Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Action Graph (1)
- Active Distribution Network (1)
- Adaptive Game (1)
- Artificial Intelligence (1)
- Artificial intelligence (1)
-
- Bound states in the continuum (1)
- Cavity resonators (1)
- Computer vision (1)
- Continual learning algorithms (1)
- Cyberattacks (1)
- Dielectric scatters (1)
- Directed Graph (1)
- Drone (1)
- Educational Game (1)
- Electromagnetic Induction (1)
- Electronics (1)
- Embedded eigenstates (1)
- Explainability AI (1)
- Geophysics (1)
- Healthcare (1)
- Iterative closest point (1)
- K-nearest neighbor (1)
- Machine Learning (1)
- Machine learning (1)
- Malicious attacks (1)
- Medical AI (1)
- Microgrid (1)
- Object Detection (1)
- Operation and Control (1)
- Personalized System (1)
Articles 1 - 10 of 10
Full-Text Articles in Engineering
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 …