Current Search: Department of Computer and Electrical Engineering and Computer Science (x)
View All Items
(1 - 20 of 785)
Pages
- Title
- Feature selection techniques and applications in bioinformatics.
- Creator
- Dittman, David, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Possibly the largest problem when working in bioinformatics is the large amount of data to sift through to find useful information. This thesis shows that the use of feature selection (a method of removing irrelevant and redundant information from the dataset) is a useful and even necessary technique to use in these large datasets. This thesis also presents a new method in comparing classes to each other through the use of their features. It also provides a thorough analysis of the use of...
Show morePossibly the largest problem when working in bioinformatics is the large amount of data to sift through to find useful information. This thesis shows that the use of feature selection (a method of removing irrelevant and redundant information from the dataset) is a useful and even necessary technique to use in these large datasets. This thesis also presents a new method in comparing classes to each other through the use of their features. It also provides a thorough analysis of the use of various feature selection techniques and classifier in different scenarios from bioinformatics. Overall, this thesis shows the importance of the use of feature selection in bioinformatics.
Show less - Date Issued
- 2011
- PURL
- http://purl.flvc.org/FAU/3175016
- Subject Headings
- Bioinformatifcs, Data mining, Technological innovations, Computational biology, Combinatorial group theory, Filters (Mathematics), Ranking and selection (Statistics)
- Format
- Document (PDF)
- Title
- TOWARDS DEPLOYABLE QUANTUM-SAFE CRYPTOSYSTEMS.
- Creator
- Koziel, Brian, Azarderakhsh, Reza, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
It is well known that in the near future, a large-scale quantum computer will be unveiled, one that could be used to break the cryptography that underlies our digital infrastructure. Quantum computers operate on quantum mechanics, enabling exponential speedups to certain computational problems, including hard problems at the cornerstone of our deployed cryptographic algorithms. With a vulnerability in this security foundation, our online identities, banking information, and precious data is...
Show moreIt is well known that in the near future, a large-scale quantum computer will be unveiled, one that could be used to break the cryptography that underlies our digital infrastructure. Quantum computers operate on quantum mechanics, enabling exponential speedups to certain computational problems, including hard problems at the cornerstone of our deployed cryptographic algorithms. With a vulnerability in this security foundation, our online identities, banking information, and precious data is now vulnerable. To address this, we must prepare for a transition to post-quantum cryptography, or cryptosystems that are protected from attacks by both classical and quantum computers. This is a dissertation proposal targeting cryptographic engineering that is necessary to deploy isogeny-based cryptosystems, one known family of problems that are thought to be difficult to break, even for quantum computers. Isogeny-based cryptography utilizes mappings between elliptic curves to achieve public-key encryption, digital signatures, and other cryptographic objectives necessary to support our digital infrastructure's security. This proposal focuses on three aspects of isogeny-based cryptography: 1) cryptographic engineering of isogeny-based cryptosystems; 2) developing and optimizing security-enabling isogeny applications; and 3) improving the security from known and emerging implementation attacks. By improving each of these aspects, we are providing confidence in the deployability of isogeny-based cryptography and helping to prepare for a post-quantum transition.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013998
- Subject Headings
- Cryptography, Quantum computers
- Format
- Document (PDF)
- Title
- EFFICIENT AND SECURE IMPLEMENTATION OF CLASSIC AND POST-QUANTUM PUBLIC-KEY CRYPTOGRAPHY.
- Creator
- Bisheh, Niasar Mojtaba, Azarderakhsh, Reza, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
To address the increased interest in crypto hardware accelerators due to performance and efficiency concerns, implementing hardware architectures of different public-key cryptosystems has drawn growing attention. Pure hardware methodology enhances architecture’s performance over a hardware/software co-design scheme at the cost of a more extended design cycle, reducing the flexibility, and demands customized data paths for different protocol-level operations. However, using pure hardware...
Show moreTo address the increased interest in crypto hardware accelerators due to performance and efficiency concerns, implementing hardware architectures of different public-key cryptosystems has drawn growing attention. Pure hardware methodology enhances architecture’s performance over a hardware/software co-design scheme at the cost of a more extended design cycle, reducing the flexibility, and demands customized data paths for different protocol-level operations. However, using pure hardware architecture makes the design smaller, faster, and more efficient. This dissertation mainly focuses on designing crypto accelerators that can be used in embedded systems and Internet-of-Things (IoT) devices where performance and efficiency are critical as a hardware accelerator to offload computations from the microcontroller units (MCU). In particular, our objective is to create a system-on-chip (SoC) crypto-accelerator with an MCU that achieves high area-time efficiency. Our implementation can also be integrated as an off-chip solution; however, other criteria, such as performance, are often as important or more important than efficiency in the external crypto-chip design, which is beyond of this work. Not only does our architecture inherently provide protection against timing and simple power analysis (SPA) attacks, but also some advanced security mechanisms to avoid differential power analysis (DPA) attacks are included, which is missing in the literature. In a nutshell, the contributions are summarized as follows:
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013981
- Subject Headings
- Cryptography, Public key cryptography, Curves, Elliptic, Quantum computers
- 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
- OPTIMIZING ECC IMPLEMENTATIONS ON EMBEDDED DEVICES.
- Creator
- Owens, Daniel, Azarderakhsh, Reza, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
As the cryptographic community turns its focus toward post-quantum cryptography, the demand for classical cryptographic schemes such as Elliptic Curve Cryptography (ECC) remains high. ECC is mature, well studied, and used in a wide range of applications such as securing visits to web pages through a web browser, Bitcoin, and the Internet of Things (IoT). In this work we present an optimized implementation of the Edwards Curve Digital Signature Algorithm (EdDSA) operations Key Generation and...
Show moreAs the cryptographic community turns its focus toward post-quantum cryptography, the demand for classical cryptographic schemes such as Elliptic Curve Cryptography (ECC) remains high. ECC is mature, well studied, and used in a wide range of applications such as securing visits to web pages through a web browser, Bitcoin, and the Internet of Things (IoT). In this work we present an optimized implementation of the Edwards Curve Digital Signature Algorithm (EdDSA) operations Key Generation and Sign using the Ed25519 parameter on the ARM Cortex-M4, and we discuss the optimization of field and group arithmetic to produce high throughput cryptographic primitives. In addition, we discuss several techniques for optimizing scalar multiplication, and present timing and memory consumption for each, as well as comparisons to other works. Our fastest implementation performs an Ed25519 Key Generation operation in 250,785 cycles and signing in 435,426 cycles utilizing 6.1 kB of additional Read Only Memory (ROM) space.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014027
- Subject Headings
- Cryptography, Embedded Internet devices
- Format
- Document (PDF)
- Title
- EFFICIENT IMPLEMENTATION OF POST-QUANTUM CRYPTOGRAPHY.
- Creator
- Elkhatib, Rami, Azarderakhsh, Reza, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Cryptography relies on hard mathematical problems that current conventional computers cannot solve in a feasible amount of time. On the other hand, quantum computers, with their quantum mechanic construction, are presumed to be able to solve some of these problems in a reasonable amount of time. More specifically, the current hard problems that public key cryptography relies upon are expected to be easily broken during the quantum era, a time when large-scale quantum computers are available....
Show moreCryptography relies on hard mathematical problems that current conventional computers cannot solve in a feasible amount of time. On the other hand, quantum computers, with their quantum mechanic construction, are presumed to be able to solve some of these problems in a reasonable amount of time. More specifically, the current hard problems that public key cryptography relies upon are expected to be easily broken during the quantum era, a time when large-scale quantum computers are available. To address this problem ahead of time, researchers and institutions have proposed post-quantum cryptography (PQC), which is an area of research that focuses on quantum-resistant public key cryptography algorithms. One of the candidates in the NIST PQC standardization process is SIKE, an isogeny-based candidate. The main advantage of SIKE is that it provides the smallest key size out of all the NIST PQC candidates at the cost of performance. Therefore, the development of hardware accelerators for SIKE is very important to achieve high performance in time-constrained applications. In this thesis, we implement several accelerators for SIKE and its primitives using different design approaches, all of which are suitable for different applications. We deliver significant enhancements to SIKE’s most expensive component, the modular multiplier. We design SIKE using a hardware-based approach and a software-hardware codesign approach, the latter of which utilizes a RISC-V processor. We also design SIKE with multi-level security level support for applications that require support of multiple security levels with minimal area usage. We enclose our performance and area results, which provide a reference to evaluate our work with other implementations.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013986
- Subject Headings
- Cryptography, Quantum computers, Cryptography--Mathematics
- Format
- Document (PDF)
- Title
- IMAGE QUALITY AND BEAUTY CLASSIFICATION USING DEEP LEARNING.
- Creator
- Golchubian, Arash, Nojoumian, Mehrdad, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
The field of computer vision has grown by leaps and bounds in the past decade. The rapid advances can be largely attributed to advances made in the field of Artificial Neural Networks and more specifically can be attributed to the rapid advancement of Convolutional Neural Networks (CNN) and Deep Learning. One area that is of great interest to the research community at large is the ability to detect the quality of images in the sense of technical parameters such as blurriness, encoding...
Show moreThe field of computer vision has grown by leaps and bounds in the past decade. The rapid advances can be largely attributed to advances made in the field of Artificial Neural Networks and more specifically can be attributed to the rapid advancement of Convolutional Neural Networks (CNN) and Deep Learning. One area that is of great interest to the research community at large is the ability to detect the quality of images in the sense of technical parameters such as blurriness, encoding artifacts, saturation, and lighting, as well as for its’ aesthetic appeal. The purpose of such a mechanism could be detecting and discarding noisy, blurry, dark, or over exposed images, as well as detecting images that would be considered beautiful by a majority of viewers. In this dissertation, the detection of various quality and aesthetic aspects of an image using CNNs is explored. This research produced two datasets that are manually labeled for quality issues such as blur, poor lighting, and digital noise, and for their aesthetic qualities, and Convolutional Neural Networks were designed and trained using these datasets. Lastly, two case studies were performed to show the real-world impact of this research to traffic sign detection and medical image diagnosis.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014029
- Subject Headings
- Deep learning (Machine learning), Computer vision, Aesthetics, Image Quality
- Format
- Document (PDF)
- Title
- INTELLIGENT OPERATION OF ROBOTIC ARMS BASED ON TURTLEBOT3 MOBILE ROBOTS.
- Creator
- Veit, Connor, Zhong, Xiangnan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
As technology progresses, tasks involving object manipulation that were once conducted by humans are now being accomplished through robots. Specifically, robots carry out these goals through the utilization of different forms of artificial intelligence, including deep learning via a convolutional neural network. One robot made to accomplish this purpose is the ROS controlled TurtleBot3 Waffle Pi with an OpenMANIPULATOR-X robotic arm. This type of TurtleBot3 was developed with the express...
Show moreAs technology progresses, tasks involving object manipulation that were once conducted by humans are now being accomplished through robots. Specifically, robots carry out these goals through the utilization of different forms of artificial intelligence, including deep learning via a convolutional neural network. One robot made to accomplish this purpose is the ROS controlled TurtleBot3 Waffle Pi with an OpenMANIPULATOR-X robotic arm. This type of TurtleBot3 was developed with the express purpose of education and research but may not be limited to those two usages. Based on the current design of this classification of TurtleBot3, it may have multiple applications outside the testing environment, granting it further uses in a variety of tasks. The TurtleBot3 is easy to setup to fulfill the purposes for which the TurtleBot3 Waffle Pi was designed, and the exploration into further uses would allow for the discovery of alternatives to some tasks that normally require more work. For that reason, this thesis was conducted to determine the various uses of the TurtleBot3 with a robotic arm and if this robot can be used outside of a testing environment for various real-world tasks.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014026
- Subject Headings
- Robotics, Artificial intelligence, Mobile robots
- Format
- Document (PDF)
- Title
- DECENTRALIZED SYSTEMS FOR INFORMATION SHARING IN DYNAMIC ENVIRONMENT USING LOCALIZED CONSENSUS.
- Creator
- Zamir, Linir, Nojoumian, Mehrdad, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Achieving a consensus among a large number of nodes has always been a challenge for any decentralized system. Consensus algorithms are the building blocks for any decentralized network that is susceptible to malicious activities from authorized and unauthorized nodes. Proof-of-Work is one of the first modern approaches to achieve at least a 51% consensus, and ever since many new consensus algorithms have been introduced with different approaches of consensus achievement. These decentralized...
Show moreAchieving a consensus among a large number of nodes has always been a challenge for any decentralized system. Consensus algorithms are the building blocks for any decentralized network that is susceptible to malicious activities from authorized and unauthorized nodes. Proof-of-Work is one of the first modern approaches to achieve at least a 51% consensus, and ever since many new consensus algorithms have been introduced with different approaches of consensus achievement. These decentralized systems, also called blockchain systems, have been implemented in many applications such as supply chains, medical industry, and authentication. However, it is mostly used as a cryptocurrency foundation for token exchange. For these systems to operate properly, they are required to be robust, scalable, and secure. This dissertation provides a different approach of using consensus algorithms for allowing information sharing among nodes in a secured fashion while maintaining the security and immutability of the consensus algorithm. The consensus algorithm proposed in this dissertation utilizes a trust parameter to enforce cooperation, i.e., a trust value is assigned to each node and it is monitored to prevent malicious activities over time. This dissertation also proposes a new solution, named localized consensus, as a method that allows nodes in small groups to achieve consensus on information that is only relevant to that small group of nodes, thus reducing the bandwidth of the system. The proposed models can be practical solutions for immense and highly dynamic environments with validation through trust and reputation values. Application for such localized consensus can be communication among autonomous vehicles where traffic data is relevant to only a small group of vehicles and not the entirety of the system.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014028
- Subject Headings
- Blockchain, Consensus algorithms
- Format
- Document (PDF)
- Title
- REAL-TIME HIGHWAY TRAFFIC FLOW AND ACCIDENT SEVERITY PREDICTION IN VEHICULAR NETWORKS USING DISTRIBUTED MACHINE LEARNING AND BIG DATA ANALYSIS.
- Creator
- Alnami, Hani Mohammed, Mahgoub, Imadeldin, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
In recent years, Florida State recorded thousands of abnormal traffic flows on highways that were caused by traffic incidents. Highway traffic congestion costed the US economy 101 billion dollars in 2020. Therefore, it is imperative to develop effective real-time traffic flow prediction schemes to mitigate the impact of traffic congestion. In this dissertation, we utilized real-life highway segment-based traffic and incident data obtained from Florida Department of Transportation (FDOT) for...
Show moreIn recent years, Florida State recorded thousands of abnormal traffic flows on highways that were caused by traffic incidents. Highway traffic congestion costed the US economy 101 billion dollars in 2020. Therefore, it is imperative to develop effective real-time traffic flow prediction schemes to mitigate the impact of traffic congestion. In this dissertation, we utilized real-life highway segment-based traffic and incident data obtained from Florida Department of Transportation (FDOT) for real-time incident prediction. We used eight years of FDOT real-life traffic and incident data for Florida I-95 highway to build prediction models for traffic accident severity. Accurate severity prediction is beneficial for responders since it allows the emergency center to dispatch the right number of vehicles without wasting additional resources.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014089
- Subject Headings
- Traffic flow, Traffic accidents, Machine learning, Big data, Traffic estimation
- Format
- Document (PDF)
- Title
- PATH PLANNING FOR THE HYBRID AERIAL UNDERWATER ROBOTIC SYSTEM.
- Creator
- Davis, Anthony C., Ouyang, Bing, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Marine food chains are highly stressed by aggressive fishing practices and environmental damage. Aquaculture has increasingly become a source of seafood which spares the deleterious impact to wild fisheries, but it requires continuous water quality data to successfully grow and harvest fish. Aerial drones have great potential to monitor large areas quickly and efficiently. The Hybrid Aerial Underwater Robotic System (HAUCS) is a swarm of unmanned aerial vehicles (UAVs) and underwater...
Show moreMarine food chains are highly stressed by aggressive fishing practices and environmental damage. Aquaculture has increasingly become a source of seafood which spares the deleterious impact to wild fisheries, but it requires continuous water quality data to successfully grow and harvest fish. Aerial drones have great potential to monitor large areas quickly and efficiently. The Hybrid Aerial Underwater Robotic System (HAUCS) is a swarm of unmanned aerial vehicles (UAVs) and underwater measurement devices designed to collect water quality data of aquaculture ponds. The routing of drones to cover each fish pond on an aquaculture farm can be reduced to the Vehicle Routing Problem (VRP). A dataset is created to simulate the distribution of ponds on a farm and is used to assess the HAUCS Path Planning Algorithm (HPP). Its performance is compared with the Google Linear Optimization Package (GLOP) and a Graph Attention Model (GAM) for routing around the simulated farms. The three methods are then implemented on a team of waterproof drones and experimentally verified at Southern Illinois University’s (SIU) Aquaculture Research Center. GLOP and GAM are demonstrated to be efficient path planning methods for small farms, while HPP is likely to be more suited to large farms. HAUCS shows great value as a future direction for intelligent aquaculture, but issues with obstacle avoidance and robust waterproofing need to be addressed before commercialization. The future of aquaculture promises more integrated and sustainable operations by mimicking natural systems and leveraging deeper understandings of biology.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014108
- Subject Headings
- Drone aircraft, Drones, Aquaculture
- 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
- EMBEDDING LEARNING FOR COMPLEX DYNAMIC INFORMATION NETWORKS.
- Creator
- Wu, Man, Zhu, Xingquan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
With the rapid development of networking platforms and data intensive applications, networks (or graphs) are becoming convenient and fundamental tools to model the complex inter-dependence among big scale data. As a result, networks (or graphs) are being widely used in many applications, including citation networks [40], social media networks [71], and so on. However, the high complexity (containing many important information) as well as the dynamic nature of the network makes the graph...
Show moreWith the rapid development of networking platforms and data intensive applications, networks (or graphs) are becoming convenient and fundamental tools to model the complex inter-dependence among big scale data. As a result, networks (or graphs) are being widely used in many applications, including citation networks [40], social media networks [71], and so on. However, the high complexity (containing many important information) as well as the dynamic nature of the network makes the graph learning task more difficult. To have better graph representations (capture both node content and graph structure), many research efforts have been made to develop reliable and efficient algorithms. Therefore, the good graph representation learning is the key factor in performing well on downstream tasks. The dissertation mainly focuses on the graph representation learning, which aims to embed both structure and node content information of graphs into a compact and low dimensional space for a new representation learning. More specifically, in order to achieve an efficient and robust graph representation, the following four problems will be studied from different perspectives: 1) We study the problem of positive unlabeled graph learning for network node classification, and present a new deep learning model as a solution; 2) We formulate a new open-world learning problem for graph data, and propose an uncertain node representation learning approach and sampling strategy to solve the problem; 3) For cross-domain graph learning, we present a novel unsupervised graph domain adaptation problem, and propose an effective graph convolutional network algorithm to solve it; 4) We consider a dynamic graph as a network with changing nodes and edges in temporal order and propose a temporal adaptive aggregation network (TAAN) for dynamic graph learning. Finally, the proposed models are verified and evaluated on various real-world datasets.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014066
- Subject Headings
- Neural networks (Computer science), Machine learning, Graphs, Embeddings (Mathematics)
- Format
- Document (PDF)
- Title
- A FRAMEWORK FOR NON-INTRUSIVE OCEAN CURRENT TURBINE ROTOR BLADE IMBALANCE FAULT DETECTION.
- Creator
- Freeman, Brittny, Tang, Yufei, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Ocean current turbines (OCT) convert the kinetic energy housed within the earth’s ocean currents into electricity. However, due to the harsh environmental conditions that these turbines operate in, their system performance naturally degrades over time. This degradation correlates to high operation and maintenance (O&M) costs, which necessitates the need for robust condition monitoring and fault detection (CMFD). Unfortunately, OCT operational data is not publicly available in large and/or...
Show moreOcean current turbines (OCT) convert the kinetic energy housed within the earth’s ocean currents into electricity. However, due to the harsh environmental conditions that these turbines operate in, their system performance naturally degrades over time. This degradation correlates to high operation and maintenance (O&M) costs, which necessitates the need for robust condition monitoring and fault detection (CMFD). Unfortunately, OCT operational data is not publicly available in large and/or diverse enough quantities to develop such frameworks. Therefore, from an industry-wide perspective, the technologies needed to harvest this energy source are still in their infancy.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014094
- Subject Headings
- Marine turbines, Marine turbines--Blades
- Format
- Document (PDF)
- Title
- ANALYSIS OF DRIVING BEHAVIORS AND RELEVANT DRIVING PREFERENCES REGARDING SELF-DRIVING CARS.
- Creator
- Tolbert, Steven William, Nojoumian, Mehrdad, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
This thesis explores the cross-cultural demands from self-driving cars in regards to their trust, safety, and driving styles. Through the use of international survey data we establish several AI trust and behavior metrics that can be used for understanding cross-cultural expectations from self-driving cars that can potentially address problems of trust between passengers and self-driving cars, social acceptability of self-driving cars, and development of customized autonomous driving...
Show moreThis thesis explores the cross-cultural demands from self-driving cars in regards to their trust, safety, and driving styles. Through the use of international survey data we establish several AI trust and behavior metrics that can be used for understanding cross-cultural expectations from self-driving cars that can potentially address problems of trust between passengers and self-driving cars, social acceptability of self-driving cars, and development of customized autonomous driving technologies. Further this thesis provides a serverless data-collection framework for future research in driving behaviors.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014115
- Subject Headings
- Automated vehicles, Automated vehicles--Social aspects, Artificial intelligence, Human-machine systems
- Format
- Document (PDF)
- Title
- DIGITAL TRANSFORMATION OF HEALTHCARE USING ARTIFICIAL INTELLIGENCE.
- Creator
- Gogova, Jennifer, Marques, Oge, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Digital transformation is rapidly changing the healthcare industry, and artificial intelligence (AI) is a critical component in this evolution. This thesis investigates three selected challenges that might delay the adoption of AI in healthcare and proposes ways to address them successfully. Challenge #1 states that healthcare professionals may not feel sufficiently knowledgeable about AI. This is addressed by Contribution #1 which is a guide for self-actualization in AI for healthcare...
Show moreDigital transformation is rapidly changing the healthcare industry, and artificial intelligence (AI) is a critical component in this evolution. This thesis investigates three selected challenges that might delay the adoption of AI in healthcare and proposes ways to address them successfully. Challenge #1 states that healthcare professionals may not feel sufficiently knowledgeable about AI. This is addressed by Contribution #1 which is a guide for self-actualization in AI for healthcare professionals. Challenge #2 explores the concept of transdisciplinary teams needing a work protocol to deliver successful results. This is addressed by Contribution #2 which is a step-by-step protocol for medical and AI researchers working on data-intensive projects. Challenge #3 states that the NIH All of Us Research Hub has a steep learning curve, and this is addressed by Contribution #3 which is a pilot project involving transdisciplinary teams using All of Us datasets.
Show less - Date Issued
- 2023
- PURL
- http://purl.flvc.org/fau/fd/FA00014179
- Subject Headings
- Healthcare, Medical care, Artificial intelligence—Medical applications
- Format
- Document (PDF)
- Title
- INVESTIGATING AND IMPROVING FAIRNESS AND BIAS IN MACHINE LEARNING MODELS FOR DERMATOLOGY.
- Creator
- Corbin, Adam, Marques, Oge, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Advancements in Artificial Intelligence (AI) and Machine Learning (ML) have significantly improved their application in dermatology. However, bias issues in AI systems can result in missed diagnoses and disparities in healthcare, especially for individuals with different skin types. This dissertation aims to investigate and improve the fairness and bias in machine learning models for dermatology by evaluating and enhancing their performance across different Fitzpatrick skin types. The...
Show moreAdvancements in Artificial Intelligence (AI) and Machine Learning (ML) have significantly improved their application in dermatology. However, bias issues in AI systems can result in missed diagnoses and disparities in healthcare, especially for individuals with different skin types. This dissertation aims to investigate and improve the fairness and bias in machine learning models for dermatology by evaluating and enhancing their performance across different Fitzpatrick skin types. The technical contributions of the dissertation include generating metadata for Fitzpatrick Skin Type using Individual Typology Angle; outlining best practices for Explainable AI (XAI) and the use of colormaps; developing and enhancing ML models through skin color transformation and extending the models to include XAI methods for better interpretation and improvement of fairness and bias; and providing a list of steps for successful application of deep learning in medical image analysis. The research findings of this dissertation have the potential to contribute to the development of fair and unbiased AI/ML models in dermatology. This can ultimately lead to better health outcomes and reduced healthcare costs, particularly for individuals with different skin types.
Show less - Date Issued
- 2023
- PURL
- http://purl.flvc.org/fau/fd/FA00014131
- Subject Headings
- Diagnostic Imaging, Machine learning, Dermatology, Artificial intelligence
- Format
- Document (PDF)
- Title
- FEDERATED LEARNING FOR MEDICAL IMAGE CLASSIFICATION.
- Creator
- Blazanovic, Danica, Zhu, Xingquan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Machine learning (ML) has traditionally been used to make predictive models by training on local data. However, due to concerns regarding privacy, it is not always possible to collect and combine data from different sources. On the other hand, if there are insufficient data available, it might not be possible to construct accurate models to produce meaningful outcomes. This is where Federated Learning comes to the rescue. Federated Learning (FL) represents a sophisticated distributed machine...
Show moreMachine learning (ML) has traditionally been used to make predictive models by training on local data. However, due to concerns regarding privacy, it is not always possible to collect and combine data from different sources. On the other hand, if there are insufficient data available, it might not be possible to construct accurate models to produce meaningful outcomes. This is where Federated Learning comes to the rescue. Federated Learning (FL) represents a sophisticated distributed machine learning strategy that enables multiple devices hosted at different institutions such as hospitals, to collaboratively train a global model while ensuring that their respective data remains securely stored on-premises. It addresses privacy concerns and data protection regulations, because raw data does not need to be shared or centralized during the training process. This thesis research studies how two different FL architectures, centralized and decentralized FL, affect medical image classification. To study and validate the findings, skin cancer images dataset is used in a federated learning setting with five sites/clients, and a center for centralized FL. Experimental results show that using both centralized and decentralized (peer to peer) version of FL for classification of skin cancer images outperforms using the traditional ML. In addition, two different FL settings, centralized federated learning (CFL) and decentralized federated learning (DFL), are compared using different data distributions across sites/clients. Our study shows that the best accuracy (95.14%) was achieved with the DFL model when tested on the original dataset (without adding bias to the class distributions). This asserts that class distribution imbalance between sites has a significant impact to the federated learning.
Show less - Date Issued
- 2023
- PURL
- http://purl.flvc.org/fau/fd/FA00014205
- Subject Headings
- Medical imaging, Diagnostic Imaging--classification, Machine learning
- Format
- Document (PDF)
- Title
- NETWORK INTRUSION DETECTION AND DEEP LEARNING MECHANISMS.
- Creator
- Chatterjee, Suvosree, Cardei, Ionut, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Cyber attack is a strong threat to the digital world. So, it’s very essential to keep the network safe. Network Intrusion Detection system is the system to address this problem. Network Intrusion Detection system functions like a firewall, and monitors incoming and outgoing traffic like ingress and egress filtering fire wall. Network Intrusion Detection System does anomaly and hybrid detection for detecting known and unknown attacks. My thesis discusses about the several network cyber attacks...
Show moreCyber attack is a strong threat to the digital world. So, it’s very essential to keep the network safe. Network Intrusion Detection system is the system to address this problem. Network Intrusion Detection system functions like a firewall, and monitors incoming and outgoing traffic like ingress and egress filtering fire wall. Network Intrusion Detection System does anomaly and hybrid detection for detecting known and unknown attacks. My thesis discusses about the several network cyber attacks we face nowadays and I created several Deep learning models to detect accurately, I used NSL-KDD dataset which is a popular dataset, that contains several network attacks. After experimenting with different deep learning models I found some disparities in the training accuracy and validation accuracy, which is a clear indication of overfitting. To reduce the overfitting I introduced regularization and dropout in the models and experimented with different hyperparameters.
Show less - Date Issued
- 2023
- PURL
- http://purl.flvc.org/fau/fd/FA00014128
- Subject Headings
- Deep learning (Machine learning), Cyberterrorism, Intrusion detection systems (Computer security)
- Format
- Document (PDF)
- Title
- A UNIFIED SOFT SENSING FRAMEWORK FOR COMPLEX DYNAMICAL SYSTEMS.
- Creator
- Huang, Yu, Tang, Yufei, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
In the past few years, the development of complex dynamical networks or systems has stimulated great interest in the study of the principles and mechanisms underlying the Internet of things (IoT). IoT is envisioned as an intelligent network infrastructure with a vast number of ubiquitous smart devices present in diverse application domains and have already improved many aspects of daily life. Many overtly futuristic IoT applications acquire data gathered via distributed sensors that can be...
Show moreIn the past few years, the development of complex dynamical networks or systems has stimulated great interest in the study of the principles and mechanisms underlying the Internet of things (IoT). IoT is envisioned as an intelligent network infrastructure with a vast number of ubiquitous smart devices present in diverse application domains and have already improved many aspects of daily life. Many overtly futuristic IoT applications acquire data gathered via distributed sensors that can be uniquely identified, localized, and communicated with, i.e., the support of sensor networks. Soft-sensing models are in demand to support IoT applications to achieve the maximal exploitation of transforming the information of measurements into more useful knowledge, which plays essential roles in condition monitoring, quality prediction, smooth control, and many other essential aspects of complex dynamical systems. This in turn calls for innovative soft-sensing models that account for scalability, heterogeneity, adaptivity, and robustness to unpredictable uncertainties. The advent of big data, the advantages of ever-evolving deep learning (DL) techniques (where models use multiple layers to extract multi-levels of feature representations progressively), as well as ever-increasing processing power in hardware, has triggered a proliferation of research that applies DL to soft-sensing models. However, many critical questions need to be further investigated in the deep learning-based soft-sensing.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013993
- Subject Headings
- Dynamical systems, Dynamics, Sensor networks, Deep learning (Machine learning)
- Format
- Document (PDF)
