Computer Engineering Commons^™

Warn: Wi-Fi Attack Recognizer And Notifier, Sudhish Sewpaul, Roshan Sevalia, Jaden Ngo, Tate Musante

Computer Science and Engineering Senior Theses

The Wi-Fi Attack Recognizer and Notifier (WARN) aims to establish a wireless network monitoring system for detection of attacks on Wi-Fi IoT devices. Millions of homes use smart home devices, and many of these are for security. However, these devices are vulnerable to attacks that can disable them or compromise their data confidentiality. WARN is capable of detecting two of these attacks: deauthentication and key reinstallation (KRACK). Deauthentication attacks hoax devices into disconnecting themselves from a network, and KRACK manipulates the authentication protocol of Wi-Fi devices to see unencrypted data. WARN uses Raspberry Pis equipped with long range Wi-Fi antennas …

Automated Retail Checkout By Computer Vision: Arc-Ai, Griffin Ellis

Computer Science and Engineering Senior Theses

There is some opportunity to apply AI and computer vision techniques to the problems in the retail industry. This paper presents a possible solution to the problem of accurate automated check-out in a retail store setting, a difficult problem due to the possibility of occlusion of hand-held products by the customer and the possible similarity of different products. This solution will identify objects being purchased frame-by-frame, propose tracks that follow individual objects across multiple frames, then determine when and where the object was brought over the region of interest, which will be determined at the start of the task. At …

Avalanche Predictions Based On Ml, William Olson, Matthew Davenport, Ben Airola

Computer Science and Engineering Senior Theses

Our Avalanche Prediction Model utilizes machine learning to analyze weather and climate data in order to provide users in the Northern California back-country with accurate probabilities of avalanche occurrences. Snow forecasts only provide information relating to how much snow will fall. Current avalanche danger ratings only provide the potential level for injury there is if an avalanche will occur. Our system, Avy Safe ML, let’s users survey geographic terrain and see direct probability indicators for precise geo-locations of mountain faces and ranges. These indicators are represented as variably-shaded geo-polygons that indicate avalanche risk classifications. Our data visualization allows access to …

Twigeenglish, Brian Burnett, Jillian Coveney, Kristin Tong, Nanki Sekhon

Computer Science and Engineering Senior Theses

TwigeEnglish is an educational platform aimed to teach English in a fun and interactive way. It comprises a mobile application for students and a web application for pre-determined administrators. The mobile application offers three key features which include: a pictionary-like game, a dictionary flash card game, and a user-friendly interface for uploading photos to be used in both games. The web application will primarily focus on providing administrators with an interface to manage the student-photo database. With moderation powers, administrators can seamlessly review and make decisions to approve or deny the inclusion of photos in the active pictionary and dictionary …

Round Trip Time Measurement Over Microgrid Power Network, Yasin Emir Kutlu, Ruairí De Fréin, Malabika Basu, Ali Malik

Conference papers

A focus of the Power Systems and Networking communities is the design and deployment of Microgrid (MG) integration systems that ensure that quality of service targets are met for load sharing systems at different endpoints. This paper presents an integrated Microgrid testbed that allows Microgrids endpoints to share their current, voltage and power values using a Network Published Shared Variable (NPSV) approach. We present Round Trip Time (RTT) measurements for time sensitive Microgrid control traffic in the presence of varying background traffic as an example quality of service measurement. Numerical results are presented using a range of different background traffic …

Whether-Weather, Lucas Voron, Graham Purvis, Malcolm Weaver, Josh Kelleran

Computer Science and Engineering Senior Theses

The WhetherWeather project is a comprehensive weather and traffic forecasting system that provides real-time insights and predictions. It utilizes Python programming language and various data sources, including Inrix data for traffic information and weather data from Meteostat. The system employs machine learning techniques, specifically XGBoost, to train models on historical data. Once trained, the models can accurately forecast traffic conditions based on weather data. To visualize the results, a Flask API is available, allowing users to access the system's functionalities through a web interface. For more information and to access the WhetherWeather website, visit WhetherWeather.org.

Singular Value Decomposition And Transformer-Based Image Super Resolution, Andy Qin, Chen Zhang, Timothy Cui

Computer Science and Engineering Senior Theses

Image super-resolution (ISR) is a prominent field in computer vision that aims to enhance the quality and resolution of low-resolution images. It finds widespread applications in various domains, including surveillance, satellite imagery, medical imaging, and media. The primary objective of ISR is to improve the visual quality and level of detail in low-resolution images. In this paper, we propose the Singular Value Decomposition and Transformer-based Image Super Resolution (SVDTIR) model, which combines both traditional and deep learning approaches to achieve image super-resolution. The SVDTIR model consists of three stages: image pre-processing, which employs the singular-value decomposition (SVD) algorithm to decompose …

Climate Cloud, Atiyut Khemkhon, Dylan Lin

Computer Science and Engineering Senior Theses

The increasing frequency and intensity of drastic climate change events have underscored the urgency for a comprehensive understanding of climate dynamics and the development of effective mitigation and adaptation strategies. In this context, our thesis addresses the critical issue of drought category prediction in Western America using machine learning techniques. We recognize the interconnectedness of efforts aimed at combating climate change and strive to make a meaningful contribution to the broader understanding of climate change, even if our impact may seem comparatively smaller. By leveraging the power of machine learning algorithms and utilizing a wide range of climatic and environmental …

Underwater Robot Path Planning In An Intermittent Communication System, Hunter Gallant

Dartmouth College Master’s Theses

Sunflower, a novel cross-medium localization system between an aerial drone and an underwater robot, has not yet been implemented in a multi-robot exploration system. This project’s aim was to simulate various configurations of multi-robot systems, and to create an algorithm, called AdjustPath, to improve exploration and avoid inter- robot collisions. With three, five, seven, and ten simulated underwater robots, there was significant improvement when the AdjustPath algorithm was used. Knowing this, future hardware using the Sunflower system could use this proposed algorithm to increase efficiency and avoid more collisions.

Ai-Powered Iot Monitoring And Security For Smart Homes, Paul Boldyrev, Timothy Hradil, Matthew Ding

Computer Science and Engineering Senior Theses

Smart home devices are becoming increasingly popular across the United States. Unfortunately, in order to keep the cost of these devices down, manufacturers tend to place cybersecurity measures lower on their list of priorities. As a result, these devices have become targets for security breaches like the Mirai Botnet and distributed denial of service (DDoS) attacks. The cybersecurity solutions currently available on the market are either expensive, difficult to set up, or follow a static set of rules for attack detection. In this thesis, we propose a novel approach to detecting attacks on Internet of Things (IoT) devices through the …

Cometrics: A New Software Tool For Behavior‑Analytic Clinicians And Machine Learning Researchers, Walker S. Arce, Seth G. Walker, Morgan L. Hurtz

Department of Electrical and Computer Engineering: Faculty Publications

Cometrics is a Microsoft Windows compatible clinical tool for the collection and recording of frequency- and duration-based target behaviors, physiological signals, and video data. This software package is designed to record in-vivo observational and physiological data. In addition, we have included features that allow observers to capture video from real-time camera feeds and import saved video for retroactive data collection. By using Microsoft Excel-based spreadsheets, also called keystroke files, assessment and treatment sessions are exported into a single document using the click of a button. Integrated interobserver agreement metrics allow comparisons across primary and reliability observers, with the output exported …

Model-Driven Analysis Of Ecg Using Reinforcement Learning, Christian O'Reilly, Sai Durga Rithvik Oruganti, Deepa Tilwani, Jessica Bradshaw

Publications

Modeling is essential to better understand the generative mechanisms responsible for experimental observations gathered from complex systems. In this work, we are using such an approach to analyze the electrocardiogram (ECG). We present a systematic framework to decompose ECG signals into sums of overlapping lognormal components. We use reinforcement learning to train a deep neural network to estimate the modeling parameters from an ECG recorded in babies from 1 to 24 months of age. We demonstrate this model-driven approach by showing how the extracted parameters vary with age. From the 751,510 PQRST complexes modeled, 82.7% provided a signal-to-noise ratio that …

Poly-Gan: Regularizing Polygons With Generative Adversarial Networks, Lasith Niroshan, James Carswell

Conference Papers

Regularizing polygons involves simplifying irregular and noisy shapes of built environment objects (e.g. buildings) to ensure that they are accurately represented using a minimum number of vertices. It is a vital processing step when creating/transmitting online digital maps so that they occupy minimal storage space and bandwidth. This paper presents a data-driven and Deep Learning (DL) based approach for regularizing OpenStreetMap building polygon edges. The study introduces a building footprint regularization technique (Poly-GAN) that utilises a Generative Adversarial Network model trained on irregular building footprints and OSM vector data. The proposed method is particularly relevant for map features …

Interactive Architecture - Intervention Of Virtual Business On Commercial Space, Yihao George Xu

Masters Theses

Traditional mall-based restaurants, such as P.F. Chang’s in the Providence Place Mall, have primarily focused on site-based dining and bar services. However, the food provided by this chain restaurant often lacks depth, and customers seldom learn the story behind the dishes. This thesis explores the integration of mixed reality technology within the physical environment of P.F. Chang’s, an American Chinese restaurant chain with over 300 locations, aiming to transform it into an authentic Shanghai food culture experience. This experience combines virtual and physical stimuli to evoke various periods of Chinese history, providing a unique encounter for customers.

The proposed transformation …

Unveiling Pain: Wearables For Objective Pain Measurement, Hanqing Tang

Masters Theses

">">Pain perception is a subjective experience that differs significantly among individuals, often leading to inconsistencies in assessment and management. A critical issue within this context is the gender bias in pain evaluation, which contributes to unequal treatment and perpetuates gender inequality within the healthcare system. This thesis presents an in-depth investigation of the problem and proposes the development of a wearable device for objective pain assessment. Physiological parameters — Electrocardiography (ECG) can be collected from cardiac sound signals auscultated by fabrics via nanometre-scale vibrations. Machine learning methods can accurately classify heart rate and acute pain intensity of participants. …

Slowly Changing Dimensions And Fast Changing Facts - The Story Of The Traditional Data Warehouse, Vishnu Pendyala

Open Educational Resources

This presentation, "Slowly Changing Dimensions and Fast Changing Facts - The Story of the Traditional Data Warehouse," explores how to generate actionable insights from organizational performance data. It begins by discussing the challenges of generating insights directly from existing databases and introduces the concept of data cubes for efficient aggregate storage. The core of the presentation focuses on dimensional modeling, particularly the Star Schema, as a solution for analytical processing needs that cannot be met by transactional systems. It details the characteristics of fast-changing fact tables (long, lean, numeric) and slowly changing dimension tables (descriptive, wide, containing strings and numbers). …

A High-Speed Portable Ground Heat Exchanger Model For Use In Various Energy Simulation Software, Ryan Davies, Matt Mitchell, Edwin Lee

Macalester Journal of Physics and Astronomy

A portable component model (PCM) of a ground source heat pump system was developed and used as a test case in the creating of a PCM development framework. By developing this framework, new building energy simulation models will be able to be easily integrated into existing simulation software such as EnergyPlus and the Modelica Buildings Library. Our model uses a time responsive g-function and numerical methods to simulate ground source heat pumps for single time steps as well as long time scales. We validated our model against GHESim and GLHEPro and found that our model agrees with these two standards …

Coastal: Crowdsourcing Reports Of Phenomena On The Santa Cruz Coast, Will Maddrey, Daniel Schott, Michael Zetino

Computer Science and Engineering Senior Theses

Every day, beachgoers witness important environmental phenomena that go completely undocumented. Huge amounts of potential data that could be used for research are lost because people don’t have the means to report them, or simply don’t understand their significance. Additionally, many of these phenomena are potentially harmful, and are relatively unknown to the public. In this paper, we develop an iOS and Android mobile app called Coastal, with the goal of crowdsourcing reports of phenomena on the Santa Cruz coast. We hope that in the future, applications like Coastal can be used for both collecting data for environmental research, and …

Dominican Republic Greenhouse Automation, Ryan Le, Erik Mitchell, Mark Castillo

Computer Science and Engineering Senior Theses

The Dominican Republic's Instituto Politécnico Loyola (IPL) needs a wirelessly connected network of sensors for their greenhouses. Our project uses long-range (LoRa) communication to receive data from sensors within the greenhouse on the recorded temperature, humidity, soil moisture, and light values; stores and organizes these measurements in a database and backup text file; and displays appropriate recordings on an interactive application. We collaborated with a team of two General Engineering majors, with our focus on data retrieval and display functionality. Aside from basic data senders used solely for testing purposes, our final design serves as a central hub remotely accessible …

Film Viability Evaluator, Caitlin Lopez, Kulsoom Sabit

Computer Science and Engineering Senior Theses

Filmmaking is a financially high-risk field of work. There are multiple variables that contribute to a movie’s success or failure, however the most impactful ones have yet to be identified. In this paper, we used publicly available datasets in combination with several forms of analysis models to determine common factors associated with historically successful movies. Our results narrowed the top categories to include the runtime, the production budget, the release year, the genres, and the primary language. The final round of analysis yielded an 84% accuracy, after the usage of XGBoosting and gradient boosting. Further improvements to this project could …

Monster Maker, Harrison Bui

Computer Science and Engineering Senior Theses

3D modeling and rigging are necessary steps when it comes to 3D animation. However, not everyone has the time and patience to learn and practice these skills. Monster Maker provides an accessible way to create creatures from their imaginations by assembling pre-made 3D body parts. The option to dynamically alter the skeleton and modify body parts opens the door to hundreds of thousands of monsters each with their own unique design. Future developments of Monster Maker could provide users with options to control specific sub-components of the currently established body parts while also providing a more appealing UI.

Nutrition Visualization For Mindfulness, Jake Tsuchiyama, Jarin Simon, Landis Fusato, Ryan Wong

Computer Science and Engineering Senior Theses

In today’s world, users face multiple obstacles obtaining relevant nutrition information for the foods they consume. While nutrition information is provided on some foods like a standard candy bar, this label is typically hard to read and inconveniently located. For other foods such as an apple, this nutrition label is not provided at all and the burden is placed on the user to go out and find this information themselves. We hope to address this inaccessibility of nutrition information to help users ultimately make more informed decisions about their eating habits.

Immersive Scu Campus Tour With Augmented Reality, Tristan Limawan, Axel Perales, Alfredo Perry

Computer Science and Engineering Senior Theses

Santa Clara University has hosted numerous guided campus tours as a way for students to understand better and immerse themselves in the university's culture and environment. However, group sizes for these tours are limited and may fill up quickly, leaving students to compete for these tour slots. As such, accompanied by the continual growth in admissions reaching new highs each year, the situation presents a great need to help first-year and prospective students navigate the campus grounds and understand and learn about the campus history and culture.

To resolve this problem, we have developed an augmented reality web application allowing …

A Submodular Optimization Framework For Imbalanced Text Classification With Data Augmentation, Eyor Alemayehu

Engineering Ph.D. Theses

In the domain of text classification, imbalanced datasets are a common occurrence. The skewed distribution of the labels of these datasets poses a great challenge to the performance of text classifiers. One popular way to mitigate this challenge is to augment underwhelmingly represented labels with synthesized items. The synthesized items are generated by data augmentation methods that can typically generate an unbounded number of items. To select the synthesized items that maximize the performance of text classifiers, we introduce a novel method that selects items that jointly maximize the likelihood of the items belonging to their respective labels and the …

Enhancing Residential Energy Sustainability With Occupancy Detection And Ai-Based Trading, Jun Jiang

Engineering Ph.D. Theses

With the rapid development and deployment of distributed energy resources (DERs), Internet of Things (IoT) technologies, and innovative energy trading markets, residential buildings as the primary energy consumers show enormous potential in promoting energy sustainability. However, achieving residential energy sustainability faces various challenges. (1) Promoting consistent energy-efficient behaviors among all residents can be challenging due to variations in their awareness and commitment to energy-saving practices. (2) While training can cultivate energy-saving habits among residents, educating residents without energy-related knowledge to effectively coordinate and operate various electrical appliances and DERs remains challenging, especially with the widespread adoption of such equipment. (3) …

When Is An Owl More Than An Owl? An Interaction Analysis Of A Computer Science Co-Design Conversation On Cultural Relevance, Stephanie M. Robillard, Victor R. Lee, Jody Clarke-Midura, Jessica F. Shumway

Publications

The learning sciences community is currently exploring new ways to enact productive and equitable co-design research-practice partnerships that are sensitive to all the concerns and needs of stakeholders. The paper contributes to that still-growing literature through an interaction analysis of a co-design discussion involving school district partners that unfolded about cultural relevance and sensitivity in relation to the use of a specific image in an elementary school coding lesson. The episode involved looking moment-by-moment at how district educators recognized and acknowledged that a specific design decision could be harmful for a minoritized population of students enrolled in the district. However, …

Embride: A Madhubani Art Creator, Jui Banik

Computer Science and Engineering Master's Theses

Creative machines are playing an increasingly important role in the art world and society at large. This gives rise to the need to consider the ethical dimensions of artistic machine agents. Whose art are we amplifying, or more importantly, who is being left behind? Computational Creativity offers the opportunity to bring awareness and visibility to art forms that have been systemically suppressed due to a range of longstanding societal biases. In this paper, we introduce EMBRIDE, a system that creates Madhubani art, practiced by women in the villages of India and Nepal. We hope that this work will encourage further …

Ocean Sight One: Mixed Reality Experience, Lucas Michael Reyna

Computer Engineering

Ocean Sight One is an interdisciplinary project group consisting of Cal Poly staff and students from several different departments. It exists to educate the public on the marine ecosystems near the Santa Barbara coastline that is the home of twenty-three abandoned oil rigs. Despite one’s initial reaction to these massive abandoned structures, they actually provide an incredibly diverse dwelling for numerous forms of sea life. The site is a shining beacon for marine ecology researchers trying to formulate how to preserve wildlife in an era of worsening global environmental disruptions. The future of these oil rigs are not certain, as …

Neural Compression Inference Accelerator: A Cost And Energy-Effective Alternative To Conventional Machine Learning Inference Methods, Matthew Wallace

Master's Theses

Recent developments in machine learning and artificial intelligence have sparked an influx of workloads that require specialized computer hardware for cloud services. The hardware running machine learning models predominantly consists of graphics processing units (GPUs) and tensor processing units (TPUs). However, these com- ponents are expensive for cloud services to purchase, costly for customers to rent, prone to price spikes, and energy-intensive. In this research we show that both cloud services and customers would benefit from utilizing field programmable gate arrays (FPGAs) to alleviate the aforementioned challenges. An FPGA can be configured as a machine learning accelerator, operating similarly to …

Polyflowbuilder: An Intuitive Tool For Academic Planning At Cal Poly San Luis Obispo, Duncan Thomas Applegarth

Computer Engineering

PolyFlowBuilder is a web application that lets users create visually intuitive flowcharts to aid in academic planning at Cal Poly. These flowcharts can be customized in a variety of ways to accurately represent complex academic plans, such as double majors, minors, taking courses out- of-order, etc. The original version of PolyFlowBuilder, released Summer 2020, was not written for continued expansion and growth. Therefore, a complete rewrite was determined to be necessary to enable the project to grow in the future. This report details the process to completely rewrite the existing version of PolyFlowBuilder over the course of six months, using …