Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Computer vision (2)
- Deep learning (2)
- 3D reconstruction (1)
- Active learning (1)
- Algorithms (1)
-
- Approximation (1)
- Astronomy (1)
- Audiogram (1)
- Automated machine learning (1)
- Bayesian (1)
- Bayesian active learning (1)
- Bayesian optimization (1)
- Clinical decision support (1)
- Compton scattering (1)
- Computational Geometry (1)
- Computer Networks (1)
- Curves (1)
- Cyber-Physical Systems (1)
- Cybersecurity (1)
- Elastic scheduling (1)
- Fault and Management (1)
- Fault-Tolerant Systems (1)
- Gaussian Process (1)
- Gaussian process (1)
- Graph classification (1)
- Graph neural network (1)
- High-energy physics (1)
- Indoor modeling (1)
- Industrial Internet of Things (1)
- Information Centric Networking (1)
Articles 1 - 15 of 15
Full-Text Articles in Physical Sciences and Mathematics
Towards Interpretable Machine Learning With Applications To Clinical Decision Support, Zhicheng Cui
Towards Interpretable Machine Learning With Applications To Clinical Decision Support, Zhicheng Cui
McKelvey School of Engineering Theses & Dissertations
Machine learning models have achieved impressive predictive performance in various applications such as image classification and object recognition. However, understanding how machine learning models make decisions is essential when deploying those models in critical areas such as clinical prediction and market analysis, where prediction accuracy is not the only concern. For example, in the clinical prediction of ICU transfers, in addition to accurate predictions, doctors need to know the contributing factors that triggered the alert, which factors can be quickly altered to prevent the ICU transfer. While interpretable machine learning has been extensively studied for years, challenges remain as among …
Graph Deep Learning: Methods And Applications, Muhan Zhang
Graph Deep Learning: Methods And Applications, Muhan Zhang
McKelvey School of Engineering Theses & Dissertations
The past few years have seen the growing prevalence of deep neural networks on various application domains including image processing, computer vision, speech recognition, machine translation, self-driving cars, game playing, social networks, bioinformatics, and healthcare etc. Due to the broad applications and strong performance, deep learning, a subfield of machine learning and artificial intelligence, is changing everyone's life.Graph learning has been another hot field among the machine learning and data mining communities, which learns knowledge from graph-structured data. Examples of graph learning range from social network analysis such as community detection and link prediction, to relational machine learning such as …
Event Reconstruction In The Advanced Particle-Astrophysics Telescope, Emily Ramey
Event Reconstruction In The Advanced Particle-Astrophysics Telescope, Emily Ramey
McKelvey School of Engineering Theses & Dissertations
The Advanced Particle-Astrophysics Telescope (APT) is a concept for a gamma-ray space telescope operating in the keV to MeV energy range. Due to the nature of the telescope and the physics of detection, reconstructing initial photon trajectories can be very computationally complex. This is a barrier to the real-time detection of astrophysical transient phenomena such as Gamma Ray Bursts (GRBs), and a faster reconstruction algorithm is needed in order to effectively study them. In this project, we develop such an algorithm based on Boggs & Jean (2000) and discuss the effects of certain algorithmic parameters on computational performance. For testing, …
Scheduling Multiple Parallel Jobs Online, Kefu Lu
Scheduling Multiple Parallel Jobs Online, Kefu Lu
McKelvey School of Engineering Theses & Dissertations
The prevalence of parallel processing has only increased in recent years. Today, most computing machines available on the market shifted from using single processors to possessing a multicore architecture. Naturally, there has been considerable work in developing parallel programming languages and frameworks which programmers can use to leverage the computing power of these machines. These languages allow users to create programs with internal parallelism. The next, and crucial, step is to ensure that the computing system can efficiently execute these parallel jobs. Executing a single parallel job efficiently is a very well-studied problem in parallel computing. In the area of …
Automating Active Learning For Gaussian Processes, Gustavo Malkomes
Automating Active Learning For Gaussian Processes, Gustavo Malkomes
McKelvey School of Engineering Theses & Dissertations
In many problems in science, technology, and engineering, unlabeled data is abundant but acquiring labeled observations is expensive -- it requires a human annotator, a costly laboratory experiment, or a time-consuming computer simulation. Active learning is a machine learning paradigm designed to minimize the cost of obtaining labeled data by carefully selecting which new data should be gathered next. However, excessive machine learning expertise is often required to effectively apply these techniques in their current form. In this dissertation, we propose solutions that further automate active learning. Our core contributions are active learning algorithms that are easy for non-experts to …
Decoupling Information And Connectivity Via Information-Centric Transport, Hila Ben Abraham
Decoupling Information And Connectivity Via Information-Centric Transport, Hila Ben Abraham
McKelvey School of Engineering Theses & Dissertations
The power of Information-Centric Networking architectures (ICNs) lies in their abstraction for communication --- the request for named data. This abstraction was popularized by the HyperText Transfer Protocol (HTTP) as an application-layer abstraction, and was extended by ICNs to also serve as their network-layer abstraction. In recent years, network mechanisms for ICNs, such as scalable name-based forwarding, named-data routing and in-network caching, have been widely explored and researched. However, to the best of our knowledge, the impact of this network abstraction on ICN applications has not been explored or well understood. The motivation of this dissertation is to address this …
Period And Computational Elasticity For Adaptive Real-Time Systems, James Wiliam Orr
Period And Computational Elasticity For Adaptive Real-Time Systems, James Wiliam Orr
McKelvey School of Engineering Theses & Dissertations
A wide range range of real-world applications (including multimedia players, ad-hoc communication networks, online trading, radar tracking software, and other adaptive control algorithms) need adaptive adjustment to their resource utilizations at run-time, while still maintaining real-time guarantees. The elastic task model of soft real-time systems allows for the run-time manipulation of tasks’ processor utilizations in order to maintain a system-wide quality of service or accommodate needs of other tasks by assigning each task a period within a specified range. As originally presented, only sequential tasks executing on a single processor were considered. However, in the two decades since the elastic …
Real-Time Rfi Mitigation In Radio Astronomy, Emily Ramey, Nick Joslyn, Richard Prestage, Michael Lam, Luke Hawkins, Tim Blattner, Mark Whitehead
Real-Time Rfi Mitigation In Radio Astronomy, Emily Ramey, Nick Joslyn, Richard Prestage, Michael Lam, Luke Hawkins, Tim Blattner, Mark Whitehead
Senior Honors Papers / Undergraduate Theses
As the use of wireless technology has increased around the world, Radio Frequency Interference (RFI) has become more and more of a problem for radio astronomers. Preventative measures exist to limit the presence of RFI, and programs exist to remove it from saved data, but the use of algorithms to detect and remove RFI as an observation is occurring is much less common. Such a method would be incredibly useful for observations in which the data must undergo several rounds of processing before being saved, as in pulsar timing studies. Strategies for real-time mitigation have been discussed and tested with …
A Visual Political World: Determinants And Effects Of Visual Content, Silvia Michelle Torres Pacheco
A Visual Political World: Determinants And Effects Of Visual Content, Silvia Michelle Torres Pacheco
Arts & Sciences Electronic Theses and Dissertations
Political communication is a central element of several political dynamics. Its visual component is crucial in understanding the origin, characteristics and consequences of the messages sent between political figures, media and citizens. However, visual features have been largely overlooked in Political Science. Thus, in this dissertation, I introduce, describe and apply computer vision techniques for the analysis and processing of visual material, in order to not only improve data collection and visual content extraction, but also the understanding of the effects that visual components have on relevant political variables. In the first main chapter of this project, I implement computer …
High Performance Wireless Sensor-Actuator Networks For Industrial Internet Of Things, Dolvara Gunatilaka
High Performance Wireless Sensor-Actuator Networks For Industrial Internet Of Things, Dolvara Gunatilaka
McKelvey School of Engineering Theses & Dissertations
Wireless Sensor-Actuator Networks (WSANs) enable cost-effective communication for Industrial Internet of Things (IIoT). To achieve predictability and reliability demanded by industrial applications, industrial wireless standards (e.g., WirelessHART) incorporate a set of unique features such as a centralized management architecture, Time Slotted Channel Hopping (TSCH), and conservative channel selection. However, those features also incur significant degradation in performance, efficiency, and agility. To overcome these key limitations of existing industrial wireless technologies, this thesis work develops and empirically evaluates a suite of novel network protocols and algorithms.
The primary contributions of this thesis are four-fold. (1) We first build an experimental testbed …
Toward Controllable And Robust Surface Reconstruction From Spatial Curves, Zhiyang Huang
Toward Controllable And Robust Surface Reconstruction From Spatial Curves, Zhiyang Huang
McKelvey School of Engineering Theses & Dissertations
Reconstructing surface from a set of spatial curves is a fundamental problem in computer graphics and computational geometry. It often arises in many applications across various disciplines, such as industrial prototyping, artistic design and biomedical imaging. While the problem has been widely studied for years, challenges remain for handling different type of curve inputs while satisfying various constraints. We study studied three related computational tasks in this thesis. First, we propose an algorithm for reconstructing multi-labeled material interfaces from cross-sectional curves that allows for explicit topology control. Second, we addressed the consistency restoration, a critical but overlooked problem in applying …
Management And Security Of Multi-Cloud Applications, Lav Gupta
Management And Security Of Multi-Cloud Applications, Lav Gupta
McKelvey School of Engineering Theses & Dissertations
Single cloud management platform technology has reached maturity and is quite successful in information technology applications. Enterprises and application service providers are increasingly adopting a multi-cloud strategy to reduce the risk of cloud service provider lock-in and cloud blackouts and, at the same time, get the benefits like competitive pricing, the flexibility of resource provisioning and better points of presence. Another class of applications that are getting cloud service providers increasingly interested in is the carriers' virtualized network services. However, virtualized carrier services require high levels of availability and performance and impose stringent requirements on cloud services. They necessitate the …
Structured Indoor Modeling, Chen Liu
Structured Indoor Modeling, Chen Liu
McKelvey School of Engineering Theses & Dissertations
In this dissertation, we propose data-driven approaches to reconstruct 3D models for indoor scenes which are represented in a structured way (e.g., a wall is represented by a planar surface and two rooms are connected via the wall). The structured representation of models is more application ready than dense representations (e.g., a point cloud), but poses additional challenges for reconstruction since extracting structures requires high-level understanding about geometries. To address this challenging problem, we explore two common structural regularities of indoor scenes: 1) most indoor structures consist of planar surfaces (planarity), and 2) structural surfaces (e.g., walls and floor) can …
Real-Time Reliable Middleware For Industrial Internet-Of-Things, Chao Wang
Real-Time Reliable Middleware For Industrial Internet-Of-Things, Chao Wang
McKelvey School of Engineering Theses & Dissertations
This dissertation contributes to the area of adaptive real-time and fault-tolerant systems research, applied to Industrial Internet-of-Things (IIoT) systems. Heterogeneous timing and reliability requirements arising from IIoT applications have posed challenges for IIoT services to efficiently differentiate and meet such requirements. Specifically, IIoT services must both differentiate processing according to applications' timing requirements (including latency, event freshness, and relative consistency of each other) and enforce the needed levels of assurance for data delivery (even as far as ensuring zero data loss). It is nontrivial for an IIoT service to efficiently differentiate such heterogeneous IIoT timing/reliability requirements to fit each application, …
Differential Estimation Of Audiograms Using Gaussian Process Active Model Selection, Trevor Larsen
Differential Estimation Of Audiograms Using Gaussian Process Active Model Selection, Trevor Larsen
McKelvey School of Engineering Theses & Dissertations
Classical methods for psychometric function estimation either require excessive resources to perform, as in the method of constants, or produce only a low resolution approximation of the target psychometric function, as in adaptive staircase or up-down procedures. This thesis makes two primary contributions to the estimation of the audiogram, a clinically relevant psychometric function estimated by querying a patient’s for audibility of a collection of tones. First, it covers the implementation of a Gaussian process model for learning an audiogram using another audiogram as a prior belief to speed up the learning procedure. Second, it implements a use case of …