Computer Sciences Commons^™

A Virtual Time Driven Simulator For Devs Models, Ronald R. Stempien

Dissertations, Master's Theses and Master's Reports

When simulating a system that includes some software component, simulation authors are faced with the problem of how to appropriately model the software within the simulation. While many formal methods for modeling software exist, in some contexts these may not be appropriate or viable for a given simulation. Instead, simulation authors may model a computer within the simulation, and run the software in question “as is” on the modeled machine. In this work, we introduce a theoretical framework to allow for the use of hardware virtualization technologies as a hardware accelerator for CPU models in Discrete Event System Specification (DEVS) …

Dynamic Memory Management For Key-Value Store, Yuchen Wang

Dissertations, Master's Theses and Master's Reports

To minimize the latency of accessing back-end servers, modern web services often use in-memory key-value (k-v) stores at the front end to cache frequently accessed objects. Due to the limited memory capacity, these stores must be configured with a fixed amount of memory. Consequently, cache replacement is required when the footprint of the accessed objects exceeds the cache size.

This thesis presents a comprehensive exploration of advanced dynamic memory management techniques for k-v stores. The first study conducts a detailed analysis of K-LRU, a random sampling-based replacement policy, proposing a dynamic K configuration scheme to exploit the potential miss ratio …

Model Guided Memory Optimization For Key-Value Caches, Daniel Byrne

Dissertations, Master's Theses and Master's Reports

Modern web services deploy key-value caches to store popular requests to backend systems. As such, how the cache stores data impacts both the cache miss ratio and throughput. Therefore, in this thesis, we introduce and apply cache modeling techniques to optimize the memory organization of a key-value cache to improve overall cache performance.

Specifically, we begin with a single-level key-value cache and use miss ratio curves to adjust the memory assigned to the residing applications dynamically. This leads to an improvement in miss ratio up to 25% over state-of-the-art techniques and an 8.8% improvement in cache throughput. We then consider …

Improving The Robustness Of Neural Networks To Adversarial Patch Attacks Using Masking And Attribution Analysis, Atandra Mahalder

Honors Undergraduate Theses

Computer vision algorithms, including image classifiers and object detectors, play a pivotal role in various cyber-physical systems, spanning from facial recognition to self-driving vehicles and security surveillance. However, the emergence of real-world adversarial patches, which can be as simple as stickers, poses a significant threat to the reliability of AI models utilized within these systems. To address this challenge, several defense mechanisms such as PatchGuard, Minority Report, and (De)Randomized Smoothing have been proposed to enhance the resilience of AI models against such attacks. In this thesis, we introduce a novel framework that integrates masking with attribution analysis to robustify AI …

Music Recommendation Using Exemplars And Contrastive Learning, Tina Tran

Honors Undergraduate Theses

The popularity of AI audio applications is growing, it is used in chatbots, automated voice translation, virtual assistants, and text-to-speech translation. Audio classification is crucial in today’s world with a growing need to sort and classify millions of existing audio data with increasing amounts of new data uploaded over time. In the area of classification lies the difficult and lucrative problem of music recommendation. Research in music recommendation has trended over time towards collaborative-based approaches utilizing large amounts of user data. These approaches tend to deal with the cold-start problem of insufficient data and are costly to train. We look …

Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Not forgetting old class knowledge is a key challenge for class-incremental learning (CIL) when the model continuously adapts to new classes. A common technique to address this is knowledge distillation (KD), which penalizes prediction inconsistencies between old and new models. Such prediction is made with almost new class data, as old class data is extremely scarce due to the strict memory limitation in CIL. In this paper, we take a deep dive into KD losses and find that "using new class data for KD"not only hinders the model adaption (for learning new classes) but also results in low efficiency for …

Introducing Flexible Assessment Into A Computer Networks Course: A Case Study, Joe Meehean

Journal of Mathematics and Science: Collaborative Explorations

With overall positive results and limited drawbacks, I have adapted modern pedagogical techniques to address a common difficulty encountered when teaching a computer networks course. Due to the tiered nature of the skills taught in the course, students often fail unnecessarily. Using mastery learning, competency-based education, and specifications grading as a foundation, I have developed a course that allows students with varied skills and abilities to pass. The heart of this approach is the flexible assessment of programming assignments which eliminates due dates and allows students to have their work graded and regraded without penalty. Flexible assessment also defines an …

Machine-Learning-Assisted Design Of Deep Eutectic Solvents Based On Uncovered Hydrogen Bond Patterns, Usman Lame Abbas, Yuxuan Zhang, Joseph Tapia, Md Selim, Jin Chen, Jian Shi, Qing Shao

Markey Cancer Center Faculty Publications

Non-ionic deep eutectic solvents (DESs) are non-ionic designer solvents with various applications in catalysis, extraction, carbon capture, and pharmaceuticals. However, discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES formation. The search for DES relies heavily on intuition or trial-and-error processes, leading to low success rates or missed opportuni- ties. Recognizing that hydrogen bonds (HBs) play a central role in DES formation, we aim to identify HB features that distinguish DES from non-DES systems and use them to develop machine learning (ML) models to discover new DES systems. We first analyze the …

Cross-Layer Design Of Highly Scalable And Energy-Efficient Ai Accelerator Systems Using Photonic Integrated Circuits, Sairam Sri Vatsavai

Theses and Dissertations--Electrical and Computer Engineering

Artificial Intelligence (AI) has experienced remarkable success in recent years, solving complex computational problems across various domains, including computer vision, natural language processing, and pattern recognition. Much of this success can be attributed to the advancements in deep learning algorithms and models, particularly Artificial Neural Networks (ANNs). In recent times, deep ANNs have achieved unprecedented levels of accuracy, surpassing human capabilities in some cases. However, these deep ANN models come at a significant computational cost, with billions to trillions of parameters. Recent trends indicate that the number of parameters per ANN model will continue to grow exponentially in the foreseeable …

Nonuniform Sampling-Based Breast Cancer Classification, Santiago Posso

Theses and Dissertations--Electrical and Computer Engineering

The emergence of deep learning models and their success in visual object recognition have fueled the medical imaging community's interest in integrating these algorithms to improve medical diagnosis. However, natural images, which have been the main focus of deep learning models and mammograms, exhibit fundamental differences. First, breast tissue abnormalities are often smaller than salient objects in natural images. Second, breast images have significantly higher resolutions but are generally heavily downsampled to fit these images to deep learning models. Models that handle high-resolution mammograms require many exams and complex architectures. Additionally, spatially resizing mammograms leads to losing discriminative details essential …

Strategyproof Mechanisms For Group-Fair Obnoxious Facility Location Problems, Jiaqian Li, Minming Li, Hau Chan

School of Computing: Faculty Publications

We study the group-fair obnoxious facility location problems from the mechanism design perspective where agents belong to different groups and have private location preferences on the undesirable locations of the facility. Our main goal is to design strategyproof mechanisms that elicit the true location preferences from the agents and determine a facility location that approximately optimizes several group-fair objectives. We first consider the maximum total and average group cost (group-fair) objectives. For these objectives, we propose deterministic mechanisms that achieve 3-approximation ratios and provide matching lower bounds. We then provide the characterization of 2-candidate strategyproof randomized mechanisms. Leveraging the characterization, …

Demonstrating Canvas-Based Processing Of Multiple Camera Streams At The Edge, Ila Gokarn, Hemanth Sabbella, Yigong Hu, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

We demonstrate criticality-aware canvas-based processing of multiple concurrent camera streams at the resource constrained edge to show substantial improvement in the accuracy-throughput trade-off. The proposed system focuses the available computation resources on select Regions of Interest (RoI) across all the camera streams by (i) extracting RoI from the input camera stream (ii) 2D bin packing the RoI on a canvas frame and (iii) batching and inferring upon these constructed composite canvas frames with a YOLOv5 object detection model. Our experiments show that such canvas-based processing can (i) sustain real-time processing throughput of 23 FPS per camera across 6 concurrent input …

Effects Of Mindfulness And Emotion Regulation On Aesthetics: A Theoretical Model From Hedonic Perspective Of Processing Fluency, Geng-Bao Lin, Fiona Fui-Hoon Nah, Choon Ling Sia

Research Collection School Of Computing and Information Systems

Research has shown that processing fluency positively impacts perceived aesthetics, with pleasure mediating the relationship. Considering the important role of pleasure, we propose studying the role of emotion regulation in moderating the mediated relationship from processing fluency to perceived aesthetics. Based on our hypotheses, individuals’ emotion regulation strategies are expected to have moderating effects on the relationship between processing fluency and perceived aesthetics such that cognitive reappraisal positively moderates the relationship from processing fluency to pleasure, and expressive suppression negatively moderates the relationship from pleasure to perceived aesthetics. Trait mindfulness is also expected to influence perceived aesthetics through emotion regulation …

Listening To The Voices Of America, Kathryn J. Edin, Corey D. Fields, David B. Grusky, Jure Leskovec, Marybeth J. Mattingly, Kristen M. Olson, Charles Varner

Department of Sociology: Faculty Publications

We make the case for building a permanent public-use platform for conducting and analyzing immersive interviews on the everyday lives of Americans. The American Voices Project (AVP)—a widely watched experiment with this new platform—provides important early evidence on its promise. The articles in this issue reveal that, although public-use interview datasets obviously cannot meet all research needs, they do provide new opportunities to study small or hidden populations, new or emerging social problems, reactions to ongoing social crises, submerged values and attitudes, and many other aspects of American life. We conclude that a permanent AVP platform would help build an …

Enabling Ai And Robotic Coaches For Physical Rehabilitation Therapy: Iterative Design And Evaluation With Therapists And Post-Stroke Survivors, Min Hun Lee, Daniel Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez I Badia

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) and robotic coaches promise the improved engagement of patients on rehabilitation exercises through social interaction. While previous work explored the potential of automatically monitoring exercises for AI and robotic coaches, the deployment of these systems remains a challenge. Previous work described the lack of involving stakeholders to design such functionalities as one of the major causes. In this paper, we present our efforts on eliciting the detailed design specifications on how AI and robotic coaches could interact with and guide patient’s exercises in an effective and acceptable way with four therapists and five post-stroke survivors. Through iterative …

A Use Case Of Chatgpt: Summary Of An Expert Panel Discussion On Electronic Health Records And Implementation Science, Seppo T Rinne, Julian Brunner, Timothy P Hogan, Jacqueline M Ferguson, Drew A Helmer, Sylvia J Hysong, Grace Mckee, Amanda Midboe, Megan E Shepherd-Banigan, A Rani Elwy

Center for Medical Ethics and Health Policy Staff Publications

Objective: Artificial intelligence (AI) is revolutionizing healthcare, but less is known about how it may facilitate methodological innovations in research settings. In this manuscript, we describe a novel use of AI in summarizing and reporting qualitative data generated from an expert panel discussion about the role of electronic health records (EHRs) in implementation science.

Materials and methods: 15 implementation scientists participated in an hour-long expert panel discussion addressing how EHRs can support implementation strategies, measure implementation outcomes, and influence implementation science. Notes from the discussion were synthesized by ChatGPT (a large language model-LLM) to generate a manuscript summarizing the discussion, …

Advancing Household Robotics: Deep Interactive Reinforcement Learning For Efficient Training And Enhanced Performance, Arpita Soni, Sujatha Alla, Suresh Dodda, Hemanth Volikatla

Engineering Management & Systems Engineering Faculty Publications

The market for domestic robots—made to perform household chore, is growing as these robots relieve people of everyday responsibilities. Domestic robots are generally welcomed for their role in easing human labour, in contrast to industrial robots, which are frequently criticised for displacing human workers. But before these robots can carry out domestic chores, they need to become proficient in a number of minor activities, such as recognizing their surroundings, making decisions, and picking up on human behaviours. Reinforcement learning, or RL, has emerged as a key robotics technology that enables robots to interact with their environment and learn how to …

Improving Neuropathological Analysis With Aβgan: Addressing Morphology Imbalance For Efficient Alzheimer's Disease Diagnosis, Sujatha Alla, Prasanthi Chidipudi, Nagesh Bheesetty, Vedvikash Reddy Velur, Joshit Mohanty, Puneeth Bheesetty, Marisha Jmukhadze, Narendra Lakshmana Gowda, Sai Gireesh Komaragiri

Engineering Management & Systems Engineering Faculty Publications

Histopathologists are experiencing a digital revolution in their field thanks to the digitization of Whole Slide Images (WSIs), which are microscope slides of tissue that can measure gigapixels in size. With so much high resolution data at their disposal, computer vision techniques can now be used to automate laboratory processes, create visual standards, and increase analysis throughput, all of which reduce the workload of pathologists [1]. The "gold" standard in neuropathology, particularly for Alzheimer's Disease- is pathological diagnosis made by looking at White Matter Inclusions (WSIs) in brain tissue. Semi-quantitative scoring in accordance with the standards established by the Consortium …

Exploring Instructional Designers' Utilization And Perspectives On Generative Ai Tools: A Mixed Methods Study, Tian Luo, Pauline S. Muljana, Xinyue Ren, Dara Young

STEMPS Faculty Publications

The emergence of generative artificial intelligence (GenAI) has caused significant disruptions on a global scale in various workplace settings, including the field of instructional design (ID). Given the paucity of research investigating the impact of GenAI on ID work, we conducted a mixed methods study to understand instructional designers (IDs)’ perceptions and experiences of utilizing GenAI across a spectrum of ID tasks. A total of 70 IDs completed an online survey, and 13 of them participated in the semi-structured interviews. The survey results indicated IDs’ familiarity with and perceived usability of GenAI tools in performing various ID responsibilities in their …

Context-Free Grammar Framework For Automatic Shooting Game Enemy Pattern Generation, Nitit Kaweeratanakit

Chulalongkorn University Theses and Dissertations (Chula ETD)

This research proposes a framework for generating enemy patterns for SHMUPs game. It is directly based on a grammar derived from the enemy behavior of existing commercial SHMUPs, and implemented using a new description language called "Enemy Pattern Description Language" (EPDL). EPDL contains all information required to construct the enemy, with no requirement of external data content. The language is human-readable and can be connected to any game engine of choice using an EPDL interpreter. The interpreter itself consists of lexer and recursive descent parser. The results shown in this research is implemented in. "rdnh", a private fork of Touhou …

การพยากรณ์การจ่ายยาของโรงพยาบาลโดยการเรียนรู้ของเครื่องและวิธีการวิเคราะห์เชิงสถิติ, วริศ ปุณณะหิตานนท์

Chulalongkorn University Theses and Dissertations (Chula ETD)

ในปัจจุบันการพยากรณ์การจ่ายยาของโรงพยาบาลถือเป็นหัวใจสำคัญต่อการจัดการคลังยาและการสั่งซื้อยาเป็นอย่างมาก เนื่องจากการพยากรณ์ที่น้อยเกินไปทำให้ยาไม่เพียงพอส่งผลให้เกิดความล่าช้าภายในโรงพยาบาล ในขณะที่การพยากรณ์ที่มากเกินไปทำให้เปลืองพื้นที่ใช้สอยและอาจทำให้ยาเสื่อมสภาพหรือหมดอายุซึ่งส่งผลให้โรงพยาบาลสูญเสียรายได้ การมีแบบจำลองที่สามารถพยากรณ์ปริมาณการจ่ายยาให้ใกล้เคียงกับค่าจริงจะสามารถลดปัญหาการขาดแคลนยาในแต่ละห้องจ่ายยาหรือการที่ห้องจ่ายยามีการกักตุนตัวยาเกินความจำเป็น จากปัญหาที่กล่าวมาข้างต้น โครงงานมหาบัณฑิตนี้จึงถูกจัดทำขึ้นเพื่อนำเสนอแบบจำลองที่จะมาแทนค่าเฉลี่ยเคลื่อนที่แบบทั่วไปซึ่งจะช่วยให้โรงพยาบาลสามารถพยากรณ์ปริมาณการจ่ายยาแต่ละวันได้แม่นยำมากขึ้น โดยจะนำเทคนิคสำหรับพยากรณ์ข้อมูลที่อยู่ในรูปแบบของอนุกรมเวลามาประยุกต์ใช้กับข้อมูลการจ่ายยาย้อนหลังและข้อมูลการนัดหมายแพทย์ย้อนหลัง หลังจากนั้นจะนำผลลัพธ์ที่ได้มาคำนวณค่าเคลาดเคลื่อนด้วยค่าเฉลี่ยของเปอร์เซ็นต์ความคลาดเคลื่อนสัมบูรณ์และค่าเฉลี่ยสมมาตรของเปอร์เซ็นต์ความคลาดเคลื่อนสัมบูรณ์และนำผลที่ได้มาใช้ในการเลือกว่าแบบจำลองไหนให้ค่าคลาดเคลื่อนต่ำที่สุด ผลการทดลองพบว่าแบบจำลองซัพพอร์ตเวกเตอร์รีเกรสชันให้ค่าความคลาดเคลื่อนที่ต่ำกว่าค่าเฉลี่ยเคลื่อนที่แบบทั่วไป แบบจำลองที่ผู้จัดทำโครงงานนำเสนอสามารถนำไปประยุกต์ใช้กับการพยากรณ์การจ่ายยาเพื่อให้แต่ละห้องจ่ายยามียาสำหรับให้บริการในปริมาณที่เพียงพอต่อความต้องการ

Machine Learning Based Three-Limb Core-Type Transformer Core Aspect Ratios Identification, Ananta Bijoy Bhadra

College of Graduate Studies: Theses & Dissertations

Power transformers are considered one of the key elements of electric grids. Transient studies include transformer transient analysis which is required for the continuous power supply. However, to perform the transient analysis, the details of the internal structure of the transformer are required which are unobtainable and considered as confidential information. Therefore, the application of topological-based transformer models is limited although the models can accurately represent the transformers. To address this concern, a novel approach utilizing Machine Learning (ML) to identify the core aspect ratios of the three-limb core-type transformer is introduced. The proposed approach, using only the voltage and …

Uncertainty Quantification In Large Language Models Through Convex Hull Analysis, Ferhat Ozgur Catak, Murat Kuzlu

Engineering Technology Faculty Publications

Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, such as probabilistic models and ensemble techniques, face challenges when applied to the complex and high-dimensional nature of LLM-generated outputs. This study proposes a novel geometric approach to uncertainty quantification using convex hull analysis. The proposed method leverages the spatial properties of response embeddings to measure the dispersion and variability of model outputs. The prompts are categorized into three types, i.e., ’easy’, ’moderate’, and ’confusing’, to generate multiple responses using different LLMs at varying temperature settings. …

Federated Learning: Overview, Strategies, Applications, Tools And Future Directions, Betul Yurdem, Murat Kuzlu, Mehmet Kemal Gullu, Maliha Tabassum

Engineering Technology Faculty Publications

Federated learning (FL) is a distributed machine learning process, which allows multiple nodes to work together to train a shared model without exchanging raw data. It offers several key advantages, such as data privacy, security, efficiency, and scalability, by keeping data local and only exchanging model updates through the communication network. This review paper provides a comprehensive overview of federated learning, including its principles, strategies, applications, and tools along with opportunities, challenges, and future research directions. The findings of this paper emphasize that federated learning strategies can significantly help overcome privacy and confidentiality concerns, particularly for high-risk applications.

A Benchmark Framework For Data Visualization And Explainable Ai (Xai), Murat Kuzlu, Gokcen Ozdemir, Umut Ozdemir

Engineering Technology Faculty Publications

This research introduces a benchmark framework, called EDUMX, designed for machine learning (ML)-based forecasting and XAI tasks, leveraging the Streamlit open-source Python library. The framework offers a comprehensive suite of functionalities, including data loading, feature selection, relationship analysis, data preprocessing, model selection, metric evaluation, training, and real-time monitoring. Users can easily upload data in diverse formats, explore relationships between variables, preprocess data using various techniques, and assess the performance of the ML model using customizable metrics. With its user-friendly interface, this framework offers invaluable insights for forecasting tasks in various domains, catering to the evolving needs of predictive analytics. EDUMX …

Towards Algorithmic Justice: Human Centered Approaches To Artificial Intelligence Design To Support Fairness And Mitigate Bias In The Financial Services Sector, Jihyun Kim

CMC Senior Theses

Artificial Intelligence (AI) has positively transformed the Financial services sector but also introduced AI biases against protected groups, amplifying existing prejudices against marginalized communities. The financial decisions made by biased algorithms could cause life-changing ramifications in applications such as lending and credit scoring. Human Centered AI (HCAI) is an emerging concept where AI systems seek to augment, not replace human abilities while preserving human control to ensure transparency, equity and privacy. The evolving field of HCAI shares a common ground with and can be enhanced by the Human Centered Design principles in that they both put humans, the user, at …

Multi-Activity Student Knowledge And Behavior Modeling Via Transfer Learning, Siqian Zhao

Electronic Theses & Dissertations (2024 - present)

Online education systems have grown in popularity over the past few years, providing abundant opportunities for students to learn. As the number of students using these systems grows, it promotes the development of the Educational Data Mining (EDM) field, which leverages statistical, machine learning, and data mining technologies to explore large-scale educational data and develop methods to better understand student learning.

In this dissertation, we investigate two essential topics in EDM: Student Knowledge Tracing (KT) and Behavior Modeling (BM). KT aims to quantify and model student knowledge gained from learning activities, while BM focuses on tasks such as modeling student …

Sparse Representation Learning For Temporal Networks, Maxwell Mcneil

Electronic Theses & Dissertations (2024 - present)

Temporal networks arise in many domains including activity of social network users, sensor network readings over time, and time course gene expression within the interaction network of a model organism. Data of this type contains a wealth of prior information such as the connectivity among nodes (e.g., a friendship graph), and prior knowledge of expected temporal patterns (e.g., periodicity). Modeling these temporal and network patterns jointly is essential for state-of-the-art performance in temporal network data analysis and mining. Sparse dictionary encoding is one modeling approach for such underlying patterns. However, most classical approaches consider only one dimension of the data …

Bias-Aware Gaze Uniformity Assessment In Group Images, Omkar Kulkarni

Electronic Theses & Dissertations (2024 - present)

Today, more than 5 billion photos are captured every day, with smartphones generating over 94\% of these images. However, despite advancements in technology, achieving aesthetically pleasing group photos remains challenging, especially when it comes to aligning the direction of everyone’s gaze. While current methods focus on facial features, they often fail to ensure consistent gaze direction. The introduction of the iPhone's Live mode, which captures a 1.5-second video snippet along with still images, complicates the selection of the best key photo due to its subjective nature and a lack of publicly available data, especially during the pandemic.

To address these …

The Effectiveness Of Cybersecurity Training, Courtney Knight

Electronic Theses & Dissertations (2024 - present)

This study seeks to answer the question of what kinds of cybersecurity training are effective by reviewing the existing literature, analyzing for gaps, and bridging the connection with known learning techniques. The research is exploratory in nature, and is inductive – intending to develop a theory. Additionally, this study seeks to offer a taxonomy of cybersecurity training methods to be evaluated.

This study did not include security operation center (SOC), cyber incident response teams (CIRTs), or other types of advanced cybersecurity professional training. This research specifically focuses on training to improve the average employee and population’s tactical cybersecurity skills.

Several …