Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Machine learning (3)
- Rotorcraft (3)
- Affine transform (2)
- Artificial Intelligence (2)
- Artificial intelligence (2)
-
- Computer Vision (2)
- Computer vision (2)
- Cyberattacks (2)
- Deep Learning (2)
- Deep learning (2)
- Machine Learning (2)
- Action Graph (1)
- Active Distribution Network (1)
- Adaptive Game (1)
- Adversarial Defense (1)
- Adversarial Machine Learning (1)
- Algorithms (1)
- Analog; Blind Source Separation; Computing; Electronic; Neural Networks; Photonic (1)
- Anomaly detection (1)
- Artificial Intelligence; Catastrophic Forgetting; Continual Learning; Deep Learning; Machine Learning; Neuroscience (1)
- Assessment (1)
- Augmented Reality (AR) (1)
- Autoencoder; BotNets; Cyber Security; Ensemble Learning; Intrusion Detection; Machine Learning (1)
- Biomedical devices (1)
- Biometrics (1)
- Bound states in the continuum (1)
- Cable coatings (1)
- Cavity resonators (1)
- Cockpit display (1)
- Computational algorithms (1)
Articles 1 - 30 of 94
Full-Text Articles in Engineering
Low-Power Sensor Design And Fusion To Edge Devices For High-Speed Object Detection And Enhanced Soldier Situational Awareness, Scott Patrick Wood
Low-Power Sensor Design And Fusion To Edge Devices For High-Speed Object Detection And Enhanced Soldier Situational Awareness, Scott Patrick Wood
Theses and Dissertations
Threat detection and physiological monitoring of soldiers from fused sensor data collected in real time is currently limited to running deep neural networks with substantial computing needs. The lack of data acquisition from sensor readings and efficient detection of novel enemy signatures motivates the need for a low-power, low-cost, wireless multisensor fusion computing system. We propose the current trends in Internet of Things to deploy a chargeable, wireless multi-channel acquisition system that can be interfaced to a high speed, Single Board Computer (SBC) such as the NVIDIA Jetson Orin capable of running object detection models, such as YOLOv7-tiny to enable …
Design And Implementation Of Truly Random Number Generation Using Memristors For In-Memory Computing, Nick Felker
Design And Implementation Of Truly Random Number Generation Using Memristors For In-Memory Computing, Nick Felker
Theses and Dissertations
This paper proposes a new security module based on non-volatile memory. The module uses a memristor-based true random number generator to generate random numbers which can be used for cryptography. The module is implemented in software using a modified RISC-V instruction set architecture. The paper evaluates the performance of the module using the RISC-V simulator Gem5. The results show that the module can generate random numbers at a rate of 63 microseconds per number, which is faster than the standard C library’s random number generator. The module can also be used to scramble strings of characters and generate hashes of …
Matrix Processing With Photonic Analog Computing, James Michael Garofolo
Matrix Processing With Photonic Analog Computing, James Michael Garofolo
Theses and Dissertations
In the digital age, a wide variety of engineering problems have been solved, to a great deal of success, by digital computing techniques. The flexibility of software and relatively low cost of digital computing hardware make it an ideal starting point for solving a majority of tasks, and the numerical stability of software solutions make it highly appealing as the major workhorse for computational tasks. Despite this, many problems are actually suboptimally solved by digital methods, leading to systems with high latency, low throughput, power hungry parallel processing units and an excess of memory for discretizing sensor inputs. Computational photonic …
Federated Learning Based Autoencoder Ensemble System For Malware Detection On Internet Of Things Devices, Steven Edward Arroyo
Federated Learning Based Autoencoder Ensemble System For Malware Detection On Internet Of Things Devices, Steven Edward Arroyo
Theses and Dissertations
New technologies are being introduced at a rate faster than ever before and smaller in size. Due to the size of these devices, security is often difficult to implement. The existing solution is a firewall-segmented “IoT Network” that only limits the effect of these infected devices on other parts of the network. We propose a lightweight unsupervised hybrid-cloud ensemble anomaly detection system for malware detection. We perform transfer learning using a generalized model trained on multiple IoT device sources to learn network traffic on new devices with minimal computational resources. We further extend our proposed system to utilize federated learning …
Back To The Future: A Case For The Resurgence Of Approximation Theory For Enabling Data Driven “Intelligence”, Michael Dominic Ciocco
Back To The Future: A Case For The Resurgence Of Approximation Theory For Enabling Data Driven “Intelligence”, Michael Dominic Ciocco
Theses and Dissertations
Artificial Intelligence (AI) has exploded into mainstream consciousness with commercial investments exceeding $90 billion in the last year alone. Inasmuch as consumer-facing applications such ChatGPT offer astounding access to algorithms that were hitherto restricted to academic research labs, public focus of attention on AI has created an avalanche of misinformation. The nexus of investor-driven hype, “surprising” inaccuracies in the answers provided by AI models – now anthropomorphically labeled as “hallucinations”, and impending legislation by well-meaning and concerned governments has resulted in a crisis of confidence in the science of AI. The primary driver for AI’s recent growth is the convergence …
Brain-Inspired Continual Learning: Rethinking The Role Of Features In The Stability-Plasticity Dilemma, Hikmat Khan
Brain-Inspired Continual Learning: Rethinking The Role Of Features In The Stability-Plasticity Dilemma, Hikmat Khan
Theses and Dissertations
Continual learning (CL) enables deep learning models to learn new tasks sequentially while preserving performance on previously learned tasks, akin to the human's ability to accumulate knowledge over time. However, existing approaches to CL face the challenge of catastrophic forgetting, which occurs when a model's performance on previously learned tasks declines after learning the new task. In this dissertation, we focus on the crucial role of input data features in determining the robustness of CL models to mitigate catastrophic forgetting. We propose a framework to create CL-robustified versions of standard datasets using a pre-trained Oracle CL model. Our experiments show …
Better Models For High-Stakes Tasks, Jacob Ryan Epifano
Better Models For High-Stakes Tasks, Jacob Ryan Epifano
Theses and Dissertations
The intersection of machine learning and healthcare has the potential to transform medical diagnosis, treatment, and research. Machine learning models can analyze vast amounts of medical data and identify patterns that may be too complex for human analysis. However, one of the major challenges in this field is building trust between users and the model. Due to things like high false alarm rate and the black box nature of machine learning models, patients and medical professionals need to understand how the model arrives at its recommendations. In this work, we present several methods that aim to improve machine learning models …
Machine Learning-Based Drone And Aerial Threat Detection For Increased Turret Gunner Survivability, Nikolas Koutsoubis
Machine Learning-Based Drone And Aerial Threat Detection For Increased Turret Gunner Survivability, Nikolas Koutsoubis
Theses and Dissertations
The introduction of aerial drones on the modern battlefield has transformed combat operations, posing a significant threat to ground-based military operations. Detecting drones in safety scenarios is crucial. However, modern machine learning (ML)-based object detectors struggle to detect small objects like drones. This thesis presents three main contributions: (a) data and algorithmic modifications to improve small object detection in YOLO to aid in drone detection, (b) the development of a benchmark drone detection dataset called DyViR, and (c) the implementation of explainable artificial intelligence (XAI) to ensure transparent and trustworthy decision-making. To boost the performance of small object detection, we …
Adversary Aware Continual Learning, Muhammad Umer
Adversary Aware Continual Learning, Muhammad Umer
Theses and Dissertations
Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In this dissertation, we have demonstrated that continual learning approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific class at test time. We then propose a novel defensive framework to counter …
A General Model For Noisy Labels In Machine Learning, Glenn Dawson
A General Model For Noisy Labels In Machine Learning, Glenn Dawson
Theses and Dissertations
Machine learning is an ever-growing and increasingly pervasive presence in every-day life; we entrust these models, and systems built on these models, with some of our most sensitive information and security applications. However, for all of the trust that we place in these models, it is essential to recognize the fact that such models are simply reflections of the data and labels on which they are trained. To wit, if the data and labels are suspect, then so too must be the models that we rely on—yet, as larger and more comprehensive datasets become standard in contemporary machine learning, it …
Towards Optimal Operation And Control Of Emerging Electric Distribution Networks, Jimiao Zhang
Towards Optimal Operation And Control Of Emerging Electric Distribution Networks, Jimiao Zhang
Theses and Dissertations
The growing integration of power-electronics converters enabled components causes low inertia in the evolving electric distribution networks, which also suffer from uncertainties due to renewable energy sources, electric demands, and anomalies caused by physical or cyber attacks, etc. These issues are addressed in this dissertation. First, a virtual synchronous generator (VSG) solution is provided for solar photovoltaics (PVs) to address the issues of low inertia and system uncertainties. Furthermore, for a campus AC microgrid, coordinated control of the PV-VSG and a combined heat and power (CHP) unit is proposed and validated. Second, for islanded AC microgrids composed of SGs and …
A Graph-Based Approach For Adaptive Serious Games, Nidhi G. Patel
A Graph-Based Approach For Adaptive Serious Games, Nidhi G. Patel
Theses and Dissertations
Traditional education systems are based on the one-size-fits-all approach, which lacks personalization, engagement, and flexibility necessary to meet the diverse needs and learning styles of students. This encouraged researchers to focus on exploring automated, personalized instructional systems to enhance students’ learning experiences. Motivated by this remark, this thesis proposes a personalized instructional system using a graph method to enhance a player’s learning process by preventing frustration and avoiding a monotonous experience. Our system uses a directional graph, called an action graph, for representing solutions to in-game problems based on possible player actions. Through our proposed algorithm, a serious game integrated …
An Incremental Based Approach For 3d Multi-Angle Point Cloud Stitching Using Icp And Knn, Pankti K. Patel
An Incremental Based Approach For 3d Multi-Angle Point Cloud Stitching Using Icp And Knn, Pankti K. Patel
Theses and Dissertations
The basic principle of stitching is joining or merging any two materials or objects. 3D point cloud stitching is basically stitching two 3D point cloud together. 3D point cloud stitching is an emerging topic and there are multiple ways to achieve it. There are various methods for stitching which all have changes throughout the time. The existing methods do have shortcomings and have ignored the multiangle stitching of a same model or an object. This shortfall leads to many deficiencies in the ability of a stitching algorithm to maintain accuracy over the period. In this work I have introduced a …
Efficient Scopeformer: Towards Scalable And Rich Feature Extraction For Intracranial Hemorrhage Detection Using Hybrid Convolution And Vision Transformer Networks, Yassine Barhoumi
Efficient Scopeformer: Towards Scalable And Rich Feature Extraction For Intracranial Hemorrhage Detection Using Hybrid Convolution And Vision Transformer Networks, Yassine Barhoumi
Theses and Dissertations
The field of medical imaging has seen significant advancements through the use of artificial intelligence (AI) techniques. The success of deep learning models in this area has led to the need for further research. This study aims to explore the use of various deep learning algorithms and emerging modeling techniques to improve training paradigms in medical imaging. Convolutional neural networks (CNNs) are the go-to architecture for computer vision problems, but they have limitations in mapping long-term dependencies within images. To address these limitations, the study explores the use of techniques such as global average pooling and self-attention mechanisms. Additionally, the …
Design Of A Non-Destructive System For Arctic Permafrost Detection Via High Frequency Electromagnetic Induction, Gray Dominic Thurston
Design Of A Non-Destructive System For Arctic Permafrost Detection Via High Frequency Electromagnetic Induction, Gray Dominic Thurston
Theses and Dissertations
Electromagnetic induction (EMI) sensors have been utilized in the past by the United States Army Corps of Engineers as a method of detecting unexploded ordnance (UXO). Recently, an EMI instrument was constructed that extended the traditional EMI frequency range from 100 kHz to 15 MHz to aid in the detection of nonmetallic ordnance, landmines, and improvised explosive devices. Building on this research, the iFROST mapper project aims to use the same high-frequency (HF) EMI technique to characterize arctic soil and subsurface permafrost deposits. Based on a device used by the US Army for UXO detection, an HF EMI instrument was …
Using Dielectric Scatters To Selectively Excite Embedded Eigenstates In Cavity Resonators, Olugbenga Joshua Gbidi
Using Dielectric Scatters To Selectively Excite Embedded Eigenstates In Cavity Resonators, Olugbenga Joshua Gbidi
Theses and Dissertations
Bound states in the continuum (BICs) are waves that remain in the continuous spectrum of radiating waves that carry energy, however, still localized within the spectrum. BICs, also embedded eigenmodes, exhibit high quality factors that have been observed in optical and acoustic waveguides, photonic structures, and other material systems. Presently, there are limited means to select these BICs in terms of the quality factor and their excitation. In this work, we show that a different type of BIC, Quasi-BICs (Q-BICs), in open resonators can have their quality attuned by introducing embedded scatters. Using microwave cavities and dielectric scatters as an …
Investigation Of Polymer Nanocomposites With Silicon Dioxide Fillers As Helium Cooled High-Temperature Superconducting Cable Dielectrics, Jordan Thomas Cook
Investigation Of Polymer Nanocomposites With Silicon Dioxide Fillers As Helium Cooled High-Temperature Superconducting Cable Dielectrics, Jordan Thomas Cook
Theses and Dissertations
In this thesis, three polymer nanocomposite configurations are fabricated for investigation as dielectrics in helium-cooled high-temperature superconducting (HTS) cables. Polyimide, polyamide, and polymethyl methacrylate are utilized as host polymers. The composite samples are synthesized through an in situ process, dispersing silicon dioxide nanoparticles throughout the polymer hosts. Fourier transform infrared spectroscopy and scanning electron microscopy were employed to validate the synthesis of each composite configuration. Thin film samples of each configuration were also tested for their dielectric strength at both room (300 K) and cryogenic (92 K) temperatures. When going from room to cryogenic temperatures, all materials demonstrated a significant …
Low Temperature Dielectric Strength Of Polyimide-Silica Nanocomposites For Applications In High-Temperature Superconducting Cables, Michael John Mccaffrey
Low Temperature Dielectric Strength Of Polyimide-Silica Nanocomposites For Applications In High-Temperature Superconducting Cables, Michael John Mccaffrey
Theses and Dissertations
Gaseous helium is often considered as an alternative to liquid nitrogen to cool modern high-temperature superconducting cables in support of increased power capacity and/or reduction of required cable size. However, the small size of helium molecules and relatively poor dielectric strength of helium gas create challenges which limit the usefulness of modern cable dielectrics. Continuous dielectric coatings have been considered as an alternative to traditional lapped tape dielectrics to support gaseous helium refrigerants, but unmatched thermal contraction between the coating and cable components would induce failures due to mechanical stress. Composite materials have been considered as a means of matching …
A Machine Learning Framework For Automatic Speech Recognition In Air Traffic Control Using Word Level Binary Classification And Transcription, Fowad Shahid Sohail
A Machine Learning Framework For Automatic Speech Recognition In Air Traffic Control Using Word Level Binary Classification And Transcription, Fowad Shahid Sohail
Theses and Dissertations
Advances in Artificial Intelligence and Machine learning have enabled a variety of new technologies. One such technology is Automatic Speech Recognition (ASR), where a machine is given audio and transcribes the words that were spoken. ASR can be applied in a variety of domains to improve general usability and safety. One such domain is Air Traffic Control (ATC). ASR in ATC promises to improve safety in a mission critical environment. ASR models have historically required a large amount of clean training data. ATC environments are noisy and acquiring labeled data is a difficult, expertise dependent task. This thesis attempts to …
A Broad Spectrum Defense Against Adversarial Examples, Sean Mcguire
A Broad Spectrum Defense Against Adversarial Examples, Sean Mcguire
Theses and Dissertations
Machine learning models are increasingly employed in making critical decisions across a wide array of applications. As our dependence on these models increases, it is vital to recognize their vulnerability to malicious attacks from determined adversaries. In response to these adversarial attacks, new defensive mechanisms have been developed to ensure the security of machine learning models and the accuracy of the decisions they make. However, many of these mechanisms are reactionary, designed to defend specific models against a known specific attack or family of attacks. This reactionary approach does not generalize to future "yet to be developed" attacks. In this …
A Deep Learning Approach For Airport Runway Identification From Satellite Imagery, Mahmut Gemici
A Deep Learning Approach For Airport Runway Identification From Satellite Imagery, Mahmut Gemici
Theses and Dissertations
The United States lacks a comprehensive national database of private Prior Permission Required (PPR) airports. The primary reason such a database does not exist is that there are no federal regulatory obligations for these facilities to have their information re-evaluated or updated by the Federal Aviation Administration (FAA) or the local state Department of Transportation (DOT) once the data has been entered into the system. The often outdated and incorrect information about landing sites presents a serious risk factor in aviation safety. In this thesis, we present a machine learning approach for detecting airport landing sites from Google Earth satellite …
Detection Of Rotorcraft Landing Sites: An Ai-Based Approach, Abdullah Nasir
Detection Of Rotorcraft Landing Sites: An Ai-Based Approach, Abdullah Nasir
Theses and Dissertations
The updated information about the location and type of rotorcraft landing sites is an essential asset for the Federal Aviation Administration (FAA) and the Department of Transportation (DOT). However, acquiring, verifying, and regularly updating information about landing sites is not straightforward. The lack of current and correct information about landing sites is a risk factor in several rotorcraft accidents and incidents. The current FAA database of rotorcraft landing sites contains inaccurate and missing entries due to the manual updating process. There is a need for an accurate and automated validation tool to identify landing sites from satellite imagery. This thesis …
Augmenting Heads-Up Displays With Intelligent Agents: A Human Factors Approach, Grant Edward Morfitt
Augmenting Heads-Up Displays With Intelligent Agents: A Human Factors Approach, Grant Edward Morfitt
Theses and Dissertations
Situational awareness, both tactical and strategic, is essential for humans engaged in complex tasks in civilian and military theaters of operation. Previous work has shown that heads-up displays are effective tools for providing critical information to operators in such situations. Hitherto, heads-up displays have been designed to relay instrument and sensor information to the operator in a topical, timely, and accurate manner. There is a large body of complementary work in the area of human factors that deals with presenting information to a user without detracting from the primary mission. This thesis investigates, measures, and validates the effectiveness of a …
Image Processing Algorithms For Detection Of Anomalies In Orthopedic Surgery Implants, Alexander William Wiese
Image Processing Algorithms For Detection Of Anomalies In Orthopedic Surgery Implants, Alexander William Wiese
Theses and Dissertations
Orthopedic implant procedures for hip implants are performed on 300,000 patients annually in the United States, with 22.3 million procedures worldwide. While most such operations are successfully performed to relieve pain and restore joint function for the duration of the patient's life, advances in medicine have enabled patients to outlive the life of their implant, increasing the likelihood of implant failure. There is significant advantage to the patient, the surgeon, and the medical community in early detection of implant failures.The research work presented in this thesis demonstrates a non-invasive digital image processing technique for the automated detection of specific arthroplasty …
Enhancing Situational Awareness For Rotorcraft Pilots Using Virtual And Augmented Reality, Ardit Pranvoku
Enhancing Situational Awareness For Rotorcraft Pilots Using Virtual And Augmented Reality, Ardit Pranvoku
Theses and Dissertations
Rotorcraft pilots often face the challenge of processing a multitude of data, integrating it with prior experience and making informed decisions in complex, rapidly changing multisensory environments. Virtual Reality (VR), and more recently Augmented Reality (AR) technologies have been applied for providing users with immersive, interactive and navigable experiences. The research work described in this thesis demonstrates that VR/AR are particularly effective in providing real-time information without detracting from the pilot's mission in both civilian and military engagements. The immersion of the pilot inside of the VR model provides enhanced realism. Interaction with the VR environment allows pilots to practice …
Unsupervised Learning For Anomaly Detection In Remote Sensing Imagery, Husam A. Alfergani
Unsupervised Learning For Anomaly Detection In Remote Sensing Imagery, Husam A. Alfergani
Theses and Dissertations
Landfill fire is a potential hazard of waste mismanagement, and could occur both on and below the surface of active and closed sites. Timely identification of temperature anomalies is critical in monitoring and detecting landfill fires, to issue warnings that can help extinguish fires at early stages. The overarching objective of this research is to demonstrate the applicability and advantages of remote sensing data, coupled with machine learning techniques, to identify landfill thermal states that can lead to fire, in the absence of onsite observations. This dissertation proposed unsupervised learning techniques, notably variational auto-encoders (VAEs), to identify temperature anomalies from …
Helipad Detection From Satellite Imagery Using Convolutional Neural Networks, David Specht
Helipad Detection From Satellite Imagery Using Convolutional Neural Networks, David Specht
Theses and Dissertations
Location data about U.S. heliports is often inaccurate or nonexistent in the FAA's databases, which leaves pilots and air ambulance operators with inaccurate information about where to find safe landing zones. In the 2018 FAA Reauthorization Act, Congress required the FAA to collect better information from the helicopter industry under part 157, which covers the construction, alteration, activation and deactivation of airports and heliports. At the same time, there is no requirement to report private helipads to the FAA when constructed or removed, and some public heliports do not have up to date records. This thesis proposes an autonomous system …
The Matrix Revisited: A Critical Assessment Of Virtual Reality Technologies For Modeling, Simulation, And Training, George Demetrius Lecakes
The Matrix Revisited: A Critical Assessment Of Virtual Reality Technologies For Modeling, Simulation, And Training, George Demetrius Lecakes
Theses and Dissertations
A convergence of affordable hardware, current events, and decades of research have advanced virtual reality (VR) from the research lab into the commercial marketplace. Since its inception in the 1960s, and over the next three decades, the technology was portrayed as a rarely used, high-end novelty for special applications. Despite the high cost, applications have expanded into defense, education, manufacturing, and medicine. The promise of VR for entertainment arose in the early 1990's and by 2016 several consumer VR platforms were released. With VR now accessible in the home and the isolationist lifestyle adopted due to the COVID-19 global pandemic, …
Artificial Intelligence For Helicopter Safety: Head Pose Estimation In The Cockpit, Eric William Feuerstein
Artificial Intelligence For Helicopter Safety: Head Pose Estimation In The Cockpit, Eric William Feuerstein
Theses and Dissertations
The recent impact of deep learning algorithms and their major breakthroughs on various aspects of our lives has led to the idea to investigate the application of these algorithms in different problem spaces. One of the novel areas of investigation is the aviation and air traffic control domain; as it offers a prime opportunity to enhance safety within the aviation community. Of particular importance to this community is improving the safety of rotorcraft operations, as this segment of the aviation industry is subject to a higher fatal accident rate than other segments of the industry. The improvement of safety for …
Towards Machine Self-Awareness - A Bayesian Framework For Uncertainty Propagation In Deep Neural Networks, Dimah Dera
Towards Machine Self-Awareness - A Bayesian Framework For Uncertainty Propagation In Deep Neural Networks, Dimah Dera
Theses and Dissertations
Deep neural networks (DNNs) have surpassed human-level accuracy in various fields, including object recognition and classification. However, DNNs being inherently deterministic, are unable to evaluate their confidence in the decisions. Bayesian inference provides a principled approach to reason about model confidence or uncertainty by estimating the posterior distribution of the unknown parameters. The challenge in DNNs is the multi-layer stages of non-linearities, which makes propagation of high-dimensional distributions mathematically intractable. This dissertation establishes the theoretical and algorithmic foundations of uncertainty or belief propagation by developing new deep learning models that can quantify their uncertainty in the decision and self-assess their …