Computer Sciences Commons^™

Deep Learning In Indus Valley Script Digitization, Deva Munikanta Reddy Atturu

Theses and Dissertations

This research introduces ASR-net(Ancient Script Recognition), a groundbreaking system that automatically digitizes ancient Indus seals by converting them into coded text, similar to Optical Character Recognition for modern languages. ASR-net, with an 95% success rate in identifying individual symbols, aims to address the crucial need for automated techniques in deciphering the enigmatic Indus script. Initially Yolov3 is utilized to create the bounding boxes around each graphemes present in the Indus Valley Seal. In addition to that we created M-net(Mahadevan) model to encode the graphemes. Beyond digitization, the paper proposes a new research challenge called the Motif Identification Problem (MIP) related …

Space Transformation For Open Set Recognition, Atefeh Mahdavi

Theses and Dissertations

Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In OSR, only a limited number of known classes are available at the time of training the model and the possibility of unknown classes never seen at training time emerges in the test environment. In such a setting, the unknown classes and their risk should be considered in the algorithm. Such systems require not only to identify and discriminate instances that belong to the source domain (i.e., the seen known classes contained in the training dataset) but also to reject unknown …

Evaluation Of Orca 2 Against Other Llms For Retrieval Augmented Generation, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

This study presents a comprehensive evaluation of Microsoft Research’s Orca 2, a small yet potent language model, in the context of Retrieval Augmented Generation (RAG). The research involved comparing Orca 2 with other significant models such as Llama-2, GPT-3.5-Turbo, and GPT-4, particularly focusing on its application in RAG. Key metrics, included faithfulness, answer relevance, overall score, and inference speed, were assessed. Experiments conducted on high-specification PCs revealed Orca 2’s exceptional performance in generating high quality responses and its efficiency on consumer-grade GPUs, underscoring its potential for scalable RAG applications. This study highlights the pivotal role of smaller, efficient models like …

Large Language Model Powered Agents In The Web, Yang Deng, An Zhang, Yankai Lin, Xu Chen, Ji-Rong Wen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Web applications serve as vital interfaces for users to access information, perform various tasks, and engage with content. Traditional web designs have predominantly focused on user interfaces and static experiences. With the advent of large language models (LLMs), there’s a paradigm shift as we integrate LLM-powered agents into these platforms. These agents bring forth crucial human capabilities like memory and planning to make them behave like humans in completing various tasks, effectively enhancing user engagement and offering tailored interactions in web applications. In this tutorial, we delve into the cutting-edge techniques of LLM-powered agents across various web applications, such as …

Difference Of Convex Functions Programming For Policy Optimization In Reinforcement Learning, Akshat Kumar

Research Collection School Of Computing and Information Systems

We formulate the problem of optimizing an agent's policy within the Markov decision process (MDP) model as a difference-of-convex functions (DC) program. The DC perspective enables optimizing the policy iteratively where each iteration constructs an easier-to-optimize lower bound on the value function using the well known concave-convex procedure. We show that several popular policy gradient based deep RL algorithms (both for discrete and continuous state, action spaces, and stochastic/deterministic policies) such as actor-critic, deterministic policy gradient (DPG), and soft actor critic (SAC) can be derived from the DC perspective. Additionally, the DC formulation enables more sample efficient learning approaches by …

Non-Vacuous Generalization Bounds For Adversarial Risk In Stochastic Neural Networks, Mustafa Waleed, Liznerski Philipp, Antoine Ledent, Wagner Dennis, Wang Puyu, Kloft Marius

Research Collection School Of Computing and Information Systems

Adversarial examples are manipulated samples used to deceive machine learning models, posing a serious threat in safety-critical applications. Existing safety certificates for machine learning models are limited to individual input examples, failing to capture generalization to unseen data. To address this limitation, we propose novel generalization bounds based on the PAC-Bayesian and randomized smoothing frameworks, providing certificates that predict the model’s performance and robustness on unseen test samples based solely on the training data. We present an effective procedure to train and compute the first non-vacuous generalization bounds for neural networks in adversarial settings. Experimental results on the widely recognized …

Q-Learning Based Framework For Solving The Stochastic E-Waste Collection Problem, Dang Viet Anh Nguyen, Aldy Gunawan, Mustafa Misir, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

Electrical and Electronic Equipment (EEE) has evolved into a gateway for accessing technological innovations. However, EEE imposes substantial pressure on the environment due to the shortened life cycles. E-waste encompasses discarded EEE and its components which are no longer in use. This study focuses on the e-waste collection problem and models it as a Vehicle Routing Problem with a heterogeneous fleet and a multi-period planning problem with time windows as well as stochastic travel times. Two different Q-learning-based methods are designed to enhance the search procedure for finding solutions. The first method involves utilizing the state-action value to determine the …

Benchmarking Marl On Long Horizon Sequential Multi-Objective Tasks, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Current MARL benchmarks fall short in simulating realistic scenarios, particularly those involving long action sequences with sequential tasks and multiple conflicting objectives. Addressing this gap, we introduce Multi-Objective SMAC (MOSMAC), a novel MARL benchmark tailored to assess MARL methods on tasks with varying time horizons and multiple objectives. Each MOSMAC task contains one or multiple sequential subtasks. Agents are required to simultaneously balance between two objectives - combat and navigation - to successfully complete each subtask. Our evaluation of nine state-of-the-art MARL algorithms reveals that MOSMAC presents substantial challenges to many state-of-the-art MARL methods and effectively fills a critical gap …

Exploring Graph Neural Networks In Reinforcement Learning: A Comparative Study On Architectures For Locomotion Tasks, Gaukhar Nurbek

Theses and Dissertations

Deep Reinforcement learning (DRL) has gained importance in optimizing control policies, while Graph Neural Networks (GNNs) offer a robust approach for modeling complex relationships within systems represented as graphs. This thesis investigates the integration of DRL and GNNs to optimize control policies for robotic tasks, with a focus on locomotion. It compares static and dynamic GNN architectures for control policy predictions, revealing their strengths and limitations in adapting to locomotion predictions. The study assesses the impact of model structure complexity on GNNs' predictive capabilities, showcasing how intricate model structure can maximize GNNs' potential in capturing spatial and relational dependencies when …

Multi-Script Handwriting Identification By Fragmenting Strokes, Joshua Jude Thomas

Graduate Theses and Dissertations (2019 - present)

This study tests the effectiveness of Multi-Script Handwriting Identification after simplifying character strokes, by segmenting them into sub-parts. Character simplification is performed through splitting the character by branching-points and end-points, a process called stroke fragmentation in this study. The resulting sub-parts of the character are called stroke fragments and are evaluated individually to identify the writer. This process shares similarities with the concept of stroke decomposition in Optical Character Recognition which attempts to recognize characters through the writing strokes that make them up. The main idea of this study is that the characters of different writing‑scripts (English, Chinese, etc.) may …

Exploring The Relationship Between Anxiety And Virtual Reality Sickness, David Wesley Woolverton

Graduate Theses and Dissertations (2019 - present)

As virtual reality (VR) becomes more commonly used in education, it is important to understand the technology’s weakness and mitigate any potential negative effects on student success. One adverse side-effect of VR use is simulation-induced motion sickness, known in the context of VR as VR sickness. Previous research by Howard and Van Zandt (2021) found that possessing a phobia had a significant positive correlation with VR sickness, but only if the phobia is triggered by the simulation, suggesting that symptoms are actually connected to the anxiety the phobia induces. This study explored the hypothesized correlation between anxiety and VR sickness, …

Examining Outcomes Of Privacy Risk And Brand Trust On The Adoption Of Consumer Smart Devices, Marianne C. Loes

Graduate Theses and Dissertations (2019 - present)

With more connected devices on earth than there are people, Internet of Things (IoT) is arguably just as innovative as the original introduction of the Internet. Though much of the research on technology acceptance and adoption has been conducted in organizational settings, the consumer use of IoT technologies, such as smart devices, is becoming a fertile field of research. The merger of these research streams is especially relevant from a societal perspective as smart devices become more embedded in consumer’s daily lives, particularly with the introduction of the “meta verse.” While original technology acceptance research is limited to two system-specific …

Cloud Computing Integration Into Mixed-Reality: Physical To Abstraction, Yassine Chahid, Patrick Slattery

Publications and Research

This research evaluates the progression of cloud computing and mixed-reality technologies, and to identify how these technologies influence advancements in the latter. Both cloud computing and mixed reality have significantly impacted the IT field and the services available to the public and various institutions. Cloud computing provides a valuable way to process information or allocate computational resources on otherwise limited hardware. Augmented or virtual reality hardware would greatly benefit from this by offloading resource-intensive tasks to other machines. The research methodology involves analyzing essential components of both innovations, divided into multiple categories. These components range from physical, hardware-based elements to …

Achieving Responsible Anomaly Detection, Xiao Han

All Graduate Theses and Dissertations, Fall 2023 to Present

In the digital transformation era, safeguarding online systems against anomalies – unusual patterns indicating potential threats or malfunctions – has become crucial. This dissertation embarks on enhancing the accuracy, explainability, and ethical integrity of anomaly detection systems. By integrating advanced machine learning techniques, it improves anomaly detection performance and incorporates fairness and explainability at its core.

The research tackles performance enhancement in anomaly detection by leveraging few-shot learning, demonstrating how systems can effectively identify anomalies with minimal training data. This approach overcomes data scarcity challenges. Reinforcement learning is employed to iteratively refine models, enhancing decision-making processes. Transfer learning enables the …

Exploring Binding Pockets In The Conformational States Of The Sars-Cov-2 Spike Trimers For The Screening Of Allosteric Inhibitors Using Molecular Simulations And Ensemble-Based Ligand Docking, Grace Gupta, Gennady M. Verkhivker

Mathematics, Physics, and Computer Science Faculty Articles and Research

Understanding mechanisms of allosteric regulation remains elusive for the SARS-CoV-2 spike protein, despite the increasing interest and effort in discovering allosteric inhibitors of the viral activity and interactions with the host receptor ACE2. The challenges of discovering allosteric modulators of the SARS-CoV-2 spike proteins are associated with the diversity of cryptic allosteric sites and complex molecular mechanisms that can be employed by allosteric ligands, including the alteration of the conformational equilibrium of spike protein and preferential stabilization of specific functional states. In the current study, we combine conformational dynamics analysis of distinct forms of the full-length spike protein trimers and …

Sports Science: An Entrepreneurial Venture, Nicole J. Jones

Senior Honors Projects

In sports science, ensuring maximum athlete safety and optimizing data utilization are pivotal yet leave room for further work. My project, Unbeaten SafeWare, addresses these critical issues by focusing on two primary concerns: preventing heat-related and cardiac illnesses, which are significant causes of athlete fatalities, and enhancing the transparency and utility of sports data. This initiative involves developing a shirt integrated with sensors to monitor vital signs and an athlete management system to handle data input, storage, analysis, and accessibility for athletes.

The project has advanced through the efforts of a multidisciplinary team, which includes biomedical engineering undergraduates, two faculty …

Online Learning For Acid-Fast Bacilli Detection In Histopathological Images, Shizhao Wang

UNLV Theses, Dissertations, Professional Papers, and Capstones

The acid-fast stain is frequently used for laboratory diagnosis of tuberculosis. It is a labor intensive task requiring thorough examination of extremely high-resolution images to pinpoint the presence of the mycobacteria. This paper presents a machine learning assisted slide image analysis tool with the aim of aiding histopathology professionals in the accurate diagnosis of tuberculosis in patients through the analysis of microscopic imagery. The proposed tool combines a digital whole slide image viewer with an online learning framework. We also conducted a survey of different state-of-the-art online learning methods, and found that MIR with pre-training has the best performance on …

Sliding Markov Decision Processes For Dynamic Task Planning On Uncrewed Aerial Vehicles, Trent Wiens

Department of Mechanical and Materials Engineering: Dissertations, Theses, and Student Research

Mission and flight planning problems for uncrewed aircraft systems (UASs) are typically large and complex in space and computational requirements. With enough time and computing resources, some of these problems may be solvable offline and then executed during flight. In dynamic or uncertain environments, however, the mission may require online adaptation and replanning. In this work, we will discuss methods of creating MDPs for online applications, and a method of using a sliding resolution and receding horizon approach to build and solve Markov Decision Processes (MDPs) in practical planing applications for UASs. In this strategy, called a Sliding Markov Decision …

The Kruger Collection Reimagined: A Case Study In 3d Scanning And Interactive Exhibit Design, Annissa Davis

Department of Anthropology: Theses and Student Research

This thesis examines the use of 3D modeling in museum exhibition to create exploratory exhibits that facilitate unique relationships between the visitors and the collection beyond what is provided by the collection’s in person counterparts. Typical use of 3D modeling in museums is currently often representative rather than exploratory. By employing a Digital Humanities lens to approach the development of a digital exhibition utilizing 3D technology and interactive elements created in a video game engine (Unity), this thesis project evaluates these potential new relationships. Using the Eloise Kruger Collection of Miniatures as a case study, the following text details the …

Multiple Continuous Top-K Queries Over Data Stream, Rui Zhu, Yujin Jia, Xiaochun Yang, Baihua Zheng, Bin Wang, Chuanyu Zong

Research Collection School Of Computing and Information Systems

Continuous top-k" role="presentation" style="box-sizing: border-box; display: inline-block; line-height: 0; font-size: 18.72px; font-size-adjust: none; overflow-wrap: normal; word-spacing: normal; text-wrap-mode: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border: 0px; margin: 0px; padding: 1px 0px; position: relative;">kk query over sliding window is a fundamental challenge in the domain of streaming data management. Specifically, a continuous top-k query q" role="presentation" style="box-sizing: border-box; display: inline-block; line-height: 0; font-size: 18.72px; font-size-adjust: none; overflow-wrap: normal; word-spacing: normal; text-wrap-mode: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border: 0px; margin: 0px; padding: 1px 0px; position: relative;" …

Collaborative Deep Reinforcement Learning For Solving Multi-Objective Vehicle Routing Problems, Yaoxin Wu, Mingfeng Fan, Zhiguang Cao, Ruobin Gao, Yaqing Hou, Guillaume Sartoretti

Research Collection School Of Computing and Information Systems

Existing deep reinforcement learning (DRL) methods for multi-objective vehicle routing problems (MOVRPs) typically decompose an MOVRP into subproblems with respective preferences and then train policies to solve corresponding subproblems. However, such a paradigm is still less effective in tackling the intricate interactions among subproblems, thus holding back the quality of the Pareto solutions. To counteract this limitation, we introduce a collaborative deep reinforcement learning method. We first propose a preference-based attention network (PAN) that allows the DRL agents to reason out solutions to subproblems in parallel, where a shared encoder learns the instance embedding and a decoder is tailored for …

Artificial Intelligence-Powered Assessment Of Pathologic Response To Neoadjuvant Atezolizumab In Patients With Nsclc: Results From The Lcmc3 Study, Sanja Dacic, William D Travis, Jennifer M Giltnane, Filip Kos, John Abel, Stephanie Hilz, Junya Fujimoto, Lynette Sholl, Jon Ritter, Farah Khalil, Yi Liu, Amaro Taylor-Weiner, Murray Resnick, Hui Yu, Fred R Hirsch, Paul A Bunn, David P Carbone, Valerie Rusch, David J Kwiatkowski, Bruce E Johnson, Jay M Lee, Stephanie R Hennek, Ilan Wapinski, Alan Nicholas, Ann Johnson, Katja Schulze, Mark G Kris, Ignacio I Wistuba

Faculty, Staff and Student Publications

Introduction: Pathologic response (PathR) by histopathologic assessment of resected specimens may be an early clinical end point associated with long-term outcomes with neoadjuvant therapy. Digital pathology may improve the efficiency and precision of PathR assessment. LCMC3 (NCT02927301) evaluated neoadjuvant atezolizumab in patients with resectable NSCLC and reported a 20% major PathR rate.

Methods: We determined PathR in primary tumor resection specimens using guidelines-based visual techniques and developed a convolutional neural network model using the same criteria to digitally measure the percent viable tumor on whole-slide images. Concordance was evaluated between visual determination of percent viable tumor (n = …

Rule-Guided Counterfactual Explainable Recommendation, Yinwei Wei, Xiaoyang Qu, Xiang Wang, Yunshan Ma, Liqiang Nie, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

To empower the trust of current recommender systems, the counterfactual explanation (CE) method is adopted to generate the counterfactual instance for each input and take their changes causing the different outcomes as the explanation. Although promising results have been achieved by existing CE-based methods, we propose to generate the attribute-oriented counterfactual explanation. Different from them, we aim to generate the counterfactual instance by performing the intervention on the attributes, and then build an attribute-oriented counterfactual explainable recommender system. Considering the correlation and categorical values of attributes, how to efficiently generate the reliable counterfactual instances on the attributes challenges us. To …

Learning To Generate Explainable Stock Predictions Using Self‑Reflective Large Language Models, Kelvin J.L. Koa, Yunshan Ma, Ritchie Ng, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important …

Fashionregen: Llm‑Empowered Fashion Report Generation, Yujuan Ding, Yunshan Ma, Wenqi Fan, Yige Yao, Tat‑Seng Chua, Qing Li

Research Collection School Of Computing and Information Systems

Fashion analysis refers to the process of examining and evaluating trends, styles, and elements within the fashion industry to understand and interpret its current state, generating fashion reports. It is traditionally performed by fashion professionals based on their expertise and experience, which requires high labour cost and may also produce biased results for relying heavily on a small group of people. In this paper, to tackle the Fashion Report Generation (FashionReGen) task, we propose an intelligent Fashion Analyzing and Reporting system based the advanced Large Language Models (LLMs), debbed as GPT-FAR. Specifically, it tries to deliver FashionReGen based on effective …

Policy-Based Remote User Authentication From Multi-Biometrics, Yangguang Tian, Yingjiu Li, Robert H. Deng, Guomin Yang, Nan Li

Research Collection School Of Computing and Information Systems

In this paper, we introduce the first generic framework of policy-based remote user authentication from multiple biometrics. The proposed framework allows an authorized user to remotely authenticate herself to an authentication server using her multiple biometrics, which enhances both the security and usability of user authentications. The authentication server approves a user's authentication request if and only if the user's multiple biometrics satisfies an authentication policy. In particular, the authentication policy can be dynamically updated to satisfy different security and usability requirements in practice. We implement an instantiation of the proposed framework and report its performance under various authentication policies.

Quantum Machine Learning For Credit Scoring, Nikolaos Schetakis, Davit Aghamalyan, Micheael Boguslavsky, Agnieszka Rees, Marc Rakotomalala, Paul Robert Griffin

Research Collection School Of Computing and Information Systems

This study investigates the integration of quantum circuits with classical neural networks for enhancing credit scoring for small- and medium-sized enterprises (SMEs). We introduce a hybrid quantum–classical model, focusing on the synergy between quantum and classical rather than comparing the performance of separate quantum and classical models. Our model incorporates a quantum layer into a traditional neural network, achieving notable reductions in training time. We apply this innovative framework to a binary classification task with a proprietary real-world classical credit default dataset for SMEs in Singapore. The results indicate that our hybrid model achieves efficient training, requiring significantly fewer epochs …

Learning Adversarial Semantic Embeddings For Zero-Shot Recognition In Open Worlds, Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Research Collection School Of Computing and Information Systems

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes for which neither samples (e.g., images) nor their side semantic information is known during training. Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes. To tackle this combined ZSL and OSR problem, we consider the case of “Zero-Shot Open-Set Recognition” (ZS-OSR), where a model is trained under the ZSL …

On The Feasibility Of Simple Transformer For Dynamic Graph Modeling, Yuxia Wu, Yuan Fang, Lizi Liao

Research Collection School Of Computing and Information Systems

Dynamic graph modeling is crucial for understanding complex structures in web graphs, spanning applications in social networks, recommender systems, and more. Most existing methods primarily emphasize structural dependencies and their temporal changes. However, these approaches often overlook detailed temporal aspects or struggle with long-term dependencies. Furthermore, many solutions overly complicate the process by emphasizing intricate module designs to capture dynamic evolutions. In this work, we harness the strength of the Transformer’s self-attention mechanism, known for adeptly handling long-range dependencies in sequence modeling. Our approach offers a simple Transformer model, called SimpleDyG, tailored for dynamic graph modeling without complex modifications. We …

An Adaptive Large Neighborhood Search For The Multi-Vehicle Profitable Tour Problem With Flexible Compartments And Mandatory Customers, Vincent F. Yu, Nabila Yuraisyah Salsabila, Aldy Gunawan, Anggun Nurfitriani Handoko

Research Collection School Of Computing and Information Systems

The home-refill delivery system is a business model that addresses the concerns of plastic waste and its impact on the environment. It allows customers to pick up their household goods at their doorsteps and refill them into their own containers. However, the difficulty in accessing customers’ locations and product consolidations are undeniable challenges. To overcome these issues, we introduce a new variant of the Profitable Tour Problem, named the multi-vehicle profitable tour problem with flexible compartments and mandatory customers (MVPTPFC-MC). The objective is to maximize the difference between the total collected profit and the traveling cost. We model the proposed …