Digital Commons Network^™

Yoga Pose Classification Using Deep Learning, Shruti Kothari

Master's Projects

Human pose estimation is a deep-rooted problem in computer vision that has exposed many challenges in the past. Analyzing human activities is beneficial in many fields like video- surveillance, biometrics, assisted living, at-home health monitoring etc. With our fast-paced lives these days, people usually prefer exercising at home but feel the need of an instructor to evaluate their exercise form. As these resources are not always available, human pose recognition can be used to build a self-instruction exercise system that allows people to learn and practice exercises correctly by themselves. This project lays the foundation for building such a system …

Emerging Technologies In Healthcare: Analysis Of Unos Data Through Machine Learning, Reyhan Merekar

Student Theses and Dissertations

The healthcare industry is primed for a massive transformation in the coming decades due to emerging technologies such as Artificial Intelligence (AI) and Machine Learning. With a practical application to the UNOS (United Network of Organ Sharing) database, this Thesis seeks to investigate how Machine Learning and analytic methods may be used to predict one-year heart transplantation outcomes. This study also sought to improve on predictive performances from prior studies by analyzing both Donor and Recipient data. Models built with algorithms such as Stacking and Tree Boosting gave the highest performance, with AUC’s of 0.6810 and 0.6804, respectively. In this …

Using Color Thresholding And Contouring To Understand Coral Reef Biodiversity, Scott Vuong Tran

Master's Projects

This paper presents research outcomes of understanding coral reef biodiversity through the usage of various computer vision applications and techniques. It aims to help further analyze and understand the coral reef biodiversity through the usage of color thresholding and contouring onto images of the ARMS plates to extract groups of microorganisms based on color. The results are comparable to the manual markup tool developed to do the same tasks and shows that the manual process can be sped up using computer vision. The paper presents an automated way to extract groups of microorganisms based on color without the use of …

Ultrasound Guided Diffuse Optical Tomography For Breast Cancer Diagnosis: Algorithm Development, K M Shihab Uddin

McKelvey School of Engineering Graduate Student Theses & Dissertations

According to National Breast Cancer Society, one in every eight women in United States is diagnosed with breast cancer in her lifetime. American Cancer Society recommends a semi-annual breast-cancer screening for every woman which can be heavily facilitated by the availability of low-cost, non-invasive diagnostic method with good sensitivity and penetration depth. Ultrasound (US) guided Diffuse Optical Tomography (US-guided DOT) has been explored as a breast-cancer diagnostic and screening tool over the past two decades. It has demonstrated a great potential for breast-cancer diagnosis, treatment monitoring and chemotherapy-response prediction. In this imaging method, optical measurements of four different wavelengths are …

Leveraging Model Flexibility And Deep Structure: Non-Parametric And Deep Models For Computer Vision Processes With Applications To Deep Model Compression, Anthony D. Rhodes

Dissertations and Theses

My dissertation presents several new algorithms incorporating non-parametric and deep learning approaches for computer vision and related tasks, including object localization, object tracking and model compression. With respect to object localization, I introduce a method to perform active localization by modeling spatial and other relationships between objects in a coherent "visual situation" using a set of probability distributions. I further refine this approach with the Multipole Density Estimation with Importance Clustering (MIC-Situate) algorithm. Next, I formulate active, "situation" object search as a Bayesian optimization problem using Gaussian Processes. Using my Gaussian Process Context Situation Learning (GP-CL) algorithm, I demonstrate improved …

Dealing With Faulty Data Via A Physics-Based Filtering Method, Ross Pellenberg

Master's Theses

Gas turbines are expensive, revenue generating machines and, as such, there is a strong interest in practicing state-of-the-art maintenance techniques to keep them running at healthy performance levels. One way to monitor and evaluate gas turbine health is to train a machine learning model on historical run-to-failure sensor data to differentiate between healthy and unhealthy performance. The biggest barrier to building these models is the scarcity of run-to-failure data. Not only is this data expensive and time consuming to acquire, but the data is often not publicly released for competitive purposes. This thesis uses a publicly available run-to-failure dataset previously …

Ml-Medic: A Preliminary Study Of An Interactive Visual Analysis Tool Facilitating Clinical Applications Of Machine Learning For Precision Medicine, Laura Stevens, David Kao, Jennifer Hall, Carsten Görg, Kaitlyn Abdo, Erik Linstead

Engineering Faculty Articles and Research

Accessible interactive tools that integrate machine learning methods with clinical research and reduce the programming experience required are needed to move science forward. Here, we present Machine Learning for Medical Exploration and Data-Inspired Care (ML-MEDIC), a point-and-click, interactive tool with a visual interface for facilitating machine learning and statistical analyses in clinical research. We deployed ML-MEDIC in the American Heart Association (AHA) Precision Medicine Platform to provide secure internet access and facilitate collaboration. ML-MEDIC’s efficacy for facilitating the adoption of machine learning was evaluated through two case studies in collaboration with clinical domain experts. A domain expert review was also …

Detecting Credit Card Fraud: An Analysis Of Fraud Detection Techniques, William Lovo

Senior Honors Projects, 2020-current

Advancements in the modern age have brought many conveniences, one of those being credit cards. Providing an individual the ability to hold their entire purchasing power in the form of pocket-sized plastic cards have made credit cards the preferred method to complete financial transactions. However, these systems are not infallible and may provide criminals and other bad actors the opportunity to abuse them. Financial institutions and their customers lose billions of dollars every year to credit card fraud. To combat this issue, fraud detection systems are deployed to discover fraudulent activity after they have occurred. Such systems rely on advanced …

Towards Natural Language Understanding In Text-Based Games, Anthony Snarr

Senior Honors Projects, 2020-current

Text-based games are a very promising space for language-focused machine learning. Within them are huge hurdles in machine learning, like long-term planning and memory, interpretation and generation of natural language, unpredictability, and more. One problem to consider in the realm of natural language interpretation is how to train a machine learning model to understand a text-based game’s objective. This work considers treating this issue like a machine translation problem, where a detailed objective or list of instructions is given as input, and output is a predicted list of actions. This work also explores how a supervised learning system might learn …

Clearing The Clouds: Extracting 3d Information From Amongst The Noise, Alexander Fafard

Theses

Advancements permitting the rapid extraction of 3D point clouds from a variety of imaging modalities across the global landscape have provided a vast collection of high fidelity digital surface models. This has created a situation with unprecedented overabundance of 3D observations which greatly outstrips our current capacity to manage and infer actionable information. While years of research have removed some of the manual analysis burden for many tasks, human analysis is still a cornerstone of 3D scene exploitation. This is especially true for complex tasks which necessitate comprehension of scale, texture and contextual learning. In order to ameliorate the interpretation …

Superb: Superior Behavior-Based Anomaly Detection Defining Authorized Users' Traffic Patterns, Daniel Karasek

Master of Science in Computer Science Theses

Network anomalies are correlated to activities that deviate from regular behavior patterns in a network, and they are undetectable until their actions are defined as malicious. Current work in network anomaly detection includes network-based and host-based intrusion detection systems. However, network anomaly detection schemes can suffer from high false detection rates due to the base rate fallacy. When the detection rate is less than the false positive rate, which is found in network anomaly detection schemes working with live data, a high false detection rate can occur. To overcome such a drawback, this paper proposes a superior behavior-based anomaly detection …

A Physics-Based Machine Learning Study Of The Behavior Of Interstitial Helium In Single Crystal W–Mo Binary Alloys, Adib J. Samin

Faculty Publications

In this work, the behavior of dilute interstitial helium in W–Mo binary alloys was explored through the application of a first principles-informed neural network (NN) in order to study the early stages of helium-induced damage and inform the design of next generation materials for fusion reactors. The neural network (NN) was trained using a database of 120 density functional theory (DFT) calculations on the alloy. The DFT database of computed solution energies showed a linear dependence on the composition of the first nearest neighbor metallic shell. This NN was then employed in a kinetic Monte Carlo simulation, which took into …

Applying Imitation And Reinforcement Learning To Sparse Reward Environments, Haven Brown

Computer Science and Computer Engineering Undergraduate Honors Theses

The focus of this project was to shorten the time it takes to train reinforcement learning agents to perform better than humans in a sparse reward environment. Finding a general purpose solution to this problem is essential to creating agents in the future capable of managing large systems or performing a series of tasks before receiving feedback. The goal of this project was to create a transition function between an imitation learning algorithm (also referred to as a behavioral cloning algorithm) and a reinforcement learning algorithm. The goal of this approach was to allow an agent to first learn to …

Investigating Machine Learning Techniques For Gesture Recognition With Low-Cost Capacitive Sensing Arrays, Michael Fahr Jr.

Computer Science and Computer Engineering Undergraduate Honors Theses

Machine learning has proven to be an effective tool for forming models to make predictions based on sample data. Supervised learning, a subset of machine learning, can be used to map input data to output labels based on pre-existing paired data. Datasets for machine learning can be created from many different sources and vary in complexity, with popular datasets including the MNIST handwritten dataset and CIFAR10 image dataset. The focus of this thesis is to test and validate multiple machine learning models for accurately classifying gestures performed on a low-cost capacitive sensing array. Multiple neural networks are trained using gesture …

Ensemble And Consensus Species Distribution Modeling Approaches Applied To Freshwater Fish, Melissa Jean Walsh

Biology Dissertations - Archive

The field of species distribution modeling has expanded rapidly over the past two decades along with increasing computing capability and the introduction of novel analytical techniques. SDMs relate species occurrence to environmental data and are a valuable tool in helping researchers understand species-environment relationships and make projections about future distributions. Model reliability has been shown to be highly dependent upon a range of factors, including statistical techniques, predictor variables, species prevalence, and choice metrics used to assess model accuracy. SDMs developed from ensembles of different models have been shown to improve reliability. Here I develop an ensemble modelling approach for …

Novel Inference Methods For Generalized Linear Models Using Shrinkage Priors And Data Augmentation., Arinjita Bhattacharyya

Electronic Theses and Dissertations

Generalized linear models have broad applications in biostatistics and sociology. In a regression setup, the main target is to find a relevant set of predictors out of a large collection of covariates. Sparsity is the assumption that only a few of these covariates in a regression setup have a meaningful correlation with an outcome variate of interest. Sparsity is incorporated by regularizing the irrelevant slopes towards zero without changing the relevant predictors and keeping the resulting inferences intact. Frequentist variable selection and sparsity are addressed by popular techniques like Lasso, Elastic Net. Bayesian penalized regression can tackle the curse of …

Integrating National Ecological Observatory Network (Neon) Airborne Remote Sensing And In-Situ Data For Optimal Tree Species Classification, Victoria M. Scholl, Megan E. Cattau, Maxwell B. Joseph, Jennifer K. Balch

Human-Environment Systems Research Center Faculty Publications and Presentations

Accurately mapping tree species composition and diversity is a critical step towards spatially explicit and species-specific ecological understanding. The National Ecological Observatory Network (NEON) is a valuable source of open ecological data across the United States. Freely available NEON data include in-situ measurements of individual trees, including stem locations, species, and crown diameter, along with the NEON Airborne Observation Platform (AOP) airborne remote sensing imagery, including hyperspectral, multispectral, and light detection and ranging (LiDAR) data products. An important aspect of predicting species using remote sensing data is creating high-quality training sets for optimal classification purposes. Ultimately, manually creating training data …

Airfoil Analysis And Design Using Surrogate Models, Nicholas Alexander Michael

Theses and Dissertations

A study was performed to compare two different methods for generating surrogate models for the analysis and design of airfoils. Initial research was performed to compare the accuracy of surrogate models for predicting the lift and drag of an airfoil with data collected from highidelity simulations using a modern CFD code along with lower-order models using a panel code. This was followed by an evaluation of the Class Shape Trans- formation (CST) method for parameterizing airfoil geometries as a prelude to the use of surrogate models for airfoil design optimization and the implementation of software to use CST to modify …

Temporal Localization Of Video Topics Using The Yt8m Dataset: An Exploration, Katherine Riedling

Honors Scholar Theses

Due to the progress made in computing resources and artificial intelligence, applications in computer vision have gained a lot of traction over the past decade. One such application applies to video understanding and content analysis, which are the main goals of the annual YouTube-8M Video Understanding Challenge. In the newest challenge, the aim is to localize events to specific video segments in addition to discerning the main topics of the video. This paper introduces and presents a broad overview of techniques, data, and the top-performing algorithms presented at the International Conference on Computer Vision (ICCV) conference last year. Ensemble methods …

How We Refactor And How We Document It? On The Use Of Supervised Machine Learning Algorithms To Classify Refactoring Documentation, Eman Abdullah Alomar, Anthony Peruma, Mohamed Wiem Mkaouer, Christian D. Newman, Marouane Kessentini, Ali Ouni

Articles

Refactoring is the art of improving the structural design of a software system without altering its external behavior. Today, refactoring has become a well-established and disciplined software engineering practice that has attracted a significant amount of research presuming that refactoring is primarily motivated by the need to improve system structures. However, recent studies have shown that developers may incorporate refactoring strategies in other development-related activities that go beyond improving the design especially with the emerging challenges in contemporary software engineering. Unfortunately, these studies are limited to developer interviews and a reduced set of projects. To cope with the above-mentioned limitations, …

Forensic Memory Classification Using Deep Recurrent Neural Networks, Aishwarya Afzulpurkar

Theses

The goal of this project is to advance the application of machine learning frameworks and tools in the process of malware detection. Specifically, a deep neural network architecture is proposed to classify application modules as benign or malicious, using the lower level memory block patterns that make up these modules. The modules correspond to blocks of functionality within files used in kernel and OS level processes as well as user level applications. The learned model is proposed to reside in an isolated core with strict communication restrictions to achieve incorruptibility as well as efficiency, therefore providing a probabilistic memory-level view …

Learning Abstractions For Planning, Brian Charles Cook

Computer Science and Engineering Dissertations - Archive

Planners for hard problems must exploit domain-specific structure to find solutions efficiently. Yet, hand-engineered solutions and optimizations are often expensive and difficult or impossible to adapt to other problems. This work applies automatic machine learning techniques to increase planner performance for specific problem domains and to learn useful abstract representations for planning. In particular, this dissertation develops methods to address important aspects of learning in planning in four different areas: State-of-the-art domain-independent classical planners utilize multiple search heuristics and decide how to allocate computational effort between heuristics prior to planning. This work presents a heuristic planning algorithm that uses a …

Analysis Of True Risk Lab’S Price Prediction Algorithm In Relation To Market Results, Chris F. Hua

Honors Theses

The concept of beating the stock market is one of the main goals of financial investors and analysts. However, seasoned analysts and investors cannot perfectly predict the movements within the stock market. Machine learning (ML) is one prediction method that has intrigued the financial industry as a means of accurately predicting the market. Though the current prediction algorithms do not grasp every change in the stock markets, the models do provide a means of looking towards stock trends as a means to hedge an investor's or fund's portfolio against market declines by looking at the artificial intelligence (AI) results. This …

An Exploration Of Neuroanatomical Signatures Of Pediatric Bipolar Disorder Using Structural Neuroimaging, Jonika Tannous

Dissertations and Theses (Open Access)

Bipolar Disorder (BD) is diagnosed using the Diagnostic and Statistical Manual (DSM) criteria, which relies heavily on symptomatology. This method, however, lends itself to error due to variance in symptom expression and is further complicated during childhood and adolescence- a period marked by major anatomical and behavioral changes. Therefore, in order to institute early and effective interventions, it is imperative that we develop more objective methods of mood disorder characterization and diagnosis. Two proposed solutions for accomplishing this task include 1) the generation of normative development models to assess BD risk and 2) data-driven clustering of patients based on specific …

Development Of Fully Balanced Ssfp And Computer Vision Applications For Mri-Assisted Radiosurgery (Mars), Jeremiah Sanders

Dissertations and Theses (Open Access)

Prostate cancer is the second most common cancer in men and the second-leading cause of cancer death in men. Brachytherapy is a highly effective treatment option for prostate cancer, and is the most cost-effective initial treatment among all other therapeutic options for low to intermediate risk patients of prostate cancer. In low-dose-rate (LDR) brachytherapy, verifying the location of the radioactive seeds within the prostate and in relation to critical normal structures after seed implantation is essential to ensuring positive treatment outcomes.

One current gap in knowledge is how to simultaneously image the prostate, surrounding anatomy, and radioactive seeds within the …

A Machine Learning Framework For Prediction Of Diagnostic Trouble Codes In Automobiles, Mohan Kopuru

Theses and Dissertations

Predictive Maintenance is an important solution to the rising maintenance costs in the industries. With the advent of intelligent computer and availability of data, predictive maintenance is seen as a solution to predict and prevent the occurrence of the faults in the different types of machines. This thesis provides a detailed methodology to predict the occurrence of critical Diagnostic Trouble codes that are observed in a vehicle in order to take necessary maintenance actions before occurrence of the fault in automobiles using Convolutional Neural Network architecture.

Glacier Change Assessment Of The Columbia Icefield In The Canadian Rocky Mountains, Canada (1985 – 2018), Adjoa Dwamena Intsiful

Theses and Dissertations

Glaciers adjust their sizes as a response to changing climatic conditions which make them a good indicator of climate change. Remote-sensing based glacier monitoring provides a robust way to inventory the health of glaciers and are estimated as a measure of changes in their area, length, volume and mass balance over a period. This research uses remote sensing methods to map glacier extents from satellite images and explores the efficacy of three machine learning algorithms for accurate glacier classification. The results indicated that the Columbia icefield lost 42 km2 of its area cover between 1985 and 2018. It was observed …

A Generalized Gaussian Process Likelihood For Psychometric Function Estimation, Jonathan Wenhan Chen

McKelvey School of Engineering Graduate Student Theses & Dissertations

Psychometric functions model the relationship between a physical phenomenon, an independent variable, and a subject’s performance on a cognitive task. The estimation of these psychometric functions is critical for the understanding of perception and cognition as well as for the diagnosis and treatment of many sensory conditions. The ability to estimate psychometric functions of any complexity is necessary to this end. In the following thesis, a generalized likelihood function for psychometric function estimation with Gaussian processes is described and validated. Such a likelihood function is necessary to enable the usage of Gaussian processes for the estimation of non-zero guess and …

High-Capacity Directional Graph Networks, Miguel Dominguez

Theses

Deep Neural Networks (DNN) have proven themselves to be a useful tool in many computer vision problems. One of the most popular forms of the DNN is the Convolutional Neural Network (CNN). The CNN effectively learns features on images by learning a weighted sum of local neighborhoods of pixels, creating filtered versions of the image. Point cloud analysis seems like it would benefit from this useful model. However, point clouds are much less structured than images. Many analogues to CNNs for point clouds have been proposed in the literature, but they are often much more constrained networks than the typical …

Ar Comic Chat, Dylan Bowald

Theses

Live speech transcription and captioning are important for the accessibility of deaf and hard of hearing individuals, especially in situations with no visible ASL translators. If live captioning is available at all, it is typically rendered in the style of closed captions on a display such as a phone screen or TV and away from the real conversation. This can potentially divide the focus of the viewer and detract from the experience. This paper proposes an investigation into an alternative, Augmented Reality driven approach to the display of these captions, using deep neural networks to compute, track and associate deep …