Barrett, The Honors College Thesis/Creative Project Collection
Barrett, The Honors College at Arizona State University proudly showcases the work of undergraduate honors students by sharing this collection exclusively with the ASU community.
Barrett accepts high performing, academically engaged undergraduate students and works with them in collaboration with all of the other academic units at Arizona State University. All Barrett students complete a thesis or creative project which is an opportunity to explore an intellectual interest and produce an original piece of scholarly research. The thesis or creative project is supervised and defended in front of a faculty committee. Students are able to engage with professors who are nationally recognized in their fields and committed to working with honors students. Completing a Barrett thesis or creative project is an opportunity for undergraduate honors students to contribute to the ASU academic community in a meaningful way.
Displaying 1 - 10 of 186
Filtering by
- All Subjects: Machine Learning
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
As the prevalence and awareness of Autism Spectrum Disorder (ASD) increases, so does the variety of treatment options for primary symptoms (social interaction, communication, behavior) and secondary symptoms (anxiety, hyperactivity, GI problems, and insomnia). Various treatments, from Adderall to Citalopram to Flax Seed Oil promise relief for these symptoms. However, very little research has actually been done on some of these treatments. Additionally, the research that has been done fails to compare these treatments against one another in terms of symptom relief. The Autism Treatment Effectiveness Survey, written by Dr. James Adams, director of the Autism/Asperger's Research Program at ASU, and graduate student/program coordinator Devon Coleman, aims to fill this gap. The survey numerically rates medications based on benefit and adverse effects, in addition to naming specific symptoms that are impacted by the treatments. However, the survey itself was retrospective in nature and requires further evidence to support its claims. Therefore, the purpose of this research paper is to evaluate evidence related to the results of the survey. After the performing an extensive literature review of over 70 different treatments, it appears that the findings of the Autism Treatment Effectiveness Survey are generally well supported. There were a few minor discrepancies regarding the primary benefitted symptom, but there was not enough of a conflict to discount the information from the survey. As research is still ongoing, conclusions cannot yet be drawn for Nutritional Supplements, although the current data looks promising.
ContributorsAnderson, Amy Lynn (Author) / Adams, James (Thesis director) / Coleman, Devon (Committee member) / School of Nutrition and Health Promotion (Contributor) / W.P. Carey School of Business (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
Vitamins and minerals are, by definition, essential substances that are necessary for good health, and needed by every cell and organ to function appropriately. A deficiency of any one vitamin or mineral can be very serious. Although a very healthy diet rich in vegetables, fruits, and protein can provide sufficient amounts of most vitamins and minerals, many people do not consume an adequate diet. During pregnancy, there is an increased need for vitamins and minerals to promote a healthy pregnancy and a healthy baby. Prenatal supplements are intended to supplement a normal diet to ensure that adequate amounts of vitamins and minerals are consumed. The US Food and Drug Administration (FDA) has established Recommended Dietary Allowances for total vitamin/mineral intake from food and supplements, but they have not established recommendations for prenatal supplements. Therefore, there is a very wide variation in the content and quality of prenatal supplements. Many prenatal supplements contain only minimal levels of some vitamins and few or no minerals, in order to minimize cost and the number of pills. This results in insufficient vitamin/mineral supplementation for many women, and hence does not fully protect them or their children from pregnancy complications and health problems. Therefore, we have created our own set of recommendations for prenatal supplements. Our recommendations are based primarily on four sources: 1) FDA's Recommended Daily Allowances for pregnant women, which are estimated to meet the needs of 97.5% of healthy pregnant women. 2) FDA's Tolerable Upper Limit, which is the maximum amount of vitamins/minerals that can be safely consumed without any risk of health problems. 3) National Health and Nutrition Examination Survey (NHANES), which evaluates the average intake of vitamins and minerals by women ages 20-40 years in the US 4) Research studies on vitamin/mineral deficiencies or vitamin/mineral supplementation during pregnancy, and the effect on pregnancy, birth, and child health problems. In summary, the RDA establishes minimum recommended levels of vitamin/mineral intake from all sources, and the NHANES establishes the average intake from foods. The difference is what needs to be consumed in a supplement, on average. However, since people vary greatly in the quality of their diet, and since most vitamins and minerals have a high Tolerable Upper Limit, we generally recommend more than the difference between the RDA and the average NHANES. Vitamins generally have a larger Tolerable Upper Limit than do minerals. So, we recommend that prenatal vitamin/mineral supplements contain 100% of the RDA for most vitamins, and about 50% of the RDA for most minerals. However, based on additional research studies described below, in some cases we vary our recommendations from those averages.
ContributorsSorenson, Jacob (Author) / Adams, James (Thesis director) / Pollard, Elena (Committee member) / College of Integrative Sciences and Arts (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
In Arizona, there are virtually no established support groups or services for children on the autism spectrum and their families when experiencing the loss of a loved one. This is due to many factors, including the complexity of autism, an inconsistent belief that children with autism are capable of grieving, and a general lack of research conducted on the crossover of children with autism and grief. This proposal is based on the social work strengths perspective, in which I argue that children living with autism are capable of grieving and need support to do so. The way families and practitioners approach grief among children with autism is with individual counseling based on a therapist's discretion, grief books and guides, and virtual communities. I attempt to compile evidence-based and practical activities, interviews with parents and professionals, and my experience in order to recommend effective support for children with autism experiencing loss. My hope is that caregivers will use this material in order to understand and help a neglected population find the language and means to safely grieve.
ContributorsCohen, Jessica Marie (Author) / Ingram-Waters, Mary (Thesis director) / Stuckey, Michelle (Committee member) / School of Criminology and Criminal Justice (Contributor) / School of Social Work (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Autism Spectrum Disorder is a disorder that makes learning, socializing and daily living much more challenging for affected children and adults because of their atypical behaviors. A few examples of these behaviors are repetitive movements, impulsive actions, inability to communicate in a social setting, and many more. There is a stigma behind autism that is caused by those who are not well informed on the disorder. These people lack information, and in the past, it was assumed that the disorder is caused by "bad parenting." The parents are then afraid of social shame brought upon them by their child and neglect or avoid a diagnosis for their child's disorder. This becomes a vicious cycle that has negative effects on the affected individuals and their loved ones. Neglect of a diagnosis may also be caused by misinformation interpreted by the parents as their child develops. The parents do not realize this child developing outside of normal behavioral patterns. Years of research have been done to attempt to alleviate the symptoms of autism and cure the disorder. The Autism and Asperger's Program at ASU has developed a year-long dietary plan that increases supplementation to alleviate nutritional deficiencies in participants with autism. These deficiencies include vitamins, minerals, essential fatty acids, sulfate, carnitine, and digestive enzymes such as sucrase, maltase, and lactase. The participants were also put on a gluten-free casein-free diet toward the end of the study. To test the effectiveness of the treatment, the Severity of Autism Scale (SAS) and Social Responsiveness Scales (SRS) were used. The SAS tested the overall severity of ASD participants by rating them from one to ten, ten being "very severe" in terms of ASD symptoms. The results of this scale were compared at the beginning of the study (day 0) and at the end of the study (day 365). The SRS tested the social responsiveness of participants in the form of overall SRS and five subscales that included awareness, cognition, communication, motivation, and mannerisms. These results were also compared at the beginning and end of the study. After analysis of the data, there seemed to be no correlation between age and severity of autism/social responsiveness of participants. There was also no statistically significant data to suggest that there was a correlation between gender and severity of autism/social responsiveness of participants. However, there was statistically significant evidence that the treatment group did improve over the non-treatment/delayed treatment group in both the SAS and SRS. Neither age nor gender had a significant effect on the effectiveness of the treatment. These positive findings suggest that the integrated dietary
utritional therapy was beneficial, and future research on dietary treatments for autism and other disorders is recommended. This may also further discoveries of affected epigenomes with regards to nutritional treatments in disorders like ASD. The epigenome is the methylation and demethylation of the genome that mediates gene expression.
utritional therapy was beneficial, and future research on dietary treatments for autism and other disorders is recommended. This may also further discoveries of affected epigenomes with regards to nutritional treatments in disorders like ASD. The epigenome is the methylation and demethylation of the genome that mediates gene expression.
ContributorsGutgsell, Crystal Megan (Author) / Adams, James (Thesis director) / Pollard, Elena (Committee member) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Research regarding social skills training techniques for youth with autism spectrum disorders does not generally include implementation in anywhere but clinical, highly structured settings. However, leisure and recreation settings are conducive to promoting social skills improvement due to assets such as typical peer groups, engaging play activities, and significant opportunities for incidental learning. This program was designed for this particular population and integrated in to the daily schedule of a six-week long therapeutic recreation summer day camp for adolescents with disabilities ages 13-18. A standardized assessment, the Home and Community Social Behavior Scales (HCSBS) evaluates various areas of social ability and was utilized to measure changes specifically in peer interaction skills of participants with autism. Results discovered that this design can complement the aims of the camp and contribute to social enrichment and inclusion; every subject showed positive gains in the peer relations subscale at a much higher rate than in any other area of social ability. Multiple recognizable patterns emerged that can be evaluated in future studies, including greater average improvements for females, those ages 16-18 and those with an Asperger's diagnosis. Replication of this program could quantify and confirm the effectiveness of social skills training within recreation, which would require controlling for the additional treatment of a therapeutic summer camp. However, this observational case study demonstrates a promising future regarding improving the efficiency and value of therapeutic recreation services for adolescents with autism spectrum disorders.
ContributorsPugh, Tara Morgan (Author) / Rodriguez, Ariel (Thesis director) / Ramella, Kelly (Committee member) / Herron, Brad (Committee member) / Barrett, The Honors College (Contributor) / School of Community Resources and Development (Contributor)
Created2014-12
Description
This research examines the presentation of ASD in fictional children's literature. The goal is to use the research collected to determine what symptoms of ASD are receiving coverage versus what is not being covered but needs to be in a children's book about ASD. This was accomplished by first consulting background literature on ASD before examining 40 children's books about characters on the spectrum. It was found that girls on the spectrum received less coverage than boys did, and that most books conformed to one of two types: looking at ASD through the eyes of a neurotypical child and looking at it through the eyes of a child who has it. This led to the proposed idea of a book about a girl on the spectrum that would alternate between her point of view and the point of view of her neurotypical friend, and the subsequent draft of said book.
ContributorsAnderson, Sarah (Contributor) / Baldini, Cajsa (Contributor) / Adams, James (Contributor) / Barrett, The Honors College (Contributor)
Created2014-12