Matching Items (240)
Filtering by
- All Subjects: Machine Learning
- All Subjects: healthcare
- Creators: Barrett, The Honors College
- Member of: Theses and Dissertations
- Resource Type: Text
Description
The built environment is responsible for a significant portion of global waste generation.
Construction and demolition (C&D) waste requires significant landfill areas and costs
billions of dollars. New business models that reduce this waste may prove to be financially
beneficial and generally more sustainable. One such model is referred to as the “Circular
Economy” (CE), which promotes the efficient use of materials to minimize waste
generation and raw material consumption. CE is achieved by maximizing the life of
materials and components and by reclaiming the typically wasted value at the end of their
life. This thesis identifies the potential opportunities for using CE in the built environment.
It first calculates the magnitude of C&D waste and its main streams, highlights the top
C&D materials based on weight and value using data from various regions, identifies the
top C&D materials’ current recycling and reuse rates, and finally estimates a potential
financial benefit of $3.7 billion from redirecting C&D waste using the CE concept in the
United States.
ContributorsAldaaja, Mohammad (Author) / El Asmar, Mounir (Thesis advisor) / Buch, Rajesh (Committee member) / Kaloush, Kamil (Committee member) / Arizona State University (Publisher)
Created2019
Description
The purpose of this study was to create a screening tool specifically for the identification of sex trafficking victims in the medical setting through the analysis of existing human trafficking screening tool studies geared towards use in the medical setting. Screening questions from these studies were compiled and modified into a survey that was distributed to healthcare professionals through the nationwide HEAL (Health Professional Education, Advocacy, Linkage) Trafficking listserv. Each screening tool study demonstrated benefits and disadvantages that were helpful in the sampling and selection of screening tool questions. The small sample size and a lack of data on the attitudes of medical professionals on sex trafficked victims were noted as limitations to this study. Further implications for this study would include validating the screening tool questions in a medical setting to determine the sensitivity of the survey in identifying patients as possible sex trafficking victims.
ContributorsCatano, Karen Samantha (Co-author) / Byun, Jiwon (Co-author) / Roe-Sepowitz, Dominique (Thesis director) / Lee, Maurice (Committee member) / School for the Science of Health Care Delivery (Contributor) / College of Integrative Sciences and Arts (Contributor) / W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Many developing countries do not have health care systems that can afford technological biomedical devices or supplies to make such devices operational. To fill this void, nonprofit organizations, like Project C.U.R.E., recondition retired biomedical instrumentation so they can send medical supplies to help these developing countries. One of the issues with this is that sometimes the devices are unusable because components or expendable supplies are not available (Bhadelia). This issue has also been shown in the Impact Evaluations that Project C.U.R.E. receives from the clinics that explain the reasons why certain devices are no longer in use. That need underlies the idea on which this honors thesis has come into being. The purpose of this honors project was to create packing lists for biomedical instruments that Project C.U.R.E. recycles. This packing list would decrease the likelihood of important items being forgotten when sending devices. If an extra fuse, battery, light bulb, cuff or transducer is the difference between a functional or a nonfunctional medical device, such a list would be of benefit to Project C.U.R.E and these developing countries. In order to make this packing list, manuals for each device were used to determine what supplies were required, what was necessary for cleaning, and what supplies were desirable but functionally optional. This list was then added into a database that could be easily navigated and could help when packing up boxes for a shipment. The database also makes adding and editing the packing list simple and easy so that as Project C.U.R.E. gets more donated devices the packing list can grow.
ContributorsGraft, Kelsey Anne (Author) / Coursen, Jerry (Thesis director) / Walters, Danielle (Committee member) / Harrington Bioengineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
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
Sustainable Materials Management and Circular Economy are both frameworks for considering the way we interact with the world's resources. Different organizations and institutions across the world have adopted one philosophy or the other. To some, there seems to be little overlap of the two, and to others, they are perceived as being interchangeable. This paper evaluates Sustainable Materials Management (SMM) and Circular Economy (CE) individually and in comparison to see how truly different these frameworks are from one another. This comparison is then extended into a theoretical walk-through of an SMM treatment of concrete pavement in contrast with a CE treatment. With concrete being a ubiquitous in the world's buildings and roads, as well as being a major constituent of Construction & Demolition waste generated, its analysis is applicable to a significant portion of the world's material flow. The ultimate test of differentiation between SMM and CE would ask: 1) If SMM principles guided action, would the outcomes be aligned with or at odds with CE principles? and conversely 2) If CE principles guided action, would the outcomes be aligned with or at odds with SMM principles? Using concrete pavement as an example, this paper seeks to determine whether or not Sustainable Materials Management and Circular Economy are simply different roads leading to the same destination.
ContributorsAbdul-Quadir, Anisa (Author) / Kelman, Candice (Thesis director) / Buch, Rajesh (Committee member) / Barrett, The Honors College (Contributor)
Created2017-05
Description
Physician-assisted suicide occurs when a physician facilitates a patient's death by prescribing a lethal medication that they understand will be used for the purpose of ending the patient's life. It is a highly contentious subject and, with the recent addition of California to the list of states that allow physician-assisted suicide, is an increasingly relevant subject. Physician-assisted suicide is rarely framed as a healthcare experience, despite being a choice in the process of end-of-life care. The research seeks to bring together the debates about physician-assisted suicide with conversations about health care experiences. The experiences and perspectives of young people are particularly valuable to evaluate now, as their voices will soon be the leaders in the debate over physician-assisted suicide. Within this research, there is an underlying theme of independence of individuals that is present through both the literature review and the body of data collected and analyzed. The study found that there was no significant relationship between the quality of a person's healthcare and their perspectives about physician-assisted suicide.
ContributorsMoeur, Katherine Elizabeth (Author) / Brian, Jennifer (Thesis director) / Graff, Sarah (Committee member) / Stevenson, Christine (Committee member) / School of Life Sciences (Contributor) / School of Human Evolution and Social Change (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
This study investigates how the patient-provider relationship between lesbian, gay, and bisexual women and their healthcare providers influences their access to, utilization of, and experiences within healthcare environments. Nineteen participants, ages 18 to 34, were recruited using convenience and snowball sampling. Interviews were conducted inquiring about their health history and their experiences within the healthcare system in the context of their sexual orientation. The data collected from these interviews was used to create an analysis of the healthcare experiences of those who identify as queer. Although the original intention of the project was to chronicle the experiences of LGB women specifically, there were four non-binary gender respondents who contributed interviews. In an effort to not privilege any orientation over another, the respondents were collectively referred to as queer, given the inclusive and an encompassing nature of the term. The general conclusion of this study is that respondents most often experienced heterosexism rather than outright homophobia when accessing healthcare. If heterosexism was present within the healthcare setting, it made respondents feel uncomfortable with their providers and less likely to inform them of their sexuality even if it was medically relevant to their health outcomes. Gender, race, and,socioeconomic differences also had an effect on the patient-provider relationship. Non-binary respondents acknowledged the need for inclusion of more gender options outside of male or female on the reporting forms often seen in medical offices. By doing so, medical professionals are acknowledging their awareness and knowledge of people outside of the binary gender system, thus improving the experience of these patients. While race and socioeconomic status were less relevant to the context of this study, it was found that these factors have an affect on the patient-provider relationship. There are many suggestions for providers to improve the experiences of queer patients within the healthcare setting. This includes nonverbal indications of acknowledgement and acceptance, such as signs in the office that indicate it to be a queer friendly space. This will help in eliminating the fear and miscommunication that can often happen when a queer patient sees a practitioner for the first time. In addition, better education on medically relevant topics to queer patients, is necessary in order to eliminate disparities in health outcomes. This is particularly evident in trans health, where specialized education is necessary in order to decrease poor health outcomes in trans patients. Future directions of this study necessitate a closer look on how race and socioeconomic status have an effect on a queer patient's relationship with their provider.
ContributorsRajan, Sindhu (Co-author) / Bradley, Arianna (Co-author) / Larson, Michelle (Co-author) / Alvarado, Aimee (Co-author) / Ingram-Waters, Mary (Thesis director) / Arnold, Michelle (Committee member) / School of Molecular Sciences (Contributor) / School of Social Transformation (Contributor) / T. Denny Sanford School of Social and Family Dynamics (Contributor) / College of Public Service and Community Solutions (Contributor) / School of Human Evolution and Social Change (Contributor) / School of Historical, Philosophical and Religious Studies (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05