhance ionic conductivity, this conventional understanding applies primarily to electrolytes with high lithium salt concentrations. The hypothesis of this investigation is that the crystallinity change induced by LLZTO ceramic particles in PEO-LiTFSI electrolytes is contingent on the EO:Li molar ratio. This hypothesis is interrogated by measuring changes in crystallinity, spherulite morphology, and stiffness of composite polymer electrolytes with two different EO:Li molar ratios using differential scanning calorimetry, …

Controllability-Constrained Deep Neural Network Models For Enhanced Control Of Dynamical Systems, Suruchi Sharma

Master's Theses

Control of a dynamical system without the knowledge of dynamics is an important and challenging task. Modern machine learning approaches, such as deep neural networks (DNNs), allow for the estimation of a dynamics model from control inputs and corresponding state observation outputs. Such data-driven models are often utilized for the derivation of model-based controllers. However, in general, there are no guarantees that a model represented by DNNs will be controllable according to the formal control-theoretical meaning of controllability, which is crucial for the design of effective controllers. This often precludes the use of DNN-estimated models in applications, where formal controllability …

Micro-Scale Laser-Induced Fluorescence Thermometry For Multiphase Flow In Porous Media, Samuel J. Simmons

Master's Theses

In this thesis the use of Laser-Induced Fluorescence (LIF) thermometry was evaluated as a temperature measurement for multiphase flow in porous media. This optical temperature measurement technique utilizes the temperature-dependent emissive properties of fluorescent dyes to measure temperature. This research evaluates the accuracy, spatial resolution, and temporal resolution of LIF thermometry compared to existing temperature measurements. In this research water-soluble and oil-soluble fluorescent dyes are evaluated in terms of their temperature sensitivity. The ability of these dyes to measure temperature is compared to an Ansys FEA simulation of a fixed temperature gradient. For multiphase flow, the fluorescent dyes were both …

Project Management And Systems Engineering Framework For Educational Cubesat Missions, Bailey Garrett

Master's Theses

The rising complexity of CubeSat missions and the unique challenges faced by educational CubeSat programs lead to high rates of mission failure. Implementing project management and systems engineering practices can alleviate these challenges and improve mission success rates for educational CubeSat developers. However, existing project management and systems engineering resources are too cumbersome and often assume the student has a base-level understanding of project management and systems engineering fundamentals. A new universal project management and systems engineering framework was created and tailored specifically to the needs of an educational CubeSat mission. The framework was designed to accommodate first-time CubeSat developers, …

Identifying And Minimizing Underspecification In Breast Cancer Subtyping, Jonathan Cheuk-Kiu Tang

Master's Theses

In the realm of biomedical technology, both accuracy and consistency are crucial to the development and deployment of these tools. While accuracy is easy to measure, consistency metrics are not so simple to measure, especially in the scope of biomedicine where prediction consistency can be difficult to achieve. Typically, biomedical datasets contain a significantly larger amount of features compared to the amount of samples, which goes against ordinary data mining practices. As a result, predictive models may fail to find valid pathways for prediction during training on such datasets. This concept is known as underspecification.

Underspecification has been more accepted …

A Design Of A Digital Lockout Tagout System With Machine Learning, Brandon H. Chen

Master's Theses

Lockout Tagout (LOTO) is a safety procedure instated by the Occupational Safety and Health Administration (OSHA) when doing maintenance on dangerous machinery and hazardous power sources. In this procedure, authorized workers shut off the machinery and use physical locks and tags to prevent operation during maintenance. LOTO has been the industry standard for 32 years since it was instantiated, being used in many different industries such as industrial work, mining, and agriculture. However, LOTO is not without its issues. The LOTO procedure requires employees to be trained and is prone to human error. As well, there is a clash between …

Design Of A System To Investigate The Relationship Between Feedback And Delivery Medium For A Novel Motor Task, Ashley Humpal

Master's Theses

Stroke is a chronic, lifelong illness, and full recovery requires continuous physical and cognitive rehabilitation. Such long-term rehabilitation is cost-prohibitive; however an approach to providing long-term therapy that has recently gained traction is the use of socially assistive agent (SAA) systems. These systems make use of non-contact communication devices and can be used to guide people through a variety of rehabilitative tasks. They have the potential supplement current rehabilitation practices by providing motivation during intense exercises, and can extend the reach of the therapist into remote and home settings.

Though SAA systems have been used in a variety of rehabilitative …

Effects Of Atomic Oxygen On Outgassing Of Silicone Materials, Samuel Westrick

Master's Theses

An important consideration for spacecraft material selection is the space environment that the spacecraft will be operating in. Two features of the space environment that drive material selection are material outgassing and the presence of atomic oxygen in low Earth orbit (LEO). Materials that are considered for use in space are tested to be able to understand how they’ll outgas on orbit and how they’ll respond to interactions with atomic oxygen. However, testing to understand how atomic oxygen interaction with a material will affect how the material will outgas is rare and not standardized. This thesis used a vacuum chamber …

A Study On The Effects Of Cementless Total Knee Arthroscopy Implants' Surface Morphology With Finite Element Analysis, Peter Hunt

Master's Theses

Total knee arthroscopy is one of the most performed and most successful orthopedic surgeries, with nearly a million procedures performed in 2020 in the United States alone. Due to changing patient demographics, the use of cementless fixation for implant stability is becoming more prevalent amongst recipients. Cementless implants rely on the surface morphology of a porous coating to bond implant to bone; the quality of this bond is dependent on an interference fit and the roughness, or coefficient of friction, between implant and bone. Stress shielding is a comparison of the properties in implanted bone to natural bone; it is …

Biodegradation Of Methyl Tert-Butyl Ether And Tert-Butyl Alcohol Using Bioaugmentation With Biowish® Aqua, Elizabeth Villanueva

Master's Theses

Aqua, a commercial product manufactured by BiOWiSH® Technologies, was utilized in this research to study its effectiveness to biodegrade methyl tert-butyl ether (MTBE) and tert-butyl alcohol (TBA). Microcosms containing varying concentrations of MTBE and TBA as well as a growth media and mineral salt solution were examined. Analytical instrumentation used in this study included the use of a gas chromatograph-mass spectrometer (GC/MS) to determine concentrations of MTBE and TBA and a spectrophotometer to extrapolate approximate active biomass concentrations in each experiment. Four different environmental conditions were tested for both MTBE and TBA. The environmental conditions tested for each contaminant included: …