View All Items
(81 - 100 of 281)
Pages
- Title
- DEEP LEARNING REGRESSION MODELS FOR LIMITED BIOMEDICAL TIME-SERIES DATA.
- Creator
- Hssayeni, Murtadha D., Behnaz Ghoraani, Behnaz, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Time-series data in biomedical applications are gaining an increased interest to detect and predict underlying diseases and estimate their severity, such as Parkinson’s disease (PD) and cardiovascular diseases. This interest is driven by advances in wearable sensors and deep learning models to a large extent. In the literature, less attention has been paid to regression models for continuous outcomes in these applications, especially when dealing with limited data. Training deep learning...
Show moreTime-series data in biomedical applications are gaining an increased interest to detect and predict underlying diseases and estimate their severity, such as Parkinson’s disease (PD) and cardiovascular diseases. This interest is driven by advances in wearable sensors and deep learning models to a large extent. In the literature, less attention has been paid to regression models for continuous outcomes in these applications, especially when dealing with limited data. Training deep learning models on raw limited data results in overfitted models, which is the main technical challenge we address in this dissertation. An example of limited and\or imbalanced time-series data is PD’s motion signals that are needed for the continuous severity estimation of Parkinson’s disease (PD). The significance of this continuous estimation is providing a tool for longitudinal monitoring of daily motor and non-motor fluctuations and managing PD medications. The dissertation objective is to train generalizable deep learning models for biomedical regression problems when dealing with limited training time-series data. The goal is designing, developing, and validating an automatic assessment system based on wearable sensors that can measure the severity of PD complications in the home-living environment while patients with PD perform their activities of daily living (ADL). We first propose using a combination of domain-specific feature engineering, transfer learning, and an ensemble of multiple modalities. Second, we utilize generative adversarial networks (GAN) and propose a new formulation of conditional GAN (cGAN) as a generative model for regression to handle an imbalanced training dataset. Next, we propose a dual-channel auxiliary regressor GAN (AR-GAN) trained using Wasserstein-MSE-correlation loss. The proposed AR-GAN is used as a data augmentation method in regression problems.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013992
- Subject Headings
- Deep learning (Machine learning), Regression analysis--Mathematical models, Biomedical engineering
- Format
- Document (PDF)
- Title
- DATA-DRIVEN IDENTIFICATION AND CONTROL OF TURBULENT STRUCTURES USING DEEP NEURAL NETWORKS.
- Creator
- Jagodinski, Eric, Verma, Siddhartha, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
- Abstract/Description
-
Wall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a...
Show moreWall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a fundamental viewpoint. One unexplained phenomenon is the formation and impact of coherent structures like the ejections of slow near-wall fluid into faster moving ow which have been shown to correlate with increases in friction drag. This thesis focuses on recognizing and regulating organized structures within wall-bounded turbulent flows using a variety of machine learning techniques to overcome the nonlinear nature of this phenomenon. Deep Learning has provided new avenues of analyzing large amounts of data by applying techniques modeled after biological neurons. These techniques allow for the discovery of nonlinear relationships in massive, complex systems like the data found frequently in fluid dynamics simulation. Using a neural network architecture called Convolutional Neural Networks that specializes in uncovering spatial relationships, a network was trained to estimate the relative intensity of ejection structures within turbulent flow simulation without any a priori knowledge of the underlying flow dynamics. To explore the underlying physics that the trained network might reveal, an interpretation technique called Gradient-based Class Activation Mapping was modified to identify salient regions in the flow field which most influenced the trained network to make an accurate estimation of these organized structures. Using various statistical techniques, these salient regions were found to have a high correlation to ejection structures, and to high positive kinetic energy production, low negative production, and low energy dissipation regions within the flow. Additionally, these techniques present a general framework for identifying nonlinear causal structures in general three-dimensional data in any scientific domain where the underlying physics may be unknown.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014119
- Subject Headings
- Turbulent flow, Turbulence, Neural networks (Computer science), Deep learning (Machine learning)
- Format
- Document (PDF)
- Title
- SELF-DIRECTED LEARNING READINESS AMONG PREDENTAL STUDENTS AT FLORIDA ATLANTIC UNIVERSITY.
- Creator
- Algahtani, Fahad, Bryan, Valerie, Florida Atlantic University, Department of Educational Leadership and Research Methodology, College of Education
- Abstract/Description
-
Dental school is a four-year, rigorous educational endeavor packed with difficulties and challenges predental students have not experienced during their undergraduate studies. In addition, dental schools demand developing new coping and learning skills to meet the requirements of a student-centered, fast-paced curriculum. In response to these challenges, it is essential to understand and embrace self-directed learning (SDL) skills and attitudes required for predental students to thrive and...
Show moreDental school is a four-year, rigorous educational endeavor packed with difficulties and challenges predental students have not experienced during their undergraduate studies. In addition, dental schools demand developing new coping and learning skills to meet the requirements of a student-centered, fast-paced curriculum. In response to these challenges, it is essential to understand and embrace self-directed learning (SDL) skills and attitudes required for predental students to thrive and succeed during their dental journey (Premkumar et al., 2014). Furthermore, SDL is essential in assisting dental students in filtering the information they need to fulfill their learning needs (Siddiqui et al., 2021). This quantitative cross-sectional descriptive study used an online survey designed by QualtricsXM to evaluate self-directed learning readiness (SDLR) level among predental students at Florida Atlantic University (FAU) and whether their SDLR level would differ based on age, sex, race/ethnicity, college/major, and year of study. A convenience sample of 155 FAU predental students completed Fisher et al.’s (2001) 40-item Self-Directed Learning Readiness Scale for Nursing Education (SDLRSNE) and seven demographic questions. Descriptive and inferential statistics were conducted to analyze and answer the six research questions and corresponding hypotheses. The results showed a positive attitude of FAU predental students toward SDL as total SDLR scores ranged from 119 to 179, with a mean of 151.33. Moreover, there was a statistically significant difference in SDLR level among participants based on age, race, and year of study. Contrastingly, there was no statistically significant difference in SDLR level among participants based on sex, ethnicity, and academic major. The college variable was not investigated as all participants were enrolled in the Charles E. Schmidt College of Science.
Show less - Date Issued
- 2023
- PURL
- http://purl.flvc.org/fau/fd/FA00014122
- Subject Headings
- Self-directed learning, Self-managed learning, College students, Florida Atlantic University
- Format
- Document (PDF)
- Title
- STUDY AND ANALYSIS OF MACHINE LEARNING TECHNIQUES FOR DETECTION OF DISTRACTED DRIVERS.
- Creator
- Qu, Fangming, Nojoumian, Mehrdad, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
The rise of Advanced Driver-Assistance Systems (ADAS) and Autonomous Vehicles (AVs) emphasizes the urgent need to combat distracted driving. This study introduces a fresh approach for improved detection of distracted drivers, combining a pre-trained Convolutional Neural Network (CNN) with a Bidirectional Long Short- Term Memory (BiLSTM) network. Our analysis utilizes both spatial and temporal features to examine a broad array of driver distractions. We demonstrate the advantage of this CNN...
Show moreThe rise of Advanced Driver-Assistance Systems (ADAS) and Autonomous Vehicles (AVs) emphasizes the urgent need to combat distracted driving. This study introduces a fresh approach for improved detection of distracted drivers, combining a pre-trained Convolutional Neural Network (CNN) with a Bidirectional Long Short- Term Memory (BiLSTM) network. Our analysis utilizes both spatial and temporal features to examine a broad array of driver distractions. We demonstrate the advantage of this CNN-BiLSTM framework over conventional methods, achieving significant precision (up to 98.97%) on the combined ’Union Dataset,’ merging the Kaggle State Farm Dataset and AUC Distracted Driver Dataset (AUC-DDD). This research enhances safety in autonomous vehicles by providing a solid and flexible solution for everyday use. Our results mark considerable progress in accurately identifying driver distractions, pushing the boundaries of safety technology in AVs.
Show less - Date Issued
- 2024
- PURL
- http://purl.flvc.org/fau/fd/FA00014418
- Subject Headings
- Deep learning (Machine learning), Distracted driving, Transportation--Safety measures, Automated vehicles--Safety measures
- Format
- Document (PDF)
- Title
- FROM DNA TO GRAVITATIONAL WAVES: APPLICATIONS OF STATISTICS AND MACHINE LEARNING.
- Creator
- Alemrajabi, Mahsa Firouzabad, Tichy, Wolfgang, Assis, Raquel, Florida Atlantic University, Department of Physics, Charles E. Schmidt College of Science
- Abstract/Description
-
In the current world of fast-paced data production, statistics and machine learning tools are essential for interpreting and utilizing the full potential of this data. This dissertation comprises three studies employing statistical analysis and Convolutional Neural Network models. First, the research investigates the genetic evolution of the SARS-CoV-2 RNA molecule, emphasizing the role of epistasis in the RNA virus’s ability to adapt and survive. Through statistical tests, this study...
Show moreIn the current world of fast-paced data production, statistics and machine learning tools are essential for interpreting and utilizing the full potential of this data. This dissertation comprises three studies employing statistical analysis and Convolutional Neural Network models. First, the research investigates the genetic evolution of the SARS-CoV-2 RNA molecule, emphasizing the role of epistasis in the RNA virus’s ability to adapt and survive. Through statistical tests, this study validates the significant impacts of genetic interactions and mutations on the virus’s structural changes over time, offering insights into its evolutionary dynamics. Secondly, the dissertation explores medical diagnosis by implementing Convolutional Neural Networks to differentiate between lung CT-scans of COVID-19 and non-COVID patients. This portion of the research demonstrates the capability of deep learning to enhance diagnostic processes, thereby reducing time and increasing accuracy in clinical settings. Lastly, we delve into gravitational wave detection, an area of astrophysics requiring precise data analysis to identify signals from cosmic events such as black hole mergers. Our goal is to utilize Convolutional Neural Network models in hopes of improving the sensitivity and accuracy of detecting these difficult to catch signals, pushing the boundaries of what we can observe in the universe. The findings of this dissertation underscore the utility of combining statistical methods and machine learning models to solve problems that are not only varied but also highly impactful in their respective fields.
Show less - Date Issued
- 2024
- PURL
- http://purl.flvc.org/fau/fd/FA00014454
- Subject Headings
- Neural networks (Computer science), Gravitational waves, Deep learning (Machine learning), Diagnosis, Epistasis, Genetic
- Format
- Document (PDF)
- Title
- Transformational experiences of African American women: their critical reflections as former migrants who evolved from harvest of shame to seeds of hope.
- Creator
- McLaughlin-Jones, Idell, Bryan, Valerie, Florida Atlantic University, College of Education, Department of Educational Leadership and Research Methodology
- Abstract/Description
-
Narrative inquiry was the qualitative method utilized to collect stories related to former migrant African American females who transformed their lives from migrant workers and found alternative career paths. Sustained poverty among migratory workers created a disenfranchised culture of uneducated citizens. A large part of this labor force was women. It was expected that this culture of poverty would perpetuate itself through generations. The universal stereotypes associated with impoverished...
Show moreNarrative inquiry was the qualitative method utilized to collect stories related to former migrant African American females who transformed their lives from migrant workers and found alternative career paths. Sustained poverty among migratory workers created a disenfranchised culture of uneducated citizens. A large part of this labor force was women. It was expected that this culture of poverty would perpetuate itself through generations. The universal stereotypes associated with impoverished migrants were so ingrained that overwhelmingly the majority of migrants accepted a life of poverty as prophesy. However, some former migrant African American women defied odds and rose above the cumulative effects of poverty. The major findings of this study revealed factors that significantly contributed to their success in a variety of professional careers: consistent family support, adaptive coping skills, catalyst for change, transformative learning, and meaningful relationships with non-family members, and commitment to community service. Sub-findings emerged that revealed that these additional factors also contributed to their success: value placed on education, strong belief in God, and leadership skills.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00004305, http://purl.flvc.org/fau/fd/FA00004305
- Subject Headings
- Experiential learning, Harvest of Shame (Motion picture), Learning by discovery, Migrant agricultural laborers -- Education, Social values, Transformative learning, United States -- Social conditions -- 20th century
- Format
- Document (PDF)
- Title
- The effects of learning strategy training on the writing performance of college students with Asperger’s syndrome.
- Creator
- Jackson, Lynn, Duffy, Mary L., Florida Atlantic University, College of Education, Department of Exceptional Student Education
- Abstract/Description
-
Individuals with Asperger’s Syndrome are entering institutions of higher education at an increasing rate. However, they may not be prepared to meet the academic and social demands of the postsecondary environment. Although studies have evaluated the impact of academic and social interventions for children and adolescents with Asperger’s Syndrome, little research has been conducted on the college population. The current study utilized a multiple baseline across participants design to evaluate...
Show moreIndividuals with Asperger’s Syndrome are entering institutions of higher education at an increasing rate. However, they may not be prepared to meet the academic and social demands of the postsecondary environment. Although studies have evaluated the impact of academic and social interventions for children and adolescents with Asperger’s Syndrome, little research has been conducted on the college population. The current study utilized a multiple baseline across participants design to evaluate the effectiveness of a writing learning strategy on the writing performance of three college students with Asperger’s Syndrome. Results indicated that the quality of the writing performance improved following strategy instruction. In addition, participants were able to generalize the use of the strategy to content specific writing tasks.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00004294, http://purl.flvc.org/fau/fd/FA00004294
- Subject Headings
- Asperger's syndrome, Autistic children -- Education, English language -- Composition and exercises -- Study and teaching, Inclusive education, Learning ability, Learning disabled children -- Education, Learning strategies
- Format
- Document (PDF)
- Title
- Specific and non-specific cognitive operations as language options for memory questions: AnfMRI study.
- Creator
- Jantzen, McNeel Gordon., Florida Atlantic University, Ashworth, Sara
- Abstract/Description
-
In order for memory questions to accomplish the goals of questions, teachers need to determine specific content and cognitive goals for each question so that questions can direct learners' attention and reinforce an organizational structure for the encoding of information. The purpose of this study was to examine the language used in memory questions for assessment purposes and to examine whether different language options used when formulating memory questions engaged brain areas related to...
Show moreIn order for memory questions to accomplish the goals of questions, teachers need to determine specific content and cognitive goals for each question so that questions can direct learners' attention and reinforce an organizational structure for the encoding of information. The purpose of this study was to examine the language used in memory questions for assessment purposes and to examine whether different language options used when formulating memory questions engaged brain areas related to memory and cognition. The language of the questions can affect the cognitive process by which the answer is derived. The two language options that affect cognitive processes are non-specific and specific. This study supplements teachers' working knowledge of the methods and techniques for questioning by providing a basic understanding of cognitive processes that different questions can evoke. This study used techniques from neuroscience to test hypotheses derived directly from education-based theories of cognition in order to validate educational theory. Neuroscience provides knowledge about how the brain senses, processes, stores, and retrieves information. It also provides findings that can be translated into practical applications for the classroom. Therefore, the relationship between education and neuroscience contributes to effective planning, practices, and assessment; it allows a more comprehensive understanding of the difficulties and apprehensions associated with learning. The following study utilized fMRI to answer the general question of the relationship between the memory processes associated with specific and non-specific questions. Seventeen undergraduate and graduate students from a university in South Florida served as subjects. Subjects were presented with a stimulus consisting of specific questions, non-specific questions, and control statements. All questions/statements followed the design of 8 seconds to read the question/statement, 10 seconds to "think" about the answer to the question or the material presented in the statement, 4 seconds for response using a "yes" or "no" button, and a 12 second rest period. Images collected were analyzed using AFNI. Specific cognitive operations improved efficiency for the retrieval of information from memory. Results elucidate differences in neural activity associated with encoding processes and the retrieval of information from memory based on the language used in specific and non-specific questions.
Show less - Date Issued
- 2004
- PURL
- http://purl.flvc.org/fau/fd/FADT12115
- Subject Headings
- Cognitive learning, Education--Effect of technological innovations on, Experiential learning, Brain--Psychophysiology, Learning--Physiological aspects, Recollection (Psychology), Memory
- Format
- Document (PDF)
- Title
- Historians of 19th Century Baseball: Exploring Their Experiences Regarding Their Avocation.
- Creator
- Berstler, Wade, Bryan, Valerie, Florida Atlantic University, College of Education, Department of Educational Leadership and Research Methodology
- Abstract/Description
-
The following document offers a qualitative case study in the field of adult and community education from an educational leadership perspective using baseball as an adult learning tool. Relevant existing theories (adult education, lifelong learning, adult learners, and certain leadership practices) for successful facilitation of historical baseball research were examined. The study focused on a purposeful sample population upon which a pilot study was conducted, revealing the experiences of...
Show moreThe following document offers a qualitative case study in the field of adult and community education from an educational leadership perspective using baseball as an adult learning tool. Relevant existing theories (adult education, lifelong learning, adult learners, and certain leadership practices) for successful facilitation of historical baseball research were examined. The study focused on a purposeful sample population upon which a pilot study was conducted, revealing the experiences of adult self-directed learners who produce the seminal work in their field as an avocation. The findings of this study included, but are not limited to, the passionate approach the study group members have for their subject matter, their love of learning, and the self-directedness of nonformally trained research historians using baseball as an adult learning tool. The findings also revealed the group members belief in the academic worthiness of baseball history, and their willingness to share their work with others to advance the field.
Show less - Date Issued
- 2016
- PURL
- http://purl.flvc.org/fau/fd/FA00004648
- Subject Headings
- Adult learning, Baseball -- United States -- History -- 19th century, Educational leadership, Experiential learning, Learning, Psychology of, Motivation in adult education, Transformational leadership
- Format
- Document (PDF)
- Title
- Plugging the school-to-prison pipeline: the impacts of culturally responsive teaching practices.
- Creator
- Maceda, Cynthia, Baxley, Traci P., Brown, Martha
- Date Issued
- 2013-04-05
- PURL
- http://purl.flvc.org/fcla/dt/3361117
- Subject Headings
- Imprisonment, Teaching--Practice, Student-centered learning
- Format
- Document (PDF)
- Title
- Limits on computational precision of image compression transformations.
- Creator
- Schmalz, Mark S., Ritter, G. X., Caimi, F. M., Harbor Branch Oceanographic Institute
- Date Issued
- 1998
- PURL
- http://purl.flvc.org/FCLA/DT/3180417
- Subject Headings
- Image compression, Adaptive computing, Adaptive computation and machine learning
- Format
- Document (PDF)
- Title
- A proposal for the investigation of the relationships among panic disorder and locus of control, learned helplessness, and anxiety sensitivity.
- Creator
- Rafkin, Amanda, Graduate College
- Date Issued
- 2013-04-12
- PURL
- http://purl.flvc.org/fcla/dt/3361343
- Subject Headings
- Panic Disorder, Locus of control, Helplessness, Learned, Anxiety sensitivity
- Format
- Document (PDF)
- Title
- Using digital collections for research, teaching, and scholarship.
- Creator
- Ress, Sunghae
- Abstract/Description
-
This poster presentation will illustrate how digital collections add value to the scholarly communication chain by supporting research, teaching, and scholarship in several ways: 1) increase access to primary materials, 2) increase access to special collections and archives 3) increase access to local materials of historical, cultural, and artistic significance 4) expand open access 5) foster collaboration with faculty and students 6) increase the reputation and visibility of your university...
Show moreThis poster presentation will illustrate how digital collections add value to the scholarly communication chain by supporting research, teaching, and scholarship in several ways: 1) increase access to primary materials, 2) increase access to special collections and archives 3) increase access to local materials of historical, cultural, and artistic significance 4) expand open access 5) foster collaboration with faculty and students 6) increase the reputation and visibility of your university and library. I will use specific examples from the Florida Atlantic University Digital Collections to “show and tell” and include the importance of creating metadata to enhance discovery and access to your digital collections. In addition, this poster will very briefly touch upon digital sustainability; mainly that of ensuring ongoing access to digital collections and ensuring long term preservation of these same materials.
Show less - Date Issued
- 2014
- PURL
- http://purl.flvc.org/fau/fd/FA00002897
- Subject Headings
- Scholarly communication, Research, Teaching, Learning and scholarship, Open access
- Format
- Document (PDF)
- Title
- Maine sailing.
- Creator
- Seidl, Jana
- Date Issued
- 2004-06
- PURL
- http://purl.flvc.org/fcla/dt/11567
- Subject Headings
- Expeditionary Learning Outward Bound, Education--Florida, Students
- Format
- Document (PDF)
- Title
- Morgan Stanley.
- Creator
- Seidl, Jana
- Date Issued
- 2006-07
- PURL
- http://purl.flvc.org/fcla/dt/11535
- Subject Headings
- Internship programs, Education--Florida, Expeditionary Learning Outward Bound
- Format
- Document (PDF)
- Title
- My outward bound experience.
- Creator
- Stetson, Natalie C.
- Date Issued
- 2004-08
- PURL
- http://purl.flvc.org/fcla/dt/11562
- Subject Headings
- Expeditionary Learning Outward Bound, Students, Education--Florida
- Format
- Document (PDF)
- Title
- An outward bound experience.
- Creator
- Grant, Jensen
- Date Issued
- 2005-07
- PURL
- http://purl.flvc.org/fcla/dt/11546
- Subject Headings
- Expeditionary Learning Outward Bound, Education--Florida, Students
- Format
- Document (PDF)
- Title
- Cold night, cold food or how I stopped worrying and love the tree.
- Creator
- Wicks, Robert
- Date Issued
- 2005-07
- PURL
- http://purl.flvc.org/fcla/dt/11557
- Subject Headings
- Expeditionary Learning Outward Bound, Students, Education--Florida
- Format
- Document (PDF)
- Title
- Dark summer: the thwarted excursion.
- Creator
- Kulb, Carolyn
- Date Issued
- 2005-05
- PURL
- http://purl.flvc.org/fcla/dt/11549
- Subject Headings
- Expeditionary Learning Outward Bound, Students, Education--Florida
- Format
- Document (PDF)
- Title
- Distinguished scholars program.
- Creator
- Kennedy, Amanda
- Date Issued
- 2005-07
- PURL
- http://purl.flvc.org/fcla/dt/11550
- Subject Headings
- Internship programs, Expeditionary Learning Outward Bound, Education--Florida
- Format
- Document (PDF)
