Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
Articles 1 - 14 of 14
Full-Text Articles in Physical Sciences and Mathematics
Reinforcement Learning Environment For Orbital Station-Keeping, Armando Herrera Iii
Reinforcement Learning Environment For Orbital Station-Keeping, Armando Herrera Iii
Theses and Dissertations
In this thesis, a Reinforcement Learning Environment for orbital station-keeping is created and tested against one of the most used Reinforcement Learning algorithm called Proximal Policy Optimization (PPO). This thesis also explores the foundations of Reinforcement Learning, from the taxonomy to a description of PPO, and shows a thorough explanation of the physics required to make the RL environment. Optuna optimizes PPO's hyper-parameters for the created environment via distributed computing. This thesis then shows and analysis the results from training a PPO agent six times.
Learning Health Information From Floor Sensor Data Within A Pervasive Smart Home Environment, Nicholas Brent Burns
Learning Health Information From Floor Sensor Data Within A Pervasive Smart Home Environment, Nicholas Brent Burns
Computer Science and Engineering Dissertations
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 …
Learning Embeddings For Wearable-Based Human Activity Analysis, Taoran Sheng
Learning Embeddings For Wearable-Based Human Activity Analysis, Taoran Sheng
Computer Science and Engineering Dissertations
The embedded sensors in widely used smartphones, wearable devices and smart environments make the sensor data stream of human activity more accessible. With the development of deep neural networks, extensive studies have been conducted using deep learning methods to extract useful information from the sensor data to recognize the human activity, identify the person, or monitor the health condition of the person. However, applying deep neural networks to the sensor based human activity analysis task remains a challenging research problem in ubiquitous computing. Some of the reasons are: (i) The majority of the acquired data has no labels; (ii) Most …
Classification Of Factual And Non-Factual Statements Using Adversarially Trained Lstm Networks, Daniel Obembe
Classification Of Factual And Non-Factual Statements Using Adversarially Trained Lstm Networks, Daniel Obembe
Computer Science and Engineering Theses
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 …
Cloud Resource Prediction Using Explainable And Cooperative Artificial Neural Networks, Nathan R. Nelson
Cloud Resource Prediction Using Explainable And Cooperative Artificial Neural Networks, Nathan R. Nelson
MSU Graduate Theses
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 …
Using Generative Adversarial Networks To Classify Structural Damage Caused By Earthquakes, Gian P. Delacruz
Using Generative Adversarial Networks To Classify Structural Damage Caused By Earthquakes, Gian P. Delacruz
Master's Theses
The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. There are several solution to automate post-earthquake reconnaissance image tagging using Machine Learning (ML) solutions to classify each occurrence of damage per building material and structural member type. ML algorithms are data driven; improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, ML and in particular Deep Learning (DL) has become one of the most …
Machine Learning And Data Mining-Based Methods To Estimate Parity Status And Age Of Wild Mosquito Vectors Of Infectious Diseases From Near-Infrared Spectra, Masabho Peter Milali
Machine Learning And Data Mining-Based Methods To Estimate Parity Status And Age Of Wild Mosquito Vectors Of Infectious Diseases From Near-Infrared Spectra, Masabho Peter Milali
Dissertations (1934 -)
Previous studies show that a trained partial least square regresser [sic] (PLSR) from near-infrared spectra classify laboratory and semi-field raised mosquitoes into less than or ≥ to seven days old with an average accuracy of 80%. This dissertation demonstrates that training models on near-infrared spectra (NIRS) using artificial neural network (ANN) as an architecture yields models with higher accuracies than training models using partial least squares (PLS) as an architecture. In addition, irrespective of the model architecture used, direct training of a binary classifier scores higher accuracy than training a regresser and interpreting it as a binary classifier. Furthermore, for …
Event-Based Visual-Inertial Odometry Using Smart Features, Zachary P. Friedel
Event-Based Visual-Inertial Odometry Using Smart Features, Zachary P. Friedel
Theses and Dissertations
Event-based cameras are a novel type of visual sensor that operate under a unique paradigm, providing asynchronous data on the log-level changes in light intensity for individual pixels. This hardware-level approach to change detection allows these cameras to achieve ultra-wide dynamic range and high temporal resolution. Furthermore, the advent of convolutional neural networks (CNNs) has led to state-of-the-art navigation solutions that now rival or even surpass human engineered algorithms. The advantages offered by event cameras and CNNs make them excellent tools for visual odometry (VO). This document presents the implementation of a CNN trained to detect and describe features within …
Driving Maneuver Detection Using Knowledge Distillation Networks, Kyle Windsor
Driving Maneuver Detection Using Knowledge Distillation Networks, Kyle Windsor
Electronic Thesis and Dissertation Repository
In this thesis, we examine the current state of Advanced Driving Assistance Systems (ADAS) and their relation to maneuver prediction in the literature. We then attempt to solve the problem of variable inter-driver behavior by applying a novel distillation learning system using RoadLab data on tracked driver cephalo-ocular gaze behavior in tandem with high-resolution CANbus data. Current training-based methods in maneuver prediction are potentially subject to underfitting as drivers may exhibit different behavior when preparing to maneuver, but it has been shown that drivers can be grouped into at least two distinct behavior models. We use this information to personalize …
Machine Learning? In My Election? It's More Likely Than You Think: Voting Rules Via Neural Networks, Daniel Firebanks-Quevedo
Machine Learning? In My Election? It's More Likely Than You Think: Voting Rules Via Neural Networks, Daniel Firebanks-Quevedo
Honors Papers
Impossibility theorems in social choice have represented a barrier in the creation of universal, non-dictatorial, and non-manipulable voting rules, highlighting a key trade-off between social welfare and strategy-proofness. However, a social planner may be concerned with only a particular preference distribution and wonder whether it is possible to better optimize this trade-off. To address this problem, we propose an end-to-end, machine learning-based framework that creates voting rules according to a social planner's constraints, for any type of preference distribution. After experimenting with rank-based social choice rules, we find that automatically-designed rules are less susceptible to manipulation than most existing rules, …
Design Of A Novel Wearable Ultrasound Vest For Autonomous Monitoring Of The Heart Using Machine Learning, Garrett G. Goodman
Design Of A Novel Wearable Ultrasound Vest For Autonomous Monitoring Of The Heart Using Machine Learning, Garrett G. Goodman
Browse all Theses and Dissertations
As the population of older individuals increases worldwide, the number of people with cardiovascular issues and diseases is also increasing. The rate at which individuals in the United States of America and worldwide that succumb to Cardiovascular Disease (CVD) is rising as well. Approximately 2,303 Americans die to some form of CVD per day according to the American Heart Association. Furthermore, the Center for Disease Control and Prevention states that 647,000 Americans die yearly due to some form of CVD, which equates to one person every 37 seconds. Finally, the World Health Organization reports that the number one cause of …
Image Features For Tuberculosis Classification In Digital Chest Radiographs, Brian Hooper
Image Features For Tuberculosis Classification In Digital Chest Radiographs, Brian Hooper
All Master's Theses
Tuberculosis (TB) is a respiratory disease which affects millions of people each year, accounting for the tenth leading cause of death worldwide, and is especially prevalent in underdeveloped regions where access to adequate medical care may be limited. Analysis of digital chest radiographs (CXRs) is a common and inexpensive method for the diagnosis of TB; however, a trained radiologist is required to interpret the results, and is subject to human error. Computer-Aided Detection (CAD) systems are a promising machine-learning based solution to automate the diagnosis of TB from CXR images. As the dimensionality of a high-resolution CXR image is very …
A Machine Learning System For Glaucoma Detection Using Inexpensive Machine Learning, Jon Kilgannon
A Machine Learning System For Glaucoma Detection Using Inexpensive Machine Learning, Jon Kilgannon
West Chester University Master’s Theses
This thesis presents a neural network system which segments images of the retina to calculate the cup-to-disc ratio, one of the diagnostic indicators of the presence or continuing development of glaucoma, a disease of the eye which causes blindness. The neural network is designed to run on commodity hardware and to be run with minimal skill required from the user by packaging the software required to run the network into a Singularity image. The RIGA dataset used to train the network provides images of the retina which have been annotated with the location of the optic cup and disc by …
A Deep Learning Approach To Mapping Irrigation: U-Net Irrmapper, Thomas Henry Colligan Iv
A Deep Learning Approach To Mapping Irrigation: U-Net Irrmapper, Thomas Henry Colligan Iv
Graduate Student Theses, Dissertations, & Professional Papers
Accurate maps of irrigation are essential for understanding and managing water resources in light of a warming climate. We present a new method for mapping irrigation and apply it to the state of Montana over the years 2000-2019. The method is based on an ensemble of convolutional neural networks that only rely on raw Landsat surface reflectance data. The ensemble of networks method learns to mask clouds and ignore Landsat 7 scan-line failures without supervision, reducing the need for preprocessing data or feature engineering. Unlike other approaches to mapping irrigation, the method doesn't use other mapping products like the Cropland …