Matching Items (555)
Filtering by
- Creators: Dean, W.P. Carey School of Business
- Resource Type: Text
Description
Brain Computer Interfaces are becoming the next generation controllers not only in the medical devices for disabled individuals but also in the gaming and entertainment industries. In order to build an effective Brain Computer Interface, which accurately translates the user thoughts into machine commands, it is important to have robust and fail proof signal processing and machine learning modules which operate on the raw EEG signals and estimate the current thought of the user.
In this thesis, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised machine learning models, for the EEG motor imagery signal classification are identified. To further improve the performance of system unsupervised feature learning techniques have been investigated by pre-training the Deep Learning models. Use of pre-training stacked autoencoders have been proposed to solve the problems caused by random initialization of weights in neural networks.
Motor Imagery (imaginary hand and leg movements) signals are acquire using the Emotiv EEG headset. Different kinds of features like mean signal, band powers, RMS of the signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques like LDA, KNN, SVM, Logistic regression and Neural Networks are applied and validated. During the validation phase the performances of various techniques are compared and some important observations are reported. Further, deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is analyzed by performing classification by using the ML techniques mentioned earlier. The performance of the neural networks has been further improved by pre-training the network in an unsupervised fashion using stacked autoencoders and supplying the stacked autoencoders’ network parameters as initial parameters to the neural network. All the findings in this research, during each phase (pre-processing, feature extraction, classification) are directly relevant and can be used by the BCI research community for building motor imagery based BCI applications.
Additionally, this thesis attempts to develop, test, and compare the performance of an alternative method for classifying human driving behavior. This thesis proposes the use of driver affective states to know the driving behavior. The purpose of this part of the thesis was to classify the EEG data collected from several subjects while driving simulated vehicle and compare the classification results with those obtained by classifying the driving behavior using vehicle parameters collected simultaneously from all the subjects. The objective here is to see if the drivers’ mental state is reflected in his driving behavior.
In this thesis, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised machine learning models, for the EEG motor imagery signal classification are identified. To further improve the performance of system unsupervised feature learning techniques have been investigated by pre-training the Deep Learning models. Use of pre-training stacked autoencoders have been proposed to solve the problems caused by random initialization of weights in neural networks.
Motor Imagery (imaginary hand and leg movements) signals are acquire using the Emotiv EEG headset. Different kinds of features like mean signal, band powers, RMS of the signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques like LDA, KNN, SVM, Logistic regression and Neural Networks are applied and validated. During the validation phase the performances of various techniques are compared and some important observations are reported. Further, deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is analyzed by performing classification by using the ML techniques mentioned earlier. The performance of the neural networks has been further improved by pre-training the network in an unsupervised fashion using stacked autoencoders and supplying the stacked autoencoders’ network parameters as initial parameters to the neural network. All the findings in this research, during each phase (pre-processing, feature extraction, classification) are directly relevant and can be used by the BCI research community for building motor imagery based BCI applications.
Additionally, this thesis attempts to develop, test, and compare the performance of an alternative method for classifying human driving behavior. This thesis proposes the use of driver affective states to know the driving behavior. The purpose of this part of the thesis was to classify the EEG data collected from several subjects while driving simulated vehicle and compare the classification results with those obtained by classifying the driving behavior using vehicle parameters collected simultaneously from all the subjects. The objective here is to see if the drivers’ mental state is reflected in his driving behavior.
ContributorsManchala, Vamsi Krishna (Author) / Redkar, Sangram (Thesis advisor) / Rogers, Bradley (Committee member) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2015
Description
This project uses Kenneth Burke’s theory of dramatism and the pentad to analyze popular narrative films about human sex trafficking. It seeks to understand the relationship between a film’s dominant philosophy (as highlighted by utilizing Burke’s pentad), its inherently suggested solutions to trafficking, and the effect that the film has on viewers’ perception of trafficking. 20 narrative feature films about sex trafficking such as the 2008 film Taken were analyzed for this study. Three out of five of Burke’s philosophies were uncovered after analysis: idealism, mysticism, and materialism. Films that aligned with idealism were found to implicitly blame women for their own trafficking. Films that aligned with mysticism were found to rally audiences around violence and racism as opposed to women’s freedom. Films that aligned with materialism were found to be the most empathetic towards trafficked women. The conclusion of this paper is that films about sex trafficking have a high potential to be harmful to women who have exited trafficking. This paper asserts that the most valuable films about trafficking are those that are not simply based on a true story but are created by trafficking survivors themselves, such as the 2016 film Apartment 407.
ContributorsHamby, Hannah Mary (Co-author) / Raum, Brionna (Co-author) / Edson, Belle (Thesis director) / Zanin, Alaina (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Hugh Downs School of Human Communication (Contributor) / School of Film, Dance and Theatre (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
This document is a proposal for a research project, submitted as an Honors Thesis to Barrett, The Honors College at Arizona State University. The proposal summarizes previous findings and literature about women survivors of domestic violence who are suffering from post-traumatic stress disorder as well as outlining the design and measures of the study. At this time, the study has not been completed. However, it may be completed at a future time.
ContributorsKunst, Jessica (Author) / Hernandez Ruiz, Eugenia (Thesis director) / Belgrave, Melita (Committee member) / School of Music (Contributor) / Dean, W.P. Carey School of Business (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05
Description
While there are many characteristics that make up a woman, femininity is one that is difficult to define because it is a communication and expression practice defined by culture. This research explores historical accounts of femininity in the 1950s as seen through the exemplar of the white, middle-class "happy homemaker" or "happy housewife." The 1950s is important to study in light of changing gender and social dynamics due to the transition from World War II to a period of prosperity. By using primary sources from the 1950s and secondary historical analyses, this research takes the form of a sociological accounting of 1950s' femininity and the lessons that can be applied today. Four cultural forces led to homemakers having an unspoken identity crisis because they defined themselves in terms of relationship with others and struggled to uphold a certain level of femininity. The forces are: the feminine mystique, patriotism, cultural normalcy, and unnecessary choices. These forces caused women to have unhealthy home relationships in their marriages and motherhood while persistently doing acts to prove their self-worth, such as housework and consuming. It is important to not look back at the 1950s as an idyllic time without also considering the social and cultural practices that fostered a feminine conformity in women. Today, changes can be made to allow women to express femininity in modern ways by adapting to reality instead of to outdated values. For example, changes in maternity leave policies allow women to be mothers and still be in the workforce. Additionally, women should find fulfillment in themselves by establishing a strong personal identity and confidence in their womanhood before identifying through other people or through society.
ContributorsHeinauer, Richelle Diane (Author) / Brouwer, Daniel (Thesis director) / Haskin, Jennifer (Committee member) / Hugh Downs School of Human Communication (Contributor) / Sanford School of Social and Family Dynamics (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
The Centers for Disease Control and Prevention in the United States announced that there has been roughly a 50% increase in the prevalence of food allergies among people between the years of 1997 - 2011. A food allergy can be described as a medical condition where being exposed to a certain food triggers a harmful immune response in the body, known as an allergic reaction. These reactions can range from mild to fatal, and they are caused mainly by the top 8 major food allergens: dairy, eggs, peanuts, tree nuts, wheat, soy, fish, and shellfish. Food allergies mainly plague children under the age of 3, as some of them will grow out of their allergy sensitivity over time, and most people develop their allergies at a young age, and not when they are older. The rise in prevalence is becoming a frightening problem around the world, and there are emerging theories that are attempting to ascribe a cause. There are three well-known hypotheses that will be discussed: the Hygiene Hypothesis, the Dual-Allergen Exposure Hypothesis, and the Vitamin-D Deficiency Hypothesis. Beyond that, this report proposes that a new hypothesis be studied, the Food Systems Hypothesis. This hypothesis theorizes that the cause of the rise of food allergies is actually caused by changes in the food itself and particularly the pesticides that are used to cultivate it.
ContributorsCromer, Kelly (Author) / Lee, Rebecca (Thesis director) / MacFadyen, Joshua (Committee member) / Sanford School of Social and Family Dynamics (Contributor) / Dean, W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2018-12
Description
Fashion is individual in its expression. It is also universal. Fashion is a cumulation of different influences and different interpretations. We currently live in a climate divided by race, culture, gender, and so much more. It is so difficult to find common ground on a global platform. Something that stands alone is fashion. Fashion is influenced by so many aspects. Of these, aspects that I am interested in are culture and sustainability. When combined with culture, fashion can anchor and have a root to the generations that came before us. When combined with sustainability, we have an anchor to the planet that we share with everyone. The result of fashion is always the same, beautiful art. I want people to see the beauty not only in the art itself, but the differences and similarities that such art provides. We all come from the same world but have different ways of expressing that world. My goal is to show people that they need to acknowledge the differences but can choose to see the similarities of each culture. Additionally, I redesign garments that capture an emotion and a story. Making each piece individual yet serving a greater purpose sustainability wise. I envision the principle of sustainable fashion to be the basis of each piece of clothing. Therefore, for my creative project I am constructing five art pieces representing five cultures that has had a significant influence on my life and personal style. These cultures are those of UAE, Germany, Nepal, Mexico, and Spain. Each of these garments are made from recycled fabric and clothing donated by family and friends. My objective is to display sustainable fashion that has deep cultural influence. Every piece has a story and an emotion attached as well to create a connection with the clothing itself.
ContributorsKreiser, Samantha Miren (Author) / Chhetri, Nalini (Thesis director) / Ellis, Naomi (Committee member) / Dean, W.P. Carey School of Business (Contributor, Contributor) / Department of Economics (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Everyone has a story to tell. Marketing nowadays is less about what is being made and more about how it is being told. Integrate an exciting or interesting story with sports and that is the ultimate storytelling experience. Social media has completely changed the game for professional teams when it comes to how teams are telling their digital stories and engaging with fans. Entire social media teams exist in these organizations, which is something that did not exist not too long ago. The rise in fans experiencing and viewing social media platforms is altering how teams engage, connect, and communicate with fans.
When it comes to my story, I wanted to make sure I told one that was interesting, relevant and worthwhile. I felt lost for quite some time in regards to what direction I wanted to take with my thesis. After meeting with Dan Moriarty and Kevin Brilliant of the Chicago Bulls during an outreach trip with the Sports Business Association, I knew I wanted to gain more insight into how teams are telling their digital stories and connecting with their fans. I wanted to learn more about how teams across the country are playing the game of social media and what strategies they put into place to be impactful and successful. I wanted to learn the value teams found in social media and how social media impacts the organizations as a whole, specifically in revenue generation. Most importantly, I wanted to learn how teams are engaging with fans and how social media has changed the world of sports. This research includes insights from various individuals in the industry as well as survey data from W. P. Carey students. The accumulation of this thesis has resulted in a closer look into social media in the sports industry and how teams are measuring success in the digital space.
When it comes to my story, I wanted to make sure I told one that was interesting, relevant and worthwhile. I felt lost for quite some time in regards to what direction I wanted to take with my thesis. After meeting with Dan Moriarty and Kevin Brilliant of the Chicago Bulls during an outreach trip with the Sports Business Association, I knew I wanted to gain more insight into how teams are telling their digital stories and connecting with their fans. I wanted to learn more about how teams across the country are playing the game of social media and what strategies they put into place to be impactful and successful. I wanted to learn the value teams found in social media and how social media impacts the organizations as a whole, specifically in revenue generation. Most importantly, I wanted to learn how teams are engaging with fans and how social media has changed the world of sports. This research includes insights from various individuals in the industry as well as survey data from W. P. Carey students. The accumulation of this thesis has resulted in a closer look into social media in the sports industry and how teams are measuring success in the digital space.
ContributorsMaguire, Allison Marie (Author) / Eaton, John (Thesis director) / Mokwa, Michael (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Department of Marketing (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
This paper seeks to emphasize how the presence of uncertainty, speculation and leverage work in concert within the stock market to exacerbate crashes in a cyclical market. It analyzes three major stock market events: the crash of Oct. 19, 1987, “Black Monday;” the dotcom bust, from 1999 to 2002; and the subprime mortgage crisis, from 2007 to 2010. Within each event period I define determinants or measurements of uncertainty, speculation. Analysis of how these three concepts functioned during boom and bust will highlight how their presence can amplify the magnitude of a crash. This paper postulates that the amount of leverage during a crash determines how long-term its effects will be. This theory is fortified by extensive research and interviews with experts in the stock market who had a front row view of the discussed crises.
ContributorsGraff, Veronica Camille (Author) / Leckey, Andrew (Thesis director) / Cohen, Sarah (Committee member) / Historical, Philosophical & Religious Studies (Contributor) / Walter Cronkite School of Journalism & Mass Comm (Contributor, Contributor) / Dean, W.P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
The purpose of this thesis project was to examine the trajectories of physical activity among newly-diagnosed Obstructive Sleep Apnea (OSA) patients within the UC+WS group of the SleepWell24 study across the first 60 days of CPAP use, alone and based on Apnea-Hypopnea Index (AHI), Body Mass Index (BMI), sex, and age. The study utilizes objective data from the SleepWell24 randomized controlled trial conducted by a collaborative research team at Arizona State University and Mayo Clinic Arizona and Rochester. Participants use wearable sensors to track activity behaviors, such as sleep, sedentary behavior, light-intensity physical activity (LPA), and moderate-vigorous physical activity (MVPA). The primary aim of the study was to examine the physical activity trajectories among newly-diagnosed OSA patients over the first 8 weeks of CPAP use, utilizing the physical activity data from wearable sensors. The secondary aim was to assess the trajectories of physical activity between categories of AHI, BMI, sex, and age. Multilevel modeling was used to account for clustering within participants considering between and within subject variations, and week was used as a level 1 predictor in the model for LPA, and MVPA, and total activity (sum of LPA and MVPA), while between subject factors of BMI, sex, age, and AHI were also included in the model. It was found that there were no statistically significant trajectories of LPA, MVPA or total activity over the first 8 weeks of CPAP use within the sample of 30 participants. However, a few notable differences in physical activity were seen between categories of age, sex, and BMI. Also, there was a significant interaction found between BMI and each week that influenced the trajectory of physical activity within obese patients, as compared to participants considered overweight or with a lower BMI. Ultimately, this study provides insight into patterns of physical activity seen in a clinical population of OSA patients over the initial period of CPAP use.
ContributorsDavis, Kiley Lynn (Author) / Buman, Matthew P. (Thesis director) / Petrov, Megan (Committee member) / Dean, W.P. Carey School of Business (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
The coronavirus envelope (E) protein is a structural component of all coronavirus. Obtaining purified E protein in an efficient, clean, and reliable manner is needed for ongoing studies. Toward this goal the E protein of Mouse Hepatitis Virus (MHV) coronavirus was tagged with with either 6 or 10 histidine (his) residues which can be used for affinity chromatography purification. The his-tags were introduced by PCR into a cDNA of the MHV A59 virus strain at the carboxy end of the E gene. A reverse genetics approach was then used to assemble three full-length cDNAs of the viral genome, two modified with the hig-tags and a control wild-type (WT) without a tag . Full-length genomic RNAs were transcribed and electroporated into baby hamster kidney cells that express the MHV receptor (BHKR) and L2 rat lung cells. Virus was recovered after 72 h only from the 6X his-tagged genome and the WT control. Western blotting using antibodies against the E protein or the nucleocapsid (N) protein was performed after cells were infected with the recovered WT and 6X-tagged recombinant viruses. The E protein was not detected with the E antibody, but was detected with a histidine probe was used to detect the histidine residues. This indicates that the tagged protein is expressed and that the tag is present.
ContributorsHesser, Kathryn Sarah (Author) / Hogue, Brenda G. (Thesis director) / Hogue, Ian B. (Committee member) / Lim, Efram (Committee member) / Dean, W.P. Carey School of Business (Contributor) / School of Life Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05