Digital Commons Network^™

Time-Controllable Keyword Search Scheme With Efficient Revocation In Mobile E-Health Cloud, Yinbin Miao, Feng Li, Xinghua Li, Zhiquan Liu, Jianting Ning, Hongwei Li, Kim-Kwang Raymond Choo, Deng, Robert H.

Research Collection School Of Computing and Information Systems

Electronic health (e-health) systems may outsource data such as patient e-health records to mobile cloud servers for efficiency gains (e.g., minimizing local storage and computation costs). However, such a move may result in privacy implications in the presence of semi-honest cloud servers. Searchable Encryption (SE) can potentially facilitate privacy-preserving searches based on keywords for encrypted data stored in the mobile cloud, but most existing SE solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users for specified time ranges). Hence, in this paper we design a time-controllable keyword search scheme by using an attribute-based …

Breathpro: Monitoring Breathing Mode During Running With Earables, Changshuo Hu, Thivya Kandappu, Yang Liu, Cecilia Mascolo, Dong Ma

Research Collection School Of Computing and Information Systems

Running is a popular and accessible form of aerobic exercise, significantly benefiting our health and wellness. By monitoring a range of running parameters with wearable devices, runners can gain a deep understanding of their running behavior, facilitating performance improvement in future runs. Among these parameters, breathing, which fuels our bodies with oxygen and expels carbon dioxide, is crucial to improving the efficiency of running. While previous studies have made substantial progress in measuring breathing rate, exploration of additional breathing monitoring during running is still lacking. In this work, we fill this gap by presenting BreathPro, the first breathing mode monitoring …

Instant3d: Instant Text-To-3d Generation, Ming Li, Pan Zhou, Jia-Wei Liu, Jussi Keppo, Shuicheng Yan, Xiangyu Xu

Research Collection School Of Computing and Information Systems

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core …

Reinforcement Nash Equilibrium Solver, Xinrun Wang, Chang Yang, Shuxin Li, Pengdeng Li, Xiao Huang, Hau Chan, Bo An

Research Collection School Of Computing and Information Systems

Nash Equilibrium (NE) is the canonical solution concept of game theory, which provides an elegant tool to understand the rationalities. Computing NE in two- or multi-player general-sum games is PPAD-Complete. Therefore, in this work, we propose REinforcement Nash Equilibrium Solver (RENES), which trains a single policy to modify the games with different sizes and applies the solvers on the modified games where the obtained solution is evaluated on the original games. Specifically, our contributions are threefold. i) We represent the games as ��-rank response graphs and leverage graph neural network (GNN) to handle the games with different sizes as inputs; …

Knowledge Enhanced Multi-Intent Transformer Network For Recommendation, Ding Zou, Wei Wei, Feida Zhu, Chuanyu Xu, Tao Zhang, Chengfu Huo

Research Collection School Of Computing and Information Systems

Incorporating Knowledge Graphs (KGs) into Recommendation has attracted growing attention in industry, due to the great potential of KG in providing abundant supplementary information and interpretability for the underlying models. However, simply integrating KG into recommendation usually brings in negative feedback in industry, mainly due to the ignorance of the following two factors: i) users' multiple intents, which involve diverse nodes in KG. For example, in e-commerce scenarios, users may exhibit preferences for specific styles, brands, or colors. ii) knowledge noise, which is a prevalent issue in Knowledge Enhanced Recommendation (KGR) and even more severe in industry scenarios. The irrelevant …

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 …

Dlvs4audio2sheet: Deep Learning-Based Vocal Separation For Audio Into Music Sheet Conversion, Nicole Teo, Zhaoxia Wang, Ezekiel Ghe, Yee Sen Tan, Kevan Oktavio, Alexander Vincent Lewi, Allyne Zhang, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

While manual transcription tools exist, music enthusiasts, including amateur singers, still encounter challenges when transcribing performances into sheet music. This paper addresses the complex task of translating music audio into music sheets, particularly challenging in the intricate field of choral arrangements where multiple voices intertwine. We propose DLVS4Audio2Sheet, a novel method leveraging advanced deep learning models, Open-Unmix and Band-Split Recurrent Neural Networks (BSRNN), for vocal separation. DLVS4Audio2Sheet segments choral audio into individual vocal sections and selects the optimal model for further processing, aiming towards audio into music sheet conversion. We evaluate DLVS4Audio2Sheet’s performance using these deep learning algorithms and assess …

Analyzing And Revivifying Function Signature Inference Using Deep Learning, Yan Lin, Trisha Singhal, Debin Gao, David Lo

Research Collection School Of Computing and Information Systems

Function signature plays an important role in binary analysis and security enhancement, with typical examples in bug finding and control-flow integrity enforcement. However, recovery of function signatures by static binary analysis is challenging since crucial information vital for such recovery is stripped off during compilation. Although function signature recovery using deep learning (DL) is proposed in an effort to handle such challenges, the reported accuracy is low for binaries compiled with optimizations. In this paper, we first perform a systematic study to quantify the extent to which compiler optimizations (negatively) impact the accuracy of existing DL techniques based on Recurrent …

Robust Auto-Scaling With Probabilistic Workload Forecasting For Cloud Databases, Haitian Hang, Xiu Tang, Jianling Sun, Lingfeng Bao, David Lo, Haoye Wang

Research Collection School Of Computing and Information Systems

Auto-scaling is crucial for achieving elasticity in cloud databases as well as other cloud systems. Predictive auto-scaling, which leverages forecasting techniques to adjust resources based on predicted workload, has been widely adopted. However, the inherent inaccuracy of forecasting presents a significant challenge, potentially causing resource under-provisioning. To address this challenge, we propose robust predictive auto-scaling that considers the uncertainty in forecasts. Unlike previous predictive approaches that rely on single-valued forecasts, we leverage probabilistic forecasting techniques to generate quan-tile forecasts, providing a more comprehensive understanding of the potential future workloads. By formulating the auto-scaling problem as a robust optimization problem, we …

Automatic Grading Of Short Answers Using Large Language Models In Software Engineering Courses, Nguyen Binh Duong Ta, Yi Meng Chai

Research Collection School Of Computing and Information Systems

Short-answer based questions have been used widely due to their effectiveness in assessing whether the desired learning outcomes have been attained by students. However, due to their open-ended nature, many different answers could be considered entirely or partially correct for the same question. In the context of computer science and software engineering courses where the enrolment has been increasing recently, manual grading of short-answer questions is a time-consuming and tedious process for instructors. In software engineering courses, assessments concern not just coding but many other aspects of software development such as system analysis, architecture design, software processes and operation methodologies …

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 …

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 …

Super Mario Evolution By The Augmentation Of Topology, Russell A. Autin

LSU New Orleans Theses and Dissertations

This paper describes the creation and development of an implementation of the NeuroEvolution of Augmenting Topologies (NEAT) architecture to train an agent to play Super Mario Brothers. Building off of a basic implementation of NEAT, this thesis project shows the process of refining the fitness calculation that ranks the networks in the population and also defines the creation and application of a dataset to train the agent. The use of a dataset to train an agent is a novel idea in the world of reinforcement learning because, generally, reinforcement learning trains an agent to complete a singular task like the …

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 …

Cross-Framework Validation Of Cnn Architectures: From Pytorch To Onnx, Shreya Nandanwar

Theses and Dissertations

This research presents CIPAC (CNN Inter-framework Parameter Analysis and Comparison), a validation approach designed to ensure the integrity of Deep Learning models during their transfer between computational frameworks. Although initially tested on Convolutional Neural Networks (CNNs), CIPAC is versatile enough for various Deep Learning architectures. It goes beyond traditional methods that focus on output accuracy, by examining the models’ architecture, parameters, and components to maintain consistency after transitions, like moving from PyTorch to ONNX framework. Inspired by software architecture’s stringent validation standards, CIPAC addresses the challenges of working with Machine Learning models on different platforms, making it an essential tool …

Learning Scene Semantics For 3d Scene Retrieval, Natalie Gleason

Honors Theses

This project presents a comprehensive exploration into semantics-driven 3D scene retrieval, aiming to bridge the gap between 2D sketches/images and 3D models. Through four distinct research objectives, this project endeavors to construct a foundational infrastructure, develop methodologies for quantifying semantic similarity, and advance a semantics-based retrieval framework for 2D scene sketch-based and image-based 3D scene retrieval. Leveraging WordNet as a foundational semantic ontology library, the research proposes the construction of an extensive hierarchical scene semantic tree, enriching 2D/3D scenes with encoded semantic information. The methodologies for semantic similarity computation utilize this semantic tree to bridge the semantic disparity between 2D …

Generative Ai In Education From The Perspective Of Students, Educators, And Administrators, Aashish Ghimire

All Graduate Theses and Dissertations, Fall 2023 to Present

This research explores how advanced artificial intelligence (AI), like the technology that powers tools such as ChatGPT, is changing the way we teach and learn in schools and universities. Imagine AI helping to summarize thick legal documents into something you can read over a coffee break or helping students learn how to code by offering personalized guidance. We looked into how teachers feel about using these AI tools in their classrooms, what kind of rules schools have about them, and how they can make learning programming easier for students. We found that most teachers are excited about the possibilities but …

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 …

A Review Of Student Attitudes Towards Keystroke Logging And Plagiarism Detection In Introductory Computer Science Courses, Caleb Syndergaard

All Graduate Theses and Dissertations, Fall 2023 to Present

The following paper addresses student attitudes towards keystroke logging and plagiarism prevention measures. Specifically, the paper concerns itself with changes made to the “ShowYourWork” plugin, which was implemented to log the keystrokes of students in Utah State University’s introductory Computer Science course, CS1400. Recent work performed by the Edwards Lab provided insights into students’ feelings towards keystroke logging as a measure of deterring plagiarism. As a result of that research, we have concluded that measures need to be taken to enable students to have more control over their data and assist students to feel more comfortable with keystroke logging. This …

Inferring A Hierarchical Input Type For An Sql Query, Santosh Aryal

All Graduate Theses and Dissertations, Fall 2023 to Present

SQL queries are a common method to retrieve information from databases, much like asking a detailed question and getting a precise answer. Plug-and-play queries simplify the process of querying. In a Plug-and-play SQL query a programmer sketches the shape of the input to the query as a hierarchy. But the programmer could make a mistake in specifying the hierarchy and it takes programmer time and effort to specify the hierarchy. A better solution is to automatically infer the hierarchy from a query. This thesis presents a system to infer a hierarchical input type for an SQL query. We consider two …

Empowering Graphics: A Distributed Rendering Architecture For Inclusive Access To Modern Gpu Capabilities, Taylor Anderson

All Graduate Theses and Dissertations, Fall 2023 to Present

Modern rendering software requires powerful GPUs with the latest hardware features in order to utilize all of the newest rendering techniques. Many users do not have access to this hardware, and rely on remote server farms or reduced performance to achieve usable results. In this thesis, the software is designed and created to allow for a user to share the resources of their computer with another, modeling a split-screen setup like was common in the past, but without requiring users to be in the same location.

By designing the software from the ground up to support this, instead of adding …

Decentralized Unknown Building Exploration By Frontier Incentivization And Voronoi Segmentation In A Communication Restricted Domain, Huzeyfe M. Kocabas

All Graduate Theses and Dissertations, Fall 2023 to Present

Exploring unknown environments using multiple robots poses a complex challenge, particularly in situations where communication between robots is either impossible or limited. Existing exploration techniques exhibit research gaps due to unrealistic communication assumptions or the computational complexities associated with exploration strategies in unfamiliar domains. In our investigation of multi-robot exploration in unknown areas, we employed various exploration and coordination techniques, evaluating their performance in terms of robustness and efficiency across different levels of environmental complexity.

Our research is centered on optimizing the exploration process through strategic agent distribution. We initially address the challenge of city roadway coverage, aiming to minimize …

Pedestrian Pathing Prediction Using Complex Contextual Behavioral Data In High Foot Traffic Settings, Laurel Bingham

All Graduate Theses and Dissertations, Fall 2023 to Present

Ensuring the safe integration of autonomous vehicles into real-world environments requires a comprehensive understanding of pedestrian behavior. This study addresses the challenge of predicting the movement and crossing intentions of pedestrians, a crucial aspect in the development of fully autonomous vehicles.

The research focuses on leveraging Honda's TITAN dataset, comprising 700 unique clips captured by moving vehicles in high-foot-traffic areas of Tokyo, Japan. Each clip provides detailed contextual information, including human-labeled tags for individuals and vehicles, encompassing attributes such as age, motion status, and communicative actions. Long Short-Term Memory (LSTM) networks were employed and trained on various combinations of contextual …

A Framework That Explores The Cognitive Load Of Cs1 Assignments Using Pausing Behavior, Joshua O. Urry

All Graduate Theses and Dissertations, Fall 2023 to Present

Pausing behavior in introductory Computer Science (CS1) courses has been related to a student’s performance in the course and could be linked to a student’s cognitive load, or assignment difficulty. Having an objective measure of the cognitive load would be beneficial to course instructors as it would help them design assignments that are not too difficult. Two studies are presented in this work. The first study uses Cognitive Load Theory and Vygotsky’s Zone of Proximal Development as a theoretical framework to analyze pause times between keystrokes to better understand what types of assignments need more educational support than others. The …

Advancing Game Development And Ai Integration: An Extensible Game Engine With Integrated Ai Support For Real-World Deployment And Efficient Model Development, Ryan Anderson

All Graduate Theses and Dissertations, Fall 2023 to Present

This thesis introduces Acacia, a game engine with built-in artificial intelligence (AI) capabilities. Acacia allows game developers to effortlessly incorporate Reinforcement Learning (RL) algorithms into their creations. By tagging game elements to convey information about the game state or rewards, developers gain precise control over how RL algorithms interact with their games, mirroring real player behavior or providing full knowledge of the game world.

To showcase Acacia’s versatility, the thesis presents three games across different genres, each demonstrating the engine’s AI plugin. The goal is to establish Acacia as a preferred resource for creating 2D games with RL support without …

Satellite Image Analysis And Sidewalk Classification Using Deep Learning Models, Subeksha Khanal

Master's Theses

Lack of sidewalk pavement can contribute to pedestrian fatalities and injuries in the USA. Although many researchers have conducted research on sidewalk detection, there are not many publicly available datasets that we would work on for sidewalk classification. In this study, I conducted classification tasks using pretrained CNN models including VGG16 and ResNet50. I extended these models by adding custom layers at the top of pretrained layers, employing various techniques to improve the classification accuracy.

The dataset comprises 4,731 images of sidewalk based on occlusion levels, including images where the sidewalk is visible from overhead and instances where sidewalk is …

Denoising Diffusion Probabilistic Models Based Accelerated Mri, Alexander Francis Bugielski

Theses and Dissertations

Magnetic Resonance Imaging (MRI) is a cornerstone in obtaining intricate visualizations of anatomy and physiological processes within the human body. However, its extensive scan duration not only causes patient discomfort but also increases the likelihood of motion-induced artifacts in the images. To address such a challenge, this study investigates deep neural network models for reconstructing high-resolution MRI images from noisy and significantly undersampled data in a supervised learning manner. Specifically, it compares three models: a conventional U-Net, a self-attentive U-Net, and an innovative probabilistic diffusion model that builds upon the self-attentive U-Net architecture. These models are evaluated on their ability …

Representation Learning For Generative Models With Applications To Healthcare, Astronautics, And Aviation, Van Minh Nguyen

Theses and Dissertations

This dissertation explores applications of representation learning and generative models to challenges in healthcare, astronautics, and aviation.

The first part investigates the use of Generative Adversarial Networks (GANs) to synthesize realistic electronic health record (EHR) data. An initial attempt at training a GAN on the MIMIC-IV dataset encountered stability and convergence issues, motivating a deeper study of 1-Lipschitz regularization techniques for Auxiliary Classifier GANs (AC-GANs). An extensive ablation study on the CIFAR-10 dataset found that Spectral Normalization is key for AC-GAN stability and performance, while Weight Clipping fails to converge without Spectral Normalization. Analysis of the training dynamics provided further …

A Comparative Analysis Of Field Electron Emission From Carbon Black Embedded Within Insulated Copper Hollowed Wires And Glass Tubes, Hatem A. Al-Braikat, Ahmad M D Jaber, Adel M. Abuamr, Mazen A. Madanat, Aseel A. Al-Jbarart, M-Ali H. Al-Akhras, Marwan S. Mousa

Karbala International Journal of Modern Science

In this study, two different methods are used to investigate carbon black as a cold field electron emitter. The first method is to incorporate carbon black into a specially designed insulated copper hollowed wire. The wire has a cup-shaped structure created by electrochemical etching. The second method involves the incorporation of carbon black into narrow glass tubes. A Comparative analyses is carried out to evaluate the effectiveness of each method. To evaluate the performance of the samples, the current-voltage characteristics will be examined using field electron microscopes. This analysis will provide an understanding of the emission of the carbon black …

Causes And Consequences Of Inefficient Drilling And Blasting In Mine Development Headings: A Case Study Of Hard Rock Gold Mining Operations In Northern Tanzania, George Bennett

Tanzania Journal of Engineering and Technology (TJET)

Despite the introduction of the perimeter blasting technique at the Tulawaka Gold Mine, the mine continued to suffer from an overbreak of mine development headings, with an average overbreak of 24% every 22 m, which is approximately twice the acceptable 10% overbreak. The causes of this problem include ineffective drilling practices and uneven and excessive charging of explosives, resulting in a slightly high powder factor of 3.94 kg/m3 instead of 3.8 kg/m3, as per the design. The problem of overbreak resulted in ore dilution, a longer mine development cycle time and additional costs of approximately US$ 45 per cut, especially …