Thesis/Project Final Defense Schedule
Join us as the School of STEM master’s degree candidates present their culminating thesis and project work. The schedule is updated throughout the quarter, check back for new defenses.
View previous quarter schedules
Select a master’s program to navigate to candidates:
Master of Science in Computer Science & Software Engineering
SUMMER 2024
Wednesday, July 24
TASNIM BASHAR
Chair: Dr. Clark Olson
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Tasnim Bashar’s Online Defense
Project: Enhancing Image Inpainting with a Novel Deep Learning Fusion
Image inpainting, the art of seamlessly filling missing or damaged parts of an image, has seen remarkable progress with deep learning. However, achieving consistently high-quality restorations across diverse image content remains a challenge. This project presents a novel image inpainting framework that harnesses the strengths of partial convolutions, Generative Adversarial Networks, and self-attention mechanisms. Our approach utilizes partial convolutions to effectively address irregular holes and preserve intricate image details. A Generative Adversarial Network architecture is incorporated to encourage the generation of realistic and visually plausible image content. Furthermore, integrating self-attention enables the model to capture long-range dependencies and contextual information within the image, leading to more coherent and higher-quality reconstructions. Evaluations using established image quality metrics demonstrate that our framework achieves superior performance compared to existing state-of-the-art methods, confirming the effectiveness of this innovative fusion in significantly enhancing image quality and restoration precision.
GREESHMA SREE PARIMI
Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Greeshma Sree Parimi’s Online Defense
Project: Enhancing Collaborative Language Analysis and Study in MeTILDA
The “Global Predictors of Language Endangerment and the Future of Linguistic Diversity” study predicts that over 1500 languages will become extinct by 2100. Blackfoot is one such endangered language majorly used in the regions of Alberta in Canada and Montana in the U.S.A. Blackfoot is a pitch accent language where the meaning of a word varies depending on the pitch used when speaking it. So, it is very challenging to document and teach the language. To address this, researchers from the University of Washington Bothell (UW) and the University of Montana (UM) have collaborated on an interdisciplinary project named MeTILDA (Melodic Transcription in Language Documentation and Application). It is a cloud-based system that analyzes the pronunciation of individual Blackfoot words, generates Pitch Art, and assists in documenting, teaching, and learning Blackfoot.
This capstone project primarily aims to enhance the MeTILDA application’s analysis, collaboration, and security features. To improve analytical capabilities, we developed the Pitch Art Version Control System, allowing users to work on and save multiple versions of the same Pitch Art. For improved collaboration, we integrated a communication mode within the application, enabling users to interact with both MeTILDA and non-MeTILDA users. To strengthen security, we implemented role-based access control for all features of the MeTILDA application and introduced email verification for new user registrations. Furthermore, substantial improvements were made to the project documentation, particularly in the areas of front-end components and database information.
HARPREET KOUR
Chair: Dr. Wooyoung Kim
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Harpreet Kour’s Online Defense
Project: Predictive Modelling of Substance Abuse: Analysing Key Features with Machine Learning
Substance abuse remains a critical public health challenge with multifaceted implications for individuals, families, and communities worldwide. This project explores how machine learning techniques can predict and classify substance abuse behaviours, focusing on alcohol, tobacco, marijuana, and nicotine vaping. Leveraging data from the (2021-2022) Behavioural Risk Factor Surveillance System (BRFSS) in 2023, we aim to identify the key predictors of substance abuse and groups at higher risk, taking into account factors like adverse childhood experiences, financial conditions, and mental health status.
Prediction models were developed using four types of machine learning algorithms, including Linear Models (Logistic Regression & SVM), Tree based Models (Random Forest, XGBoost & ADABoost), Neural Networks (MLP & CNN) and Clustering algorithm. Respondents were randomly divided into training and testing samples. The performance of all the models was compared using accuracy, precision, recall, AUC and false positive rate. The study included 31060 respondents of whom, 5867 (19%) were found to be substance abusers. Of the respondents who reported substance abuse 62.93% were between the ages of 18-64, 60.61% were males and 84.76% were non-Hispanic Whites. Random Forest was the best performing model with AUC 0.86, followed by XGBoost (AUC 0.85). The most important factors for substance abuse were BMI, male sex, lower income levels, young adult age group, lower education levels, poor mental health and adverse childhood experiences. Data mining methods were useful in examining patterns across demographics, health conditions and lifestyle behaviours so as to understand the co-morbidities associated with substance abuse.
Another goal of this project was to highlight the importance of collaboration between domain experts and machine learning practitioners and assess the impact it has on the results compared to when domain experts are not involved. Their contributions in feature selection and data interpretability solutions were instrumental in achieving this enhancement. We prioritised model interpretability to foster trust and refine understanding. Additionally, our project introduces a novel approach to interpretability, analysing misclassified data, offering insights into substance abuse dynamics. These results can be used to generate further hypotheses for research, increase public awareness and help provide targeted substance abuse education.
Friday, July 26
JEFFREY MCCREA
Chair: Dr. Munehiro Fukuda
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Jeffrey McCrea’s Online Defense
Project: Enhancement of Agent Performance with Q-Learning
Graphs store data from various domains, including social networks, biological networks, transportation systems, and computer networks. As these graphs grow in size and complexity, single-machine solutions become impractical due to limitations in computational resources. Distributed graph computing addresses these challenges by leveraging multiple machines to process and analyze large-scale graphs collaboratively.
This capstone project investigates the enhancement of distributed graph computing performance in the Multi-Agent Spatial Simulation (MASS) library by integrating Q-learning for computing shortest path, closeness centrality, and betweenness centrality on distributed large-scale dynamic graphs. This approach is compared to traditional and agent-based graph computing algorithms. Previous approaches in the MASS framework relied on large populations of unintelligent agents to exhaustively traverse graphs to compute solutions, making them inefficient when faced with dynamic graph data. By leveraging Q-learning and the distributed agent-based graph capabilities of MASS, we aim to optimize the decision-making processes of distributed agents, thus improving computational efficiency and accuracy.
Experimental results demonstrate that the adaptive learning mechanism of Q-learning, coupled with the MASS library, allows agents to dynamically adjust to changing graph structures, leading to a more robust and scalable distributed graph computing solution. This research contributes to the field of distributed systems and artificial intelligence by providing an innovative approach to enhancing multi-agent intelligence for graph computing tasks.
Monday, July 29
SAURAV JAYAKUMAR
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Saurav Jayakumar’s Online Defense
Thesis: GraphConv: Geometric Deep Learning for Multiple Conformation Generation from Electron Density Images
In the realm of cryo-electron microscopy (cryo-EM) structural analysis, the precise prediction of molecular conformations within datasets stands as a fundamental endeavor. Despite strides made in deep learning methodologies, existing solutions often yield volumes of suboptimal quality. Addressing this critical limitation, our research introduces GraphConv, an innovative encoder model designed to embed particle images into a latent space, thereby supplanting the conventional encoder utilized by CryoDRGN. This novel approach employs a Graph Neural Network (GNN) architecture featuring multiple GraphConv and Convolutional layers, aimed at capturing richer information from particle images and faithfully reconstructing corresponding 3D volumes. Rigorous testing across two authentic datasets and three simulated datasets underscores the efficacy of our model, showcasing marked enhancements in reconstruction quality. Notably, our findings reveal enhancements in resolution by up to 20\% compared to CryoDRGN. By harnessing the power of GNNs, our methodology heralds significant advancements in the fidelity and accuracy of output volumes, thereby contributing to the ongoing refinement of cryo-EM structural analysis methodologies.
Tuesday, July 30
SUGAM JAISWAL
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Sugam Jaiswal’s Online Defense
Thesis: Development of Personality Adaptive Conversational AI For Mental Health Therapy Using LLMs
Many individuals with mental health issues cannot get access to professional help due to reasons such as lack of awareness, limited availability, and high costs. Conversational agents present a viable alternative to deliver mental health support that is accessible, affordable, and scalable. However, the effectiveness of these agents can vary among users, as different users have different personality types such as extroversion, agreeability, etc. which influence how users interact with chatbots. Therefore, it is important to develop therapy chatbots that adapt to individual personalities. In this study, we highlight the significant role of Personality Adaptive Conversational Agents (PACAs) in mental healthcare. We designed an architecture around traditional ML models and open-source LLMs to build a PACA for mental health (based on the existing iCare project). We built a functional prototype based on it and conducted a user study, which concluded that personality adaptability is a critical feature for mental health chatbots.
During this research, we were able to build a personality classifier that achieved an average F1-score of 0.96 across the Big Five personality dimensions – Agreeableness, Extraversion, Openness, Conscientiousness, and Neuroticism, and successfully integrated that with an open-source LLM to generate adapted responses. The remote user study demonstrated that 95% of the test users found the responses from the adaptive chatbot relevant to their situation compared to 30% for the non-adaptive chatbot, and 55% of users agreed that the responses felt suited according to their personality as opposed to 15% for the non-adaptive chatbot. With this study, we have shown that it is feasible to create free, accessible, and personalized mental healthcare solutions and that the adoption of PACAs could represent a pivotal step toward making mental healthcare more personalized and widely available.
ANI AVETIAN
Chair: Dr. Annuska Zolyomi
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Ani Avetian’s Online Defense
Project: The Views Application: Introducing Augmented Reality into Travel Applications
The travel and tourism industry is growing worldwide and experiencing a resurgence following the COVID-19 global pandemic travel restrictions. When people travel to unfamiliar places, they need to orient themselves to their surroundings, find their way around, and gain information about the local culture. Traditional travel applications, like websites and smartphone apps, are for arranging travel and providing information. However, the information and services provided by websites and apps are presented out-of-context with the real-world surroundings of the traveler. Emerging technology, specifically, Augmented Reality (AR), presents an opportunity to enhance the traveler’s experience with real-time information that is easy to access and contextually relevant.
Here we introduce a novel AR travel application called “Views.” This app uses image detection to allow users to easily learn about the landmarks they visit. Once detection is complete, users will have an AR environment where they can interact with their surroundings. A fact will be displayed in AR with the help of Artificial Intelligence (AI) working in the background. This provides an experience that a user can effortlessly incorporate into their travel plans and activities. Additionally, this project entailed identifying potential cybersecurity risks that come with these kinds of applications and developing a potential solution to them. We looked at attacks of clickjacking in AR environments and developed a solution to combat these attacks with image detection. As we envision a future where wearable devices may become the norm, applications like this will be at the forefront of these innovations. Using this application as a stepping stone, we begin to understand the important aspects of AR travel user experience and implementation approaches to build usable and secure AR features.
Thursday, August 1
HARIKA CHADALAVADA
Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Harika Chadalavada’s Online Defense
Project: I’poyít – Blackfoot Language Learning Application
The Blackfoot language, a vital part of the cultural heritage of the Blackfoot tribes of the Great Plains in North America, is facing imminent risk of extinction with only about 3,000 fluent speakers remaining. This paper details the development of an application aimed at revitalizing the Blackfoot language by leveraging modern technology to make learning accessible and engaging. The application was developed using the versatile Flutter framework, ensuring seamless cross-platform compatibility.
The primary goal of this application was to build a comprehensive solution that addresses and fills the gaps identified in existing Blackfoot language learning applications and provides a more effective and engaging learning experience. To achieve this goal, the application features distinct student and admin login interfaces, with Firebase serving as the backend to manage user data and interactions efficiently. The application provides a comprehensive suite of interactive learning modules that include vocabulary exercises with flashcards and audio pronunciation guides, along with phrase modules that facilitate practical language use in everyday contexts. To enhance the learning experience, the application incorporates gamified elements such as experience points, badges for progress, and quizzes that test and reinforce language skills. A leaderboard and a discussion forum are integrated to foster a community of learners who motivate each other through shared achievements and discussions. Significantly, the content within the application is curated by a linguistics expert known for her extensive research in Blackfoot phonology to ensure that the educational material is authentic and culturally resonant. This project not only offers a practical solution to the preservation of the Blackfoot language but also serves as a model for preserving other endangered languages, ultimately demonstrating how digital technology can be harnessed to safeguard linguistic diversity.
ARSHEYA RAJ
Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Arsheya Raj’s Online Defense
Thesis: NeuroGaming: Innovative Rehabilitation for Upper Limb Neurologic Conditions Using Mixed-Reality Simulation Games and EEG/EMG Biofeedback
Recent advances in Augmented Reality (AR), Mixed Reality (MR), Electroencephalogram (EEG), and Electromyogram (EMG) offer significant opportunities in medicine and neuroscience. This research aims to use these technologies to aid stroke patients with upper limb extremity weakness. This work extends the Edge Computing Ecosystem for Neuroscience Patients’ Rehabilitation, part of the ‘Stroke Rehabilitation Project’ by University of Washington Bothell Engineering, University of Washington Seattle Neuroscience, and Rehabilitation Medicine at Harborview Medical Center (UWHM). Recently, UW Bothell’s CSSE has also contributed, focusing on solutions for stroke patient rehabilitation. Traditional motor rehabilitation is costly, resource intensive and often monotonous, reducing patient engagement. We introduce “NeuroGaming”, an interactive approach engaging elements of AR / MR games that can enhance rehabilitation programs and improve patient outcomes. Using augmented and mixed reality technologies, interactive environments can be created on mobile devices, providing engaging and motivating experiences for patients. AR simulates real-world scenarios, offering a safe and fun way to practice tasks and aid in
rehabilitation.
We used EEG and EMG sensors to conduct experiments and to collect data in a controlled environment targeting a reduced set of representative relevant motor tasks. The data were processed using various signal processing and statistical techniques, which in combination with the MR / AR game can be used to build a novel feedback and guidance system. This system is a building block of our “NeuroRehab” ecosystem, which will use various ML models and algorithms for sequential prediction, with the aim of guiding patients through an optimal rehabilitation path within the game environment.
Results showed that the combination of Frequency Filtering, ICA, and ERP with FNN and SVM models yield, so far, the best accuracy for classifying the motor tasks in EEG and EMG data. These findings contribute to the field of stroke rehabilitation of upper limb extremity weakness. It also contributes to a larger project that aims for better understanding and rehabilitation of other neurological ailments by offering insights to different hand gestures using EMG, and EEG data, and creating a framework for data processing, and feedback systems.
Friday, August 2
NOURA ALROOMI
Chair: Dr. Afra Mashhadi
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Noura Alroomi’s Online Defense
Project: Automated Expansion of Sketch Datasets
Free-hand sketches offer a unique reflection of human perception and creativity, playing a crucial role in various computer vision and machine learning applications. These sketches are used in image and sketch recognition algorithms, sketch-based retrieval systems, and generative art neural networks, enhancing our understanding of artistic expression. However, the limited variety of object categories in existing sketch datasets restricts their applications and the development of robust machine-learning models. This limitation is primarily due to the manual curation required for these datasets, which is time-consuming and slows the addition of new sketches. Automated systems using advanced computer vision techniques present a solution to enhance the diversity and quality of sketch datasets efficiently.
In this capstone project, we introduce an Automated Dataset Expansion System designed to streamline and automate the process of adding new categories to sketch datasets. Our system employs a web-based platform that integrates user-generated sketches with an advanced auto-expansion pipeline. This pipeline consists of two phases: the first phase involves synthetically generating baseline sketches from photos using a pre-trained Photo-Sketching model, effectively capturing the structural attributes of simpler objects. The second phase evaluates the similarity of user-generated sketches to these baselines using both Structural Similarity Index Measure (SSIM)-based and Convolutional Neural Network (CNN)-based encoder similarity metric pipelines. Our findings indicate that the CNN-based encoder with the Cosine Similarity measure provides consistent and reliable performance across categories, achieving the highest precision and true positive rates. This reliable method was subsequently implemented in our system. The enriched datasets produced by this system can support innovative machine learning and computer vision applications, fostering advancements in these fields.
Monday, August 5
AISHWARYA PANI
Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Aishwarya Pani’s Online Defense
Project: I’poyít – Platform for Learning Blackfoot Language
Preserving endangered languages is essential for maintaining cultural identity. Blackfoot is categorized as endangered, with nearly 2,900 speakers remaining. Existing solutions for preserving Blackfoot lack engagement, accessibility, community learning, and gamified experiences. To address this, we developed “I’poyít – Blackfoot Language Learning Application,” a cross-platform app designed to facilitate learning and preservation. In collaboration with the University of Montana, the application features content from researchers and linguists.
The primary objective of our development was to establish a codebase that is both maintainable and robust. This culturally sensitive and interactive application utilizes the Flutter framework for cross-platform compatibility and Firebase for backend services, which provide real-time updates and data storage. State management was handled using Riverpod, ensuring optimization across the application. This approach led to enhanced performance by decoupling UI components from business logic. Loading performance was optimized through asynchronous programming, ensuring minimal delays and seamless navigation. The real-time database capabilities of Firebase provided instant synchronization and updating of user data. Flutter’s integration with Firebase enabled users to upload audio files, which were then instantly accessible to all users. The features were designed to be easily extendable, allowing new functionality to be added with minimal changes to existing code.
The key features of the application include vocabulary flashcards, a phrases learning module with audio translations from native speakers, and customizable quizzes with detailed visual analytics to provide an immersive experience. Gamified elements, such as XP points, a leaderboard, and a robust notification system, ensure daily study engagement. User profile management and discussion forums stimulate community engagement. A content management system was designed for efficient phrase management, batch uploading, and fault-tolerant multimedia integration. “I’poyít” demonstrates the potential for cross-platform accessibility to improve language learning and preserve the Blackfoot language. By combining modern technology with cultural insights, the application offers an engaging and effective learning experience, highlighting the potential for similar solutions to support other endangered languages.
GNANA SANJANA KILLI
Chair: Dr. Min Chen
Candidate: Master of Science in Computer Science & Software Engineering
5:45 P.M.; Join Gnana Sanjana Killi’s Online Defense
Project: Facilitating Endangered Language Revitalization: An E-Learning Platform for Blackfoot
The preservation and revitalization of endangered languages are crucial for maintaining cultural diversity and heritage. This project introduces an innovative e-learning platform specifically designed for the revitalization of endangered languages, with a particular focus on the Blackfoot language, which is currently at risk of extinction. The platform aims to engage indigenous communities, educators specializing in language revitalization, and linguists through interactive language learning facilitated by a user-centric design.
The development of the platform was driven by the need for accessible, engaging, and pedagogically sound language learning tools that overcome the limitations of traditional methods. Key features of the platform include secure account creation and management, seamless access to courses, lessons, and assignments, an intuitive and adaptive user interface for various devices, developed using React.js, and robust data management capabilities using SQL databases ensuring the security and integrity of user data. The system’s architecture supports multimedia content managed through AWS, accommodating diverse teaching methods that appeal to different learning styles.
Throughout its development, the platform has evolved through continuous stakeholder feedback, leading to significant enhancements such as updated administrative controls for user management, enhanced security measures, and enriched interactive content. This adaptive approach has significantly improved the platform’s effectiveness. Future enhancements will focus on expanding the range of languages offered, integrating adaptive learning technologies, and enhancing peer-to-peer interaction features. This project not only contributes to the field of language revitalization but also serves as a significant model for the further development of educational technologies that respect and promote cultural heritage.
Tuesday, August 6
SONAL YADAV
Chair: Dr. Afra Mashhadi
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Sonal Yadav’s Online Defense
Project: Clustered Federated Learning for Next-Point Prediction in Mobility Datasets
Individual trajectories vary significantly, making the task of next-point prediction challenging due to privacy concerns and potential convergence issues in machine learning models. To address these challenges, I added functionality to the Inflorescence framework, developed by Professor Mashhadi’s Lab, enabling trajectory datasets to leverage clustered federated learning (CFL) strategies. This project evaluates the performance of CFL on state-of-the-art mobility datasets, GeoLife and MDC, demonstrating its robustness compared to traditional federated learning. Additionally, the study analyzes which types of clients benefit the most from CFL, finding that high-entropy clients, characterized by more non-identical and random datasets, experience the greatest advantages. This enhanced functionality is now part of the open Python package Inflorescence, which extends Flower.
JOSHUA MEDVINSKY
Chair: Dr. Marc Dupuis
Candidate: Master of Science in Computer Science & Software Engineering
3:30 P.M.; Join Joshua Medvinsky’s Online Defense
Project: Exploring the Influence of Human Factors on the Effective Utilization of Password Managers
In today’s digital realm, password managers are important tools for securely managing login credentials. Amidst an array of options like LastPass, RoboForm, Dashlane, 1Password, and Bitwarden, these tools not only handle online account credentials but also extend their utility to desktop application credentials.
But despite their proven effectiveness, users rarely use password managers, which raises questions about online security given the growing threat of password attacks. This capstone project proposes an exploration into the impact of user education on enhancing the adept utilization of password managers. By addressing this challenge, the aim is to uplift security practices and bridge existing gaps in cybersecurity knowledge.
Through an extensive literature review, the project identifies a notable research gap regarding the influence of targeted user education on password manager effectiveness. By exploring user motivations and concerns, this study seeks to contribute valuable insights to the cybersecurity field.
The project’s methodology entails in-person interviews with students from the University of Washington Bothell, dividing them into groups receiving user education and a control group. Data collection suggests that targeted education may significantly enhance password manager adoption and usage.
This project shows significant improvements among participants who receive targeted education. It emphasizes the critical role of organizations in making sure their users have a good understanding of password manager benefits with practical application, which improves cybersecurity measures and mitigates data breach risks. Moving forward, the project aims to highlight the importance of exploring long-term educational intervention effects and scalability within organizational contexts to improve cybersecurity defenses effectively.
Thursday, August 8
SUNJIL GAHATRAJ
Chair: Dr. Erika Parsons
Candidate: Master of Science in Computer Science & Software Engineering
8:45 A.M.; Join Sunjil Gahatraj’s Online Defense
Thesis: Enhancing Neurological Rehabilitation: Combining Gaming, Robotics and Machine Learning in an Edge Computing Environment
Recent advancements in Electroencephalography (EEG) technology has made it more accessible, opening new avenues for collecting and studying EEG data. In the context of neurological rehabilitation, it enables us to develop new strategies to enhance this experience for patients recovering from conditions such as stroke, spine surgery and nerve damage. On the other hand, the continued evolution of hardware and rapid onset of High Performance
Computing (HPC) has allowed for smaller devices to become more computationally powerful, making Edge Computing (EC) environments ubiquitous and suitable for many applications.
The goal of this research is to explore the combined use of Computer Vision (CV), Gaming, Machine Learning (ML) and robotics technologies to develop improved rehabilitation approaches for neurology patients. Specifically, our target is the gamification of some aspects of this area of rehabilitation to make it more engaging to help patients achieve their goals. Our approach is to investigate the feasibility of this strategy by studying EEG data collected
from healthy subjects to analyse brain signals associated with specific hand movements. The EEG data is then processed and ML models are used to predict these hand movements, which then can be used to guide a Raspberry Pi robot. In addition, a camera is used to supervise hand gestures. In the future, together with medical expert input, these experiments can help train such a robot to follow optimal paths based on patient hand exercises. In our experiments, we used a reduced set of hand movements and healthy subjects to serve as a proxy to real patients. Initial results using CNN and FNN models are encouraging, showing high precision and accuracy in predicting hand movements, indicating that our research serves as a proof of concept and continued exploration is justifiable.
This research is a novel work carried out as an interdisciplinary collaboration between computer science, engineering, neuroscience involving the Computing and Software Systems (CSS) division at the University of Washington Bothell collaborated with the University of Washington Seattle Neuroscience and Rehabilitation Medicine at Harborview Medical Center (UWHM).
HONGYANG LIU
Chair: Dr. Kelvin Sung
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Hongyang Liu’s Online Defense
Thesis: A Comprehensive Categorization Framework for Interactive Fiction Games
Interactive Fiction (IF) games are digital experiences that merge storytelling with interactive gameplay, allowing players to navigate and influence story-driven adventures. These games have evolved significantly, integrating advanced visual and interactive elements alongside traditional textual narratives, making them an intriguing area of study. However, currently, there are few structured frameworks designed for the systemic classification of IF games and it can be challenging to analyze these games wholistically.
This thesis presents a comprehensive categorization framework for IF games, designed to facilitate systematic classification and analysis. Based on features derived from a human-computer interface, story genre, game mechanics, and business model, the framework supports the classification of IF games into distinct categories. This structured approach allows feature-based examination and facilitates the holistic analysis of IF games and their evolution.
Validation for the proposed framework involved three rounds of sampling and categorizing IF games. The first round sampled popular IF games developed based on well-established game engines to demonstrate the fundamental robustness of the framework. The second round sampled popular IF games over time for insights into potential trends as IF games continue to develop and evolve. The third round was based on popular IF game series and traditional action-adventure series to examine potential similarities between the two genres.
The three rounds of sampling and categorizing reveal potential patterns and trends that enhance our understanding of IF games. Key findings include the trend from text-only to image-based or even animation-based, the trend from single-defined endings to multiple-defined endings, the trend from no or little towards more sophisticated support for stats and resource management, and the potential overlapping and merging of IF and action-adventure games.
These findings demonstrate that the proposed framework is an effective tool for systematic analysis that can offer valuable insights into the development and trends of IF games. Since classification involves subjectivity, future work should repeat the process based on stakeholders with distinct backgrounds, e.g., publishers, developers, and gamers. Additionally, the proposed framework is but a first step and should be continuously reviewed and refined.
ESHA GAVALI
Chair: Dr. Dong Si
Candidate: Master of Science in Computer Science & Software Engineering
1:15 P.M.; Join Esha Gavali’s Online Defense
Thesis: Enhancing the Performance of GNN and Utilizing 3D Instance Segmentation for Ligand Binding Site Prediction
This study addresses the challenge of accurately predicting ligand binding sites (LBS) on proteins, a critical aspect of structure-based drug design. Ligand binding site prediction is crucial for designing effective drugs and understanding protein functions, benefiting pharmaceutical companies, biotechnologists, and researchers by accelerating drug discovery and improving therapeutic interventions. We employ and improve Graph Neural Networks (GNNs) and innovative 3D point cloud instance segmentation to refine and advance LBS prediction methods. This research demonstrates significant enhancements in predictive accuracy by evaluating these methods on widely used datasets. Our novel clustering algorithm, which combines density-based and fuzzy clustering, notably improves the definition and identification of ligand binding sites without prior knowledge of the number of clusters. This methodology allows for more precise predictions, effectively managing binding sites’ overlapping nature. Implementing instance segmentation further delineates individual binding pockets, offering a more granular understanding of ligand-protein interactions. The results illustrate that our approaches meet the current state-of-the-art for ligand binding site prediction and support their potential utility in real-world pharmaceutical applications. Future work will focus on refining these methods and extending their application to molecular docking studies.
Friday, August 9
KARAN BHATT
Chair: Dr. Marc Dupuis
Candidate: Master of Science in Computer Science & Software Engineering
11:00 A.M.; Join Karan Bhatt’s Online Defense
Project: Privacy Concerns and User Perception in Targeted Digital Advertising: A Survey Project
This study investigates the relationship between users’ perceptions of privacy control and transparency in data usage practices and their subsequent trust and acceptance of targeted advertising. The purpose of this research is to understand how perceived control over personal data and transparency in data usage influence user trust and acceptance of targeted ads, thereby aiding in the design of more user-friendly and trustworthy advertising strategies. Utilizing an extensive literature review and a comprehensive survey, data were collected on users’ awareness of data collection practices, perceived control over personal data, trust in advertisers, and acceptance of targeted advertisements. Additional questions addressed concerns regarding data privacy, the effectiveness of privacy-enhancing technologies, and user preferences for regulatory measures. The primary hypothesis posits that users’ perception of control over their data significantly influences their acceptance and trust in targeted digital advertising, while the secondary hypothesis examines how transparency in data usage and collection practices affects users’ trust and comfort with targeted advertising. The survey results highlight critical factors influencing user acceptance and trust in targeted advertising. The findings of this study contribute to the body of knowledge on digital marketing and privacy, offering practical recommendations for advertisers on designing more user-friendly and trustworthy advertising strategies. By understanding the importance of perceived control and transparency, advertisers can improve their practices to better align with user expectations, thereby enhancing the overall effectiveness and acceptance of targeted advertising.
Master of Science in Cybersecurity Engineering
SUMMER 2024
Monday, August 5
KRISHNA PAUDEL
Chair: Dr. Brent Lagesse
Candidate: Master of Science in Cybersecurity Engineering
8:45 A.M.; Join Krishna Paudel’s Online Defense
Project: MalBuster: An Integrated Approach to Securing Systems through Port Monitoring and Malware Detection
The importance of computer security in today’s digital world cannot be overstated. As cyber threats become more sophisticated and widespread, strong security measures are essential to protect information and ensure smooth operations. This is where traditional anti-malware solutions come in, but our approach takes a different route through the continuous monitoring of network ports for any signs of malicious activity. While most malware scanners merely examine files, MalBuster does its work by detecting malware that tries to communicate with external systems by monitoring system ports in real time and identifying suspicious processes.
MalBuster works by continuously watching local machine’s network ports for inbound and outbound connections, capturing data packets in real-time, linking them to the corresponding processes and classifying the processes using both static and predictive malware analysis techniques. The tool also features a user interface where users can access the generated reports and act on suspected malware. The tool is implemented using various python libraries to perform static and predictive ML analysis on the processes. The data for analysis and testing were collected from real network traffic, malware sample repositories, and normal software applications. Benchmarking various KPIs, our results show that MalBuster is effective at detecting threats accurately, processing data quickly, and using minimal system resources across various test scenarios. These results underline its capabilities in providing proactive detection of threats and mitigation, improving the accuracy and reliability of current security measures. There is scope for improvement through further research to fine-tune the algorithms and expand MalBuster’s capabilities, ensuring even better threat detection and protection.
ANURODH ACHARYA
Chair: Dr. Marc Dupuis
Candidate: Master of Science in Cybersecurity Engineering
3:30 P.M.; Join Anurodh Acharya’s Online Defense
Project: Examining the Interplay of Psychological Factors in Remote Workers’ Cybersecurity Practices
This research examines the interplay of psychological factors that are influencing cybersecurity practices of remote workers focusing on how perceived severity, perceived vulnerability, self-efficacy, response efficacy, and response cost can impact both protection intention and protection behavior. A survey conducted with a diverse sample of remote workers showed that perceived severity and perceived vulnerability significantly enhance the protection intentions which in turn strongly predict the protection behaviours. Self-efficacy and response efficacy positively influence protection intentions while perceived response cost impacts protection intention but not the actual protective behaviours.
This study also identifies common cybersecurity challenges including network and device security and highlights prevalent issues such as malware attacks and data breaches. Survey participants showed a high level of caution in dealing with suspicious emails, often opting for verification and reporting to the IT departments. Emotional responses to the cybersecurity roles also varied with many of the respondents feeling either positive or neutral showing a general sense of awareness and responsibility. The findings also highlight the important role that psychological factors play in shaping cybersecurity behaviours among the remote workers and further suggest that targeted intervention can greatly improve the cybersecurity practices in remote work environments.
Wednesday, August 7
GAUTAM KUMAR
Chair: Dr. Brent Lagesse
Candidate: Master of Science in Cybersecurity Engineering
8:45 A.M.; Join Gautam Kumar’s Online Defense
Project: Foodereum: Revolutionizing Food Supply Chains with Blockchain Authentication
Blockchain technology has the potential to revolutionize supply chain management by enhancing transparency, traceability, and security. The proposed work suggests adopting a private Ethereum-based blockchain system to record, track, and verify food products throughout the supply chain. The immutability of blockchain ensures that transactions cannot be altered or concealed, as they are recorded in a distributed ledger accessible to all authorized parties. This transparency allows receivers to access the entire history of a product on the blockchain network, improving food quality and safety. By implementing this blockchain-based solution, the food industry aims to increase consumer appeal and overcome challenges such as centralized systems, third-party involvement, high costs, food waste due to spoilage and contamination, lack of accountability, and communication gaps between supply chain partners.
However, the system faces security threats like cross-site scripting (XSS) attacks, sensitive information exposure, and hardcoded credentials. To mitigate these risks, the project incorporates robust input validation, output encoding, secure storage, and strong authentication mechanisms, including two-factor authentication and strong password policies. Regular security audits, penetration testing, and software updates are also implemented to identify and address vulnerabilities. These security enhancements, combined with blockchain’s inherent benefits, create a more robust and trustworthy system for food supply chain management, increasing transparency, and efficiency, and providing a significantly more secure environment for all stakeholders involved in the food supply chain by increasing consumer appeal and overcoming challenges such as centralized systems, third-party involvement, high costs, food waste, lack of accountability, and communication gaps between supply chain partners.
MANUEL M. DUARTE
Chair: Professor Mark Kochanski
Candidate: Master of Science in Cybersecurity Engineering
1:15 P.M.; Join Manuel M. Duarte’s Online Defense
Project: Analysis of Enhancing Security Measures in Docker Containers: A Threat Model Approach
This project aims to explore new mitigation strategies and understand the risks
associated with deploying Docker as an architectural solution. We researched various security
issues with Docker container images and reviewed Docker’s architecture and its application
usage. In addition to this analysis, we investigated industry best practices to understand
what can mitigate these threats effectively. We created a Threat Model specifically for
Docker Components and analyzed threats using STRIDE analysis.
Based on our findings, we present a few recommendations for enhancing the secure use of
Docker in application deployment, i.e. when using Docker Hub, always use a security scanner
tool before deploying any images and disable unused services on a Dockerfile; we mention
other good security practices that should be applied in the early stages of development.
Our future work will involve further experiments focusing on using ML real-time anomaly
detection algorithms such as support vector machine (SVM) and Isolation Forrest to detect
vulnerabilities early on, in SSL protocols and other attacks to root access. Also, using
machine learning to improving certificate management. Continued research in this area is
essential to deepen our understanding of Docker container security and to develop robust
defenses against emerging threats.
Keywords: Docker, Dockerfile, Anomaly detection, Encryption STRIDE, DREAD.