Digital Commons Network^™

Physics-Augmented Modeling And Optimization Of Complex Systems: Healthcare Applications, Jianxin Xie

Doctoral Dissertations

The rapid advances in sensing technology have created a data-rich environment that tremendously

benefits predictive modeling and decision-making for complex systems. Harnessing

the full potential of this complexly-structured sensing data requires the development of

novel and reliable analytical models and tools for system informatics. Such advancements in

sensing present unprecedented opportunities to investigate system dynamics and optimize

decision-making processes for smart health. Nevertheless, sensing data is typically

characterized by high dimensionality and intricate structures. To fully unlock the potential of

this data, we significantly rely on innovative analytical methods and tools that can effectively

process information.

The objective of this …

Optimizing Collective Communication For Scalable Scientific Computing And Deep Learning, Jiali Li

Doctoral Dissertations

In the realm of distributed computing, collective operations involve coordinated communication and synchronization among multiple processing units, enabling efficient data exchange and collaboration. Scientific applications, such as simulations, computational fluid dynamics, and scalable deep learning, require complex computations that can be parallelized across multiple nodes in a distributed system. These applications often involve data-dependent communication patterns, where collective operations are critical for achieving high performance in data exchange. Optimizing collective operations for scientific applications and deep learning involves improving the algorithms, communication patterns, and data distribution strategies to minimize communication overhead and maximize computational efficiency.

Within the context of this …

Deep Learning Based Power System Stability Assessment For Reduced Wecc System, Yinfeng Zhao

Doctoral Dissertations

Power system stability is the ability of power system, for a giving initial operating condition, to reach a new operation condition with most of the system variables bounded in normal range after subjecting to a short or long disturbance. Traditional power system stability mainly uses time-domain simulation which is very time consuming and only appropriate for offline assessment.

Nowadays, with increasing penetration of inverter based renewable, large-scale distributed energy storage integration and operation uncertainty brought by weather and electricity market, system dynamic and operating condition is more dramatic, and traditional power system stability assessment based on scheduling may not be …

Insights Into The Application Of Deep Reinforcement Learning In Healthcare And Materials Science, Benjamin R. Smith

Doctoral Dissertations

Reinforcement learning (RL) is a type of machine learning designed to optimize sequential decision-making. While controlled environments have served as a foundation for RL research, due to the growth in data volumes and deep learning methods, it is now increasingly being applied to real-world problems. In our work, we explore and attempt to overcome challenges that occur when applying RL to solve problems in healthcare and materials science.

First, we explore how issues in bias and data completeness affect healthcare applications of RL. To understand how bias has already been considered in this area, we survey the literature for existing …

Improving Customer Experience Throughout The Customer Journey In The Big Data Era, Mohammad Saljoughian

Doctoral Dissertations

My PhD dissertation focuses on how firms should adapt their strategies to improve customer engagement throughout customer journey. My first paper examines firm-customer conversations on social media. Many firms struggle with how to craft their messages in conversations with customers on social media, and the lack of guidance for interacting with customers is among the top social media challenges reported by firms. The problem is compounded by the fact that these conversations take place in different, simultaneous threads, each of which potentially requiring a different approach. This paper studies how firms can adapt their responses in individual social media conversations …

Learning From Sequential User Data: Models And Sample-Efficient Algorithms, Aritra Ghosh

Doctoral Dissertations

Recent advances in deep learning have made learning representation from ever-growing datasets possible in the domain of vision, natural language processing (NLP), and robotics, among others. However, deep networks are notoriously data-hungry; for example, training language models with attention mechanisms sometimes requires trillions of parameters and tokens. In contrast, we can often access a limited number of samples in many tasks. It is crucial to learn models from these `limited' datasets. Learning with limited datasets can take several forms. In this thesis, we study how to select data samples sequentially such that downstream task performance is maximized. Moreover, we study …

On Interpreting Eddy Covariance In Small Area Agricultural Situations With Contrasting Site Management., Joel Oetting

Doctoral Dissertations

This dissertation examined the carbon sequestration potential of a low C:N soil amendment and its incorporation into the soil over a rolling agricultural field. A segmented planar fit was developed to assess and correct the systematic errors the topography introduces on the carbon dioxide fluxes. The carbon dioxide fluxes were then be partitioned into gross primary productivity and soil respiration to understand the influence of the contrasting management practices, using flux variance partitioning. Concomitant with the partitioning, high resolution temporal and spatial scale remote sensing images were interpolated and standardized to conduct hypothesis testing for treatment effects.

Learning With Limited Labeled Data For Image And Video Understanding, Razieh Kaviani Baghbaderani

Doctoral Dissertations

Deep learning-based algorithms have remarkably improved the performance in many computer vision tasks. However, deep networks often demand a large-scale and carefully annotated dataset and sufficient sample coverage of every training category. However, it is not practical in many real-world applications where only a few examples may be available, or the data annotation is costly and require expert knowledge. To mitigate this issue, learning with limited data has gained considerable attention and is investigated thorough different learning methods, including few-shot learning, weakly/semi supervised learning, open-set learning, etc.

In this work, the classification problem is investigated under an open-world assumption to …

Social Media Analytics With Applications In Disaster Management And Covid-19 Events, Md Yasin Kabir

Doctoral Dissertations

"Social media such as Twitter offers a tremendous amount of data throughout an event or a disastrous situation. Leveraging social media data during a disaster is beneficial for effective and efficient disaster management. Information extraction, trend identification, and determining public reactions might help in the future disaster or even avert such an event. However, during a disaster situation, a robust system is required that can be deployed faster and process relevant information with satisfactory performance in real-time. This work outlines the research contributions toward developing such an effective system for disaster management, where it is paramount to develop automated machine-enabled …

Remote Sensing Of High Latitude Rivers: Approaches, Insights, And Future Ramifications, Merritt E. Harlan

Doctoral Dissertations

High latitude rivers across the pan-Arctic domain are changing due to changes in climate and positive Arctic feedback loops. Understanding and contextualizing these changes is challenging due to a lack of data and methods for estimating and modeling river discharge, and mapping rivers. Remote sensing, and the availability of satellite imagery can provide ways to overcome these challenges. Through combining various forms of fieldwork, modeling, deep learning, and remote sensing, we contribute methodologies and knowledge to three key challenges associated with better understanding high latitude rivers. In the first chapter, we combine field data that can be rapidly deployed with …

Deep Learning-Based Surrogate Models For Post-Earthquake Damage Assessment, Xinzhe Yuan

Doctoral Dissertations

"Seismic damage assessment is a critical step to enhance community resilience in the wake of an earthquake. This study aims to develop deep learning-based surrogate models for widely used fragility curves to achieve more accurate and rapid assessment in practice. These surrogate models are based on artificial neural networks trained from the labelled ground motions whose resulting damage classes on targeted structures are determined by nonlinear time history analyses. The development of various surrogate models is progressed in four phases. In Phase I, the multilayer perceptron (MLP) is used to develop multivariate seismic classifiers with up to 50 hand-crafted intensity …

Auto-Curation Of Large Evolving Image Datasets, Sara Mousavicheshmehkaboodi

Doctoral Dissertations

Large image collections are becoming common in many fields and offer tantalizing opportunities to transform how research, work, and education are conducted if the information and associated insights could be extracted from them. However, major obstacles to this vision exist. First, image datasets with associated metadata contain errors and need to be cleaned and organized to be easily explored and utilized. Second, such collections typically lack the necessary context or may have missing attributes that need to be recovered. Third, such datasets are domain-specific and require human expert involvement to make the right interpretation of the image content. Fourth, the …

Qualitative And Quantitative Improvements For Positron Emission Tomography Using Different Motion Correction Methodologies, Tasmia Rahman Tumpa

Doctoral Dissertations

Positron Emission Tomography (PET) data suffers from low image quality and quantitative accuracy due to different kinds of motion of patients during imaging. Hardware-based motion correction is currently the standard; however, is limited by several constraints, the most important of which is retroactive data correction. Data-driven techniques to perform motion correction in this regard are active areas of research. The motivation behind this work lies in developing a complete data-driven approach to address both motion detection and correction. The work first presents an algorithm based on the positron emission particle tracking (PEPT) technique and makes use of time-of-flight (TOF) information …

Deep Learning Models For Irregularly Sampled And Incomplete Time Series, Satya Narayan Shukla

Doctoral Dissertations

Irregularly sampled time series data arise naturally in many application domains including biology, ecology, climate science, astronomy, geology, finance, and health. Such data present fundamental challenges to many classical models from machine learning and statistics. The first challenge with modeling such data is the presence of variable time gaps between the observation time points. The second challenge is that the dimensionality of the inputs can be different for different data cases. This occurs naturally due to the fact that different data cases are likely to include different numbers of observations. The third challenge is that different irregularly sampled instances have …

Utilizing Graph Structure For Machine Learning, Stefan Dernbach

Doctoral Dissertations

The information age has led to an explosion in the size and availability of data. This data often exhibits graph-structure that is either explicitly defined, as in the web of a social network, or is implicitly defined and can be determined by measuring similarity between objects. Utilizing this graph-structure allows for the design of machine learning algorithms that reflect not only the attributes of individual objects but their relationships to every other object in the domain as well. This thesis investigates three machine learning problems and proposes novel methods that leverage the graph-structure inherent in the tasks. Quantum walk neural …

Neural Methods For Answer Passage Retrieval Over Sparse Collections, Daniel Cohen

Doctoral Dissertations

Recent advances in machine learning have allowed information retrieval (IR) techniques to advance beyond the stage of handcrafting domain specific features. Specifically, deep neural models incorporate varying levels of features to learn whether a document answers the information need of a query. However, these neural models rely on a large number of parameters to successfully learn a relation between a query and a relevant document.

This reliance on a large number of parameters, combined with the current methods of optimization relying on small updates necessitates numerous samples to allow the neural model to converge on an effective relevance function. This …

Fabrication, Characterization Of High-Entropy Alloys And Deep Learning-Based Inspection In Metal Additive Manufacturing, Wenyuan Cui

Doctoral Dissertations

"Alloying has been used to confer desirable properties to materials. It typically involves the addition of small amounts of secondary elements to a primary element. In the past decade, however, a new alloying strategy that involves the combination of multiple principal elements in high concentrations to create new materials called high- entropy alloys (HEAs) has been in vogue. In the first part, the investigation focused on the fabrication process and property assessment of the additive manufactured HEA to broaden its engineering applications. Additive manufacturing (AM) is based on manufacturing philosophy through the layer-by-layer method and accomplish the near net-shaped components …

Automated Intelligent Cueing Device To Improve Ambient Gait Behaviors For Patients With Parkinson's Disease, Nader Naghavi

Doctoral Dissertations

Freezing of gait (FoG) is a common motor dysfunction in individuals with Parkinson’s disease (PD). FoG impairs walking and is associated with increased fall risk. Although pharmacological treatments have shown promise during ON-medication periods, FoG remains difficult to treat during medication OFF state and in advanced stages of the disease. External cueing therapy in the forms of visual, auditory, and vibrotactile, has been effective in treating gait deviations. Intelligent (or on-demand) cueing devices are novel systems that analyze gait patterns in real-time and activate cues only at moments when specific gait alterations are detected. In this study we developed methods …

Deep Learning Techniques For Power System Operation: Modeling And Implementation, Yan Du

Doctoral Dissertations

The fast development of the deep learning (DL) techniques in the most recent years has drawn attention from both academia and industry. And there have been increasing applications of the DL techniques in many complex real-world situations, including computer vision, medical diagnosis, and natural language processing. The great power and flexibility of DL can be attributed to its hierarchical learning structure that automatically extract features from mass amounts of data. In addition, DL applies an end-to-end solving mechanism, and directly generates the output from the input, where the traditional machine learning methods usually break down the problem and combine the …

Improving Visual Recognition With Unlabeled Data, Aruni Roy Chowdhury

Doctoral Dissertations

The success of deep neural networks has resulted in computer vision systems that obtain high accuracy on a wide variety of tasks such as image classification, object detection, semantic segmentation, etc. However, most state-of-the-art vision systems are dependent upon large amounts of labeled training data, which is not a scalable solution in the long run. This work focuses on improving existing models for visual object recognition and detection without being dependent on such large-scale human-annotated data. We first show how large numbers of hard examples (cases where an existing model makes a mistake) can be obtained automatically from unlabeled video …

Application Of Big Data In Transportation Safety Analysis Using Statistical And Deep Learning Methods, Ramin Arvin

Doctoral Dissertations

The emergence of new sensors and data sources provides large scale high-resolution big data from instantaneous vehicular movements, driver decision and states, surrounding environment, roadway characteristics, weather condition, etc. Such a big data can be served to expand our understanding regarding the current state of the transportation and help us to proactively evaluate and monitor the system performance. The key idea behind this dissertation is to identify the moments and locations where drivers are exhibiting different behavior comparing to the normal behavior. The concept of driving volatility is utilized which quantifies deviation from normal driving in terms of variations in …

Higher-Order Representations For Visual Recognition, Tsung-Yu Lin

Doctoral Dissertations

In this thesis, we present a simple and effective architecture called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs generalize classical orderless texture-based image models such as bag-of-visual-words and Fisher vector representations. However, unlike prior work, they can be trained in an end-to-end manner. In the experiments, we demonstrate that these representations generalize well to novel domains by fine-tuning and achieve excellent results on fine-grained, texture and scene recognition tasks. The visualization of fine-tuned convolutional filters …

Improving Face Clustering In Videos, Souyoung Jin

Doctoral Dissertations

Human faces represent not only a challenging recognition problem for computer vision, but are also an important source of information about identity, intent, and state of mind. These properties make the analysis of faces important not just as algorithmic challenges, but as a gateway to developing computer vision methods that can better follow the intent and goals of human beings. In this thesis, we are interested in face clustering in videos. Given a raw video, with no caption or annotation, we want to group all detected faces by their identity. We address three problems in the area of face clustering …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …

Hierarchical Neural Architectures For Classifying Cancer Pathology Reports, Shang Gao

Doctoral Dissertations

Electronic health records (EHRs) are the primary method for documenting and storing patient outcomes in modern healthcare; data mining and machine learning approaches utilize the information stored in EHRs to assist in clinical decision support and other critical healthcare applications. Important information in EHRs is often stored in the form of unstructured clinical text. Unfortunately, the state-of-the-art methods used to automatically extract useful information from unstructured clinical text lags significantly behind the state-of-the-art methods used in the general natural language processing (NLP) community for other tasks such as machine translation, question answering, and sentiment analysis. In this work, we attempt …

Neural Models For Information Retrieval Without Labeled Data, Hamed Zamani

Doctoral Dissertations

Recent developments of machine learning models, and in particular deep neural networks, have yielded significant improvements on several computer vision, natural language processing, and speech recognition tasks. Progress with information retrieval (IR) tasks has been slower, however, due to the lack of large-scale training data as well as neural network models specifically designed for effective information retrieval. In this dissertation, we address these two issues by introducing task-specific neural network architectures for a set of IR tasks and proposing novel unsupervised or \emph{weakly supervised} solutions for training the models. The proposed learning solutions do not require labeled training data. Instead, …

Efficient Self-Supervised Deep Sensorimotor Learning In Robotics, Takeshi Takahashi

Doctoral Dissertations

Deep learning has been successful in a variety of applications, such as object recognition, video games, and machine translation. Deep neural networks can automatically learn important features given large training datasets. However, the success of deep learning in robotic systems in the real world is still limited mainly because obtaining large datasets and labeling are costly. As a result, much of the successful work in deep learning has been limited to domains where large datasets are readily available or easily collected. To address this issue, I propose a framework for acquiring re-usable skills efficiently combining intrinsic motivation and the control …

Machine Learning Models For Efficient And Robust Natural Language Processing, Emma Strubell

Doctoral Dissertations

Natural language processing (NLP) has come of age. For example, semantic role labeling (SRL), which automatically annotates sentences with a labeled graph representing who did what to whom, has in the past ten years seen nearly 40% reduction in error, bringing it to useful accuracy. As a result, a myriad of practitioners now want to deploy NLP systems on billions of documents across many domains. However, state-of-the-art NLP systems are typically not optimized for cross-domain robustness nor computational efficiency. In this dissertation I develop machine learning methods to facilitate fast and robust inference across many common NLP tasks. First, …

Cross Domain Image Transformation And Generation By Deep Learning, Yang Song

Doctoral Dissertations

Compared with single domain learning, cross-domain learning is more challenging due to the large domain variation. In addition, cross-domain image synthesis is more difficult than other cross learning problems, including, for example, correlation analysis, indexing, and retrieval, because it needs to learn complex function which contains image details for photo-realism. This work investigates cross-domain image synthesis in two common and challenging tasks, i.e., image-to-image and non-image-to-image transfer/synthesis.The image-to-image transfer is investigated in Chapter 2, where we develop a method for transformation between face images and sketch images while preserving the identity. Different from existing works that conduct domain transfer in …

Applications Of Machine Learning In Nuclear Imaging And Radiation Detection, Shaikat Mahmood Galib

Doctoral Dissertations

"The main focus of this work is to use machine learning and data mining techniques to address some challenging problems that arise from nuclear data. Specifically, two problem areas are discussed: nuclear imaging and radiation detection. The techniques to approach these problems are primarily based on a variant of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN), which is one of the most popular forms of 'deep learning' technique.

The first problem is about interpreting and analyzing 3D medical radiation images automatically. A method is developed to identify and quantify deformable image registration (DIR) errors from lung CT scans …