Computer Sciences Commons^™

Medical Devices And Cybersecurity, Hilary Finch

School of Cybersecurity Posters

I begin by looking at the role of cybersecurity in the medical world. The healthcare industry adopted information technology quite quickly. While the advancement was obviously beneficial and necessary to keep up with an ever-growing demand, the healthcare industry did not place any kind of pointed focus on the security of their IT department, or the sensitive information housed therein.

When rapid advancements of technology outpaced the gradual advancement of hospital cybersecurity, security concerns became a difficult issue to control. There is a serious need for more advancements in hospital security. Each interconnected medical device has its own unique security …

Why Rectified Linear Unit Is Efficient In Machine Learning: One More Explanation, Barnabas Bede, Vladik Kreinovich, Uyen Pham

Departmental Technical Reports (CS)

In many applications, in particular, in econometric application, deep learning techniques are very effective. In this paper, we provide a new explanation for why rectified linear units -- the main units of deep learning -- are so effective. This explanation is similar to the usual explanation of why Gaussian (normal) distributions are ubiquitous -- namely, it is based on an appropriate limit theorem.

A Parallel Algorithm Template For Updating Single-Source Shortest Paths In Large-Scale Dynamic Networks, Arindam Khanda, Sriram Srinivasan, Sanjukta Bhowmick, Boyana Norris, Sajal K. Das

Computer Science Faculty Research & Creative Works

The Single Source Shortest Path (SSSP) problem is a classic graph theory problem that arises frequently in various practical scenarios; hence, many parallel algorithms have been developed to solve it. However, these algorithms operate on static graphs, whereas many real-world problems are best modeled as dynamic networks, where the structure of the network changes with time. This gap between the dynamic graph modeling and the assumed static graph model in the conventional SSSP algorithms motivates this work. We present a novel parallel algorithmic framework for updating the SSSP in large-scale dynamic networks and implement it on the shared-memory and GPU …

K-Means Clustering Using Gravity Distance, Ajinkya Vishwas Indulkar

Masters Theses & Specialist Projects

Clustering is an important topic in data modeling. K-means Clustering is a well-known partitional clustering algorithm, where a dataset is separated into groups sharing similar properties. Clustering an unbalanced dataset is a challenging problem in data modeling, where some group has a much larger number of data points than others. When a K-means clustering algorithm with Euclidean distance is applied to such data, the algorithm fails to form good clusters. The standard K-means tends to split data into smaller clusters during a clustering process evenly.

We propose a new K-means clustering algorithm to overcome the disadvantage by introducing a different …

The Causal Fairness Field Guide: Perspectives From Social And Formal Sciences, Alycia Carey, Xintao Wu

Computer Science and Computer Engineering Faculty Publications and Presentations

Over the past several years, multiple different methods to measure the causal fairness of machine learning models have been proposed. However, despite the growing number of publications and implementations, there is still a critical lack of literature that explains the interplay of causality-based fairness notions with the social sciences of philosophy, sociology, and law. We hope to remedy this issue by accumulating and expounding upon the thoughts and discussions of causality-based fairness notions produced by both social and formal (specifically machine learning) sciences in this field guide. In addition to giving the mathematical backgrounds of several popular causality-based fair machine …

Improving I/O Performance For Exascale Applications Through Online Data Layout Reorganization, Lipeng Wan, Axel Huebl, Junmin Gu, Franz Poeschel, Ana Gainaru, Ruonan Wang, Jieyang Chen, Xin Liang, Dmitry Ganyushin, Todd Munson, Ian Foster, Jean Luc Vay, Norbert Podhorszki, Kesheng Wu

Computer Science Faculty Research & Creative Works

The applications being developed within the U.S. Exascale Computing Project (ECP) to run on imminent Exascale computers will generate scientific results with unprecedented fidelity and record turn-around time. Many of these codes are based on particle-mesh methods and use advanced algorithms, especially dynamic load-balancing and mesh-refinement, to achieve high performance on Exascale machines. Yet, as such algorithms improve parallel application efficiency, they raise new challenges for I/O logic due to their irregular and dynamic data distributions. Thus, while the enormous data rates of Exascale simulations already challenge existing file system write strategies, the need for efficient read and processing of …

Measurement Errors In Range-Based Localization Algorithms For Uavs: Analysis And Experimentation, Francesco Betti Sorbelli, Cristina M. Pinotti, Simone Silvestri, Sajal K. Das

Computer Science Faculty Research & Creative Works

Localizing Ground Devices (GDs) is an Important Requirement for a Wide Variety of Applications, Such as Infrastructure Monitoring, Precision Agriculture, Search and Rescue Operations, to Name a Few. to This End, Unmanned Aerial Vehicles (UAVs) or Drones Offer a Promising Technology Due to their Flexibility. However, the Distance Measurements Performed using a Drone, an Integral Part of a Localization Procedure, Incur Several Errors that Affect the Localization Accuracy. in This Paper, We Provide Analytical Expressions for the Impact of Different Kinds of Measurement Errors on the Ground Distance between the UAV and GDs. We Review Three Range-Based and Three Range-Free …

Tony Hawk Pro Skater, Kelly Stone-Patrick

ART 108: Introduction to Games Studies

Looking back on life there are so many memories that have truly made a lasting impact, these can include different vacations, accomplishments, and family, but have you ever had one that included a game or video game? From my personal experience, Tony Hawk Pro Skater has been one of those memories for me from childhood and now as an adult. Tony Hawk Pro Skater was a key part of my enjoyment and leisure as a child while also providing me with memories of time spent with my older brothers. In this paper, we will be highlighting the different elements of …

Game-Theoretic Approach Explains -- On The Qualitative Level -- The Antigenic Map Of Covid-19 Variants, Olga Kosheleva, Vladik Kreinovich, Nguyen Hoang Phuong

Departmental Technical Reports (CS)

To effectively defend the population against future variants of Covid-19, it is important to be able to predict how it will evolve. For this purpose, it is necessary to understand the logic behind its evolution so far. At first glance, this evolution looks random and thus, difficult to predict. However, we show that already a simple game-theoretic model can actually explain -- on the qualitative level -- how this virus mutated so far.

Reinforcement Learning With Deep Q-Networks, Caleb Cassady

Masters Theses & Specialist Projects

In the past decade, machine learning strategies centered on the use of Deep Neural Networks (DNNs) have caught the interest of researchers due to their success in complicated classification and prediction problems. More recently, these DNNs have been applied to reinforcement learning tasks with state of- the-art results using Deep Q-Networks (DQNs) based on the Q-Learning algorithm. However, the DQN training process is different from standard DNNs and poses significant challenges for certain reinforcement learning environments. This paper examines some of these challenges, compares proposed solutions, and offers novel solutions based on previous research. Experiment implementation available at https://github.com/caleb98/dqlearning.

Minimizing The Deployment Cost Of Uavs For Delay-Sensitive Data Collection In Iot Networks, Wenzheng Xu, Tao Xiao, Junqi Zhang, Weifa Liang, Zichuan Xu, Xuxun Liu, Xiaohua Jia, Sajal K. Das

Computer Science Faculty Research & Creative Works

In this paper, we study the deployment of Unmanned Aerial Vehicles (UAVs) to collect data from IoT devices, by finding a data collection tour for each UAV. To ensure the 'freshness' of the collected data, the total time spent in the tour of each UAV that consists of the UAV flying time and data collection time must be no greater than a given delay B, e.g., 20 minutes. In this paper, we consider a problem of deploying the minimum number of UAVs and finding their data collection tours, subject to the constraint that the total time spent in each tour …

Gamerz, Derek Kwok

ART 108: Introduction to Games Studies

Gaming - it is a hobby enjoyed by many and easily accessible for all. But what is considered gaming? A game can be classified as something to do for past time or as an amusement. As it is defined in the oxford dictionary “gaming” can be categorized into two definitions: 1.the playing of games developed to teach something or to help solve a problem, as in a military or business situation, or 2. Digital Technology. the playing of computer or video games. According to the definition on Dictionary.com, board games or physical games can still be considered gaming. Definition two …

A New Application Of The Central Limit Theorem, Kenneth Winters

Selected Honors Theses

This paper discusses the Central Limit Theorem (CLT) and its applications. The paper gives an introduction to what the CLT is and how it can be applied to real life. Additionally, the paper gives a conceptual understanding of the theorem through various examples and visuals. The paper discusses the applications of the CLT in fields such as computer science, psychology, and political science. The author then suggests a new mathematical theorem as an application of the CLT and provides a proof of the theorem. The new theorem relates to expected value and probabilities of random variables and provides a link …

Why Constraint Interval Arithmetic Works Well: A Theorem Explains Empirical Success, Barnabas Bede, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Vladik Kreinovich

Departmental Technical Reports (CS)

Often, we are interested in a quantity that is difficult or impossible to measure directly, e.g., tomorrow's temperature. To estimate this quantity, we measure auxiliary easier-to-measure quantities that are related to the desired ones by a known dependence, and use the known relation to estimate the desired quantity. Measurements are never absolutely accurate, there is always a measurement error, i.e., a non-zero difference between the measurement result and the actual (unknown) value of the corresponding quantity. In many practical situations, the only information that we have about each measurement error is the bound on its absolute value. In such situations, …

When Is Deep Learning Better And When Is Shallow Learning Better: Qualitative Analysis, Salvador Robles Herrera, Martine Ceberio, Vladik Kreinovich

Departmental Technical Reports (CS)

In many practical situations, deep neural networks work better than the traditional "shallow" ones, however, in some cases, the shallow neural networks lead to better results. At present, deciding which type of neural networks will work better is mostly done by trial and error. It is therefore desirable to come up with some criterion of when deep learning is better and when shallow is better. In this paper, we argue that this depends on whether the corresponding situation has natural symmetries: if it does, we expect deep learning to work better, otherwise we expect shallow learning to be more effective. …

Engr 692 Section 66: Randomized Algorithms, Yixin Chen

GMAS Course Syllabi

No abstract provided.

A Technological Skills Gap: What Can We Do About It?, Will Moore

Cybersecurity Undergraduate Research Showcase

In the last thirty years, education has transformed faster than ever before. As a society we have developed new classroom technologies that allow for better communication and access to more information than ever before. However, at the same time, education seems rockier than ever before. Several major companies, including Tesla, Apple, Google and Netflix, no longer require a college degree for employment, and many companies, such as Amazon, Google, and Microsoft, have begun programs to train their own employees in skills and create their own certification programs to help employees learn necessary skills (Akhtar, O’Donnell). Why do these major corporations …

Application Of U.S. Sanction Laws And Ransomware Payments, Trinity Woodbury

Cybersecurity Undergraduate Research Showcase

Ransomware is a major threat that widely affects individuals and organizations, including businesses. Ransomware victims face the situation of potentially paying ransom payments to threat actors, some of whom might be foreign-based criminals. Ransomware affects victims from all sectors and industries.

Cova Cci Undergrad Cyber Research, Nana Jeffrey

Cybersecurity Undergraduate Research Showcase

Is your digital assistant your worst enemy? Modern technology has impacted our lives in a positive way making tasks that were once time consuming become more convenient. For example a few years ago writing down your grocery list with a paper and pen was a norm, now with technology we have access to IoT devices such as smart fridges that can inform us on what items are low in stock, send a message to our digital assistants such as iOS Siri and Amazon's Alexa to remind us to buy those groceries. Although these digital assistants have helped make our daily …

Causal Inference In Healthcare: Approaches To Causal Modeling And Reasoning Through Graphical Causal Models, Riddhiman Adib

Dissertations (1934 -)

In the era of big data, researchers have access to large healthcare datasets collected over a long period. These datasets hold valuable information, frequently investigated using traditional Machine Learning algorithms or Neural Networks. These algorithms perform great in finding patterns out of datasets (as a predictive machine); however, the models lack extensive interpretability to be used in the healthcare sector (as an explainable machine). Without exploring underlying causal relationships, the algorithms fail to explain their reasoning. Causal Inference, a relatively newer branch of Artificial Intelligence, deals with interpretability and portrays causal relationships in data through graphical models. It explores the …

How Online Platforms Are Used By Child Predators And What Are The Effective Preventive Measures?, Kayla Macpherson

Cybersecurity Undergraduate Research Showcase

As technology has evolved greatly in the twenty-first century alone, younger generations have had an opportunity to grow up with devices at their fingertips none have ever before. This accessibility has strengthened their ability of quick use, skill, and a strong feeling of comfort with using and having access to technology. There seems to be more children with access to the internet than there are without, but there is also an ongoing issue behind the screens.

A New Metaphor: How Artificial Intelligence Links Legal Reasoning And Mathematical Thinking, Melissa E. Love Koenig, Colleen Mandell

Marquette Law Review

Artificial intelligence’s (AI’s) impact on the legal community expands exponentially each year. As AI advances, lawyers have more powerful tools to enhance their ability to research and analyze the law, as well as to draft contracts and other legal documents. Lawyers are already using tools powered by AI and are learning to shift their methodologies to take advantage of these enhancements. To continue to grow into their shifting role, lawyers should understand the relationship between AI, mathematics, and legal reasoning.

Super-High Resolution Imaging Using Easy Accessible Resources, Jamison Murphy

LMU Theses and Dissertations

Most generic systems and hardware for non-governmental users lack capability to process images in high resolution coming from aerial crafts such as satellites, drones, airplanes and helicopters. These images are being displayed in poor quality due to the software running on low budgets, which restricts the high resolution they need. In this project I researched ways to obtain super high resolution images from aerial crafts for low cost and compared which method works best in producing the clearest and fastest images. I connected with the Loyola Marymount University Marketing team to collaborate with their photographers in producing the best quality …

Leaderboard Design Principles Influencing User Engagement In An Online Discussion, Brian S. Bovee

Masters Theses & Doctoral Dissertations

Along with the popularity of gamification, there has been increased interest in using leaderboards to promote engagement with online learning systems. The existing literature suggests that when leaderboards are designed well they have the potential to improve learning, but qualitative investigations are required in order to reveal design principles that will improve engagement. In order to address this gap, this qualitative study aims to explore students' overall perceptions of popular leaderboard designs in a gamified, online discussion. Using two leaderboards reflecting performance in an online discussion, this study evaluated multiple leaderboard designs from student interviews and other data sources regarding …

A False Sense Of Security - Organizations Need A Paradigm Shift On Protecting Themselves Against Apts, Srinivasulu R. Vuggumudi

Masters Theses & Doctoral Dissertations

Organizations Advanced persistent threats (APTs) are the most complex cyberattacks and are generally executed by cyber attackers linked to nation-states. The motivation behind APT attacks is political intelligence and cyber espionage. Despite all the awareness, technological advancements, and massive investment, the fight against APTs is a losing battle for organizations. An organization may implement a security strategy to prevent APTs. However, the benefits to the security posture might be negligible if the measurement of the strategy’s effectiveness is not part of the plan. A false sense of security exists when the focus is on implementing a security strategy but not …

Fine-Grained Detection Of Academic Emotions With Spatial Temporal Graph Attention Networks Using Facial Landmarks, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

With the incidence of the Covid-19 pandemic, institutions have adopted online learning as the main lessondelivery channel. A common criticism of online learning is that sensing of learners’ affective states such asengagement is lacking which degrades the quality of teaching. In this study, we propose automatic sensing of learners’ affective states in an online setting with web cameras capturing their facial landmarks and head poses. We postulate that the sparsely connected facial landmarks can be modelled using a Graph Neural Network. Using the publicly available in the wild DAiSEE dataset, we modelled both the spatial and temporal dimensions of the …

Immersivepov: Filming How-To Videos With A Head-Mounted 360° Action Camera, Kevin Huang, Jiannan Li, Maurício Sousa, Tovi Grossman

Research Collection School Of Computing and Information Systems

How-to videos are often shot using camera angles that may not be optimal for learning motor tasks, with a prevalent use of third-person perspective. We present immersivePOV, an approach to film how-to videos from an immersive first-person perspective using a head-mounted 360° action camera. immersivePOV how-to videos can be viewed in a Virtual Reality headset, giving the viewer an eye-level viewpoint with three Degrees of Freedom. We evaluated our approach with two everyday motor tasks against a baseline first-person perspective and a third-person perspective. In a between-subjects study, participants were assigned to watch the task videos and then replicate the …

Authenticated Key Establishment Protocol For Constrained Smart Healthcare Systems Based On Physical Unclonable Function, Abdalla Saleh Elkushli

Theses

Smart healthcare systems are one of the critical applications of the internet of things. They benefit many categories of the population and provide significant improvement to healthcare services. Smart healthcare systems are also susceptible to many threats and exploits because they run without supervision for long periods of time and communicate via open channels. Moreover, in many implementations, healthcare sensor nodes are implanted or miniaturized and are resource-constrained. The potential risks on patients/individuals’ life from the threats necessitate that securing the connections in these systems is of utmost importance. This thesis provides a solution to secure end-to-end communications in such …

Few-Shot Object Detection Via Baby Learning, Anh-Khoa Nguyen Vu, Nhat-Duy Nguyen, Khanh-Duy Nguyen, Vinh-Tiep Nguyen, Thanh Duc Ngo, Thanh-Toan Do, Tam Nguyen

Computer Science Faculty Publications

Few-shot learning is proposed to overcome the problem of scarce training data in novel classes. Recently, few-shot learning has been well adopted in various computer vision tasks such as object recognition and object detection. However, the state-of-the-art (SOTA) methods have less attention to effectively reuse the information from previous stages. In this paper, we propose a new framework of few-shot learning for object detection. In particular, we adopt Baby Learning mechanism along with the multiple receptive fields to effectively utilize the former knowledge in novel domain. The propoed framework imitates the learning process of a baby through visual cues. The …

The Social Problems And Benefits Of Video Games, Steven Ly

ART 108: Introduction to Games Studies

In today’s society, video games have improved and increased alongside technology. Many games have made many communities increase their social media intake and gaming addiction. In the uprise of video games, multiple genres of video games have been created to contain the gamer. This paper will discuss the number of negatives and positives that affect a video gamer. We will also discuss other factors that could correlate to games involving people. The downsides and upsides of video gaming will primarily revolve around social problems that gamers develop and or positive outcomes from gaming. We will dive into the topics such …