Digital Commons Network^™

Open Set Classification For Deep Learning In Large-Scale And Continual Learning Models, Ryne Roady

Theses

Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers require the ability to recognize inputs from outside the training set as unknowns and update representations in near real-time to account for novel concepts unknown during offline training. This problem has been studied under multiple paradigms including out-of-distribution detection and open set recognition; however, for convolutional neural networks, there have been two major approaches: 1) inference methods to separate known inputs from unknown inputs and 2) feature space regularization …

Deep Learning To Predict Ocean Seabed Type And Source Parameters, David Franklin Van Komen

Theses and Dissertations

In the ocean, light from the surface dissipates quickly leaving sound the only way to see at a distance. Different sediment types on the ocean floor and water properties like salinity, temperature, and ocean depth all change how sound travels across long distances. Hard sediment types, such as sand and bedrock, are highly reflective while softer sediment types, such as mud, are more absorptive and change the received sound upon arrival. Unfortunately, the vast majority of the ocean floor is not mapped and the expenses involved in creating such a map are far too great. Traditional signal processing methods in …

Point Completion Networks And Segmentation Of 3d Mesh, Naga Durga Harish Kanamarlapudi

Theses

Deep learning has made many advancements in fields such as computer vision, natural language processing and speech processing. In autonomous driving, deep learning has made great improvements pertaining to the tasks of lane detection, steering estimation, throttle control, depth estimation, 2D and 3D object detection, object segmentation and object tracking. Understanding the 3D world is necessary for safe end-to-end self-driving. 3D point clouds provide rich 3D information, but processing point clouds is difficult since point clouds are irregular and unordered. Neural point processing methods like GraphCNN and PointNet operate on individual points for accurate classification and segmentation results. Occlusion of …

Flight Data Of Airplane For Wind Forecasting, Astha Sharma

LSU New Orleans Theses and Dissertations

This research solely focuses on understanding and predicting weather behavior, which is one of the important factors that affect airplanes in flight. The future weather information is used for informing pilots about changing flight conditions. In this paper, we present a new approach towards forecasting one component of weather information, wind speed, from data captured by airplanes in flight. We compare NASA’s ACT-America project against NOAA’s Wind Aloft program for prediction suitability. A collinearity analysis between these datasets reveals better model performance and smaller test error with NASA’s dataset. We then apply machine learning and a genetic algorithm to process …

Query-Driven Global Graph Attention Model For Visual Parsing: Recognizing Handwritten And Typeset Math Formulas, Mahshad Mahdavi

Theses

We present a new visual parsing method based on standard Convolutional Neural Networks (CNNs) for handwritten and typeset mathematical formulas. The Query-Driven Global Graph Attention (QD-GGA) parser employs multi-task learning, using a single feature representation for locating, classifying, and relating symbols. QD-GGA parses formulas by first constructing a Line-Of-Sight (LOS) graph over the input primitives (e.g handwritten strokes or connected components in images). Second, class distributions for LOS nodes and edges are obtained using query-specific feature filters (i.e., attention) in a single feed-forward pass. This allows end-to-end structure learning using a joint loss over primitive node and edge class distributions. …

An Exploration Of Success Factors In The Healthcare Supply Chain, Matthew Tidwell

Theses and Dissertations

This research builds off previous research conducted in 2009 which included a survey of healthcare professionals assessing their organization’s levels of supply chain maturity (SCM) and data standard readiness (DSR) from 1 to 5 [Smith, 2011]. With the survey data, Smith developed a 0-1 quadratic program to conserve the maximum amount of survey data while removing non-responses. This research uses the quadratic program as well as other machine learning algorithms and analysis methods to investigate what factors contribute to an organization’s SCM and DSR levels the most. No specific factors were found; however, different levels of prediction accuracy were achieved …

Advanced In-Situ Layer-Wise Quality Control For Laser-Based Additive Manufacturing Using Image Sequence Analysis, Mehrnaz Noroozi Esfahani

Theses and Dissertations

Quality assurance has been one of the major challenges in laser-based additive manufacturing (AM) processes. This study proposes a novel process modeling methodology for layer-wise in-situ quality monitoring based on image series analysis. An image-based autoregressive (AR) model has been proposed based on the image registration function between consecutively observed thermal images. Image registration is used to extract melt pool location and orientation change between consecutive images, which contains sensing stability information. Subsequently, a Gaussian process model is used to characterize the spatial correlation within the error matrix. Finally, the extracted features from the aforementioned processes are jointly used for …

Towards Generation Of Creative Software Requirements, Quoc Anh Do Jr

Theses and Dissertations

Increasingly competitive software industry, where multiple systems serve the same application domain and compete for customers, favors software with creative features. To promote software creativity, research has proposed multi-day workshops with experienced facilitators, and semi-automated tools to provide a limited support for creative thinking. Such approach is either time consuming and demands substantial involvement from analysts with creative abilities, or useful only for existing large-scale software with a rich issue tracking system. In this dissertation, we present different approaches leveraging advanced natural language processing and machine learning techniques to provide automated support for generating creative software requirements with minimal human …

Identifying And Mitigating Heat Stress Of Grazing Dairy Cattle Using Shade And Sprinklers, Carly Becker

Theses and Dissertations

Animal welfare, reproduction, and milk production can be negatively affected when dairy cattle experience heat stress. Dairy cows in southern latitudes spend nearly 4 to 6 months in a state of heat stress. Animal health professionals and dairy producers use changes in physiological responses and behavioral patterns of cows as a tool for identifying poor health and welfare in periods of heat stress. The objectives of this study were to monitor the effects of heat stress on grazing dairy cows provided with shade or sprinklers by comparing various physiological indices of heat stress, and to, design and utilize a heat …

Smarter Simulation Placement Of Kilonova Light Curve Models For Computationally Inexpensive Surrogate Model Creation, Marko Ristic

Theses

The first detected binary neutron star merger GW170817 allowed for the simultaneous detection of gravitational and electromagnetic waves which started the era of multi-messenger astrophysics. The existence of an electromagnetic counterpart to a compact object merger allowed for a significantly deeper analysis of the merger event and much tighter resultant constraints on existing physical models of neutron stars, nuclear physics, and the Universe itself.

Multi-messenger analysis requires sophisticated source modeling. For the foreseeable future, demanding computational resource costs will result in a sparse availability of state-of-the-art neutron star merger light curve simulations. Astrophysical inference can proceed using an alternate approach …

Predicting Materials Behavior With Atomistic Simulations And Machine Learning, Ayana Ghosh

Doctoral Dissertations

Data driven approaches based on machine learning (ML) algorithms are very popular in the domain of physical sciences for the determination of yet unknown structure- properties-performance relationships for a wide range of different material families. This dissertation focuses on studying a number of such cases where various ML algorithms and statistical techniques, coupled with appropriate materials data obtained from experiments and atomistic simulations, are employed to build comprehensive ML-based frameworks capable of predicting complex materials behavior. The materials spaces investigated encompass isolated organic molecules, polymer crystals, inorganic multiferroics and actinides, while the target system characteristics or functionalities include molecular crystallization …

Mammography Image Bi-Rads Classification Using Ohplall, Bob Vanderheyden, Ying Xie

OHPL Publications

Medical image analysis and classification, using machine learning, particularly Convolutional Neural Networks, have demonstrated a great deal of success. Research into mammography image classification tended to focus on either binary outcome (malignancy or benign) or nominal (unordered) classification for multiclass labels [1]. The industry standard metric for radiologist’s classification of mammography images is a rating scale called BI-RADS (Breast Imaging Reporting and Data System), where values 1 through 5 are a distinct progression of assessment that are intended to denote higher risk of a malignancy, based on the characteristics of anomalies within an image [1][2][3]. The development of a classifier …

In Situ Sensor Calibration Using Noise Consistency, Shriiesh Var Sharma

Computer Science and Engineering Theses - Archive

Robots rely on sensors to map their surroundings. As a result, the accuracy of the map depends heavily on the sensor noise and in particular on accurate knowledge of it. The common way to minimize the impact of sensor noise is to use filtering algorithms. Accuracy of these filtering algorithms (like the Kalman filter) relies on the accuracy of the user supplied measurement noise model. Inaccurate noise models lead to higher residual noise in state estimates and errors in the estimate of the precision of the state estimate. It is therefore important to have precise noise models and thus accurately …

Classification Of Factual And Non-Factual Statements Using Adversarially Trained Lstm Networks, Daniel Obembe

Computer Science and Engineering Theses - Archive

Being able to determine which statements are factual and therefore likely candidates for further verification is a key value-add in any automated fact-checking system. For this task, it has been shown that LSTMs outperform regular machine learning models, such as SVMs. However, the complexity of LSTMs can also result in over fitting (Gal and Ghahramani,1997), leading to poorer performance as models fail to generalize. To resolve this issue, we set out to utilize adversarial training as away to improve the performance of LSTMs for the task of classifying statements as factual or non-factual. In our experiment, we implement the adversarial …

Person Identification And Tinetti Score Assessment Using Balance Parameters To Determine Fall Risk, Varsha Rani Chawan

Computer Science and Engineering Theses - Archive

This thesis is aimed at a substantial health problem among the elderly population that is “Fall”, a major cause of accidental home deaths. Studies show approximately one-third of community-dwelling people over 65 years of age will experience one or more falls each year. The balance and walking pattern are useful to determine the risk of fall in an individual and is highly influenced by several parameters and conditions. The deterioration in the balance and walking stability of an individual can occur because of the natural processes related to aging or as a result of various underlying health conditions, fatigue, muscle …

Analyzing The Fractal Dimension Of Various Musical Pieces, Nathan Clark

Industrial Engineering Undergraduate Honors Theses

One of the most common tools for evaluating data is regression. This technique, widely used by industrial engineers, explores linear relationships between predictors and the response. Each observation of the response is a fixed linear combination of the predictors with an added error element. The method is built on the assumption that this error is normally distributed across all observations and has a mean of zero. In some cases, it has been found that the inherent variation is not the result of a random variable, but is instead the result of self-symmetric properties of the observations. For data with these …

Computer Vision Methods For Sign Language And Cognitive Evaluation Through Physical Tasks, Alex J. Dillhoff

Computer Science and Engineering Dissertations - Archive

Analyzing human motion is vital for a multitude of tasks including human-computer interaction, sign language recognition, and the assessment of cognitive disorders. Providing automatic assessments for cognitive disorders increases the accessibility and affordability of life-changing tests and treatments. For sign language recognition, automated translation systems bridge the gap between native and non-native signers. Additionally, dictionary look-up systems are helpful for native signers learning a new language. Common to both of these tasks is the reliance of fine motor function in the hands. Hand Pose Estimation methods are used to drive applications that rely on hand shape. These tasks present unique …

Gaining Computational Insight Into Psychological Data: Applications Of Machine Learning With Eating Disorders And Autism Spectrum Disorder, Natalia Rosenfield

Computational and Data Sciences (PhD) Dissertations

Over the past 100 years, assessment tools have been developed that allow us to explore mental and behavioral processes that could not be measured before. However, conventional statistical models used for psychological data are lacking in thoroughness and predictability. This provides a perfect opportunity to use machine learning to study the data in a novel way. In this paper, we present examples of using machine learning techniques with data in three areas: eating disorders, body satisfaction, and Autism Spectrum Disorder (ASD). We explore clustering algorithms as well as virtual reality (VR).

Our first study employs the k-means clustering algorithm to …

Learning Health Information From Floor Sensor Data Within A Pervasive Smart Home Environment, Nicholas Brent Burns

Computer Science and Engineering Dissertations - Archive

Spatial and temporal gait analysis can provide useful measures for determining a person’s state of health while also identifying deviations in day-to-day activity. The SmartCare project is a multi-discipline health technologies project that aims to provide an unobtrusive and pervasive system that provides in-home health monitoring for the elderly. This research work focuses on the pressure-sensitive smart floor of the SmartCare project by using an experimental floor to develop methods for future use on a floor deployed within a home. This work presents a procedure to automatically calibrate a smart floor’s pressure sensors without specialized physical effort. The calibration algorithm …

Behavioral Model Based Trust Management Design For Iot At Scale, Brennan Huber

Masters Theses and Doctoral Dissertations

With the rise in the number of devices in the Internet of Things (IoT), the number of malicious devices will also drastically increase. Smart cities' decisions are based on data being collected by IoT devices in real-time, of which a connected-vehicle system is included. Behaviors such as malicious data injection can significantly impact connected vehicles. To aid in combating this threat, monitoring smart city and connected vehicle's sensor data will allow for construction of a behavioral model. Implementing machine learning will aid in constructing a standard behavior such that any device that begins to malfunction or behave maliciously can be …

Use Of Self-Organizing Maps To Study Sex- And Speed-Dependent Changes In Running Biomechanics, Marwan Mahmoud A Aljohani, Kristof Kipp

Exercise Science Faculty Research and Publications

Background

Up to 79% of runners get injured every year, with higher rates of injuries occurring in females than males. A self-organizing map (SOM) is a type of artificial neural network that can be used to inspect large datasets and study coordination patterns. The purpose of this study was to use an SOM to study the effects of sex and speed on biomechanical coordination patterns.

Method

Thirty-two healthy runners ran on an instrumented treadmill at their long slow distance speed (LSD) and at speed 30% faster (LSD + 30%). Vertical ground reaction force (vGRF), vertical tibial acceleration, step parameters, electromyograms …

Cloud Resource Prediction Using Explainable And Cooperative Artificial Neural Networks, Nathan R. Nelson

Graduate Theses/Dissertations

This work proposes a system for predicting cloud resource utilization by using runtime assembled cooperative artificial neural networks (RACANN). RACANN breaks up the problem into smaller contexts, each represented by a small-scale artificial neural network (ANN). The relevant ANNs are joined together at runtime when the context is present in the data for training and predictions. By analyzing the structure of a complete ANN, the influence of inputs is calculated and used to create linguistic descriptions (LD) of model behavior, so RACANN becomes explainable (eRACANN). The predictive results of eRACANN are compared against its prototype and a single deep ANN …

Antipodal Robotic Grasping Using Deep Learning, Shirin Joshi

Theses

In this work, we discuss two implementations that predict antipodal grasps for novel objects: A deep Q-learning approach and a Generative Residual Convolutional Neural Network approach. We present a deep reinforcement learning based method to solve the problem of robotic grasping using visio-motor feedback. The use of a deep learning based approach reduces the complexity caused by the use of hand-designed features. Our method uses an off-policy reinforcement learning framework to learn the grasping policy. We use the double deep Q-learning framework along with a novel Grasp-Q-Network to output grasp probabilities used to learn grasps that maximize the pick success. …

Hand-Over-Face Segmentation, Sakher Ghanem

Computer Science and Engineering Dissertations - Archive

Accurate hand segmentation is vital in many applications in which the hands play a central role, such as sign language recognition, action recognition, and gesture recognition. A relatively unexplored obstacle to correct hand segmentation is when the hand overlaps the face. The shortage of a dataset for this research area has been one motivation for this work. However, this dissertation investigates and proposes improvements for the hand-over-face segmentation task. Toward an in-depth study of the hand segmentation problem, the work presented in this dissertation will yield several contributions. First, it introduces a survey on sign language recognition systems using mobile …

A Sense Of Scale: Mapping Exotic Annual Grasses With Satellite Imagery Across A Landscape And Quantifying Their Biomass At A Plot Level With Structure-From-Motion In A Semi-Arid Ecosystem, Monica Vermillion

Boise State University Theses and Dissertations

The native vegetation communities in the sagebrush steppe, a semi-arid ecosystem type, are under threat from exotic annual grasses. Exotic annual grasses increase fire severity and frequency, decrease biodiversity, and reduce soil carbon storage amongst other ecosystem services. The invasion of exotic annual grasses is causing detrimental impacts to land use by eliminating forage for livestock and creating a huge economic cost from fire control and post-fire restoration. To combat invasion, land managers need to know what exotic annual grasses are present, where they are invading, and estimates of their biomass. Mapping exotic annual grasses is challenging because many areas …

Improving Spellchecking For Children: Correction And Design, Brody Downs

Boise State University Theses and Dissertations

Children commonly use software applications such as search engines and word processors in the classroom environment. However, a major barrier to using these programs successfully is the ability of children to type and spell effectively. While many programs make use of spellcheckers to provide spelling corrections to their users, they are designed for more traditional users (i.e., adults) and have proven inadequate for children. The aims of this work is twofold: first, to address the types of spelling errors children make by researching, developing, and evaluating algorithms to generate and rank candidate spelling suggestions; and second, to evaluate the impact …

Assessing The Prevalence Of Suspicious Activities In Asphalt Pavement Construction Using Algorithmic Logics And Machine Learning, Mostofa Najmus Sakib

Boise State University Theses and Dissertations

Quality Control (QC) and Quality Assurance (QA) is a planned systematic approach to secure the satisfactory performance of Hot mix asphalt (HMA) construction projects. Millions of dollars are invested by government and state highway agencies to construct large-scale HMA construction projects. QC/QA is statistical approach for checking the desired construction properties through independent testing. The practice of QC/QA has been encouraged by the Federal Highway Administration (FHWA) since the mid 60’s. However, the standard QC/QA practice is often criticized on how effective such statistical tests and how representative the reported material tests are. Material testing data alteration in the HMA …

Archaeology Or Crime Scene? Teeth Micro And Macro Structure Analysis As Dating Variable, Jessica A. Vincenty

Student Theses

Simple methods to aid in the determination of forensic or archaeologic relevancy of skeletonized remains have been researched since the 1950s. With advances in microscopic imaging techniques and machine learning computer data analysis methods the relevancy of decontextualized, comingled remains has room for improvement. This thesis is a study done to pioneer a new approach to analyzing dental skeletal remains to determine forensic relevancy.

Archaeological dental samples collected from the ancient city of Ur in modern day southern Iraq in addition to modern dental extractions were processed for scanning electron microscopy imaging. Archaeological and modern samples displayed different surface and …

Learning Dynamics From Large Biological Data Sets: Machine Learning Meets Systems Biology, William Gilpin, Yitong Huang, Daniel B. Forger

Mathematics Sciences: Faculty Publications

In the past few decades, mathematical models based on dynamical systems theory have provided new insight into diverse biological systems. In this review, we ask whether the recent success of machine learning techniques for large-scale biological data analysis provides a complementary or competing approach to more traditional modeling approaches. Recent applications of machine learning to the problem of learning biological dynamics in diverse systems range from neuroscience to animal behavior. We compare the underlying mechanisms and limitations of traditional dynamical models with those of machine learning models. We highlight the unique role that traditional modeling has played in providing predictive …

Novel Deep Learning Methods Combined With Static Analysis For Source Code Processing, Duy Quoc Nghi Bui

Dissertations and Theses Collection (Open Access)

It is desirable to combine machine learning and program analysis so that one can leverage the best of both to increase the performance of software analytics. On one side, machine learning can analyze the source code of thousands of well-written software projects that can uncover patterns that partially characterize software that is reliable, easy to read, and easy to maintain. On the other side, the program analysis can be used to define rigorous and unique rules that are only available in programming languages, which enrich the representation of source code and help the machine learning to capture the patterns better. …