View All Items

Title: AN ARTIFICIAL INTELLIGENCE DRIVEN FRAMEWORK FOR MEDICAL IMAGING.
Creator: Sanghvi, Harshal A., Agarwal, Ankur, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The major objective of this dissertation was to create a framework which is used for medical image diagnosis. In this diagnosis, we brought classification and diagnosing of diseases through an Artificial Intelligence based framework, including COVID, Pneumonia, and Melanoma cancer through medical images. The algorithm ran on multiple datasets. A model was developed which detected the medical images through changing hyper-parameters. The aim of this work was to apply the new transfer learning...
Show moreThe major objective of this dissertation was to create a framework which is used for medical image diagnosis. In this diagnosis, we brought classification and diagnosing of diseases through an Artificial Intelligence based framework, including COVID, Pneumonia, and Melanoma cancer through medical images. The algorithm ran on multiple datasets. A model was developed which detected the medical images through changing hyper-parameters. The aim of this work was to apply the new transfer learning framework DenseNet-201 for the diagnosis of the diseases and compare the results with the other deep learning models. The novelty in the proposed work was modifying the Dense Net 201 Algorithm, changing hyper parameters (source weights, Batch Size, Epochs, Architecture (number of neurons in hidden layer), learning rate and optimizer) to quantify the results. The novelty also included the training of the model by quantifying weights and in order to get more accuracy. During the data selection process, the data were cleaned, removing all the outliers. Data augmentation was used for the novel architecture to overcome overfitting and hence not producing false absurd results the computational performance was also observed. The proposed model results were also compared with the existing deep learning models and the algorithm was also tested on multiple datasets.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014274
Subject Headings: Diagnostic imaging, Artificial intelligence, Deep learning (Machine learning)
Format: Document (PDF)

Title: FEATURE REPRESENTATION LEARNING FOR ONLINE ADVERTISING AND RECOMMENDATIONS.
Creator: Gharibshah, Zhabiz, Zhu, Xingquan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Online advertising [100], as a multi-billion dollar business, provides a common marketing experience when people access online services using electronic devices, such as desktop computers, tablets, smartphones, and so on. Using the Internet as a means of advertising, different stakeholders take actions in the background to provide and deliver advertisements to users through numerous platforms, such as search engines, news sites, and social networks, where dedicated spots of areas are used to...
Show moreOnline advertising [100], as a multi-billion dollar business, provides a common marketing experience when people access online services using electronic devices, such as desktop computers, tablets, smartphones, and so on. Using the Internet as a means of advertising, different stakeholders take actions in the background to provide and deliver advertisements to users through numerous platforms, such as search engines, news sites, and social networks, where dedicated spots of areas are used to display advertisements (ads) along with search results, posts, or page content. Online advertising is mainly based on dynamically selecting ads through a real-time bidding (or auction) mechanism. Predicting user responses like clicking ads in e-commerce platforms and internet-based advertising systems, as the first measurable user response, is an essential step for many digital advertising and recommendation systems to capture the user’s propensity to follow up actions, such as purchasing a product or subscribing to a service. To maximize revenue and user satisfaction, online advertising platforms must predict the expected user behavior of each displayed advertisement and maximize the user’s expectations of clicking [28]. Based on this observed feedback, these systems are tailored to user preferences to decide the order in that ads or any promoted content should be served to them. This objective provides an incentive to develop new research by using ideas derived from different domains like machine learning and data mining combined with models for information retrieval and mathematical optimization. They introduce different machine learning and data mining methods that employ deep learning-based predictive models to learn the representation of input features with the aim of user response prediction. Feature representation learning is known as a fundamental task on how to input information is going to be represented in machine learning models. A good feature representation learning method that seeks to learn low-dimensional embedding vectors is a key factor for the success of many downstream analytics tasks, such as click-through prediction and conversion prediction in recommendation systems and online advertising platforms.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014269
Subject Headings: Internet advertising, Deep learning (Machine learning), Internet marketing
Format: Document (PDF)

Title: DATA AUGMENTATION IN DEEP LEARNING.
Creator: Shorten, Connor, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Recent successes of Deep Learning-powered AI are largely due to the trio of: algorithms, GPU computing, and big data. Data could take the shape of hospital records, satellite images, or the text in this paragraph. Deep Learning algorithms typically need massive collections of data before they can make reliable predictions. This limitation inspired investigation into a class of techniques referred to as Data Augmentation. Data Augmentation was originally developed as a set of label-preserving...
Show moreRecent successes of Deep Learning-powered AI are largely due to the trio of: algorithms, GPU computing, and big data. Data could take the shape of hospital records, satellite images, or the text in this paragraph. Deep Learning algorithms typically need massive collections of data before they can make reliable predictions. This limitation inspired investigation into a class of techniques referred to as Data Augmentation. Data Augmentation was originally developed as a set of label-preserving transformations used in order to simulate large datasets from small ones. For example, imagine developing a classifier that categorizes images as either a “cat” or a “dog”. After initial collection and labeling, there may only be 500 of these images, which are not enough data points to train a Deep Learning model. By transforming these images with Data Augmentations such as rotations and brightness modifications, more labeled images are available for model training and classification! In addition to applications for learning from limited labeled data, Data Augmentation can also be used for generalization testing. For example, we can augment the test set to set the visual style of images to “winter” and see how that impacts the performance of a stop sign detector. The dissertation begins with an overview of Deep Learning methods such as neural network architectures, gradient descent optimization, and generalization testing. Following an initial description of this technology, the dissertation explains overfitting. Overfitting is the crux of Deep Learning methods in which improvements to the training set do not lead to improvements on the testing set. To the rescue are Data Augmentation techniques, of which the Dissertation presents an overview of the augmentations used for both image and text data, as well as the promising potential of generative data augmentation with models such as ChatGPT. The dissertation then describes three major experimental works revolving around CIFAR-10 image classification, language modeling a novel dataset of Keras information, and patient survival classification from COVID-19 Electronic Health Records. The dissertation concludes with a reflection on the evolution of limitations of Deep Learning and directions for future work.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014228
Subject Headings: Deep learning (Machine learning), Artificial intelligence, Data augmentation
Format: Document (PDF)

Title: Computer-aided diagnosis of skin cancers using dermatology images.
Creator: Gilani, Syed Qasim, Marques, Oge, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Skin cancer is a prevalent cancer that significantly contributes to global mortality rates. Early detection is crucial for a high survival rate. Dermatologists primarily rely on visual inspection to diagnose skin cancers, but this method is inaccurate. Deep learning algorithms can enhance the diagnostic accuracy of skin cancers. However, these algorithms require substantial labeled data for effective training. Acquiring annotated data for skin cancer classification is time-consuming,...
Show moreSkin cancer is a prevalent cancer that significantly contributes to global mortality rates. Early detection is crucial for a high survival rate. Dermatologists primarily rely on visual inspection to diagnose skin cancers, but this method is inaccurate. Deep learning algorithms can enhance the diagnostic accuracy of skin cancers. However, these algorithms require substantial labeled data for effective training. Acquiring annotated data for skin cancer classification is time-consuming, expensive, and necessitates expert annotation. Moreover, skin cancer datasets often suffer from imbalanced data distribution. Generative Adversarial Networks (GANs) can be used to overcome the challenges of data scarcity and lack of labels by automatically generating skin cancer images. However, training and testing data from different distributions can introduce domain shift and bias, impacting the model’s performance. This dissertation addresses this issue by developing deep learning-based domain adaptation models. Additionally, this research emphasizes deploying deep learning models on hardware to enable real-time skin cancer detection, facilitating accurate diagnoses by dermatologists. Deploying conventional deep learning algorithms on hardware is not preferred due to the problem of high resource consumption. Therefore, this dissertation presents spiking neural network-based (SNN) models designed specifically for hardware implementation. SNNs are preferred for their power-efficient behavior and suitability for hardware deployment.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014233
Subject Headings: Deep learning (Machine learning), Diagnostic imaging, Skin--Cancer--Diagnosis
Format: Document (PDF)

Title: OCR2SEQ: A NOVEL MULTI-MODAL DATA AUGMENTATION PIPELINE FOR WEAK SUPERVISION.
Creator: Lowe, Michael A., Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: With the recent large-scale adoption of Large Language Models in multidisciplinary research and commercial space, the need for large amounts of labeled data has become more crucial than ever to evaluate potential use cases for opportunities in applied intelligence. Most domain specific fields require a substantial shift that involves extremely large amounts of heterogeneous data to have meaningful impact on the pre-computed weights of most large language models. We explore extending the...
Show moreWith the recent large-scale adoption of Large Language Models in multidisciplinary research and commercial space, the need for large amounts of labeled data has become more crucial than ever to evaluate potential use cases for opportunities in applied intelligence. Most domain specific fields require a substantial shift that involves extremely large amounts of heterogeneous data to have meaningful impact on the pre-computed weights of most large language models. We explore extending the capabilities a state-of-the-art unsupervised pre-training method; Transformers and Sequential Denoising Auto-Encoder (TSDAE). In this study we show various opportunities for using OCR2Seq a multi-modal generative augmentation strategy to further enhance and measure the quality of noise samples used when using TSDAE as a pretraining task. This study is a first of its kind work that leverages converting both generalized and sparse domains of relational data into multi-modal sources. Our primary objective is measuring the quality of augmentation in relation to the current implementation of the sentence transformers library. Further work includes the effect on ranking, language understanding, and corrective quality.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014367
Subject Headings: Natural language processing (Computer science), Deep learning (Machine learning)
Format: Document (PDF)

Title: ADVANCING ONE-CLASS CLASSIFICATION: A COMPREHENSIVE ANALYSIS FROM THEORY TO NOVEL APPLICATIONS.
Creator: Abdollah, Zadeh Azadeh, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: This dissertation explores one-class classification (OCC) in the context of big data and fraud detection, addressing challenges posed by imbalanced datasets. A detailed survey of OCC-related literature forms a core part of the study, categorizing works into outlier detection, novelty detection, and deep learning applications. This survey reveals a gap in the application of OCC to the inherent problems of big data, such as class rarity and noisy data. Building upon the foundational insights...
Show moreThis dissertation explores one-class classification (OCC) in the context of big data and fraud detection, addressing challenges posed by imbalanced datasets. A detailed survey of OCC-related literature forms a core part of the study, categorizing works into outlier detection, novelty detection, and deep learning applications. This survey reveals a gap in the application of OCC to the inherent problems of big data, such as class rarity and noisy data. Building upon the foundational insights gained from the comprehensive literature review on OCC, the dissertation progresses to a detailed comparative analysis between OCC and binary classification methods. This comparison is pivotal in understanding their respective strengths and limitations across various applications, emphasizing their roles in addressing imbalanced datasets. The research then specifically evaluates binary and OCC using credit card fraud data. This practical application highlights the nuances and effectiveness of these classification methods in real-world scenarios, offering insights into their performance in detecting fraudulent activities. After the evaluation of binary and OCC using credit card fraud data, the dissertation extends this inquiry with a detailed investigation into the effectiveness of both methodologies in fraud detection. This extended analysis involves utilizing not only the Credit Card Fraud Detection Dataset but also the Medicare Part D dataset. The findings show the comparative performance and suitability of these classification methods in practical fraud detection scenarios. Finally, the dissertation examines the impact of training OCC algorithms on majority versus minority classes, using the two previously mentioned datasets in addition to Medicare Part B and Durable Medical Equipment, Prosthetics, Orthotics and Supplies (DMEPOS) datasets. This exploration offers critical insights into model training strategies and their implications, suggesting that training on the majority class can often lead to more robust classification results. In summary, this dissertation provides a deep understanding of OCC, effectively bridging theoretical concepts with novel applications in big data and fraud detection. It contributes to the field by offering a comprehensive analysis of OCC methodologies, their practical implications, and their effectiveness in addressing class imbalance in big data.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014387
Subject Headings: Classification, Big data, Deep learning (Machine learning), Computer engineering
Format: Document (PDF)

Title: An evaluation of Unsupervised Machine Learning Algorithms for Detecting Fraud and Abuse in the U.S. Medicare Insurance Program.
Creator: Da Rosa, Raquel C., Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: The population of people ages 65 and older has increased since the 1960s and current estimates indicate it will double by 2060. Medicare is a federal health insurance program for people 65 or older in the United States. Medicare claims fraud and abuse is an ongoing issue that wastes a large amount of money every year resulting in higher health care costs and taxes for everyone. In this study, an empirical evaluation of several unsupervised machine learning approaches is performed which...
Show moreThe population of people ages 65 and older has increased since the 1960s and current estimates indicate it will double by 2060. Medicare is a federal health insurance program for people 65 or older in the United States. Medicare claims fraud and abuse is an ongoing issue that wastes a large amount of money every year resulting in higher health care costs and taxes for everyone. In this study, an empirical evaluation of several unsupervised machine learning approaches is performed which indicates reasonable fraud detection results. We employ two unsupervised machine learning algorithms, Isolation Forest and Unsupervised Random Forest, which have not been previously used for the detection of fraud and abuse on Medicare data. Additionally, we implement three other machine learning methods previously applied on Medicare data which include: Local Outlier Factor, Autoencoder, and k-Nearest Neighbor. For our dataset, we combine the 2012 to 2015 Medicare provider utilization and payment data and add fraud labels from the List of Excluded Individuals/Entities (LEIE) database. Results show that Local Outlier Factor is the best model to use for Medicare fraud detection.
Show less
Date Issued: 2018
PURL: http://purl.flvc.org/fau/fd/FA00013042
Subject Headings: Machine learning, Medicare fraud, Algorithms
Format: Document (PDF)

Title: EFFECTS OF OPTOGENETICALLY STIMULATING THE REUNIENS NUCLEUS DURING SLEEP IN A NOVEL ATTENTIONAL SET-SHIFTING TASK.
Creator: Yarden, Ori Simon, Varela, Carmen, Florida Atlantic University, Department of Psychology, Charles E. Schmidt College of Science
Abstract/Description: Sparse thalamocortical cell population synchronicity during sleep spindle oscillations has been hypothesized to promote the integration of hippocampal memory information into associated neocortical representations 1. We asked the question of whether sparse or rhythmic activity in thalamocortical cells of the reuniens nucleus influence memory consolidation and cognitive flexibility during learning after sleep. For this study, I designed a novel attentional set-shifting task and incorporated...
Show moreSparse thalamocortical cell population synchronicity during sleep spindle oscillations has been hypothesized to promote the integration of hippocampal memory information into associated neocortical representations 1. We asked the question of whether sparse or rhythmic activity in thalamocortical cells of the reuniens nucleus influence memory consolidation and cognitive flexibility during learning after sleep. For this study, I designed a novel attentional set-shifting task and incorporated optogenetics with closed-loop stimulation in sleeping rats to investigate the effects of sparse (nonrhythmic) or rhythmic spindle-like (~10Hz) activity in thalamic cells of the reuniens nucleus on learning and cognitive flexibility. We show that, as predicted, post-sleep setshifting performance improved after sleep with non-rhythmic optogenetic stimulation in the thalamic nucleus reuniens relative to rhythmic optogenetic stimulation. While both non-rhythmic and rhythmic optogenetic stimulation led to an increase in perseverative errors, only non-rhythmic optogenetic stimulation showed effects of learning from errors, which correlated with sleep, and which ultimately had a net benefit in set-shifting performance compared to rhythmic optogenetic stimulation and the control group.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013632
Subject Headings: Optogenetics, Thalamic Nuclei, Sleep, Learning
Format: Document (PDF)

Title: ASSESSING METHODS AND TOOLS TO IMPROVE REPORTING, INCREASE TRANSPARENCY, AND REDUCE FAILURES IN MACHINE LEARNING APPLICATIONS IN HEALTHCARE.
Creator: Garbin, Christian, Marques, Oge, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Artificial intelligence (AI) had a few false starts – the AI winters of the 1970s and 1980s. We are now in what looks like an AI summer. There are many useful applications of AI in the field. But there are still unfulfilled promises and outright failures. From self-driving cars that work only in constrained cases, to medical image analysis products that would replace radiologists but never did, we still struggle to translate successful research into successful real-world applications. The...
Show moreArtificial intelligence (AI) had a few false starts – the AI winters of the 1970s and 1980s. We are now in what looks like an AI summer. There are many useful applications of AI in the field. But there are still unfulfilled promises and outright failures. From self-driving cars that work only in constrained cases, to medical image analysis products that would replace radiologists but never did, we still struggle to translate successful research into successful real-world applications. The software engineering community has accumulated a large body of knowledge over the decades on how to develop, release, and maintain products. AI products, being software products, benefit from some of that accumulated knowledge, but not all of it. AI products diverge from traditional software products in fundamental ways: their main component is not a specific piece of code, written for a specific purpose, but a generic piece of code, a model, customized by a training process driven by hyperparameters and a dataset. Datasets are usually large and models are opaque. We cannot directly inspect them as we can inspect the code of traditional software products. We need other methods to detect failures in AI products.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013580
Subject Headings: Machine learning, Artificial intelligence, Healthcare
Format: Document (PDF)

Title: GENERATIVE ADVERSARIAL NETWORK DATA GENERATION FOR THE USE OF REAL TIME IMAGE DETECTION IN SIDE-SCAN SONAR IMAGERY.
Creator: McGinley, James Patrick, Dhanak, Manhar, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
Abstract/Description: Automatic target recognition of unexploded ordnances in side scan sonar imagery has been a struggling task, due to the lack of publicly available side-scan sonar data. Real time image detection and classification algorithms have been implemented to combat this task, however, machine learning algorithms require a substantial amount of training data to properly detect specific targets. Transfer learning methods are used to replace the need of large datasets, by using a pre trained network on...
Show moreAutomatic target recognition of unexploded ordnances in side scan sonar imagery has been a struggling task, due to the lack of publicly available side-scan sonar data. Real time image detection and classification algorithms have been implemented to combat this task, however, machine learning algorithms require a substantial amount of training data to properly detect specific targets. Transfer learning methods are used to replace the need of large datasets, by using a pre trained network on the side-scan sonar images. In the present study the implementation of a generative adversarial network is used to generate meaningful sonar imagery from a small dataset. The generated images are then added to the existing dataset to train an image detection and classification algorithm. The study looks to demonstrate that generative images can be used to aid in detecting objects of interest in side-scan sonar imagery.
Show less
Date Issued: 2019
PURL: http://purl.flvc.org/fau/fd/FA00013394
Subject Headings: Sidescan sonar, Algorithms, Machine learning
Format: Document (PDF)

Title: THE EFFECTS OF ELABORATION AND DISTANCE ON THE RETRIEVAL OF TEXT.
Creator: MCCANDLESS, KATHY LEE, Florida Atlantic University
Abstract/Description: Two experiments are presented that examined the manner in which antecedents are retrieved from memory. In Experiment 1, subjects read passages containing two antecedents, with one appearing early in a passage and one appearing late. In addition, one of the antecedents was mentioned briefly while the other was elaborated on in much greater detail. The last line of each passage required reinstatement of either the early or late antecedent. Following reinstatement, subjects were required to name...
Show moreTwo experiments are presented that examined the manner in which antecedents are retrieved from memory. In Experiment 1, subjects read passages containing two antecedents, with one appearing early in a passage and one appearing late. In addition, one of the antecedents was mentioned briefly while the other was elaborated on in much greater detail. The last line of each passage required reinstatement of either the early or late antecedent. Following reinstatement, subjects were required to name either the early or the late antecedent. Reading time results showed that search time was a function of both recency and elaboration with late antecedents retrieved more quickly than early antecedents and elaborated antecedents retrieved more quickly than nonelaborated antecedents. Naming times confirmed that subjects were performing the required reinstatement; reinstated antecedents were named faster than nonreinstated antecedents. Experiment 2 demonstrated that there was no difference in the activation level of either antecedent prior to reinstatement. (Abstract shortened with permission of author.)
Show less
Date Issued: 1987
PURL: http://purl.flvc.org/fcla/dt/14385
Subject Headings: Memory transfer, Learning, Psychology of
Format: Document (PDF)

Title: The experience of being a leader during a ropes course program and at work: A heuristic inquiry.
Creator: Starr, Malika, Florida Atlantic University, Bryan, Valerie
Abstract/Description: This study explored the question, "What is the experience of being a leader during participation in a ropes course program and at work?" The ropes course as a training medium provides opportunities for people to engage in challenging activities to improve interpersonal skills. From ten ropes course programs and 130 participants, the researcher purposefully selected thirteen co-researchers who exhibited pre-determined leadership behaviors. Dialogue with each co-researcher provided rich...
Show moreThis study explored the question, "What is the experience of being a leader during participation in a ropes course program and at work?" The ropes course as a training medium provides opportunities for people to engage in challenging activities to improve interpersonal skills. From ten ropes course programs and 130 participants, the researcher purposefully selected thirteen co-researchers who exhibited pre-determined leadership behaviors. Dialogue with each co-researcher provided rich descriptions and metaphors about the experience of being a leader. Using heuristic research methods, the researcher analyzed the data and uncovered redundant themes to better understand the phenomenon of being a leader. While each experience was unique, the composite encompassed the principles of several leadership theories. The significant meaning revealed was that being a leader was a big responsibility and it provided opportunities to transform and be transformed, which was enjoyable, rewarding and sometimes frustrating. Six major findings emerged from the inquiry. The first related to the concept of leaderless groups and emergent leaders. A leader emerged from each of the leaderless groups that started on the ropes course. The second finding was that the experiences of leading on the ropes course and at work closely mirrored each other. The third finding represented the major difference between being a leader on the ropes course and being a leader at work. The ropes course provided a setting for participants to experience being transformational leaders, without the ramifications of office politics, transactions and economic pressures. The fourth finding was that managing followers was the single most frustrating aspect of the experience of being a leader. All of the frustrations occurred when the values and principles espoused by leaders and followers were not aligned. The fifth finding was that the experience of being a leader was holistic because it encompassed who the individuals were, how they performed in two different settings, what feelings this evoked and what significance it held for them. The sixth finding revealed that trait, style, situational, transformational and visionary leadership theories are not mutually exclusive. The study findings serve as a guide for practitioners to design more meaningful leadership development programs.
Show less
Date Issued: 2004
PURL: http://purl.flvc.org/fau/fd/FADT12073
Subject Headings: Leadership, Adventure education, Experiential learning
Format: Document (PDF)

Title: Individual Differences in Learning and Perseveration.
Creator: Preache, Maurline, Adamson, Robert E., Florida Atlantic University
Abstract/Description: Two groups of rats received training and testing in learning situations designed to induce perseveration. One task involved discrimination training on one bar of a two-bar Skinner box and a subsequent shift of reinforcement to the opposite bar. The second task was a maze-learning one in which the training route was blocked after 40 trials at a point just before the entrance to the goal box. Thereafter, access to the goal box was possible only through a shorter, but not previously reinforced...
Show moreTwo groups of rats received training and testing in learning situations designed to induce perseveration. One task involved discrimination training on one bar of a two-bar Skinner box and a subsequent shift of reinforcement to the opposite bar. The second task was a maze-learning one in which the training route was blocked after 40 trials at a point just before the entrance to the goal box. Thereafter, access to the goal box was possible only through a shorter, but not previously reinforced route. The third task involved escape training through one door of a four-door shock compartment. After 40 trials, the training door was locked and S was permitted to escape shock only through one of the three previously-locked doors. In each of the three tasks, indices of initial learning and perseveration were selected, and within-subject comparisons were made for both initial learning and perseveration across tasks. Within each task there was a comparison of the initial learning measures to those used to define perseveration. Finally, one of the groups was given conditioning and extinction sessions in a single-bar Skinner box. The extinction measure was compared with perseveration measures in the other tasks. Four hypotheses were stated. These were that between tasks perseverative measures would be positively related; that between tasks initial learning measures would be positively related; that within each task initial learning and perseveration would be neeatively related; and finally that extinction in the single-bar Skinner box would have a positive relationship to measures of perseveration in the other tasks. Only the last two hypotheses were supported and this support was not uncontradicted. Also~ in the case of the extinction-perseveration comparisons, none of the supporting evidence reached significance at the .05 level of confidence.
Show less
Date Issued: 1969
PURL: http://purl.flvc.org/fau/fd/FA00000813
Subject Headings: Learning, Psychology of, Perseveration (Psychology)
Format: Document (PDF)

Title: The relationship between vocal pitch-matching and learning disabilities.
Creator: Mozingo, John Marshall., Florida Atlantic University, Fleitas, Patricia P.
Abstract/Description: Pitch-matching tests were conducted with learning disabled (LD) and non-learning disabled (NLD) third through fifth graders to examine whether a significant difference between pitch-matching abilities exists. Subjects were given a two part pitch-matching test using a tape recorded vocal model. The vocal model was a 12 year-old boy with unchanged voice singing the test examples on the neutral syllable "loo." Subjects were instructed to echo the vocal model and were given a single point for...
Show morePitch-matching tests were conducted with learning disabled (LD) and non-learning disabled (NLD) third through fifth graders to examine whether a significant difference between pitch-matching abilities exists. Subjects were given a two part pitch-matching test using a tape recorded vocal model. The vocal model was a 12 year-old boy with unchanged voice singing the test examples on the neutral syllable "loo." Subjects were instructed to echo the vocal model and were given a single point for each correctly sung pitch. Statistical analysis revealed a significant difference in the pitch-matching skills of the learning disabled and the non-learning disabled students.
Show less
Date Issued: 1997
PURL: http://purl.flvc.org/fcla/dt/15505
Subject Headings: Musical pitch, Learning disabled children
Format: Document (PDF)

Title: KINOVA ROBOTIC ARM MANIPULATION WITH PYTHON PROGRAMMING.
Creator: Veit, Cameron, Zhong, Xiangnan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: As artificial intelligence (AI), such as reinforcement learning (RL), has continued to grow, the introduction of AI for use in robotic arms in order to have them autonomously complete tasks has become an increasingly popular topic. Robotic arms have recently had a drastic spike in innovation, with new robotic arms being developed for a variety of tasks both menial and complicated. One robotic arm recently developed for everyday use in close proximity to the user is the Kinova Gen 3 Lite, but...
Show moreAs artificial intelligence (AI), such as reinforcement learning (RL), has continued to grow, the introduction of AI for use in robotic arms in order to have them autonomously complete tasks has become an increasingly popular topic. Robotic arms have recently had a drastic spike in innovation, with new robotic arms being developed for a variety of tasks both menial and complicated. One robotic arm recently developed for everyday use in close proximity to the user is the Kinova Gen 3 Lite, but limited formal research has been conducted about controlling this robotic arm both with an AI and in general. Therefore, this thesis covers the implementation of Python programs in controlling the robotic arm physically as well as the use of a simulation to train an RL based AI compatible with the Kinova Gen 3 Lite. Additionally, the purpose of this research is to identify and solve the difficulties in the physical instance and the simulation as well as the impact of the learning parameters on the robotic arm AI. Similarly, the issues in connecting two Kinova Gen 3 Lites to one computer at once are also examined. This thesis goes into detail about the goal of the Python programs created to move the physical robotic arm as well as the overall setup and goal of the robotic arm simulation for the RL method. In particular, the Python programs for the physical robotic arm pick up the object and place it at a different location, identifying a method to prevent the gripper from crushing an object without a tactile sensor in the process. The thesis also covers the effect of various learning parameters on the accuracy and steps to goal curves of an RL method designed to make a Kinova Gen 3 Lite grab an object in a simulation. In particular, a neural network implementation of RL method with one of the learning parameters changed in comparison to the optimal learning parameters. The neural network is trained using Python Anaconda to control a Kinova Gen 3 Lite robotic arm model for a simulation made in the Unity compiler.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014022
Subject Headings: Robotics, Artificial intelligence, Reinforcement learning
Format: Document (PDF)

Title: MEASUREMENT, ANALYSIS, CLASSIFICATION AND DETECTION OF GUNSHOT AND GUNSHOT-LIKE SOUNDS.
Creator: Baliram, Rajesh Singh, Zhuang, Hanqi, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The recent uptick in senseless shootings in otherwise quiet and relatively safe environments is powerful evidence of the need, now more than ever, to reduce these occurrences. Artificial intelligence (AI) can play a significant role in deterring individuals from attempting these acts of violence. The installation of audio sensors can assist in the proper surveillance of surroundings linked to public safety, which is the first step toward AI-driven surveillance. With the increasing popularity...
Show moreThe recent uptick in senseless shootings in otherwise quiet and relatively safe environments is powerful evidence of the need, now more than ever, to reduce these occurrences. Artificial intelligence (AI) can play a significant role in deterring individuals from attempting these acts of violence. The installation of audio sensors can assist in the proper surveillance of surroundings linked to public safety, which is the first step toward AI-driven surveillance. With the increasing popularity of machine learning (ML) processes, systems are being developed and optimized to assist personnel in highly dangerous situations. In addition to saving innocent lives, supporting the capture of the responsible criminals is part of the AI algorithm that can be hosted in acoustic gunshot detection systems (AGDSs). Although there has been some speculation that these AGDSs produce a higher false positive rate (FPR) than reported in their specifications, optimizing the dataset used for the model’s training and testing will enhance its performance. This dissertation proposes a new gunshot-like sound database that can be incorporated into a dataset for improved training and testing of a ML gunshot detection model. Reduction of the sample bias (that is, a bias in ML caused by an incomplete database) is achievable. The Mel frequency cepstral coefficient (MFCC) feature extraction process was utilized in this research. The uniform manifold and projection (UMAP) algorithm revealed that the MFCCs of this newly created database were the closest sounds to a gunshot sound, as compared to other gunshot-like sounds reported in literature. The UMAP algorithm reinforced the outcome derived from the calculation of the distances of the centroids of various gunshot-like sounds in MFCCs’ clusters. Further research was conducted into the feature reduction aspect of the gunshot detection ML model. Reducing a feature set to a minimum, while also maintaining a high accuracy rate, is a key parameter of a highly efficient model. Therefore, it is necessary for field deployed ML applications to be computationally light weight and highly efficient. Building on the discoveries of this research can lead to the development of highly efficient gunshot detection models.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014110
Subject Headings: Firearms, Sound, Detectors, Machine learning
Format: Document (PDF)

Title: ADVANCED DATA SCIENCE AND PHYSICS-BASED MODELING FOR DYNAMIC SYSTEMS.
Creator: Hashemi, Ali, Jang, Jinwoo, Florida Atlantic University, Department of Civil, Environmental and Geomatics Engineering, College of Engineering and Computer Science
Abstract/Description: This dissertation focuses on the development of data-driven and physics-based modeling for two distinct significant structural engineering applications: time-varying response variables estimation and unwanted lateral vibration control. In the first part, I propose a machine learning (ML)-based surrogate modeling to directly predict dynamic responses over an entire mechanical system during operations. Any mechanical system design, as well as structural health monitoring systems, require...
Show moreThis dissertation focuses on the development of data-driven and physics-based modeling for two distinct significant structural engineering applications: time-varying response variables estimation and unwanted lateral vibration control. In the first part, I propose a machine learning (ML)-based surrogate modeling to directly predict dynamic responses over an entire mechanical system during operations. Any mechanical system design, as well as structural health monitoring systems, require transient vibration analysis. However, traditional methods and modeling calculations are time- and resource-consuming. The use of ML approaches is particularly promising in scientific and engineering challenges containing processes that are not completely understood, or where it is computationally infeasible to run numerical or analytical models at desired resolutions in space and time. In this research, an ML-based surrogate for the FEA approach is developed to forecast the time-varying response, i.e., displacement of a two-dimensional truss structure. Various ML regression algorithms including decision trees and deep neural networks are developed to predict movement over a truss structure, and their efficiencies are investigated. ML algorithms have been combined with FEA in preliminary attempts to address issues in static mechanical systems.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014048
Subject Headings: Dynamics, Data Science, Machine learning
Format: Document (PDF)

Title: An exploration of the relationship between experiential learning and self-directed learning readiness.
Creator: Amey, Beth E., Florida Atlantic University, College of Education, Department of Educational Leadership and Research Methodology
Abstract/Description: The purpose of this study was to explore the relationship between experiential learning and self-directed learning readiness of bachelor's and master's level social work students. A quantitative design was utilized. The study consisted of 115 senior social work students and 70 master's level social work students (separated into three student groups) from a state university. Students participated in a one-semester field education component as part of their social work degree program. The...
Show moreThe purpose of this study was to explore the relationship between experiential learning and self-directed learning readiness of bachelor's and master's level social work students. A quantitative design was utilized. The study consisted of 115 senior social work students and 70 master's level social work students (separated into three student groups) from a state university. Students participated in a one-semester field education component as part of their social work degree program. The research instrument utilized was the Self-Directed Learning Readiness Scale (SDLRS) constructed by Guglielmino (1978). The SDLRS is a self-report questionnaire with 58 Likert scale items designed to measure the attitudes, values and abilities of learners relating to their readiness to engage in self-directed learning. A pretest, treatment, posttest design was utilized. Demographic data were collected with the pretest administration and level of satisfaction information was collected with the posttest administration. The bachelor's level social work students demonstrated statistically significant differences in the pre and posttest SDLRS scores while the master's level social work students' changes in readiness for self-directed learning were not significant. It is important to note that the master's level social work students spent only half the amount of hours in the field education as the bachelor's level students at the time of the posttest. Correlations between change score from pretest to posttest SDLRS with students' previous exposure to the field of social work, prior experiential learning in a social work program, their satisfaction with the experiential learning component, and demographic factors of gender, age, ethnicity, marital status, number of children, and number of years pursuing degree were not significant., The initial SDLRS scores of the bachelor's level students were found to be consistent with those of nursing students previously scored on the SDLRS. In the ANOVA of all groups, significant differences were not found with the four groups of social work students in their change scores of pretest and posttest SDLRS or their overall level of satisfaction with the field experience and overall level of satisfaction with the quality of the supervisor in the field experience. The internship did not demonstrate particular merit for improving readiness for self-directed learning except for the bachelor's level students. However, students were satisfied with the experience and felt it changed their perceptions of self and others.
Show less
Date Issued: 2008
PURL: http://purl.flvc.org/FAU/107799
Subject Headings: Experiential learning, Adult learning, Learning, Psychology of, Self-culture
Format: Document (PDF)

Title: PRESERVING KNOWLEDGE IN SIMULATED BEHAVIORAL ACTION LOOPS.
Creator: St.Clair, Rachel, Barenholtz, Elan, Hahn, William, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
Abstract/Description: One basic goal of artificial learning systems is the ability to continually learn throughout that system’s lifetime. Transitioning between tasks and re-deploying prior knowledge is thus a desired feature of artificial learning. However, in the deep-learning approaches, the problem of catastrophic forgetting of prior knowledge persists. As a field, we want to solve the catastrophic forgetting problem without requiring exponential computations or time, while demonstrating real-world relevance....
Show moreOne basic goal of artificial learning systems is the ability to continually learn throughout that system’s lifetime. Transitioning between tasks and re-deploying prior knowledge is thus a desired feature of artificial learning. However, in the deep-learning approaches, the problem of catastrophic forgetting of prior knowledge persists. As a field, we want to solve the catastrophic forgetting problem without requiring exponential computations or time, while demonstrating real-world relevance. This work proposes a novel model which uses an evolutionary algorithm similar to a meta-learning objective, that is fitted with a resource constraint metrics. Four reinforcement learning environments are considered with the shared concept of depth although the collection of environments is multi-modal. This system shows preservation of some knowledge in sequential task learning and protection of catastrophic forgetting in deep neural networks.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00013896
Subject Headings: Artificial intelligence, Deep learning (Machine learning), Reinforcement learning, Neural networks (Computer science)
Format: Document (PDF)

Title: TACKLING BIAS, PRIVACY, AND SCARCITY CHALLENGES IN HEALTH DATA ANALYTICS.
Creator: Wang, Shuwen, Zhu, Xingquan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Health data analysis has emerged as a critical domain with immense potential to revolutionize healthcare delivery, disease management, and medical research. However, it is confronted by formidable challenges, including sample bias, data privacy concerns, and the cost and scarcity of labeled data. These challenges collectively impede the development of accurate and robust machine learning models for various healthcare applications, from disease diagnosis to treatment recommendations. Sample...
Show moreHealth data analysis has emerged as a critical domain with immense potential to revolutionize healthcare delivery, disease management, and medical research. However, it is confronted by formidable challenges, including sample bias, data privacy concerns, and the cost and scarcity of labeled data. These challenges collectively impede the development of accurate and robust machine learning models for various healthcare applications, from disease diagnosis to treatment recommendations. Sample bias and specificity refer to the inherent challenges in working with health datasets that may not be representative of the broader population or may exhibit disparities in their distributions. These biases can significantly impact the generalizability and effectiveness of machine learning models in healthcare, potentially leading to suboptimal outcomes for certain patient groups. Data privacy and locality are paramount concerns in the era of digital health records and wearable devices. The need to protect sensitive patient information while still extracting valuable insights from these data sources poses a delicate balancing act. Moreover, the geographic and jurisdictional differences in data regulations further complicate the use of health data in a global context. Label cost and scarcity pertain to the often labor-intensive and expensive process of obtaining ground-truth labels for supervised learning tasks in healthcare. The limited availability of labeled data can hinder the development and deployment of machine learning models, particularly in specialized medical domains.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014336
Subject Headings: Data analytics, Data mining, Ensemble learning (Machine learning), Machine learning, Health
Format: Document (PDF)

FAU Theses and Dissertations (247)	+ -
FAU College Collections (27)	+ -
FAU Graduate Student Research (3)	+ -
Speeches (2)	+ -
HBOI Faculty Contributions (1)	+ -

Machine learning (55)	+ -
Learning, Psychology of (30)	+ -
Education--Florida (25)	+ -
Expeditionary Learning Outward Bound (25)	+ -
Neural networks (Computer science) (19)	+ -

Experiential learning (18)	+ -
Deep learning (Machine learning) (17)	+ -
Students (16)	+ -
Artificial intelligence (12)	+ -
Big data (11)	+ -
Deep learning (11)	+ -
Internship programs (10)	+ -
Algorithms (9)	+ -
Discrimination learning (9)	+ -
Academic achievement (8)	+ -
Educational leadership (8)	+ -
Machine learning. (8)	+ -
Learning (7)	+ -
Adult learning (6)	+ -
Cognition in children (6)	+ -
Data mining (6)	+ -
Education (6)	+ -
Educational tests and measurements (6)	+ -
Reinforcement learning (6)	+ -
School improvement programs (6)	+ -
Cognitive learning (5)	+ -
Learning disabled children (5)	+ -
Machine learning--Technique (5)	+ -
Motivation in education (5)	+ -
Nonprofit organizations (5)	+ -

United States (5)	+ -
Florida (3)	+ -
Academic achievement--Florida--Palm Beach County (1)	+ -
Children with disabilities--Education--United States (1)	+ -
Cognitive styles--Florida--Palm Beach County--Case studies (1)	+ -

Educational accountability--United States (1)	+ -
Individualized instruction--Florida--Palm Beach County--Case studies (1)	+ -
Learning disabled children--Education--United States (1)	+ -
Mathematics--Study and teaching (Middle school)--Florida--Palm Beach County--Case studies (1)	+ -
Seminole Indians--Florida (1)	+ -
Special education--United States--Evaluation (1)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Collection

Topical Subject

Geographic Subject

Genre Subject

Title as Subject

Genre

Type of Resource

Language

Creator

Format

Owner