Matching Items (304)
Filtering by
- All Subjects: sports
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
- Member of: Theses and Dissertations
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
The National Basketball Association (NBA) is one of the Big Four Sporting Leagues of US Professional Sports. In recent years, the NBA has enjoyed milestone seasons in both attendance and television ratings, resulting in steady increases to both, over the previous decade. (Morgan, 2017) This surge can be attributed in part to the integration of "cultural recognition" initiatives and the overall message of inclusivity on the part of NBA franchises, with their respective promotions and advertisements such as television, social media, radio, etc. Heritage Nights, such as "Noche Latina," among other variants in the NBA, typically feature culturally influenced changes to team logos, giveaways, and other consumer offerings. In markets where Hispanics make up a significant percentage of the fan-base, such as Phoenix, NBA franchises such as the Phoenix Suns must ascertain the financial or perceptual impacts, associated with risks of stereotyping, offending or otherwise unintentionally alienating different categories of fans. To this end, data was collected from the local NBA franchises' fanbase, specifically Phoenix Suns season-ticket holders, and was statistically checked for significant relationships between both categories of fans and several different variables. This analysis found that only $192K in revenue is being missed through the investment of Heritage Nights, and that fan perceptions of stereotypical or offensive giveaways and practices have no significant effect on game or event attendance, despite the stereotypes toward giveaways and practices still being present. Implications of this study provide possible next steps for the Suns and continue to widen the scope of demographical sports marketing both in professional basketball and beyond.
ContributorsGibbens, Patrick Alexander (Author) / Eaton, John (Thesis director) / McIntosh, Daniel (Committee member) / Department of Supply Chain Management (Contributor) / School of Music (Contributor) / Department of Marketing (Contributor) / W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This paper is intended to identify a correlation between the winning percentage of sports teams in the four major professional sports leagues in the United States and the GDP per capita of their respective cities. We initially compiled fifteen years of franchise performance along with economic data from the Federal Reserve Bank of St. Louis to analyze this relationship. After converting the data into a language recognized by Stata, the regression tool we used, we ran multiple regressions to find relevant correlations based off of our inputs. This paper will show the value of the economic impact of strong or weak performance throughout various economic cycles through data analysis and conclusions drawn from the results of the regression analysis.
ContributorsAndl, Tyler (Co-author) / Shirk, Brandon (Co-author) / Goegan, Brian (Thesis director) / Eaton, John (Committee member) / School of Accountancy (Contributor) / Department of Finance (Contributor) / Department of Supply Chain Management (Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12
Description
Cystic Fibrosis (CF) is a genetic disorder that disrupts the hydration of mucous of the lungs, which promotes opportunistic bacterial infections that begin in the affected person’s childhood, and persist into adulthood. One of the bacteria that infect the CF lung is Pseudomonas aeruginosa. This gram-negative bacterium is acquired from the environment of the CF lung, changing the expression of phenotypes over the course of the infection. As P. aeruginosa infections become chronic, some phenotype changes are known to be linked with negative patient outcomes. An important exoproduct phenotype is rhamnolipid production, which is a glycolipid that P. aeruginosa produces as a surfactant for surface-mediated travel. Over time, the expression of this phenotype decreases in expression in the CF lung.
The objective of this investigation is to evaluate how environmental changes that are related to the growth environment in the CF lung alters rhamnolipid production. Thirty-five P. aeruginosa isolates from Dartmouth College and Seattle Children’s Hospital were selected to observe the impact of temperature, presence of Staphylococcus aureus metabolites, and oxygen availability on rhamnolipid production. It was found that the rhamnolipid production significantly decreased for 30C versus 37C, but not at 40C. The addition of S. aureus spent media, in any of the tested conditions, did not influence rhamnolipid production. Finally, the change in oxygen concentration from normoxia to hypoxia significantly reduced rhamnolipid production. These results were compared to swarming assay data to understand how changes in rhamnolipid production impact surface-mediated motility.
The objective of this investigation is to evaluate how environmental changes that are related to the growth environment in the CF lung alters rhamnolipid production. Thirty-five P. aeruginosa isolates from Dartmouth College and Seattle Children’s Hospital were selected to observe the impact of temperature, presence of Staphylococcus aureus metabolites, and oxygen availability on rhamnolipid production. It was found that the rhamnolipid production significantly decreased for 30C versus 37C, but not at 40C. The addition of S. aureus spent media, in any of the tested conditions, did not influence rhamnolipid production. Finally, the change in oxygen concentration from normoxia to hypoxia significantly reduced rhamnolipid production. These results were compared to swarming assay data to understand how changes in rhamnolipid production impact surface-mediated motility.
ContributorsKiermayr, Jonathan Patrick (Author) / Bean, Heather (Thesis director) / Misra, Rajeev (Committee member) / Haydel, Shelley (Committee member) / School of International Letters and Cultures (Contributor) / School of Molecular Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
The ability to draft and develop productive Major League players is vital to the success of any MLB organization. A core of cost-controlled, productive players is as important as ever with free agent salaries continuing to rise dramatically. In a sport where mere percentage points separate winners from losers at the end of a long season, any slight advantage in identifying talent is valuable. This study examines the 2004-2008 MLB Amateur Drafts in order to analyze whether certain types of prospects are more valuable selections than others. If organizations can better identify which draft prospects will more likely contribute at the Major League level in the future, they can more optimally spend their allotted signing bonus pool in order to acquire as much potential production as possible through the draft. Based on the data examined, during these five drafts high school prospects provided higher value than college prospects. While college players reached the Majors at a higher rate, high school players produced greater value in their first six seasons of service time. In the all-important first round of the draft, where signing bonuses are at their largest, college players proved the more valuable selection. When players were separated by position, position players held greater expected value than pitchers, with corner infielders leading the way as the position group with the highest expected value. College players were found to provide better value than high school players at defensively demanding positions such as catcher and middle infield, while high school players were more valuable among outfielders and pitchers.
ContributorsGildea, Adam Joseph (Author) / Eaton, John (Thesis director) / McIntosh, Daniel (Committee member) / Department of Economics (Contributor) / W. P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Abstract My documentary is about the concussion detection study with Arizona State Football, Translational Genomics Research Institute (TGen), Riddell and the Barrow Neurological Institute. Football players voluntarily participate in the study that aims to identify a biomarker released from the brain to identify if a player has suffered from a concussion. The study uses blood, urine and saliva samples, along with head impact data from Riddell's Sideline Response System. The study is also focusing on the impact of sub-concussive hits and the effects. According to the Barrow Neurological Institute, 84% of respondents believe concussions are "a serious medical condition," and a third of Valley parents will not let their children play football. I interviewed an ASU football player who participated in the study and found out about his experiences with concussions. The severity of concussions has received a lot of attention in recent years, and this study hopes to mitigate concussions symptoms and the fear of concussions. According to the 2015 NFL Health and Safety Report, since 2012 the NFL reported concussions were down by 35%. I interviewed the TGen leaders of the study and the neurologist at the Barrow Concussion and Brain Injury center involved in the study to find out how they plan to find a biomarker and use it to develop an objective way to diagnose concussions. An example of a possible objective test is a mouthguard that changes from clear to blue after a player sustained a hit that resulted in a concussion. The 2015-2016 ASU football season marked the study's third year of research. At the time of my documentary, the study had no timeline to release data.
ContributorsSeki, Katryna Marie (Author) / Lodato, Mark (Thesis director) / Kurland, Brett (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / School of Politics and Global Studies (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Each year, a select few minor league baseball players are chosen to attend the Arizona Fall League, a development league within Major League Baseball that hones the next generation of players, coaches, managers, and even umpires. These players make up the top talent currently in the minor leagues from each of Major League Baseball's 30 organizations. Of the thousands in the minors, just seven players from each organization can go to this extra six-week season, and learn to play alongside the best future talent the sport has to offer. On Deck: Inside the Arizona Fall League is a short documentary that looks at some of these players, as they continue their baseball journey that they hope leads them one day to the Majors. The documentary can be viewed online at https://youtu.be/jkggYiDtn14 or nicolesheraefox.com
ContributorsFox, Nicole Sherae (Author) / Lodato, Mark (Thesis director) / Kurland, Brett (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05