Matching Items (183)
Filtering by
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
Leveraging Machine Learning and Wireless Sensing for Robot Localization - Location Variance Analysis
Description
Object localization is used to determine the location of a device, an important aspect of applications ranging from autonomous driving to augmented reality. Commonly-used localization techniques include global positioning systems (GPS), simultaneous localization and mapping (SLAM), and positional tracking, but all of these methodologies have drawbacks, especially in high traffic indoor or urban environments. Using recent improvements in the field of machine learning, this project proposes a new method of localization using networks with several wireless transceivers and implemented without heavy computational loads or high costs. This project aims to build a proof-of-concept prototype and demonstrate that the proposed technique is feasible and accurate.
Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.
As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.
Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.
As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.
ContributorsChang, Roger (Co-author) / Kann, Trevor (Co-author) / Alkhateeb, Ahmed (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson’s disease classification and severity assessment. An automated, stable, and accurate method to evaluate Parkinson’s would be significant in streamlining diagnoses of patients and providing families more time for corrective measures. We propose a methodology which incorporates TDA into analyzing Parkinson’s disease postural shifts data through the representation of persistence images. Studying the topology of a system has proven to be invariant to small changes in data and has been shown to perform well in discrimination tasks. The contributions of the paper are twofold. We propose a method to 1) classify healthy patients from those afflicted by disease and 2) diagnose the severity of disease. We explore the use of the proposed method in an application involving a Parkinson’s disease dataset comprised of healthy-elderly, healthy-young and Parkinson’s disease patients.
ContributorsRahman, Farhan Nadir (Co-author) / Nawar, Afra (Co-author) / Turaga, Pavan (Thesis director) / Krishnamurthi, Narayanan (Committee member) / Electrical Engineering Program (Contributor) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This thesis dives into the world of artificial intelligence by exploring the functionality of a single layer artificial neural network through a simple housing price classification example while simultaneously considering its impact from a data management perspective on both the software and hardware level. To begin this study, the universally accepted model of an artificial neuron is broken down into its key components and then analyzed for functionality by relating back to its biological counterpart. The role of a neuron is then described in the context of a neural network, with equal emphasis placed on how it individually undergoes training and then for an entire network. Using the technique of supervised learning, the neural network is trained with three main factors for housing price classification, including its total number of rooms, bathrooms, and square footage. Once trained with most of the generated data set, it is tested for accuracy by introducing the remainder of the data-set and observing how closely its computed output for each set of inputs compares to the target value. From a programming perspective, the artificial neuron is implemented in C so that it would be more closely tied to the operating system and therefore make the collected profiler data more precise during the program's execution. The program is designed to break down each stage of the neuron's training process into distinct functions. In addition to utilizing more functional code, the struct data type is used as the underlying data structure for this project to not only represent the neuron but for implementing the neuron's training and test data. Once fully trained, the neuron's test results are then graphed to visually depict how well the neuron learned from its sample training set. Finally, the profiler data is analyzed to describe how the program operated from a data management perspective on the software and hardware level.
ContributorsRichards, Nicholas Giovanni (Author) / Miller, Phillip (Thesis director) / Meuth, Ryan (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This honors thesis outlines a method for teaching argument writing in the secondary classroom, including the elements of an argument based upon the Toulmin method, and diverse ways to help students who are all types of learners become engaged and receive the support they need. It includes all elements of argument, including evidence, warrants, backing, counterargument, claims, theses, the rhetorical triangle and the rhetorical appeals, including definitions and how they fit together in an argumentative essay. The largest portion of the project is dedicated to activities and resources for teachers based upon all of those elements, along with activities for the writing process as a whole. These activities are based upon the student's individual experience as well as various scholarly resources from leading professionals in the curriculum development field for English Language Arts. This is not meant to be an end-all be-all solution for teaching argument writing, but rather one of many resources that teachers can use in their classroom. This 30-page paper, including references, are condensed into an accessible website for teachers to use more easily. Each tab on the website refers to a different element or focus of the argument writing process, with both a definition and introduction as well as one or more activities for teachers to implement into the classroom. The activities are versatile and general for the purpose of teachers being able to include them into whatever curriculum they are currently teaching. The goal is that they can add argument instruction into what they are already either willingly or being required to teach in an easy and logical way. The website is available for any secondary teachers to use as they see fit at www.teachingargumentwriting.weebly.com.
ContributorsBrooks, Jenna Nicole (Author) / Blasingame, James (Thesis director) / Barnett, Juliet (Committee member) / Division of Teacher Preparation (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Fringe: Abstract Fringe is a feature length screenplay and a work of original science fiction. The story takes place in the future, on a planet far from Earth but it is told from the human perspective and is meant to draw into question many issues present in society today: prejudice, hatred, multiculturalism, war, and social division. The screenplay seeks to pose an allegorical relationship between the humanity living on the planet, and the enemies they face, and the present day conflict between America and the Middle East or ISIS. The story follows Miles as he is forced to ally with his sworn enemy, the Lue, and learn to fight together to save his world from destruction. Miles begins the film bitter, resentful, and filled with prejudice towards his foes, much like a majority of Americans today. Instead of focussing on that conflict though, my story unites these two bitter enemies and asks them to put aside their violent and hateful pasts to fight a new, more powerful foe together. As the events unfold my characters learn that their enemies can be just like them and that they have something valuable to offer their world. My screenplay is about finding commonality with the enemy, on both sides of a conflict. By the end of my tale, Miles learns that there is good to be found in the world, even in his sworn enemies, if he looks close enough. It may seem like an archetypal plot on the surface but I worked hard to create a world that has not been seen in film before, an original science fiction universe that can bring these issues into the light and entertain an audience while doing so. I feel that my screenplay does just that, offering entertainment with and edge of social commentary, and stays true to the science fiction form.
ContributorsTrcic, Colton Walker (Author) / Maday, Gregory (Thesis director) / Bernstein, Gregory (Committee member) / WPC Graduate Programs (Contributor) / W. P. Carey School of Business (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Each part of the book is written from a different relative, literarily-inclined perspective. The portion of this submission that captures what my experience as a Barrett student has lended to my approved manuscript (by Dorrance Publishing Co.) lies with the excerpted material from Part IV. Below is the table of contents for the novel work itself, as well as the styles of writing assumed per part.
ContributorsDampare, Patrick Nelu (Author) / Blasingame, James (Thesis director) / Glenn, Bruce (Committee member) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
Over the course of my undergraduate experience, I have grown significantly as an artist - developing an assortment of strengths in a variety of cinematic disciplines ranging from screenwriting and producing to post-production and cinematography. All the while, I have been giving back to the Sun Devil community by serving in a number of leadership positions around campus which exposed me to a plethora of communities differ from my own. The combination of these experiences allows me to continuously explore new passions in synergy with my art. Two of these standing as the concept of live performance and the work of William Shakespeare. Through this exploration of artistic synergy, I have experimented with integrating the works of the Bard of Avon into the realm of cinema. From the beginning of 2105, I have been drafting a feature-length screenplay which serves as a quasi-prequel to Shakespeare's The Tempest. Under the title of A Kingdom or a Cure, it tells the story of the revolutionary war-hero Miguel Prosperiti as he struggles to save his daughter form a mysterious disease which has baffled the best medical minds while the country he has rebuilt comes crumbling down in post-apocalyptic Italy. Deposed and left to die at the hands of his brother, Miguel must defend his child from the evil witch Sycorax who attempts to kill the pair in order to feed off of their suffering and prolong her own life. Serving to fill the requirements for the Film and Media Production Capstone, A Kingdom or a Cure reimagines the world of Shakespeare's play and creates a new context for the words and actions of its leading characters. Such stands as the foundation of what I have created for what I have created as my applied project - a stylistic re-imagining of William Shakespeare's The Tempest which draws from multiple interpretations of the narrative to be performed as a piece within a larger theatrical presentation staged with only the classical techniques which stand contemporary to the Bard of Avon. The remainder of this document shall lie in six primary sections. The first two establish the project and detail its evolution over the course of the thesis process. Next stands as the production log which chronicles my journey over the Classical and Poetic Drama course as well as the rehearsal process for Mythfest and the Chaucer Festival. Fourth shall consist of a bibliography of all the texts which I have worked with over the course of this thesis experience. Fifth rests A Kingdom or a Cure - the screenplay which inspired me to embark on the grand journey which this thesis has taken me. Sixth shall assume the form of the PowerPoint Presentation which I presented at my thesis defense which contains a collection of images which have provided me with artistic inspiration throughout the thesis process. In conjunction with one another, these pieces serve as the written elements of my applied project.
ContributorsArcaro, Michael Anthony (Author) / Giner, Oscar (Thesis director) / Eckard, Bonnie (Committee member) / WPC Graduate Programs (Contributor) / School of Historical, Philosophical and Religious Studies (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
"The Problem of Hope: Literary Tragedy in Mid-Twentieth Century American Fiction" examines Arthur Miller's Death of a Salesman, Ralph Ellison's Invisible Man, and Sylvia Plath's The Bell Jar through the lens of tragedy. This thesis delves into how conflicts between internal and external identities can create a tragic individual, what kinds of success count toward achievement of the "American Dream," and whether the tragic "common man" is the socially normative one or the socially disenfranchised one. It raises a three-dimensional theoretical approach to American tragedy and, most importantly, considers the significance of tragic hope for American literature. This paper questions the construction of American identities across class, race, and gender according to social scripts. It seeks to uncover what forces these scripts exert on American cultural myths and rereads those myths through tragedy to explore Miller's idea of a noble common man. By moving from Miller to Ellison to Plath, this thesis traces the undercurrents of tragedy through some of the most identity-focused novels of mid-twentieth century American fiction to see how the overarching American narrative changed from 1940 to 1969 as the US underwent significant social changes domestically and image changes abroad. Ultimately, this paper concludes that tragedy in mid-twentieth century American fiction points toward a new idea of American success as a success that occurs beyond social scripts.
ContributorsMedeiros, Amy Marie (Author) / Holbo, Christine (Thesis director) / Sadowski-Smith, Claudia (Committee member) / Department of English (Contributor) / W. P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
This project focuses on techniques contemporary American poets use in their work. Ten different poetry collections are analyzed for dominant writing styles and techniques, which I then apply to my own poems, concentrating on modeling that particular poet. I then reflect on those poems through an evaluation of my writing process, how those techniques were implemented, and how they affected the poem. In addition to these reviews and reflections, I also wrote three articles about the literary community and what I've learned from my interactions in that community. All these materials are organized into a website, which shows the connections between the different writings via links and menus. Creating this website brings all the materials together to demonstrate my growth as a poet, writer, and designer. This heavy focus on poetry and analysis has helped sharpen my critical thinking skills and has better prepared me for a career in design and journalism.
ContributorsHansen, Elizabeth Sarah (Author) / Murphy, Patricia (Thesis director) / Savard, Jeannine (Committee member) / Barrett, The Honors College (Contributor) / Department of English (Contributor) / Hugh Downs School of Human Communication (Contributor) / Walter Cronkite School of Journalism and Mass Communication (Contributor)
Created2015-05