Computer Engineering Commons^™

The Character Jar: Trait-Based Facial Feature Generation Software, Angela Shao

Computer Science and Engineering Senior Theses

While AI has come a long way in random facial generation, very limited research has been done on targeted generation. Initial impressions given by faces vary widely depending on the shape and proportions of the features. This project will design a program that manipulates a face shape according to given traits. By using preexisting research on the correlation between facial features and associated characteristics and impressions, the practical uses of facial generation increase many fold. This allows facial generation to be applied to marketing and design, as well as increasing the overall accessibility to any laypersons seeking such applications.

Galapago!, Kristina Anderson, Kat Hibbert, Mariah Manzano, Catrina Nguyen

Computer Science and Engineering Senior Theses

When traveling to the Galápagos Islands, tourists are unaware of all the Islands have to offer and only visit popular tourist spots. They bring in pests which are damaging to the ecological structure and do not contribute to the local economy. There is very limited Internet services on the Islands and not many online resources to be found. We have created a mobile and web application that show users recommendations for their visit. Because the Galápagos Islands do not have reliable internet connectivity, our application must not rely on connectivity to function. Instead, users will only need to connect once …

Omwanathrive: A Neonatal Survival App, Story Deweese, Tiffany Lee, Samantha Sy, Emily Zhang

Computer Science and Engineering Senior Theses

Uganda’s infant mortality rate is alarmingly high, ranking twenty-first in the world for highest infant mortality; eighty-one babies die within their first month of life each day in Uganda. The UN reports the greatest risk factors are rural location, prematurity, and young impoverished mothers with limited educational opportunities. Thus, young women are giving birth to children before they even learn about how to take care of their newborn infant. Our solution to this problem is in the form of a mobile application called OmwanaThrive: Neonatal Survival App. The purpose of the app is to educate women about how to properly …

Youlearn: Offline Media Streaming Application For Rural Uganda, Emma Allegrucci, Jiabei Luo, Brianna Mcgovern

Computer Science and Engineering Senior Theses

The country of Uganda has implemented universal primary and secondary education. But still, some families cannot afford to send their children to school. When young people drop out of school, they often must resort to working illegal, unsafe, and low-paying jobs. Job prospects are even worse for disabled children. The objective of this project is to bring digital educational resources into rural villages in a low-cost manner.

YouLearn is an educational system that allows for o✏ine media streaming. Our system includes a Raspberry Pi to store the media locally and allows for streaming without WiFi being necessary. Our system supports …

Deep Reinforcement Learning For Dialogue Systems With Dynamic User Goals, Glen Chandler

Computer Science and Engineering Master's Theses

Dialogue systems have recently become a widely used system across the world. Some of the functionality offered includes application user interfacing, social conversation, data interaction, and task completion. Most recently, dialogue systems have been developed to autonomously and intelligently interact with users to complete complex tasks in diverse operational spaces. This kind of dialogue system can interact with users to complete tasks such as making a phone call, ordering items online, searching the internet for a question, and more. These systems are typically created by training a machine learning model with example conversational data. One of the existing problems with …

Drive Health: Road Condition Detection, Peter Ferguson, Brian Walker

Computer Science and Engineering Senior Theses

Roadways play an essential role in toady’s society by contributing to economic growth and development, providing social benefits and fast routes to travel around efficiently. With more and more cars on roads, the quality of the streets is deteriorating faster than before. This decrease in road health contributes to hazards such as potholes and can cause significant damage to vehicles on the road. Currently, the process of improving and monitoring roads’ health is done infrequently and is time-consuming for the government. Therefore, many road quality issues are manually reported by the people who drive on them. This requires filling out …

Mobile Application To Distribute Water Quality In Rural Nicaragua, Rachael Freitag, Sarah Ortiz-Jones

Computer Science and Engineering Senior Theses

The organization ASDENIC provides the citizens of northern Nicaragua with many resources to help them become more informed farmers and improve the quality of their lives. ASDENIC currently holds weekly meetings to distribute information such as water quality, weather conditions, and other important agricultural updates. However, technological limitations still prevent Nicaraguan farmers from getting updates from ASDENIC in real-time. We have partnered with Santa Clara University’s Frugal Innovation Hub and ASDENIC to create a mobile application to distribute necessary information to communities in rural Nicaragua in realtime.

Our mobile application is a platform for community leaders to share relevant information …

Photo-Realistic Image Synthesis From Text Descriptions, Ryan Cain, Gabriel Kralik, Campbell Munson

Computer Science and Engineering Senior Theses

Deep convolutional generative adversarial networks (DCGANs) have proven capable at generating diverse, photorealistic images of human faces, but it is difficult and often time-consuming to choose what kind of image these generative adversarial networks (GANs) produce. We create a simple, intuitive web application through which users may write a description of a human face in plain text and generate photos that appear to match the given description. In this paper, we show how text can be used to direct the output of a conditional GAN with a DCGAN architecture. While our images did somewhat resemble human faces, they often had …

Smart Quizzes, Andres Cisneros-Munoz, Cole Sanchez

Computer Science and Engineering Senior Theses

Standardized testing, while efficient for testing a large amount of people, is not an effective or holistic method of evaluating test takers. They fail to take into consideration factors such as stress, which can inhibit a student’s ability to perform well on a test. Our goal is to create a framework for creating tests that are dynamic, adaptive assessments, minimize stress levels, and overall improve student performance. This solution will produce in tests that even out the academic playing field while being more informative in their assessments.

Neptune: Marine Robot Rov Control System, Alex Achramowicz, Chris Layco, Cooper Zediker

Computer Science and Engineering Senior Theses

The mysteries of the aquatic world and the dangers human activity poses to its environmental health are important considerations. It is pivotal we find ecient methods to study and monitor the subsea environments in order to maintain and improve their health. This document provides insight into the planning, design, implementation, and testing in developing an enhanced control system for a marine remotely operated vehicle (ROV) to eectively control various mounted hardware components. Our goal for this design is to greatly assist scientists and environmentalists observe and collect subsea data to improve the subsea environment.

Clubgrove, Travis Le, Lyman Shen

Computer Science and Engineering Senior Theses

The current Santa Clara University Club system does not provide the necessary information in a relevant and concise fashion. As a solution, we built a system that caters towards students who are looking for clubs. In addition, the system also caters towards club leaders who want to increase their clubs’ visibility. Our system allows students to look up clubs, search club events, and look at interested clubs as well as previously joined clubs. The goal of this project is to provide an easy way for students to be involved in more clubs and allow clubs to gain members without spending …

A Low-Cost And Energy-Effcient Wearable Device For Posture Monitoring, George Shappell, Ying Huang, Ali Nazemi

Computer Science and Engineering Senior Theses

Millions of Americans suffer every year from back problems, now imagine if there was a way to help track and prevent back problems. Our solution to this problem is PostureBot a device that will help its users to correct their back posture and maintain good back posture.In doing so this device can help elevate and prevent people from developing minor and serious back problems in their future.

Flomosys: A Flood Monitoring System, Tai Groot

Computer Science and Engineering Senior Theses

The expansion of the Internet of Things (IoT) has led to numerous innovations in the industry, including improvements to existing systems. Disaster prevention and monitoring systems are a prime example of such systems. Every year, there are significant and preventable financial losses, not to mention the safety hazards caused by floods. To warn people ahead of time, it is possible to deploy low-power wireless sensor nodes to send readings across any terrain to a cloud platform, which can perform pattern analysis, prediction, and alert forwarding to anyone's cellular device. In this paper, I propose Flomosys, a low-cost, low-power, secure, scalable, …

Advocasea, Emily Dang

Computer Science and Engineering Senior Theses

Plastics and pollution in the ocean pose a tremendous threat to the world’s biodiversity and human life on the planet. However, this issue is characterized by a lack of visibility and urgency. People do not understand the importance of this pollution because they do not sense an immediate or tangible impact on their lives. AdvocaSea is a virtual reality experience that teaches people about plastics in the ocean in a more immersive and engaging way, and by doing so, gives them more motivation and agency to make change in the world. This experience was delivered at Santa Clara’s Senior Design …

Acas: Always Connected, Always Secure, Blaise Aranador, Antonio Gigliotti, Shining Liu

Computer Science and Engineering Senior Theses

There is no place where safety is more important than in the home. Research has shown that home security systems are effective in deterring burglars; additionally, these security systems allow residents to monitor their property at all times, even while they are away. More and more of these home security devices rely on a stable Internet connection and cannot provide functionality without it. ACAS is a system that helps keep smart devices connected to the Internet, even in the event of a home internet outage.

ACAS includes a programmable router that can connect to multiple Internet sources, which sets it …

Securely Updating Iot Using Blockchain, Rachael Brooks

Computer Science and Engineering Senior Theses

Because of the extensive growth of loT devices in the last few years, researchers have been looking for ways to reduce the amount of power they use. One cause for concern is the energy used to communicate with manufacturers when an update has to occur. Our solution to this problem is to move those communications off the device and onto a blockchain, with the owner of the device as an intermediary. The update is handled through the blockchain and is mediated by a smart contract. Overall, the owner pays for the update, the manufacturer passes the encrypted keys for the …

Truck Routing Application, Adam Miller

Computer Science and Engineering Senior Theses

This application aims to provide dispatchers with an accessible tool to assist them in routing a fleet of trucks in the most ecient way. The vehicle routing problem is a notoriously complex and inecient problem to solve, yet dispatchers are tasked with solving it every single day by hand. Rather than radically transform a dispatcher’s time-sensitive workflow, my application seeks to provide them with a simple, powerful tool that can supplement their daily duties. This application will ultimately help dispatchers perform their jobs more eciently and contribute to the reduction of fuel consumption, carbon emissions, and vehicle maintenance costs.

Leapi: Wireless Diagnostic Assistant, Jeff Collins, Austin Iverson, Collin Seaman, Joseph Sindelar

Computer Science and Engineering Senior Theses

Nearly every person who usesWiFi on a daily basis has had trouble with a bad connection. Wireless connectivity issues are often difficult to diagnose and fix. Current solutions such as wired extenders, and MeshWiFi commercial packages are expensive and do not provide the user with a system that suggests placement of mesh units to maximize coverage. Our solution is an inexpensive and open-source diagnostic tool that maps out Wifi quality and informs the user of interference. With a simple, meaningful display, users will find trouble spots in their house, diagnose why IoT devices are not working, effectively place WiFi extenders …

Mitigating Fake Digital Media And Quality Assurance, Hetesh Sehgal, Xinyu Chen, Kyle Jiang

Computer Science and Engineering Senior Theses

With the introduction of social media, the internet is filled with an excess of data and content. Users feeds are cluttered with fake, malicious, and unnecessary information, polluting their page and wasting their time. As observed in the 2016 US election, spam accounts posting fake news were successfully able to sway political opinion and misinform the general population. Additionally, with social media becoming one of the biggest advertising markets, there is a rise in the number of fake accounts with a large number of followers that mainly consist of bots. It should be a priority to protect the public from …

Multilock: A Document Escrow Service, Dominic Lagorio, Steven Herman

Computer Science and Engineering Senior Theses

The objective of this project is to create a system wherein it is no one person’s responsibility to claim agency over a given file, but rather that the responsibility is distributed amongst a number of individuals who must decide as a unit to grant access to said files. There are a number of driving factors here, including removing culpability for individual involvement with the file, preventing compulsory access to files, and providing sophisticated security protocols for file access.

Biometric Authentication Via Electrocardiogram Signals, Austin Miles, Carlos Garcia

Computer Science and Engineering Senior Theses

Biometric authentication has proven to be a reliable form of security as we have seen its continuous acceptance in multiple areas of technology. This includes facial recognition, fingerprints, gait analysis, and others. In this project, we develop a system that will provide authentication via electrocardiogram (ECG) signals. This system will employ a supervised machine learning approach to connect the various features generated by an ECG signal with the user. We will collect data using an online database. We will use this data to train the machine learning model that will be used to authenticate. Once a user is authenticated, then …

Platica: Personalized Language Acquisition Training & Instruction Chatbot Assistant, Nam Tran, Philip Cori, Andres Morales, Evan Johnson

Computer Science and Engineering Senior Theses

English is immensely important and useful in our society, however there are many people across the world who are learning English as a second language and have limited options to practice. Casual English conversations with native speakers is one of the most proven and immersive ways to practice a language. However, not everyone has those opportunities or the resources to attend ESL classes. We aim to solve this issue with our project PLATICA, a robust, low-cost mobile application that anyone can use to build experience conversing in English. PLATICA takes advantage of state-of-the-art deep learning and natural language processing techniques …

Gaussian-Awareness Deep Learning For Block-Level Compressive Video Sensing, Yifei Pei

Computer Science and Engineering Master's Theses

Compressive sensing (CS) is a signal processing framework that effectively recovers a signal from a small number of samples. Traditional compressed sensing algorithms, such as basis pursuit (BP) and orthogonal matching pursuit (OMP) have several drawbacks, such as low reconstruction performance at small compressed sensing rates and high time complexity. Recently, researchers focus on deep learning to get compressive sensing matrix and reconstruction operations collectively. However, they failed to consider sparsity in their neural networks to compressive sensing recovery; thus, the reconstruction performances are still unsatisfied. In this thesis, we use 2D-discrete cosine transform and 2D-discrete wavelet transform to impose …

Deep Learning Methods For Efficient Image Coding, Zachary Daniel Bellay

Computer Science and Engineering Master's Theses

Video data makes up 58% of all internet traffic and is growing as self-driving car cameras, 4K televisions, and video surveillance systems continue to come online. Traditional heuristics based image and video codecs such as JPEG and HEVC have been successful thus far, however, these approaches lack the ability to leverage big data to gain massive insights. Six deep learning based approaches are proposed to tackle efficient image/video compression and image compression for machine classification.

Adaptive Robotic Chassis (Arc), Darran Casey, Ryan Ku, Noah Kane Manuel, Isabella Morales, James Reimer, Lavelle Simmons

Interdisciplinary Design Senior Theses

The ARC is a width adjusting agricultural robot and accommodates auxiliary functions for supporting crop production and maintenance. Easily interchangeable payloads and components provide a modular solution to perform focused crop surveying functions with the potential for herbicide distribution, weeding, and harvesting while driving through varying crop rows. The potential auxiliary functions will be implemented by future teams with this year's effort being put toward finishing the physical chassis. The final product was successfully designed to weigh approximately 600 pounds targeting rolling speeds of0.90 fps to 2.30 fps with proof of concept shown in testing consisting of chain drive attached …

Prioritized Anomaly Catalog Generation Using Model-Based Reasoning, Jake Hedlund

Computer Science and Engineering Master's Theses

Anomaly management—the detection, diagnosis, and resolution of anomalies in a system—is traditionally performed using experiential techniques which are quickly computed, but poorly structured. Newer model-based approaches are more systematic and higher performing but are computationally expensive, which is a particular challenge for execution in an operational environment. This paper builds on a novel system to pre-compute model-based anomaly symptoms to enable quick retrieval and diagnosis in operational settings. New additions to this system include a simplified model interface, anomaly likelihoods associated with each component, and easier interpretation of results. The implemented system has been used successfully to detect and diagnose …

Basil Leaf Automation, Andrew Soong, Chris Nelson, John Goldsberry, Kalle Suzuki, Nikolas Abenoja, Sherene Victor, Simon Liu

Interdisciplinary Design Senior Theses

Recent population and wage increases have forced farmers to grow more food without a proportionate increase in work force. Automation is a key factor in reducing cost and increasing efficiency. In this paper, we explore our automation solution that utilizes position manipulation and vision processing to identify, pick up, and drop a leaf into a can. Two stepper motors and a linear actuator drove the three-dimensional actuation. Leaf and can recognition were accomplished through edge detection and machine learning algorithms. Testing proved subsystem-level functionality and proof of concept of a delicate autonomous pick-and-place robot.

Deep Generative Models For Semantic Text Hashing, Suthee Chaidaroon

Engineering Ph.D. Theses

As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original data samples by compact binary codes through hashing. A spectrum of machine learning methods have been utilized, but they often lack expressiveness and flexibility in modeling to learn effective representations. The recent advances of deep learning in a wide range of applications has demonstrated its capability to learn robust and powerful feature representations for complex data. Especially, deep generative models naturally combine the expressiveness of …

Channel Scanning And Access Point Selection Mechanisms For 802.11 Handoff: A Survey, Dhananjay Singh

Computer Science and Engineering Master's Theses

While the cellular technology has been evolving continuously in recent years and client handoffs remain unnoticed, the 802.11 networks still impose an enormous latency issue once the client device decides to roam between the Access Point (AP). This latency is caused by many factors reckoning on scanning the channels and searching for APs with better signal strength. Once data from all the nearby APs has been collected, the client picks the most suitable AP and tries to connect with it. The AP verifies if it has enough capability to serve the client. It also ensures that the client has the …

Analysis Of The Duration And Energy Consumption Of Aes Algorithms On A Contiki-Based Iot Device, Brandon Tsao

Computer Science and Engineering Master's Theses

With the growing prevalence of the Internet of Things, securing the sheer abundance of devices is critical. The current IoT and security landscapes lack empirical metrics on encryption algorithm implementations that are optimized for constrained devices, such as encryption/decryption duration and energy consumption. In this paper, we achieve two things. First, we survey for optimized implementations of symmetric encryption algorithms. Seconds, we study the performance of various symmetric encryption algorithms on a Contiki-based IoT device. This paper provides encryption and decryption durations and energy consumption results on three implementations of AES: TinyAES, B-Con’s AES, and Contiki’s own built-in AES. In …