Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 30 of 219
Full-Text Articles in Entire DC Network
Learning-Based Sensing For Solving Health-Related Problems, Minglong Sun
Learning-Based Sensing For Solving Health-Related Problems, Minglong Sun
Dissertations, Theses, and Masters Projects
In the field of ubiquitous computing, health-related problem analysis has gained increasing attention. Collaborations between domain doctors and computing researchers have been established to recognize and address health-related issues. However, accurate detection and recognition of health-related problems remain a major challenge that attracts extensive research efforts. Among all the research works, wearable sensors-based health-related problem recognition is promising as it is low cost, low power, and easy to carry. This dissertation focuses on utilizing wearable sensors to study health-related problems. The first project introduced in this dissertation is TremorSense, a PD tremor detection system designed to classify Parkinson's Disease hand …
Low-Rank Matrix And Tensor Models For Data Science Applications, Jeremy Moulton Myers
Low-Rank Matrix And Tensor Models For Data Science Applications, Jeremy Moulton Myers
Dissertations, Theses, and Masters Projects
Low-rank approximations play an important role in data science analysis and applications. When the model is linear and the data is represented as a matrix, the optimal rank-r approximation is given by the r dominant factors of the singular value decomposition (SVD). When the model is multilinear and the data is represented as a multi-way array called a tensor, the optimal rank-r approximation may not even exist. Nonetheless, the canonical polyadic decomposition (CP) provides a useful low-rank tensor approximation for interpretability and analysis in a way similar to the matrix SVD but across multiple axes simultaneously. In this dissertation, we …
Exploring Transient Execution Vulnerabilities, Side-Channel Attacks, And Defenses, Tao Zhang
Exploring Transient Execution Vulnerabilities, Side-Channel Attacks, And Defenses, Tao Zhang
Dissertations, Theses, and Masters Projects
Modern microprocessors utilize branch prediction and speculative execution to enhance instruction throughput. Instead of stalling the pipeline and waiting for branch targets to be computed, the CPU consults branch predictors for a possible destination and performs speculative execution. These microarchitectural techniques improve the efficiency of instruction pipelining and out-of-order execution, enabling higher performance and better resource utilization. Despite their widespread adoption, the potential security implications of branch misprediction and transient execution have not drawn much attention until recently. Around early 2018, the discovery of Spectre attacks exposed critical vulnerabilities in CPUs, undermining both software and hardware isolation and confidentiality. These …
A Reevaluation Of Why Crypto-Detectors Fail: A Systematic Revaluation Of Cryptographic Misuse Detection Techniques, Scott Marsden
A Reevaluation Of Why Crypto-Detectors Fail: A Systematic Revaluation Of Cryptographic Misuse Detection Techniques, Scott Marsden
Dissertations, Theses, and Masters Projects
The correct use of cryptography is central to ensuring data security in modern software systems. Hence, several academic and commercial static analysis tools have been developed for detecting and mitigating crypto-API misuse. While developers are optimistically adopting these crypto-API misuse detectors (or crypto-detectors) in their software development cycles, this momentum must be accompanied by a rigorous understanding of their effectiveness at finding crypto-API misuse in practice. The original paper presents the MASC framework, which enables a systematic and data-driven evaluation of crypto-detectors using mutation testing. MASC was grounded in a comprehensive view of the problem space by developing a data-driven …
Learning-Based Ubiquitous Sensing For Solving Real-World Problems, Woosub Jung
Learning-Based Ubiquitous Sensing For Solving Real-World Problems, Woosub Jung
Dissertations, Theses, and Masters Projects
Recently, as the Internet of Things (IoT) technology has become smaller and cheaper, ubiquitous sensing ability within these devices has become increasingly accessible. Learning methods have also become more complex in the field of computer science ac- cordingly. However, there remains a gap between these learning approaches and many problems in other disciplinary fields. In this dissertation, I investigate four different learning-based studies via ubiquitous sensing for solving real-world problems, such as in IoT security, athletics, and healthcare. First, I designed an online intrusion detection system for IoT devices via power auditing. To realize the real-time system, I created a …
Exploring Software Licensing Issues Faced By Legal Practitioners, Nathan James Wintersgill
Exploring Software Licensing Issues Faced By Legal Practitioners, Nathan James Wintersgill
Dissertations, Theses, and Masters Projects
Most modern software products incorporate open source components, which requires compliance with each component’s licenses. As noncompliance can lead to significant repercussions, organizations often seek advice from legal practitioners to maintain license compliance, address licensing issues, and manage the risks of noncompliance. While legal practitioners play a critical role in the process, little is known in the software engineering community about their experiences within the open source license compliance ecosystem. To fill this knowledge gap, a joint team of software engineering and legal researchers designed and conducted a survey with 30 legal practitioners and related occupations and then held 16 …
A Comprehensive Study Of Bills Of Materials For Software Systems, Trevor Stalnaker
A Comprehensive Study Of Bills Of Materials For Software Systems, Trevor Stalnaker
Dissertations, Theses, and Masters Projects
Software Bills of Materials (SBOMs) have emerged as tools to facilitate the management of software dependencies, vulnerabilities, licenses, and the supply chain. Significant effort has been devoted to increasing SBOM awareness and developing SBOM formats and tools. Despite this effort, recent studies have shown that SBOMs are still an early technology not adequately adopted in practice yet, mainly due to limited SBOM tooling and lack of industry consensus on SBOM content, tool usage, and practical benefits. Expanding on previous research, this paper reports a comprehensive study that first investigates the current challenges stakeholders encounter when creating and using SBOMs. The …
Domain-Specific Optimization For Machine Learning System, Yu Chen
Domain-Specific Optimization For Machine Learning System, Yu Chen
Dissertations, Theses, and Masters Projects
The machine learning (ML) system has been an indispensable part of the ML ecosystem in recent years. The rapid growth of ML brings new system challenges such as the need of handling more large-scale data and computation, the requirements for higher execution performance, and lower resource usage, stimulating the demand for improving ML system. General-purpose system optimization is widely used but brings limited benefits because ML applications vary in execution behaviors based on their algorithms, input data, and configurations. It's difficult to perform comprehensive ML system optimizations without application specific information. Therefore, domain-specific optimization, a method that optimizes particular types …
Recoverable Memory Bank For Class-Incremental Learning, Jiangtao Kong
Recoverable Memory Bank For Class-Incremental Learning, Jiangtao Kong
Dissertations, Theses, and Masters Projects
Incremental learning aims to enable machine learning systems to sequentially learn new tasks without forgetting the old ones. While some existing methods, such as data replay-based and parameter isolation-based approaches, achieve remarkable results in incremental learning, they often suffer from memory limits, privacy issues, or generation instability. To address these problems, we propose Recoverable Memory Bank (RMB), a novel non-exemplar-based approach for class incremental learning (CIL). Specifically, we design a dynamic memory bank that stores only one aggregated memory representing each class of the old tasks. Next, we propose a novel method that combines a high-dimensional space rotation matrix and …
Intelligent Software Tooling For Improving Software Development, Nathan Allen Cooper
Intelligent Software Tooling For Improving Software Development, Nathan Allen Cooper
Dissertations, Theses, and Masters Projects
Software has eaten the world with many of the necessities and quality of life services people use requiring software. Therefore, tools that improve the software development experience can have a significant impact on the world such as generating code and test cases, detecting bugs, question and answering, etc. The success of Deep Learning (DL) over the past decade has shown huge advancements in automation across many domains, including Software Development processes. One of the main reasons behind this success is the availability of large datasets such as open-source code available through GitHub or image datasets of mobile Graphical User Interfaces …
Appearance Driven Reflectance Modeling, James Christopher Bieron
Appearance Driven Reflectance Modeling, James Christopher Bieron
Dissertations, Theses, and Masters Projects
Creating realistic computer generated imagery is essential for modern movies and video games. Recreating the appearance of materials is integral to generating such photo-realistic images. While the problem of how to model materials is well studied, here we will focus on the question of how to recreate the appearance of specific materials found in the real world. In this dissertation we will begin with a short introduction to rendering, followed by a discussion of various material models, techniques for measuring reflectance, and strategies for fitting these models to reflectance data. We will then introduce a novel two-stage process for fitting, …
Achieving Real-Time Dnn Execution On Mobile Devices With Compiler Optimizations, Wei Niu
Achieving Real-Time Dnn Execution On Mobile Devices With Compiler Optimizations, Wei Niu
Dissertations, Theses, and Masters Projects
Deep learning, particularly deep neural networks (DNNs), has led to significant advancements in various fields, such as autonomous driving, natural language processing, extended reality (XR), and view synthesis. Mobile and edge devices, with their efficient and specialized processors and suitability for real-time scenarios, have become the primary carriers for these emerging applications. The advancements in AutoML tools (e.g., Network Architecture Search) and training techniques have resulted in increasingly complex and deep DNN architectures with larger computational requirements. However, achieving real-time DNN execution (inference) on mobile devices is a challenging task due to the limited computing and storage resources available on …
Matfusion: A Generative Diffusion Model For Svbrdf Capture, Samuel Lee Sartor
Matfusion: A Generative Diffusion Model For Svbrdf Capture, Samuel Lee Sartor
Dissertations, Theses, and Masters Projects
We formulate SVBRDF estimation from photographs as a diffusion task. To model the distribution of spatially varying materials, we first train a novel unconditional SVBRDF diffusion backbone model on a large set of 312,165 synthetic spatially varying material exemplars. This SVBRDF diffusion backbone model, named MatFusion, can then serve as a basis for refining a conditional diffusion model to estimate the material properties from a photograph under controlled or uncontrolled lighting. Our backbone MatFusion model is trained using only a loss on the reflectance properties, and therefore refinement can be paired with more expensive rendering methods without the need for …
Program Analysis For Software Engineers And Students, Jialiang Tan
Program Analysis For Software Engineers And Students, Jialiang Tan
Dissertations, Theses, and Masters Projects
Software inefficiencies are inevitable in computer systems. At the code level, software packages have become increasingly complex, they are comprised of a large amount of source code, sophisticated control and data flow, and growing levels of abstraction. This complexity often introduces inefficiencies across software stacks, leading to performance degradation. At the resource level, the evolution of hardware outpaces the performance optimization of software, leading to resource wastage and energy dissipation in emerging architecture. To better understand program behaviors, software developers take advantage of performance profiling tools. Existing profiling techniques, whether fine-grained profilers or coarse-grained profilers focus on identifying hotspots, which …
Efficient Parallelization Of Irregular Applications On Gpu Architectures, Qihan Wang
Efficient Parallelization Of Irregular Applications On Gpu Architectures, Qihan Wang
Dissertations, Theses, and Masters Projects
With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with a computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to a coarse-grained kernel; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. …
Exploring Multi-Level Parallelism For Graph-Based Applications Via Algorithm And System Co-Design, Zhen Peng
Exploring Multi-Level Parallelism For Graph-Based Applications Via Algorithm And System Co-Design, Zhen Peng
Dissertations, Theses, and Masters Projects
Graph processing is at the heart of many modern applications where graphs are used as the basic data structure to represent the entities of interest and the relationships between them. Improving the performance of graph-based applications, especially using parallelism techniques, has drawn significant interest both in academia and industry. On the one hand, modern CPU architectures are able to provide massive computational power by using sophisticated memory hierarchy and multi-level parallelism, including thread-level parallelism, data-level parallelism, etc. On the other hand, graph processing workloads are notoriously challenging for achieving high performance due to their irregular computation pattern and unpredictable control …
Techniques For Accelerating Large-Scale Automata Processing, Hongyuan Liu
Techniques For Accelerating Large-Scale Automata Processing, Hongyuan Liu
Dissertations, Theses, and Masters Projects
The big-data era has brought new challenges to computer architectures due to the large-scale computation and data. Moreover, this problem becomes critical in several domains where the computation is also irregular, among which we focus on automata processing in this dissertation. Automata are widely used in applications from different domains such as network intrusion detection, machine learning, and parsing. Large-scale automata processing is challenging for traditional von Neumann architectures. To this end, many accelerator prototypes have been proposed. Micron's Automata Processor (AP) is an example. However, as a spatial architecture, it is unable to handle large automata programs without repeated …
Practical Gpgpu Application Resilience Estimation And Fortification, Lishan Yang
Practical Gpgpu Application Resilience Estimation And Fortification, Lishan Yang
Dissertations, Theses, and Masters Projects
Graphics Processing Units (GPUs) are becoming a de facto solution for accelerating a wide range of applications but remain susceptible to transient hardware faults (soft errors) that can easily compromise application output. One of the major challenges in the domain of GPU reliability is to accurately measure general purpose GPU (GPGPU) application resilience to transient faults. This challenge stems from the fact that a typical GPGPU application spawns a huge number of threads and then utilizes a large amount of potentially unreliable compute and memory resources available on the GPUs. As the number of possible fault locations can be in …
Flexible And Robust Iterative Methods For The Partial Singular Value Decomposition, Steven Goldenberg
Flexible And Robust Iterative Methods For The Partial Singular Value Decomposition, Steven Goldenberg
Dissertations, Theses, and Masters Projects
The Singular Value Decomposition (SVD) is one of the most fundamental matrix factorizations in linear algebra. As a generalization of the eigenvalue decomposition, the SVD is essential for a wide variety of fields including statistics, signal and image processing, chemistry, quantum physics and even weather prediction. The methods for numerically computing the SVD mostly fall under three main categories: direct, iterative, and streaming. Direct methods focus on solving the SVD in its entirety, making them suitable for smaller dense matrices where the computation cost is tractable. On the other end of the spectrum, streaming methods were created to provide an …
Deep Learning From Space: Methods & Applications In High-Resolution Satellite Imagery Analysis, Ethan Brewer
Deep Learning From Space: Methods & Applications In High-Resolution Satellite Imagery Analysis, Ethan Brewer
Dissertations, Theses, and Masters Projects
Satellite imagery analysis using deep learning methods, specifically convolutional neural networks (CNNs), has grown in popularity since 2012, with uses extending into the estimation of population, wealth, poverty, conflict, migration, education, and infrastructure, among other applications. This dissertation contributes to this body of literature in three parts. First, I explore the use of deep learning to overcome the sparsity, or complete lack, of accurate information regarding existing road infrastructure across much of the world. Using a novel labeled dataset generated by a custom-coded Android application, I show that a transfer learning approach can estimate road quality based on high-resolution satellite …
Enabling Practical Evaluation Of Privacy Of Commodity-Iot, Sunil Manandhar
Enabling Practical Evaluation Of Privacy Of Commodity-Iot, Sunil Manandhar
Dissertations, Theses, and Masters Projects
There has been a massive shift towards the use of IoT products in recent years. While companies have come a long way in making these devices and services easily accessible to the consumers, very little is known about the privacy issues pertaining to these devices. In this dissertation, we focus on evaluating privacy pertaining to commodity-IoT devices by studying device usage behavior of consumers and privacy disclosure practices of IoT vendors. Our analyses consider deep intricacies tied to commodity-IoT domain, revealing insightful findings that help with building automated tools for a large scale analysis. We first present the design and …
Communication And Computation Efficient Deep Learning, Zeyi Tao
Communication And Computation Efficient Deep Learning, Zeyi Tao
Dissertations, Theses, and Masters Projects
Recent advances in Artificial Intelligence (AI) are characterized by ever-increasing datasets and rapid growth of model complexity. Many modern machine learning models, especially deep neural networks (DNNs), cannot be efficiently carried out by a single machine. Hence, distributed optimization and inference have been widely adopted to tackle large-scale machine learning problems. Meanwhile, quantum computers that process computational tasks exponentially faster than classical machines offer an alternative solution for resource-intensive deep learning. However, there are two obstacles that hinder us from building large-scale DNNs on the distributed systems and quantum computers. First, when distributed systems scale to many nodes, the training …
Data-Driven Reflectance Estimation Under Natural Lighting, Victoria Cooper
Data-Driven Reflectance Estimation Under Natural Lighting, Victoria Cooper
Dissertations, Theses, and Masters Projects
Bidirectional Reflectance Distribution Functions, (BRDFs), describe how light is reflected off of a material. BRDFs are captured so that the materials can be re-lit under new while maintaining accuracy. BRDF models can approximate the reflectance of a material, but are unable to accurately represent the full BRDF of the material. Acquisition setups for BRDFs trade accuracy for speed with the most accurate methods, gonioreflectometers, being the slowest. Image-based BRDF acquisition approaches range from using complicated controlled lighting setups to uncontrolled known lighting to assuming the lighting is unknown. We propose a data-driven method for recovering BRDFs under known, but uncontrolled …
Performance Optimization With An Integrated View Of Compiler And Application Knowledge, Ruiqin Tian
Performance Optimization With An Integrated View Of Compiler And Application Knowledge, Ruiqin Tian
Dissertations, Theses, and Masters Projects
Compiler optimization is a long-standing research field that enhances program performance with a set of rigorous code analyses and transformations. Traditional compiler optimization focuses on general programs or program structures without considering too much high-level application operations or data structure knowledge. In this thesis, we claim that an integrated view of the application and compiler is helpful to further improve program performance. Particularly, we study integrated optimization opportunities for three kinds of applications: irregular tree-based query processing systems such as B+ tree, security enhancement such as buffer overflow protection, and tensor/matrix-based linear algebra computation. The performance of B+ tree query …
Low-Overhead Techniques For Secure And Reliable Gpu Computing, Gurunath Kadam
Low-Overhead Techniques For Secure And Reliable Gpu Computing, Gurunath Kadam
Dissertations, Theses, and Masters Projects
In recent years, Graphics Processing Units (GPUs) have become a de facto choice to accelerate the computations in various domains such as machine learning, security, financial and scientific computing. GPUs leverage the inherent data parallelism in the target applications to provide high throughput at superior energy efficiency. Due to the rising usage of GPUs for a large number of applications, they are facing new challenges, especially in the security and reliability domains. From the security side, recently several microarchitectural attacks targeting GPUs have been demonstrated. These attacks leak the secret information stored on GPUs, for example, the parameters of a …
Epidemic Spread Modeling For Covid-19 Using Hard Data, Anna Schmedding
Epidemic Spread Modeling For Covid-19 Using Hard Data, Anna Schmedding
Dissertations, Theses, and Masters Projects
We present an individual-centric model for COVID-19 spread in an urban setting. We first analyze patient and route data of infected patients from January 20, 2020 ,to May 31, 2020, collected by the Korean Center for Disease Control & Prevention (KCDC) and illustrate how infection clusters develop as a function of time. This analysis offers a statistical characterization of mobility habits and patterns of individuals. We use this characterization to parameterize agent-based simulations that capture the spread of the disease, we evaluate simulation predictions with ground truth, and we evaluate different what-if counter-measure scenarios. Although the presented agent-based model is …
Combining Performance Profiling And Modeling For Accuracy And Efficiency, Hao Xu
Combining Performance Profiling And Modeling For Accuracy And Efficiency, Hao Xu
Dissertations, Theses, and Masters Projects
Modern computer systems have evolved to employ powerful parallel architectures, including multi-core processors, multi-socket chips, large memory subsystems, and fast network communication. Given such powerful hardware, developers rely on performance profiling and modeling to guide their performance optimization. However, performance optimization is facing new challenges on efficiency and accuracy with emerging computer systems. In this dissertation, we propose approaches to address these challenges. We first study memory contention in Non-Uniform Memory Access (NUMA) architectures. We present DR-BW, a new tool based on machine learning to identify bandwidth contention in NUMA architectures and provide optimization guidance. DR-BW collects performance data with …
On Supporting Android Software Developers And Testers, Carlos Eduardo Bernal Cardenas
On Supporting Android Software Developers And Testers, Carlos Eduardo Bernal Cardenas
Dissertations, Theses, and Masters Projects
Users entrust mobile applications (apps) to help them with different tasks in their daily lives. However, for each app that helps to finish a given task, there are a plethora of other apps in popular marketplaces that offer similar or nearly identical functionality. This makes for a competitive market where users will tend to favor the highest quality apps in most cases. Given that users can easily get frustrated by apps which repeatedly exhibit bugs, failures, and crashes, it is imperative that developers promptly fix problems both before and after the release. However, implementing and maintaining high quality apps is …
Rethinking Cache Hierarchy And Interconnect Design For Next-Generation Gpus, Mohamed Assem Abd Elmohsen Ibrahim
Rethinking Cache Hierarchy And Interconnect Design For Next-Generation Gpus, Mohamed Assem Abd Elmohsen Ibrahim
Dissertations, Theses, and Masters Projects
To match the increasing computational demands of GPGPU applications and to improve peak compute throughput, the core counts in GPUs have been increasing with every generation. However, the famous memory wall is a major performance determinant in GPUs. In other words, in most cases, peak throughput in GPUs is ultimately dictated by memory bandwidth. Therefore, to serve the memory demands of thousands of concurrently executing threads, GPUs are equipped with several sources of bandwidth such as on-chip private/shared caching resources and off-chip high bandwidth memories. However, the existing sources of bandwidth are often not sufficient for achieving optimal GPU performance. …
Distributed Byzantine Tolerant Machine Learning, Qi Xia
Distributed Byzantine Tolerant Machine Learning, Qi Xia
Dissertations, Theses, and Masters Projects
Oftentimes, training a large-scale deep learning neural network on a single machine becomes more difficult in a complex network model. Distributed training provides an efficient solution, but opens up participating workers to Byzantine attacks. This problem emerges when some workers cheat during uploading gradients or weights to the central server, e.g., the information received by the server is not always the true result computed by workers. In order to address this problem, we investigate Byzantine problems in distributed machine learning and respectively defend against these kinds of attacks in three scenarios: i) classic distributed machine learning; ii) federated learning; and …