View All Items

Title: Synthesis of vision-based robot calibration using moving cameras.
Creator: Wang, Kuanchih., Florida Atlantic University, Roth, Zvi S., Zhuang, Hanqi, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Robot calibration using a vision system and moving cameras is the focus of this dissertation. The dissertation contributes in the areas of robot modeling, kinematic identification and calibration measurement. The effects of perspective distortion of circular camera calibration points is analyzed. A new modified complete and parametrically continuous robot kinematic model, an evolution of the complete and parametrically continuous (CPC) model, is proposed. It is shown that the model's error...
Show moreRobot calibration using a vision system and moving cameras is the focus of this dissertation. The dissertation contributes in the areas of robot modeling, kinematic identification and calibration measurement. The effects of perspective distortion of circular camera calibration points is analyzed. A new modified complete and parametrically continuous robot kinematic model, an evolution of the complete and parametrically continuous (CPC) model, is proposed. It is shown that the model's error-model can be developed easily as the structure of this new model is very simple and similar to the Denavit-Hartenbert model. The derivation procedure of the error-model follows a systematic method that can be applied to any kind of robot arms. Pose measurement is the most crucial step in robot calibration. The use of stereo as well as mono mobile camera measurement system for collection of pose data of the robot end-effector is investigated. The Simulated Annealing technique is applied to the problem of optimal measurement configuration selection. Joint travel limits can be included in the cost function. It is shown that trapping into local minimum points can be effectively avoided by properly choosing an initial point and a temperature schedule. The concept of simultaneous calibration of camera and robot is developed and implemented as an automated process that determines the system model parameters using only the system's internal sensors. This process uses a unified mathematical model for the entire robot/camera system. The results of the kinematic identification, optimal configuration selection, and simultaneous calibration of robot and camera using the PUMA 560 robot arm have demonstrated that the modified complete and parametrically continuous model is a viable and simple modeling tool, which can achieve desired accuracy. The systematic way of modeling and performing of different kinds of vision-based robot applications demonstrated in this dissertation will pave the way for industrial standardizing of robot calibration done by the robot user on the manufacturing floor.
Show less
Date Issued: 1993
PURL: http://purl.flvc.org/fcla/dt/12339
Subject Headings: Robot vision, Robot cameras--Calibration
Format: Document (PDF)

Title: A body area network as a pre-screening surrogate to the polysomnography.
Creator: LaFleur, Sheryl, Mahgoub, Imad, Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Out of 60 million Americans suffering from sleep disorder, an estimated 18 million have sleep apnea. According to the U.S. Department of Health & Human Services, sleep apnea is a chronic condition that disrupts a patient’s sleep. While the annual cost of treating sleep apnea patients in the United States is approximately $3.18 billion (including screening costs) it is estimated that untreated sleep apnea may cause $3.4 billion in additional medical costs. A polysomnography (PSG) is an all...
Show moreOut of 60 million Americans suffering from sleep disorder, an estimated 18 million have sleep apnea. According to the U.S. Department of Health & Human Services, sleep apnea is a chronic condition that disrupts a patient’s sleep. While the annual cost of treating sleep apnea patients in the United States is approximately $3.18 billion (including screening costs) it is estimated that untreated sleep apnea may cause $3.4 billion in additional medical costs. A polysomnography (PSG) is an all-night sleep study which monitors various physical functions during sleep including electrical activity of the heart, brain wave patterns, eye movement, muscle tone, body movements, and breathing. It is currently, the most accurate and sophisticated test for the diagnosis of sleep-disordered breathing (SDB), but also, the most expensive. The cost of an overnight sleep study is estimated between $900 and $3,000. In addition, the PSG is not mobile and has to be administered outside a patient’s home. The Long QT Syndrome (LQTS) is a rhythm disorder that causes erratic (unpredictable) heartbeats. The LQTS has been linked to patients with the most severe form of sleep apnea. If LQTS is left untreated, sudden cardiac death may occur.
Show less
Date Issued: 2014
PURL: http://purl.flvc.org/fau/fd/FA00004300
Subject Headings: Neurophysiology, Nevous system -- Diseases -- Diagnosis, Polysomnography, Sleep -- Physiological aspects, Sleep apnea syndromes -- Diagnosis, Sleep disorders -- Diagnosis
Format: Document (PDF)

Title: COLLISION FREE NAVIGATION IN 3D UNSTRUCTURED ENVIRONMENTS USING VISUAL LOOMING.
Creator: Yepes, Juan David Arango, Raviv, Daniel, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Vision is a critical sense for many species, with the perception of motion being a fundamental aspect. This aspect often provides richer information than static images for understanding the environment. Motion recognition is a relatively simple computation compared to shape recognition. Many creatures can discriminate moving objects quite well while having virtually no capacity for recognizing stationary objects. Traditional methods for collision-free navigation require the reconstruction of...
Show moreVision is a critical sense for many species, with the perception of motion being a fundamental aspect. This aspect often provides richer information than static images for understanding the environment. Motion recognition is a relatively simple computation compared to shape recognition. Many creatures can discriminate moving objects quite well while having virtually no capacity for recognizing stationary objects. Traditional methods for collision-free navigation require the reconstruction of a 3D model of the environment before planning an action. These methods face numerous limitations as they are computationally expensive and struggle to scale in unstructured and dynamic environments with a multitude of moving objects. This thesis proposes a more scalable and efficient alternative approach without 3D reconstruction. We focus on visual motion cues, specifically ’visual looming’, the relative expansion of objects on an image sensor. This concept allows for the perception of collision threats and facilitates collision-free navigation in any environment, structured or unstructured, regardless of the vehicle’s movement or the number of moving objects present.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014239
Subject Headings: Motion perception (Vision), Collision avoidance systems, Visual perception
Format: Document (PDF)

Title: NOVEL KIRIGAMI-INSPIRED FLEXIBLE ROBOTIC EXTENSION FOR MOBILE PLATFORMS.
Creator: Den Ouden, Casey, Su, Tsung-Chow, Ouyang, Bing, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
Abstract/Description: Since 2010, aquaculture practices have produced 70% of global seafood consumption. However, this fast-growing sector of agriculture has yet to see the adoption of advanced technologies to improve farm operations. The Hybrid Aerial Underwater robotiCs System (HAUCS) is an Internet of Things (IoT) framework that aims to bring transformative changes to pond aquaculture. This project focuses on the latest developments in the HAUCS mobile sensing platform and field deployment. A novel rigid...
Show moreSince 2010, aquaculture practices have produced 70% of global seafood consumption. However, this fast-growing sector of agriculture has yet to see the adoption of advanced technologies to improve farm operations. The Hybrid Aerial Underwater robotiCs System (HAUCS) is an Internet of Things (IoT) framework that aims to bring transformative changes to pond aquaculture. This project focuses on the latest developments in the HAUCS mobile sensing platform and field deployment. A novel rigid Kirigami-based robotic extension subsystem was created to expand the functionality of the HAUCS platform. The primary objective of this design was to limit the surface area of an extender arm on the drone during flight operations and minimize the in-flight drag. By utilizing a novel combination of shape memory polymer (SMP) and nitinol to extend and retrieve the sensing arm, the structure was able to conserve energy while operating under varying environmental conditions.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014324
Subject Headings: Aquaculture, Sensors, Robotics
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: DEVELOPMENT OF A WEARABLE DEVICE FOR MONITORING PHYSIOLOGICAL PARAMETERS RELATED TO HEART FAILURE.
Creator: Iqbal, Sheikh Muhammad Asher, Asghar, Waseem, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Heart failure is a chronic cardiovascular disease that is caused due to the lack of blood supply from heart. This lack of blood supply leads to accumulation of the fluid in the thoracic region. Traditionally, implantable cardioverter defibrillators (ICDs) are used to treat HF and to monitor its parameters. Healthcare wearable devices (HWDs) are healthcare devices that can be worn or attached to the skin. HWD are non-invasive and low-cost means of providing healthcare at the point-of-care (POC...
Show moreHeart failure is a chronic cardiovascular disease that is caused due to the lack of blood supply from heart. This lack of blood supply leads to accumulation of the fluid in the thoracic region. Traditionally, implantable cardioverter defibrillators (ICDs) are used to treat HF and to monitor its parameters. Healthcare wearable devices (HWDs) are healthcare devices that can be worn or attached to the skin. HWD are non-invasive and low-cost means of providing healthcare at the point-of-care (POC). Herein, this dissertation discusses the development of a HWD for the monitoring of the parameters of heart failure (HF). These parameters include thoracic impedance, electrocardiogram (ECG), heart rate, oxygen saturation in blood and activity status of the subject. These are similar parameters as monitored using ICD. The dissertation will discuss the development, design, and results of the HWD.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014349
Subject Headings: Wearable technology--Design and construction, Wearable devices, Heart failure
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 EXPERIMENTAL APPROACH TO EVALUATE THE EFFECTIVENESS AND PERFORMANCE OF CHLORINE AS A DISINFECTANT FOR ENTAMOEBA DISPAR IN GROUNDWATER.
Creator: Chowdhury. Rakib Ahmed, Lashaki, Masoud Jahandar, Meeroff, Daniel E., Florida Atlantic University, Department of Civil, Environmental and Geomatics Engineering, College of Engineering and Computer Science
Abstract/Description: Deep injection well technology is a reliable and cost-effective technique to manage hazardous wastewater. However, reduced injectivity is an issue for the performance of an injection well which can happen due to the occurrence of biogeochemical clogging. A class 1 deep injection well located at the Solid Waste Authority of Palm Beach County has long suffered similar problems that occurred due to the formation of chemical precipitation and biofilm. In the case of the biofilm, the dominant...
Show moreDeep injection well technology is a reliable and cost-effective technique to manage hazardous wastewater. However, reduced injectivity is an issue for the performance of an injection well which can happen due to the occurrence of biogeochemical clogging. A class 1 deep injection well located at the Solid Waste Authority of Palm Beach County has long suffered similar problems that occurred due to the formation of chemical precipitation and biofilm. In the case of the biofilm, the dominant microorganism detected in previous work was determined to be Entamoeba dispar. The prime source of the protozoan was identified as the local groundwater, which is employed for different purposes within the solid waste facility, such as cooling water and dilution water. Therefore, it is imperative to examine the effectiveness of the commonly used disinfectant chlorine to inactivate the protozoan to eliminate biofilms and clogging. This study conducted a laboratory-based chlorination of the groundwater sample to reveal the required dosages of chlorine needed for 3.0-log inactivation of E. dispar in various temperature (20°C, 25°C, 30°C, and 35°C) and pH (6.5, 7.0, 7.5) conditions.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014439
Subject Headings: Groundwater, Entamoeba dispar, Chlorine, Injection wells
Format: Document (PDF)

Title: FACILITATING PEER-TO-PEER ENERGY TRADING THROUGH COOPERATIVE GAMES AND FUZZY INFERENCE SYSTEMS.
Creator: Lopez, Hector, Zilouchian, Ali, Abtahi, Amir, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: This dissertation proposes a utility-centric peer-to-peer (P2P) energy trading framework as an alternative to traditional net metering, aiming to resolve conflicts between distributed energy resource owners and utilities. It advocates for practical software services and dynamic payment mechanisms tailored to prosumer needs, offering an alternative to reducing net metering incentives. Additionally, it explores game theory principles to ensure equitable compensation for prosumer cooperation,...
Show moreThis dissertation proposes a utility-centric peer-to-peer (P2P) energy trading framework as an alternative to traditional net metering, aiming to resolve conflicts between distributed energy resource owners and utilities. It advocates for practical software services and dynamic payment mechanisms tailored to prosumer needs, offering an alternative to reducing net metering incentives. Additionally, it explores game theory principles to ensure equitable compensation for prosumer cooperation, driving the adoption of P2P energy markets. It also builds on demand-side payment mechanisms like NRG-X-Change by adapting it to provide fair payment distribution to prosumer coalitions. The interoperable energy storage systems with P2P trading also presented battery chemistry detection using neural network models. A fuzzy inference system is also designed to facilitate prosumers' choice in participating in P2P markets, providing flexibility for energy trading preferences. The simulation results demonstrated the effectiveness of the proposed design schemes.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014425
Subject Headings: Energy, Fuzzy systems, Cooperative game theory, Electrical engineering
Format: Document (PDF)

Title: FRAUD DETECTION IN HIGHLY IMBALANCED BIG DATA WITH NOVEL AND EFFICIENT DATA REDUCTION TECHNIQUES.
Creator: Hancock III, John T., Taghi M. Khoshgoftaar, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The rapid growth of digital transactions and the increasing sophistication of fraudulent activities have necessitated the development of robust and efficient fraud detection techniques, particularly in the financial and healthcare sectors. This dissertation focuses on the use of novel data reduction techniques for addressing the unique challenges associated with detecting fraud in highly imbalanced Big Data, with a specific emphasis on credit card transactions and Medicare claims. The highly...
Show moreThe rapid growth of digital transactions and the increasing sophistication of fraudulent activities have necessitated the development of robust and efficient fraud detection techniques, particularly in the financial and healthcare sectors. This dissertation focuses on the use of novel data reduction techniques for addressing the unique challenges associated with detecting fraud in highly imbalanced Big Data, with a specific emphasis on credit card transactions and Medicare claims. The highly imbalanced nature of these datasets, where fraudulent instances constitute less than one percent of the data, poses significant challenges for traditional machine learning algorithms. This dissertation explores novel data reduction techniques tailored for fraud detection in highly imbalanced Big Data. The primary objectives include developing efficient data preprocessing and feature selection methods to reduce data dimensionality while preserving the most informative features, investigating various machine learning algorithms for their effectiveness in handling imbalanced data, and evaluating the proposed techniques on real-world credit card and Medicare fraud datasets. This dissertation covers a comprehensive examination of datasets, learners, experimental methodology, sampling techniques, feature selection techniques, and hybrid techniques. Key contributions include the analysis of performance metrics in the context of newly available Big Medicare Data, experiments using Big Medicare data, application of a novel ensemble supervised feature selection technique, and the combined application of data sampling and feature selection. The research demonstrates that, across both domains, the combined application of random undersampling and ensemble feature selection significantly improves classification performance.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014424
Subject Headings: Fraud, Big data, Data reduction, Credit card fraud, Medicare fraud
Format: Document (PDF)

Title: Small Anodic Polarization as a Mean to Modestly Accelerate Rebar Corrosion.
Creator: da Silveira, Gabrielle Pimentel, Presuel-Moreno, Francisco, Pierre-Philippe, Beaujean, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
Abstract/Description: The study of non-invasive techniques to analyze the propagation of corrosion in steel reinforced concrete structures proves to be a great alternative to better understanding the corrosive process of rebar and increasing its useful life. The study presented in this document examines the evolution of steel reinforced concrete corrosion over time by applying a small anodic current over four samples, one with a single rebar (16X) and three with three rebars. The rebars were interconnected to...
Show moreThe study of non-invasive techniques to analyze the propagation of corrosion in steel reinforced concrete structures proves to be a great alternative to better understanding the corrosive process of rebar and increasing its useful life. The study presented in this document examines the evolution of steel reinforced concrete corrosion over time by applying a small anodic current over four samples, one with a single rebar (16X) and three with three rebars. The rebars were interconnected to apply the anodic current and accelerate their corrosion. Galvanostatic Pulse (GP) was used. This method applies a constant current pulse to the rebar for 150 seconds while monitoring the potential of the rebars. Each rebar's corrosion current was assessed using GP measurements when no anodic current was applied, and the rebars were disconnected. Sample 16X additionally underwent ultrasonic acoustic analysis by collecting the surface and rebar echo response with a transducer and modeling the sound propagation for poroelastic media with an adapted version of the novel Biot-Stoll method.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014491
Subject Headings: Reinforced concrete--Corrosion, Reinforced concrete--Analysis, Nondestructive testing
Format: Document (PDF)

Title: INFRASTRUCTURE AND METHODS FOR WIFI-BASED PASSIVE DEVICE LOCALIZATION, FINGERPRINTING, AND RE-IDENTIFICATION FOR MOBILITY INTELLIGENCE.
Creator: Mazokha, Stepan, Hallstrom, Jason O., Sklivanitis, George, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Mobility monitoring in urban environments can provide valuable insights into pedestrian and vehicle movement – where people want to go, how they get there, and the challenges they face along the way. Today, local governments can automate the acquisition of such data using video surveillance to understand the potential impact of investment and policy decisions. However, public disapproval of computer vision due to privacy concerns opens opportunities for research into alternative tools built...
Show moreMobility monitoring in urban environments can provide valuable insights into pedestrian and vehicle movement – where people want to go, how they get there, and the challenges they face along the way. Today, local governments can automate the acquisition of such data using video surveillance to understand the potential impact of investment and policy decisions. However, public disapproval of computer vision due to privacy concerns opens opportunities for research into alternative tools built with privacy constraints at the core of the design. WiFi sensing emerges as a promising solution. Modern mobile devices ubiquitously support the 802.11 standard and regularly emit WiFi probe requests for network discovery. We can passively monitor this traffic to estimate the levels of congestion in public spaces. In this dissertation, we address three fundamental research problems pertaining to developing streetscape-scale mobility intelligence: scalable infrastructure for WiFi signal capture, passive device localization, and device re-identification.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014551
Subject Headings: Deep learning (Machine learning), IEEE 802.11 (Standard), Wireless sensor networks, Computer engineering
Format: Document (PDF)

Title: NOVEL TECHNIQUES FOR HANDLING IMBALANCED DATA WITH UNSUPERVISED METHODS.
Creator: Kennedy, Robert Kwan Lee, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: In the modern data landscape, vast amounts of unlabeled data are continuously generated, necessitating development of robust unsupervised techniques for handling unlabeled data. This is the case for fraud detection and healthcare sectors analyses, where data is often significantly imbalanced. This dissertation focuses on novel techniques for handling imbalanced data, with specific emphasis on a novel unsupervised class labeling technique for unlabeled fraud detection datasets and unlabeled...
Show moreIn the modern data landscape, vast amounts of unlabeled data are continuously generated, necessitating development of robust unsupervised techniques for handling unlabeled data. This is the case for fraud detection and healthcare sectors analyses, where data is often significantly imbalanced. This dissertation focuses on novel techniques for handling imbalanced data, with specific emphasis on a novel unsupervised class labeling technique for unlabeled fraud detection datasets and unlabeled cognitive datasets. Traditional supervised machine learning relies on labeled data, which is often expensive and difficult to create, particularly in domains requiring expert input. Additionally, such datasets suffer from challenges associated with class imbalance, where one class has significantly fewer examples than another, complicating model training and significantly reducing performance. The primary objectives of this dissertation include developing a novel unsupervised cleaning method, and an innovative unsupervised class labeling method. We validate and evaluate our methods across various datasets, which include two Medicare fraud detection datasets, a credit card fraud detection dataset, and three datasets used for detecting cognitive decline. Our unique approach involves using an unsupervised autoencoder to learn from dataset features and synthesize labels. Primarily targeting imbalanced datasets, but still effective for balanced datasets, our method calculates an error metric for each instance. This metric is used to distinguish between fraudulent and legitimate cases, allowing us to assign a binary class label. To further improve label generation, we integrate an unsupervised feature selection method that ranks and identifies the most important features without using class labels.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014547
Subject Headings: Machine learning, Big data, Computer science
Format: Document (PDF)

Title: SPATIAL DEEP LEARNING APPROACH TO OLDER DRIVER CLASSIFICATION.
Creator: Boateng, Charles, Yang, KwangSoo, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Telemetry data has become a crucial resource for detecting abnormal driving behaviors, especially for elderly drivers with Mild Cognitive Impairment (MCI) or dementia. This thesis proposes a novel spatial deep learning method that combines traditional telematics features with Grid-Index Resolution (GIR) to enhance the detection of abnormal driving behavior. By utilizing grid-indexed spatial-temporal analysis, the approach aims to capture more intricate driving patterns, which are often missed...
Show moreTelemetry data has become a crucial resource for detecting abnormal driving behaviors, especially for elderly drivers with Mild Cognitive Impairment (MCI) or dementia. This thesis proposes a novel spatial deep learning method that combines traditional telematics features with Grid-Index Resolution (GIR) to enhance the detection of abnormal driving behavior. By utilizing grid-indexed spatial-temporal analysis, the approach aims to capture more intricate driving patterns, which are often missed by traditional methods that rely only on basic telematics data such as speed, direction, and distance. The methodology integrates Simple Neural Networks (SNN) to process traditional telematics features and Convolutional Neural Networks (CNN) to handle spatial relationships through grid-based data. The fusion of these two feature sets into a combined model improves the model's ability to accurately classify normal and abnormal driving behaviors. This thesis evaluates the proposed approach using a dataset collected over 3.5 years from elderly drivers, including those with MCI. Experimental results demonstrate that the combined model achieves a classification accuracy of 97%, outperforming existing methods. The findings suggest that integrating grid-based spatial-temporal analysis into deep learning models offers significant potential for improving road safety, insurance risk assessment, and targeted interventions for at-risk drivers.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014535
Subject Headings: Older automobile drivers, Telemetry, Deep learning (Machine learning), Spatial data mining
Format: Document (PDF)

Title: AN ENTITY SOLUTION FRAME (ESF) FOR AUTONOMOUS CARS.
Creator: Thapa, Bijayita, Larrondo-Petrie, Maria M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The Cyber-Physical Systems (CPSs) and Internet of Things (IoT) have become emerging and essential technologies of the past few decades that connect various heterogeneous systems and devices. Sensors and actuators are fundamental units in most CPS and IoT systems, they are used extensively in vehicle systems, smart health care systems, smart buildings and cities, and many other types of applications. The extensive use of sensors and actuators, coupled with their increasing connectivity,...
Show moreThe Cyber-Physical Systems (CPSs) and Internet of Things (IoT) have become emerging and essential technologies of the past few decades that connect various heterogeneous systems and devices. Sensors and actuators are fundamental units in most CPS and IoT systems, they are used extensively in vehicle systems, smart health care systems, smart buildings and cities, and many other types of applications. The extensive use of sensors and actuators, coupled with their increasing connectivity, exposes them to a wide range of threats. Given their integration into various systems and the use of multiple technologies, it is very useful to characterize their functions abstractly. For concreteness, we study them here in the context of autonomous cars. An autonomous car is an example of a CPS, which includes IoT applications. For instance, IoT units allow an autonomous car to be connected wirelessly to roadside units, other vehicles, and fog and cloud systems. Also, the IoT allows them to collect and share information on traffic, navigation, roads, and other aspects. An autonomous car is a complex system, not only due to its intricate design but also because it operates in a dynamic environment, interacting with other vehicles and the surrounding infrastructure. To manage these functions, it must integrate various technologies from different sources. Specifically, a diverse array of sensors and actuators is essential for the functionality of autonomous vehicles.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014533
Subject Headings: Automated vehicles, Sensors, Actuators, Automobiles--Design and construction, Automotive engineering
Format: Document (PDF)

Title: Proceedings of the ... Conference on Recent Advances in Robotics.
Creator: Conference on Recent Advances in Robotics (Boca Raton), Florida Atlantic University
PURL: http://purl.flvc.org/fau/fd/FAadvancerob
Subject Headings: Robotics -- Congresses
Format: Serial

Title: Transducer design for underwater acoustic communications using the finite element method.
Creator: Jacquemin, Jean-Philippe M. J., Florida Atlantic University, LeBlanc, Lester R.
Abstract/Description: The behavior of radially polarized free-flooded ring (FFR) transducers is studied for application in underwater acoustic communications. Theoretical models are first presented. Then the finite element method (FEM) is introduced and a FEM model for the FFR transducer is proposed. Experimental data are collected and compared to the simulation results with good correspondence. A series of FEM simulations lead then to optimum geometrical parameters for a fine-tuned FFR transducer dedicated to...
Show moreThe behavior of radially polarized free-flooded ring (FFR) transducers is studied for application in underwater acoustic communications. Theoretical models are first presented. Then the finite element method (FEM) is introduced and a FEM model for the FFR transducer is proposed. Experimental data are collected and compared to the simulation results with good correspondence. A series of FEM simulations lead then to optimum geometrical parameters for a fine-tuned FFR transducer dedicated to underwater acoustic communications. Finally, stack transducers models and the piezocomposite technology are presented as possible improvement of the present transducer.
Show less
Date Issued: 2001
PURL: http://purl.flvc.org/fcla/dt/12758
Subject Headings: Underwater acoustics, Finite element method, Transducers, Interdigital
Format: Document (PDF)

FAU Theses and Dissertations (1718)	+ -
FAU College Collections (27)	+ -

Neural networks (Computer science) (60)	+ -
Wireless communication systems (50)	+ -
Machine learning (45)	+ -
Computer software--Quality control (40)	+ -
Underwater acoustics (36)	+ -

Computer network protocols (34)	+ -
Algorithms (29)	+ -
Robotics (29)	+ -
Computer algorithms (27)	+ -
Software engineering (27)	+ -
Artificial intelligence (26)	+ -
Florida Atlantic University -- History (26)	+ -
Software measurement (26)	+ -
Finite element method (25)	+ -
Fault-tolerant computing (24)	+ -
Computer networks (23)	+ -
Computer architecture (21)	+ -
Deep learning (Machine learning) (21)	+ -
Computer security (20)	+ -
Fluid dynamics (20)	+ -
Image processing--Digital techniques (20)	+ -
Steel--Corrosion (20)	+ -
Mobile computing (19)	+ -
Cathodic protection (18)	+ -
Expert systems (Computer science) (18)	+ -
Hydrodynamics (18)	+ -
Signal processing--Digital techniques (18)	+ -
Computer software--Development (17)	+ -
Fracture mechanics (17)	+ -
Reinforced concrete--Corrosion (17)	+ -

Electronic Thesis or Dissertation (1718)	+ -
Program Review (26)	+ -
conference publication (12)	+ -

Florida Atlantic University (1744)	+ -
College of Engineering and Computer Science (1361)	+ -
Department of Computer and Electrical Engineering and Computer Science (653)	+ -
Department of Ocean and Mechanical Engineering (565)	+ -
Department of Civil, Environmental and Geomatics Engineering (142)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Collection

Topical Subject

Genre

Type of Resource

Language

Creator

Format

Owner

Document (PDF) (1756)	+ -
Serial (1)	+ -