Computer Sciences Commons^™

Beyond Accuracy In Machine Learning., Aneseh Alvanpour

Electronic Theses and Dissertations

Machine Learning (ML) algorithms are widely used in our daily lives. The need to increase the accuracy of ML models has led to building increasingly powerful and complex algorithms known as black-box models which do not provide any explanations about the reasons behind their output. On the other hand, there are white-box ML models which are inherently interpretable while having lower accuracy compared to black-box models. To have a productive and practical algorithmic decision system, precise predictions may not be sufficient. The system may need to have transparency and be able to provide explanations, especially in applications with safety-critical contexts …

Modeling And Debiasing Feedback Loops In Collaborative Filtering Recommender Systems., Sami Khenissi

Electronic Theses and Dissertations

Artificial Intelligence (AI)-driven recommender systems have been gaining increasing ubiquity and influence in our daily lives, especially during time spent online on the World Wide Web or smart devices. The influence of recommender systems on who and what we can find and discover, our choices, and our behavior, has thus never been more concrete. AI can now predict and anticipate, with varying degrees of accuracy, the news article we will read, the music we will listen to, the movies we will watch, the transactions we will make, the restaurants we will eat in, the online courses we will be interested …

Balancing Data- Vs. Art-Driven Decisions In Video Game Design, Jaden D. Goter

Honors Program: Senior Projects (Public)

Video games, like software, need to be designed. Video game development studios tend to use data-driven or art-driven decision-making to design their games. Data-driven decision-making is where active and passive data is collected in order to make informed decisions about the design of a game. Art-driven decision-making is when designers use their artistic intuition to design games, potentially ignoring player data. This paper elaborates on the advantages and disadvantages of both approaches and provides case studies of games designed under both approaches. Based on these studies, for a game to be successful, a combined approach of data- and art-driven decision-making …

Hci Education And Ux Practice: Highlights From Singapore, Tamas Makany, Dharani Perera-Schulz

Research Collection Lee Kong Chian School Of Business

This position paper highlights trends in education, practice, and support of HCI/UX in Singapore, a small city-state island in Southeast Asia. The paper was prepared for the 2022 Southeast Asia Computer-Human Interaction (SEACHI'22) virtual workshop on Apr 14, 2022, as part of the ACM CHI Conference on Human Factors in Computing Systems (CHI'22) international conference.

A Machine Learning Approach To Stochastic Optimal Control, Pablo Ever Avalos

Open Access Theses & Dissertations

Merton's portfolio optimization problem is a well-renowned problem in financial mathematics which seeks to optimize the investment decision for an investor. In the simplest situation, the market consists of a risk-less asset (i.e. a bond) that pays back a relatively low interest rate, and a risky asset (i.e. a stock) that follows a geometric Brownian motion. The optimal allocation strategy of the investor's wealth is found by optimizing the expected utility along the stochastic evolution of the market. This thesis focuses on several different applications of this optimization problem. We look at pre-constructed analytical solutions and showcase the results. We …

Transparscit: A Transformer-Based Citation Parser Trained On Large-Scale Synthesized Data, Md Sami Uddin

Computer Science Theses & Dissertations

Accurately parsing citation strings is key to automatically building large-scale citation graphs, so a robust citation parser is an essential module in academic search engines. One limitation of the state-of-the-art models (such as ParsCit and Neural-ParsCit) is the lack of a large-scale training corpus. Manually annotating hundreds of thousands of citation strings is laborious and time-consuming. This thesis presents a novel transformer-based citation parser by leveraging the GIANT dataset, consisting of 1 billion synthesized citation strings covering over 1500 citation styles. As opposed to handcrafted features, our model benefits from word embeddings and character-based embeddings by combining the bidirectional long …

Material Synthesis And Machine Learning For Additive Manufacturing, Jaime Eduardo Regis

Open Access Theses & Dissertations

The goal of this research was to address three key challenges in additive manufacturing (AM), the need for feedstock material, minimal end-use fabrication from lack of functionality in commercially available materials, and the need for qualification and property prediction in printed structures. The near ultraviolet-light assisted green reduction of graphene oxide through L-ascorbic acid was studied with to address the issue of low part strength in additively manufactured parts by providing a functional filler that can strengthen the polymer matrix. The synthesis of self-healing epoxy vitrimers was done to adapt high strength materials with recyclable properties for compatibility with AM …

Verification In Generalizations Of The 2-Handed Assembly Model, David Caballero

Theses and Dissertations

Algorithmic Self Assembly is a well studied field in theoretical computer science motivated by the analogous real world phenomenon of DNA self assembly, as well as the emergence of nanoscale technology. Abstract mathematical models of self assembly such as the Two Handed Assembly model (2HAM) allow us to formally study the computational capabilities of self assembly. The 2HAM is one of the most thoroughly studied models of self assembly, and thus in this paper we study generalizations of this model. The Staged Tile Assembly model captures the behavior of being able to separate assembly processes and …

Engaging Students During Research Through The Use Of Games, Francisco Gonzalez

Theses and Dissertations

Engaging students during a research seminar/meeting can be a difficult challenge, and as as student myself, I can attest to how difficult actively listening to a presentation can be. As such, upon researching more ways to have an audience engaged, one of the most promising concepts is the use of games. Games, in any form, can be very engaging to a person, and even more so if there is active engagement and participation within an audience group. With this concept in mind, I decided to take it upon myself to create a game based around a theoretical computer …

Hardware Isolation Approach To Securely Use Untrusted Gpus In Cloud Environments For Machine Learning, Lucas D. Hall

Theses and Dissertations

Machine Learning (ML) is now a primary method for getting useful information out of the immense volumes of data being generated and stored in society today. Useful data is a commodity for training ML models and those that need data for training are often not the owners of the data leading to a desire to use cloud-based services. Deep learning algorithms are best suited to run on a graphical processing unit (GPU) which presents a specific problem since the GPU is not a secure or trusted piece of hardware in the cloud computing environment.

In this paper, we will analyze …

Computational Complexity In Tile Self-Assembly, Timothy Gomez

Theses and Dissertations

One of the most fundamental and well-studied problems in Tile Self-Assembly is the Unique Assembly Verification (UAV) problem. This algorithmic problem asks whether a given tile system uniquely assembles a specific assembly. The complexity of this problem in the 2-Handed Assembly Model (2HAM) at a constant temperature is a long-standing open problem since the model was introduced. Previously, only membership in the class coNP was known and that the problem is in P if the temperature is one (τ = 1). The problem is known to be hard for many generalizations of the model, such as allowing one …

Iot Security For Iotmon Attacks Based On Devices’ App Description, Raghad Jameel A. Alhazmi

Theses and Dissertations

There are concerns associated with ”inter-app” interactions, which occur when many independently developed home automation apps interact and affect one another, causing possibly dangerous unexpected app action. We extended a security tool named IoTMon, an IoT device management system capable of identifying all potential cross-app communication paths and analyzing their danger status. As part of our work, we keep an eye on the app description and safeguard IoTMon from being altered in any way that could obscure the real interaction related to another app action. We validate the IoTMon system’s integrity by applying the hash algorithm SHA512 with digital signature …

Risk Gameplay Analysis Using Stochastic Beam Search, Jacob Gillenwater

Electronic Theses and Dissertations

Hasbro’s RISK, first published in 1959, is a complex multiplayer strategy game that has received little attention from the scientific community. Training artificial intelligence (AI) agents using stochastic beam search gives insight into effective strategy when playing RISK. A comprehensive analysis of the systems of play challenges preconceptions about good strategy in some areas of the game while reinforcing those preconceptions in others. This study applies stochastic beam search to discover optimal strategies in RISK. Results of the search show both support for and challenges to traditionally held positions about RISK gameplay. While stochastic beam search competently investigates gameplay on …

Context-Aware Graph-Based Self-Supervised Learning Of Whole Slide Images, Milam Aryal, Nasim Yahyasoltani

Computer Science Faculty Research and Publications

The gigapixel resolution of a single whole slide image (WSI), and the lack of huge annotated datasets needed for computational pathology, makes cancer diagnosis and grading with WSIs a challenging task. Moreover, downsampling of WSIs might result in loss of information critical for cancer diagnosis. Motivated by the fact that context such as topological structures in the tumor environment may contain critical information in cancer grading and diagnosis, a novel two-stage learning approach is proposed. Self-supervised learning is applied to improve training through unlabled data and graph convolutional network (GCN) is deployed to incorporate context from tumor and surrounding tissues. …

Robust And Fair Machine Learning Under Distribution Shift, Wei Du

Graduate Theses and Dissertations

Machine learning algorithms have been widely used in real world applications. The development of these techniques has brought huge benefits for many AI-related tasks, such as natural language processing, image classification, video analysis, and so forth. In traditional machine learning algorithms, we usually assume that the training data and test data are independently and identically distributed (iid), indicating that the model learned from the training data can be well applied to the test data with good prediction performance. However, this assumption is quite restrictive because the distribution shift can exist from the training data to the test data in many …

Github Sponsors: Exploring A New Way To Contribute To Open Source, Naomichi Shimada, Tao Xiao, Hideaki Hata, Christoph Treude, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

GitHub Sponsors, launched in 2019, enables donations to individual open source software (OSS) developers. Financial support for OSS maintainers and developers is a major issue in terms of sustaining OSS projects, and the ability to donate to individuals is expected to support the sustainability of developers, projects, and community. In this work, we conducted a mixed-methods study of GitHub Sponsors, including quantitative and qualitative analyses, to understand the characteristics of developers who are likely to receive donations and what developers think about donations to individuals. We found that: (1) sponsored developers are more active than non-sponsored developers, (2) the possibility …

Improved Sensor-Based Human Activity Recognition Via Hybrid Convolutional And Recurrent Neural Networks, Sonia Perez-Gamboa

Electronic Theses, Projects, and Dissertations

Non-intrusive sensor-based human activity recognition is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTMs) recurrent neural networks provide a way to achieve human activity recognition accurately and effectively. This project designed and explored a variety of multi-layer hybrid deep learning architectures which aimed to improve human activity recognition performance by integrating local features and was scale invariant with dependencies of activities. We achieved a 94.7% activity recognition rate on the University of California, Irvine public domain dataset …

Advantages And Disadvantages Of Centralized Versus Decentralized Information Systems And Services From A Project Management Perspective, Garrett William Cuillier

Electronic Theses, Projects, and Dissertations

After an extensive review of the available literature, it is evident that within the Information Systems and Technology (IT) field, project managers are still debating whether to centralize or decentralize IT systems and services personnel. This decision can have a major impact on the effectiveness of the project management process with both organizational structures having advantages and disadvantages. The study examines two real-world examples of projects in the aerospace and defense technology industry that were performed from either a centralized or decentralized organizational structure. Using an industry standard project management methodology (i.e., Agile and Scrum), the study clearly identified the …

A Machine Learning Approach For Reconnaissance Detection To Enhance Network Security, Rachel Bakaletz

Electronic Theses and Dissertations

Before cyber-crime can happen, attackers must research the targeted organization to collect vital information about the target and pave the way for the subsequent attack phases. This cyber-attack phase is called reconnaissance or enumeration. This malicious phase allows attackers to discover information about a target to be leveraged and used in an exploit. Information such as the version of the operating system and installed applications, open ports can be detected using various tools during the reconnaissance phase. By knowing such information cyber attackers can exploit vulnerabilities that are often unique to a specific version.

In this work, we develop an …

Quid Pro Quo: An Exploration Of Reciprocity In Code Review, Carlos Gavidia-Calderon, Donggyun Han, Amel Bennaceur

Research Collection School Of Computing and Information Systems

We explore the role of reciprocity in code review processes. Reciprocity manifests itself in two ways: 1) reviewing code for others translates to accepted code contributions, and 2) having contributions accepted increases the reviews made for others. We use vector autoregressive (VAR) models to explore the causal relation between reviews performed and accepted contributions. After fitting VAR models for 24 active open-source developers, we found evidence of reciprocity in 6 of them. These results suggest reciprocity does play a role in code review, that can potentially be exploited to increase reviewer participation.

Exploring And Adapting Chinese Gpt To Pinyin Input Method, Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi

Research Collection School Of Computing and Information Systems

While GPT has become the de-facto method for text generation tasks, its application to pinyin input method remains unexplored. In this work, we make the first exploration to leverage Chinese GPT for pinyin input method. We find that a frozen GPT achieves state-of-the-art performance on perfect pinyin. However, the performance drops dramatically when the input includes abbreviated pinyin. A reason is that an abbreviated pinyin can be mapped to many perfect pinyin, which links to even larger number of Chinese characters. We mitigate this issue with two strategies, including enriching the context with pinyin and optimizing the training process to …

Neighbor-Anchoring Adversarial Graph Neural Networks (Extended Abstract), Zemin Liu, Yuan Fang, Yong Liu, Vincent W. Zheng

Research Collection School Of Computing and Information Systems

While graph neural networks (GNNs) exhibit strong discriminative power, they often fall short of learning the underlying node distribution for increased robustness. To deal with this, inspired by generative adversarial networks (GANs), we investigate the problem of adversarial learning on graph neural networks, and propose a novel framework named NAGNN (i.e., Neighbor-anchoring Adversarial Graph Neural Networks) for graph representation learning, which trains not only a discriminator but also a generator that compete with each other. In particular, we propose a novel neighbor-anchoring strategy, where the generator produces samples with explicit features and neighborhood structures anchored on a reference real node, …

Guided Attention Multimodal Multitask Financial Forecasting With Inter-Company Relationships And Global And Local News, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Most works on financial forecasting use information directly associated with individual companies (e.g., stock prices, news on the company) to predict stock returns for trading. We refer to such company-specific information as local information. Stock returns may also be influenced by global information (e.g., news on the economy in general), and inter-company relationships. Capturing such diverse information is challenging due to the low signal-to-noise ratios, different time-scales, sparsity and distributions of global and local information from different modalities. In this paper, we propose a model that captures both global and local multimodal information for investment and risk management-related forecasting tasks. …

Do Pre-Trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation And A Reasonable Approach, Xin Lv, Yankai Lin, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

Research Collection School Of Computing and Information Systems

In recent years, pre-trained language models (PLMs) have been shown to capture factual knowledge from massive texts, which encourages the proposal of PLM-based knowledge graph completion (KGC) models. However, these models are still quite behind the SOTA KGC models in terms of performance. In this work, we find two main reasons for the weak performance: (1) Inaccurate evaluation setting. The evaluation setting under the closed-world assumption (CWA) may underestimate the PLM-based KGC models since they introduce more external knowledge; (2) Inappropriate utilization of PLMs. Most PLM-based KGC models simply splice the labels of entities and relations as inputs, leading to …

Chinese Idiom Understanding With Transformer-Based Pretrained Language Models, Minghuan Tan

Dissertations and Theses Collection (Open Access)

In this dissertation, I study the understanding of Chinese idioms using transformer-based pretrained language models. By ``understanding", I confine the topics to word embeddings learning, contextualized word representations learning, multiple-choice cloze-test reading comprehension and conditional text generation. Chinese idioms are fixed phrases that have special meanings usually derived from an ancient story. The meanings of these idioms are oftentimes not directly related to their component characters, which makes it hard to model them compared with standard phrases whose meanings are compositional. We initiate the work with studying idiom representations derived from pretrained language models, in particular, BERT. We adopt probing-based …

I'M Special But A.I. Doesn't Get It, Huei Huei Laurel Teo

Dissertations and Theses Collection (Open Access)

A growing body of management research on artificial intelligence (AI) has consistently shown that people innately distrust decisions made by AI and find such decision processes simply less fair compared to decisions made by humans. My dissertation adopts a different perspective to propose that aside from fairness concerns, AI decision methods trigger perceptions in people that their individual uniqueness has not be adequately considered and this has negative consequences for their psychological or subjective well-being.

By combining theories of uniqueness, individuality, power, and well-being, I develop five studies to provide empirical evidence that aversion to AI-mediated decisions also operates through …

College Of Education Filemaker Extraction And End-User Database Development, Andrew Tran

Electronic Theses, Projects, and Dissertations

The College of Education (CoE) at the California State University San Bernardino (CSUSB) developed a system to keep track of both state and national accreditation requirements using FileMaker 5, a database system. This accreditation data is crucial for reporting and record-keeping for the CSU Chancellor’s Office as well as the State of California. However, the database system was developed several decades ago, and software support has long since been dropped, causing the CoE’s legacy accreditation data to be at risk of being lost should the software or hardware suffer permanent failure. The purpose of this project was to perform extraction …

An Exploratory Study On Refactoring Documentation In Issues Handling, Eman Abdullah Alomar, Anthony Peruma, Mohamed Wiem Mkaouer, Christian D. Newman, Ali Ouni

Articles

Understanding the practice of refactoring documentation is of paramount importance in academia and industry. Issue tracking systems are used by most software projects enabling developers, quality assurance, managers, and users to submit feature requests and other tasks such as bug fixing and code review. Although recent studies explored how to document refactoring in commit messages, little is known about how developers describe their refactoring needs in issues. In this study, we aim at exploring developer-reported refactoring changes in issues to better understand what developers consider to be problematic in their code and how they handle it. Our approach relies on …

Studying Alive : An Application For The Wellness Of College Students During The Covid-19 Pandemic, Natasia Fernandez

Theses, Dissertations and Culminating Projects

Mental health awareness has become an increasingly important topic over the past couple of years due the Covid-19 pandemic. Many individuals find it difficult to discuss their mental health. An individual’s mental health is a significant factor in maintaining their overall wellness. College students, specifically, face various hurdles and challenges that can affect their mental health. They have several responsibilities weighing on their shoulders which can lead to stress, depression and/or anxiety. College students may find it difficult to express these topics and seek healthy ways to cope. During the Covid-19 pandemic, additional challenges have been added onto college students …

A Co-Evolutionary Approach To Test Case Generation For Safety-Critical Systems, Brad Thomas Costa

Theses and Dissertations

Safety-critical software development is a costly and time-consuming process that involves thousands of hours dedicated to test development. Tests must meet stringent developmental guidelines to verify the correct and complete implementation of their parent requirements. Further compounding any such effort is the tendency towards requirement churn or the frequent change to the software and other system requirements. This thesis presents a solution, PyTcGen, that alleviates these challenges by processing natural language requirements and programmatically generating the requisite test cases to ensure the software meets all of the conditions of that requirement. The solution uses template matching to marry requirements to …