Electrical and Computer Engineering Commons^™

Yolot: A Recurrent Yolo Model For Robust Video-Based Automotive Object Detection, Dylan Jay Baxter

Master's Theses

Though incredibly effective at detecting objects in isolated frames, modern object detection models are often not designed to take advantage of information present in previous frames of a video stream, despite that data being readily avail- able. To address this shortcoming, this paper proposes YOLOT, a modification of the widely used YOLOv8 object detection model, which seeks to utilize this temporal information with the addition of recurrent structures. In the design of YOLOT, a series of recurrent convolutional modules were inserted at backbone and neck outputs and the final and most effective design was found to be the insertion of …

Perceptual Hash Based Content Matching, Nicholas Daniel Chenevey

Master's Theses

The proliferation of video content and AI generated imagery has introduced a number of new challenges in content identification and verification. The ability to trace content back to its source has become a critical problem as video content increases both naturally and synthetically through AI generation. This thesis provides the design, analysis, and experimental verification for a perceptual hash based framework aimed at addressing these challenges. Perceptual hashing is a method for encoding the visual content of images into compact and easily comparable binary strings. This process is used as the foundation for content matching in videos and source verification …

Photophoretic Optical Particle Trapping Improvements Using Beam Reflection, Ian A. Garcia, Xiaomin Jin Phd., Kun Hua Phd.

Master's Theses

Current research has shown that photophoretic optical trapping (POT) is a promising method for creating true three-dimensional holograms. A landmark study by Smalley et. al. at BYU was able to generate a full hologram within a 2 cm edge cube with remarkable success. However, a key drawback to this method is its poor ability to hold trapped particles within the focal point of the laser for an extended period of time. An investigation from our group presented at SPIE Photonics West 2023 sought to improve these results by varying the focal length of the trapping and the wavelength of the …

Hypoxic Incubator: Improving Robustness/Reliability And Demonstrating Physiological Efficacy, Damon Dennis Tan

Master's Theses

The Microphysiological Systems Laboratory aims to develop colorectal cancer tumor models under a hypoxic environment to assess model response to pharmaceutical compounds in vitro. To perform relevant studies, researchers have attempted to use different hypoxic inducing strategies such as a nitrogen pod and hypoxic incubator to recreate in vivo physiological responses to hypoxia. However, studies would be interrupted due to incubator functionality failure. To ensure successful and physiologically relevant studies, I improved and verified the robustness and reliability of a hypoxic incubator previously designed and manufactured in the lab. Through the testing and iterating design processes, I engineered and implemented …

3d Printed Microfluidic Fabrication Methodology, Characterization, Mechanical Design, And Applications In Electrostatic Artificial Muscles And Benthic Microbial Fuel Cells, Terak B. Hornik

Master's Theses

The fabrication of microfluidic devices often requires specialized methods. The development of these methods requires careful characterization and understanding of the processes involved. Using primarily PolyJet 3D printing technology, microfluidics offers a wide scope of applications such as microfluidic benthic microbial fuel cells (MBMFCs) and electrostatic artificial muscles. MBMFCs benefit from the confinement of the microbes resulting in close proximity between the electrode and the organisms. Using a modular design called the Sponge, assembly and upscaling is possible. Electrostatic artificial muscles benefit from a microfluidic approach due to the non-linearity of electrostatic attraction creating disproportionate benefits when miniaturized. When designed …

Dual Base Sige Is-Hbt For Use In Biosensing Applications, Liam Stephen Hayes

Master's Theses

The proposed research is for a novel SiGe-based Ion-Sensitive Dual Hetero-junction Bipolar Transistor (IS-HBT) to be used in both trans-dermal biological sensing as well as Lab-on-Chip (LOC) applications. The end goals for the device designed are two: For one, the research done for this work will be used to substantiate the claims made by Zafar et al. [1] that an HBT-style structure is better suited for biosensing application rather than a conventional Field Effect Transistor (FET) based geometries. Secondly, it provides the final element to be integrated along with a selectivity membrane, as well as with a reverse-iontophoresis system to …

Design And Implementation Of An Inverted Short Baseline Acoustic Positioning System, Jakob Frabosilio

Master's Theses

This document details the design, implementation, testing, and analysis of an inverted short baseline acoustic positioning system. The system presented here is an above-water, air-based prototype for an underwater acoustic positioning system; it is designed to determine the position of remotely-operated underwater vehicles (ROVs) and autonomous underwater vehicles (AUVs) in the global frame using a method that does not drift over time.

A ground-truth positioning system is constructed using a stacked hexapod platform actuator, which mimics the motion of an AUV and provides the true position of an ultrasonic microphone array. An ultrasonic transmitter sends a pulse of sound towards …

A Broadband, Dual Polarized Antenna For The Radio Neutrino Observatory In Greenland, Danny Maas

Master's Theses

The Radio Neutrino Observatory in Greenland (RNO-G) is a multidisciplinary, multinational collaboration which uses antennas to detect neutrino interactions with arctic ice sheets. Neutrinos are formed from nuclear reactions; predominant sources include nuclear reactors, stars, supernovae, and the big bang. They rarely interact with normal matter and thus travel from origin to destination relatively unimpeded, with applications including tracking nuclear weapons tests and supernovae. Measurements of galactic neutrino flux can provide information about how the universe developed and its current evolution. Neutrino interactions produce signals from 100 to 1000MHz. Current RNO-G antennas operate over only a portion of this band; …

Providing Cadence Feedback In Real-Time To Guide Cardiovascular Workouts, Levi O. Rash

Master's Theses

Cardiovascular workouts offer numerous health benefits, yet beginners often find it challenging to initiate them. Existing wearable technologies, although providing valuable feedback such as heart rate zones, often disrupt the workout flow and distract users due to the need for interaction with the wearable display. In response, we propose an alternative feedback mechanism: cadence, measured in steps per minute. This feedback mechanism uses multiplicative control to produce the correct cadence for the user’s target heart rate (HR). To model the HR and cadence relationship, a first-order system was used. The prototype implementation of this system was completed in Arduino, using …

Enhancing Direction Finding Accuracy In Perturbed Digital Arrays Via Rf Ranging-Based Self Calibration, Ariel Freiman

Master's Theses

Direction finding with radio-frequency (RF) waves have numerous applications in radio navigation, wireless localization, emergency aid, and air traffic control, among others. Direction-finding using digital arrays outperforms traditional analog techniques but requires precise knowledge of the location of the array elements to obtain accurate results. Array perturbations can lead to algorithm failures and false detection, compromising direction-finding capabilities.

This research proposes implementing a Matched Filter - Least Square (MF-LS) algorithm for Two-Way Ranging (TWR) to enhance direction-finding accuracy in arrays with perturbed element locations. The MF-LS algorithm leverages the properties of matched filters to accurately determine element positions by measuring …

Shuffled Faster Than Nyquist Signaling For Spectrally Efficient And Secure Wireless Communication, John Gharib

Master's Theses

This thesis investigates the implementation and performance of Shuffled Faster than Nyquist (SFTN) signaling, a communication method that enhances spectral efficiency and provides physical layer security (PLS) in wireless communications. In Faster than Nyquist signaling, the Nyquist inter-symbol interference (ISI) criterion is exceeded, thereby increasing spectral efficiency. By varying the transmission rate of symbols above the Nyquist rate, SFTN signaling is able to obfuscate the timing of transmitted symbols with ISI. The work in this thesis evaluates the performance of SFTN in Additive White Gaussian Noise (AWGN) channels and the MATLAB 802.11ax fading channels. Results show that while SFTN signaling …

An Analysis Of Indoor Air Quality At Cal Poly For Sensor Design, Isabella M. Santi

Master's Theses

Prior research has shown that indoor air quality (IAQ) impacts cognitive performance. At Cal Poly, many older buildings are unable to maintain appropriate IAQ because of their outdated ventilation systems and the increasing number of students in the rooms. This work analyzes the IAQ of different buildings at Cal Poly, with a focus on Building 20. Carbon dioxide, temperature, and relative humidity inside classrooms are collected using an integrated circuit sensor and a microcontroller. A total of 38 hours of data was collected, with 22 of those hours in Building 20 specifically. We find that unlike temperature and relative humidity, …

Filter: Framework For Integrated Legislative Transparency And Exploratory Research, Kenny Lau

Master's Theses

Digital Democracy, established at Cal Poly's Institute for Advanced Technology and Public Policy, initially provided users access to a distinctive dataset, including state legislative committee hearings, transcripts, videos, and more. However, the discontinuation of funding ended operations for the project and emphasized the need for a streamlined application independent of third-party dependencies and capable of offering real-time and organized access to the invaluable Digital Democracy dataset. We introduce FILTER, a cloud-hosted API designed for read access to the Digital Democracy dataset through twelve distinct endpoints. The system contains two databases: the Digital Democracy Database (DDDB) and the Digital Democracy Knowledge …

Power Flow Modeling And Analysis Of A Green Seaport Power System, Alejandra Zapata

Master's Theses

Indonesia has committed to achieving Net-Zero emissions by 2060, signaling a significant shift towards sustainability, which includes impactful initiatives such as the implementation of Green Seaports. This thesis focuses on designing and developing a model for a proposed Green Seaport power system and the subsequent performance of power flow analysis under various operating conditions. The model, constructed using MATLAB Simulink, underwent extensive testing and analysis, with a specific emphasis on the Battery Energy Storage System (BESS) operating modes, including individual charging, discharging, and simultaneous charging and discharging. This comprehensive investigation and analysis, involving 62 separate simulations, evaluated the impact of …

A Hybrid Computer To Solve The Selective Harmonic Minimization Problem In Single-Phase Inverters, Dillon Nguyen

Master's Theses

Power electronics possess forms of non-ideality due to the nonlinearity present in physical switches. These switches are driven with pulse width modulation (PWM), which properly down-converts or up-converts based on converter topology. When these switches turn on or off, they introduce the main proponent of efficiency loss: harmonics. This becomes a nonlinear optimization problem with many converters. The solution proposed in this thesis is an analog/digital hybrid computer that utilizes the speed of analog computation and the accuracy of digital computing together. A Plexim RT Box provides the programmability needed for algorithms, while the analog circuit provides low-power, high-speed computation …

Harmonic Flow Modeling And Analysis Of A Green Hybrid Ac/Dc Seaport Power System, Krishan Kaushal Ram, Taufik, Helen Yu, Siddharth Vyas

Master's Theses

This thesis aims to design and develop a model for a proposed Green Seaport power system and perform harmonic analysis. The model was developed using MATLAB Simulink and tests were performed by dividing the system into several Battery Energy Storage System (BESS) operating modes such as simultaneous charging and discharging, simultaneous charging, and simultaneous discharging. For each mode, BESS state of charge and other factors such as solar irradiance for the PV system, load levels and power factor were varied to observe the impact on system’s voltage Total Harmonic Distortion (THD) level and current Total Demand Distortion (TDD). 62 separate …

Optimal False Data Injection (Fdi) In Simulated Cooperative Adaptive Cruise Control (Cacc) Systems, Lovro Dukic

Master's Theses

In the rapidly advancing field of autonomous vehicles, ensuring the security and reliability of self-driving systems is crucial. Autonomous vehicle systems, such as cooperative adaptive cruise control (CACC), must undergo significant research and testing before their integration into commercial intelligent transportation systems. CACC considers multiple vehicles in close proximity as a single entity, or platoon, with each vehicle equipped with a controller that uses sensor-based measurements and vehicle-to-vehicle (V2V) communication to control inter-vehicle spacing. While this system offers numerous potential benefits for traffic safety and efficiency, it is also susceptible to False Data Injection (FDI) attacks, which can cause the …

Generative Data Augmentation: Using Dcgan To Expand Training Datasets For Chest X-Ray Pneumonia Detection, Ryan D. Maier

Master's Theses

Recent advancements in computer vision have demonstrated remarkable success in image classification tasks, particularly when provided with an ample supply of accurately labeled images for training. These techniques have also exhibited significant potential in revolutionizing computer-aided medical diagnosis by enabling the segmentation and classification of medical images, leveraging Convolutional Neural Networks (CNNs) and similar models. However, the integration of such technologies into clinical practice faces notable challenges. Chief among these is the obstacle of acquiring high-quality medical imaging data for training purposes. Patient privacy concerns often hinder researchers from accessing large datasets, while less common medical conditions pose additional hurdles …

Design Of A Dynamic, Reconfigurable, Self-Balancing Battery Pack, Alexander Hallett Neiman

Master's Theses

This thesis details the design and testing of a reconfigurable battery array. Reconfigurable battery arrays, specifically for mobile applications, have the potential to reduce or eliminate use of auxiliary charging, balancing, and inverter systems. Design work included a bidirectional solid state switch and a cell-to-cell bidirectional current-limiting power converter. While the overall efficiency, size, and cost of the battery pack was not competitive with existing options, it demonstrated cell-to-cell balancing and native four-level square wave AC inverter output with an array of only two cells. This demonstrates viability of the concept as well as reveals important requirements and safety features …

Design And Characterization Of A Broadband Rf Switch Utilizing Surface Mount Devices, Daniel Bracamontes

Master's Theses

High frequency solid-state switches are critical elements in communication systems, radio frequency (RF) systems and instrumentation. Key parameters to an RF switch include insertion loss while on and off-state isolation. Power handling and linearity are important to consider for a cost-effective construction. This becomes a design challenge into K-band frequencies as components required need to be small, dielectric losses and transmission lines need to be physically matched for proper isolative and through states. This thesis presents a novel single pole eight throw (SP8T) hybrid design composed of commercially available surface mount technology solutions to achieve high isolation and low insertion …

Design And Analysis Of A New Buck-Boost Converter With A Low-Side Switch, Abdullah Awidah

Master's Theses

This work explores the design, simulation, construction, and analysis of a novel Non-isolated DC-DC Buck-Boost converter which has the advantage of incorporating a low-side switch compared to the traditional buck-boost which requires a high-side switch. This allows the use of a low-side driver which further simplifies the design and operation of the converter. The proposed Buck-Boost converter was constructed to provide -24 V output from an input range of 12V-18V with 15V nominal input at 10W maximum output power utilizing 500kHz switching frequency. Findings from simulations and hardware tests verify that the converter effectively provides the desired -24 V output …

Generalized Model To Enable Zero-Shot Imitation Learning For Versatile Robots, Yongshuai Wu

Master's Theses

The rapid advancement in Deep Learning (DL), especially in Reinforcement Learning (RL) and Imitation Learning (IL), has positioned it as a promising approach for a multitude of autonomous robotic systems. However, the current methodologies are predominantly constrained to singular setups, necessitating substantial data and extensive training periods. Moreover, these methods have exhibited suboptimal performance in tasks requiring long-horizontal maneuvers, such as Radio Frequency Identification (RFID) inventory, where a robot requires thousands of steps to complete.

In this thesis, we address the aforementioned challenges by presenting the Cross-modal Reasoning Model (CMRM), a novel zero-shot Imitation Learning policy, to tackle long-horizontal robotic …

A Sindy Hardware Accelerator For Efficient System Identification On Edge Devices, Michael Sean Gallagher

Master's Theses

The SINDy (Sparse Identification of Non-linear Dynamics) algorithm is a method of turning a set of data representing non-linear dynamics into a much smaller set of equations comprised of non-linear functions summed together. This provides a human readable system model the represents the dynamic system analyzed. The SINDy algorithm is important for a variety of applications, including high precision industrial and robotic applications. A Hardware Accelerator was designed to decrease the time spent doing calculations. This thesis proposes an efficient hardware accelerator approach for a broad range of applications that use SINDy and similar system identification algorithms. The accelerator is …

A Study Of Random Partitions Vs. Patient-Based Partitions In Breast Cancer Tumor Detection Using Convolutional Neural Networks, Joshua N. Ramos

Master's Theses

Breast cancer is one of the deadliest cancers for women. In the US, 1 in 8 women will be diagnosed with breast cancer within their lifetimes. Detection and diagnosis play an important role in saving lives. To this end, many classifiers with varying structures have been designed to classify breast cancer histopathological images. However, randomly partitioning data, like many previous works have done, can lead to artificially inflated accuracies and classifiers that do not generalize. Data leakage occurs when researchers assume that every image in a dataset is independent of each other, which is often not the case for medical …

Design And Analysis Of Zero Voltage Switching Hybrid Voltage Divider, Stephen Ulysses Alvarado Estrada

Master's Theses

This work explores the design, construction, and analysis of a novel DC-DC converter which incorporates combinations of switching capacitors and inductors to achieve an integer voltage divider function, without the need for a feedback loop controller to achieve the desired output voltage. The proposed Hybrid Voltage Divider additionally provides zero voltage switching (ZVS) at turn on transitions which yields improved overall efficiency of the converter. Besides a proof-of-concept via computer simulations, another primary goal of this thesis is to demonstrate the functionalities of the proposed Zero Voltage Switching Hybrid Voltage Divider (ZVS-HVD) through hardware prototyping. The proposed ZVS-HVD was designed …

An Analysis On Wildfire Mitigations Employed By Utilities In California, Evan Luu

Master's Theses

As climate change continues to worsen, environmental effects are felt by many people around the world. In California, some of its most damaging wildfires have been found to be started by utilities. As the state continues to suffer from worsening wildfire conditions, the utilities need to implement a variety of wildfire mitigations to help reduce the risk of wildfires that can affect the state and its residents. This paper analyzes the effectiveness of four mitigations employed across three California utilities and suggests potential ways for the mitigations to be used together. The technologies evaluated are covered conductor, rapid earth fault …

A Study On Rapidly Exploring Random Tree Algorithms For Robot Path Planning, Sahil Sharma

Master's Theses

Robot path planning is a critical feature of autonomous systems. Rapidly-exploring Random Trees (RRT) is a path planning technique that randomly samples the robot configuration space to find a path between the start and end point. This thesis studies and compares the performance of four important RRT algorithms, namely, the original RRT, the optimal RRT (also termed RRT*), RRT*-Smart, and Informed RRT* for six different environments. The performance measures include the final path length (which is also the shortest path length found by each algorithm), time to find the first path, run time (of 1000 iterations) for each algorithm, total …

Characterization And Estimation Of Musculoskeletal Pain Using Machine Learning, Boluwatife Faremi

Master's Theses

Traditional scales utilized for recording pain are known to be highly subjective and biased due to inaccuracies in recollecting actual pain intensities. As a result, machine learning (ML) models that are trained using these scores as ground truth are reported to have low performance for objective pain classification because of the huge disparity between what was felt in moments of pain and the scores recorded afterward.

In the present study, two devices were designed for gathering real-time, continuous in-session subjective pain scores and the recording of the autonomic nervous system (ANS) altered endodermal (EDA) activity. 24 participants were recruited to …

Efficiency Study Of A Hybrid Ac/Dc House, Eunice Dominique Solomon Santiago

Master's Theses

With the proliferation of residential-scale renewable energy sources and DC loads, it has become attractive to use residential DC electrical system that could offer benefits over the legacy residential AC electrical system. The Hybrid AC/DC house provides a sustainable alternative to preexisting residential electrical system by having both AC and DC buses. The DC bus facilitates the connection from DC sources to DC loads, whereas the AC bus interfaces AC sources to AC loads. The study develops the equations to calculate losses based on a model consisting of four main components: Multiple-Input Single-Output (MISO) converter, AC-DC converter, inverter, and DC-DC …

Design Of Class F-Based Doherty Power Amplifier For S-Band Applications, Kyle Chang

Master's Theses

Modern RF and millimeter-wave communication links call for high-efficiency front end systems with high output power and high linearity to meet minimum transmission requirements. Advanced modulation techniques, such as orthogonal frequency-division multiplexing (OFDM) require a large power amplifier (PA) dynamic range due to the high peak-to-average power ratio (PAPR). This thesis provides the analysis, design, and experimental verification of a high-efficiency, high-linearity S-band Doherty power amplifier (DPA) based on the Class F PA. Traditional Class F PAs use harmonically tuned output matching networks to obtain up to 88.4% power-added efficiency (PAE) theoretically, however the amplifier experiences poor linearity performance due …