Thermal overheating is a serious concern in modern supercomputing systems. Elevated temperature levels reduce the reliability and the lifetime of the underlying hardware and increase their power consumption. Previous studies on mitigating thermal hotspots at the hardware and run-time system levels have typically used approaches that trade off performance for...
The goal of this thesis is to design practical algorithms for nonlinear optimization in the case when the objective function is stochastic or nonsmooth. The thesis is divided into three chapters. Chapter 1 describes an active-set method for the minimization of an objective function that is structurally nonsmooth, viz., it...
In this dissertation, we start with the dictionary learning (DL) based single-frame super-resolution (SR) problem, where low resolution (LR) input frames are super-resolved to high resolution (HR) output frames. We propose to extend the previous single-frame SR methods to multiple-frames, i.e., estimating single HR output frame by multiple LR input...
The ability of a machine to synthesize textual output in a form of human language is a long-standing goal in a field of artificial intelligence and has wide-range of applications such as spell correction, speech recognition, machine translation, abstractive summarization, etc. The statistical approach to enable such ability mainly involves...
Image colorization is the process of artificially coloring a black and white image such that this fabrication appears realistic and authentic to the viewer. There are many nontrivial applications of this process, such as the colorization and augmentation of historical photos as well as the removal of color tone filters...
With a glut of competing priorities, the financial industry faces major challenges in extracting timely, relevant, and specifically-focused information from text. Without clear-cut business cases, making the investment in text analysis methods does not justify the return on investment. Furthermore, the business landscape continues to become increasingly complex, and at...
Polymer nanocomposites have attracted great interest in recent years because of their potential as tailored materials with enhanced properties. Recent experiments have shown that polymer nanocomposites are able to achieve significant improvement in dielectrical, thermal, mechanical and other physical properties compared with their parent polymer systems. More importantly, these outstanding...
Platelets are circulating anucleate discs derived from megakaryocytes, and play major roles in hemostasis, inflammation, thrombosis, and vascular biology. Multi-phase culture systems for inducing in vitro platelet production from mature megakaryocytes have been explored to allow progenitor expansion, megakaryocyte maturation, and promotion of platelet formation and shedding. In this thesis,...
Cells are complex, autonomous machines that integrate many environmental cues to execute a desired response. Though this property makes cells versatile, it presents significant design challenges when, to treat diseases, we must alter cellular responses. To understand changes to the complex regulatory pathways that cause diseases, studies often investigate the...
Deep learning is a new area of machine learning research that allows deep neural networks composed of multiple processing layers to learn representations of data with multiple levels of abstraction. Deep learning has helped in achieving the objective of pushing machine learning closer to one of its original goals of...
This is an attempt to recreate a reference architecture with the intention of completing a data engineering capstone project and also learning the services and technologies along the progress. The objective of the project is to use aws cloud managed services to build at scale solution to process, parse and...
The task of classification has been increasingly attracting attention from researchers in recent years. The objective is to assign labels given attributes of samples. The classification task is practical in real-world applications and is widely explored in fields such as computer vision, natural language processing and information retrieval. The recent...
This dissertation asks how researchers can create more equitable algorithmic systems. Ultimately, this thesis explores methods and implications of representing subjects of analysis in the design and evaluation of algorithmic systems. I also unpack how algorithmic tools measure and quantify human behavior, giving heed to the potential impacts of these...
Computational imaging (CI) is a class of imaging systems that optimize both the opto-electronic hardware and computing software to achieve task-specific improvements. Machine/deep learning models have proven effective in drawing statistical priors from adequate datasets. Yet when designing computational models for CI problems, physics-based models derived from the image formation...
Pseudomonas aeruginosa is an important gram-negative opportunistic pathogen whose large genome allows it to thrive in diverse environments. There is a wide range of phenotypic variation within the species, which can be attributed both to variation in sequences present in most isolates (the core genome) or the presence or absence...
In this paper, we propose a two-stage approach for predicting a trips destination by clustering geocoordinates and leveraging incremental learning and contextual rule-based methods for the prediction of end destinations. The proposed approach dynamically adapts to users change in behavior and is resilient against concept drift. Using this solution, 76.39%...
In the U.S., approximately 840,000 Americans die from cardiovascular disease (CVD) each year, and it is the leading cause of morbidity and mortality worldwide. The prevalence of CVD is on the rise and widespread disparities in CVD exist across economic, racial, and ethnic groups. In order to address the rising...
Mixing by cutting-and-shuffling (like that for a deck of cards or a Rubik's cube) is a paradigm that has not been studied in detail even though it can be applied in a variety of situations including the mixing of granular materials. Mathematically, cutting- and-shuffling is described by piecewise isometries (PWIs),...
This thesis work addresses the creation and evaluation of deep learning architectures which are trained only on synthetic images. The goal of these models is to autonomously detect rocks on the surface of asteroids.
In this document, I demonstrate that: 1) Linear basis functions cannot outperform nonlinear ones to represent hand kinematics 2) Nonlinear autoencoders outperform PCA on the dimensionality reduction of hand kinematics, 3) Nonlinear autoencoders outperform PCA in human gait representation and recurrent nonlinear autoencoders can seamlessly express the temporal dynamics, 4)...