Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Cold regions (4)
- Hydrogels (4)
- Machine Learning (4)
- Machine learning (4)
- Artificial intelligence (3)
-
- Bioprinting (3)
- Durability (3)
- Electrospinning (3)
- Nanoparticles (3)
- New Jersey (3)
- Optimization (3)
- Performance Testing (3)
- Polymer (3)
- Rotorcraft (3)
- Spinal Cord Injury (3)
- Additive Manufacturing (2)
- Affine transform (2)
- Artificial Intelligence (2)
- Asphalt Mixtures (2)
- BUILDER SMS (2)
- Bio-based (2)
- Biocompatibility (2)
- Biomaterials (2)
- Cancer (2)
- Composite (2)
- Computer Vision (2)
- Computer vision (2)
- Controlled Release (2)
- Cyberattacks (2)
- Deep Learning (2)
Articles 1 - 30 of 300
Full-Text Articles in Entire DC Network
Nanofiber-Hydrogel Composite Scaffold Fabrication Methods For Peripheral Nerve Regeneration, Jacob Lee Carter
Nanofiber-Hydrogel Composite Scaffold Fabrication Methods For Peripheral Nerve Regeneration, Jacob Lee Carter
Theses and Dissertations
Nerve graft conduits (NGCs) are a rapidly advancing field for treating peripheral nerve injuries that aim to guide the growth of regenerating axons across damaged gaps. A more effective NGC can be manufactured by combining the use of nanofibers to act as guidewires within a 3-D hydrogel that imitates the extracellular matrix of nerve tissue. Several methods have been developed to embed aligned nanofibers in an ordered architecture within a hydrogel matrix. The first method involves layer-by-layer additive manufacturing to create NGCs with rows of polycaprolactone (PCL) nanofibers surrounded by a gelatin methacrylate (GelMe) hydrogel in a 3-D structure. A …
Development Of Bio-Based Organogels For The Replacement Of Silicone Elastomers In Cosmetic & Personal Care Applications, Courtney A. Lemasney
Development Of Bio-Based Organogels For The Replacement Of Silicone Elastomers In Cosmetic & Personal Care Applications, Courtney A. Lemasney
Theses and Dissertations
Silicone elastomers (SE) are a major component in many cosmetic and personal care products, providing excellent spreading properties, leaving a dry, silky feel on the skin. Unfortunately, the manufacturing of silicone is a high energy consuming process, and these products are not biodegradable. Capryloyl/glycerin/sebacic acid (CGS) copolymers are an economical, nontoxic platform for synthesizing bio-based materials with tailored properties. These polyester networks are formed through esterification with water as its only side product. By altering feed ratios and reaction conditions, final products can vary from branched fluids to highly crosslinked elastomers. This thesis investigated controlling the crosslink density of the …
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 …
A Novel Perfused Contusion Spinal Cord Injury Model To Assess Rapid Mechanical Properties Changes After Blood Spinal Cord Barrier Breakdown, Laura De Marchi
A Novel Perfused Contusion Spinal Cord Injury Model To Assess Rapid Mechanical Properties Changes After Blood Spinal Cord Barrier Breakdown, Laura De Marchi
Theses and Dissertations
Blood-spinal cord barrier (BSCB) disruption exacerbates the tissue damage caused by spinal cord injury (SCI), but the mechanisms and dynamics of how the barrier breakdown affects the mechanical properties of the tissue remain unclear. The perfused bovine ex vivo indentation injury model described here represents a new platform to investigate the short-term effects of altered blood flow and vascular permeability following traumatic spinal cord injury. Our results indicate that injured cords exhibit changes to bulk perfusion, as evidenced by laser speckle contrast imaging, in addition to decreased barrier function shortly after injury. Indentation tests that simultaneously simulate a crush injury …
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 …
Manufacturing Of Aligned Electrospun Nanofiber Yarns For Their Enhanced Mechanical And Piezoelectric Properties, Adaugo Mary-Frances Enuka
Manufacturing Of Aligned Electrospun Nanofiber Yarns For Their Enhanced Mechanical And Piezoelectric Properties, Adaugo Mary-Frances Enuka
Theses and Dissertations
Electrospinning is a widely used technique for producing nanofibers with diverse applications. This method uses polymer solutions and strong electric fields to generate nano-sized fibers with unique properties. This study presents a novel manufacturing approach that enables the production of electrospun poly(vinylidene fluoride-co-hexafluoropropylene) (PVDF-HFP) nanofiber yarns using an automated parallel track system and an adjustable roll-to-roll collector. This research examines the impact of an automated post-drawing system on the polymer chain orientation, crystallinity, tensile strength, morphology, and piezoelectric properties of PVDF-HFP nanofiber yarn. The results reveal that the post-drawing process significantly improves molecular alignment, increases tensile strength, and enhances the …
Study Of Polymer-On-Polymer Cold Spray Deposition Windows Under Apparently Similar Conditions, Ülar Tiitma
Study Of Polymer-On-Polymer Cold Spray Deposition Windows Under Apparently Similar Conditions, Ülar Tiitma
Theses and Dissertations
The purpose of this thesis is to explore and expand the capabilities of polymer-on-polymer cold spray demonstrated herein using polyamide 6 (PA6)-based powder and substrates. Experiments were conducted using three different cold spray systems described in this work, permitting more in-depth examination of process response to different cold spray process control parameters, such as nominal system pressure and temperature. Two specific responses of interest were the deposition window (DW) and deposition efficiency (DE) of PA6. The DW was determined by performing several sprays at different calculated particle impact velocities and temperatures. The composite result from these experiments was identification of …
Hardware Acceleration Of Numerical Methods For Solving Ordinary Differential Equations, Soham Bhattacharya
Hardware Acceleration Of Numerical Methods For Solving Ordinary Differential Equations, Soham Bhattacharya
Theses and Dissertations
Along with the advancement in technology, the role of hardware accelerators is increasing consistently, delivering advancements in scientific simulations and data analysis in scientific computing, signal processing tasks in communication systems, matrix operations, and neural network computations in artificial intelligence and machine learning models. On the other hand, several high-speed computer applications in this era of high-performance computing often depend on ordinary differential equations (ODEs); however, their nonlinear nature can present a challenge to obtaining analytic solutions. Consequently, numerical approaches prove effective in delivering only approximate solutions to these equations. This research discusses the implementation of a customized hardware accelerator …
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 …
Towards A Practical Method For Monitoring Kinetic Processes In Polymers With Low-Frequency Raman Spectroscopy, Robert Vito Chimenti
Towards A Practical Method For Monitoring Kinetic Processes In Polymers With Low-Frequency Raman Spectroscopy, Robert Vito Chimenti
Theses and Dissertations
Unlike liquids and crystalline solids, glassy materials exist in a constant state of structural nonequilibrium. Therefore, a comprehensive understanding of material kinetics is critical for understanding the structure-property-processing relationships of polymeric materials. Amorphous materials universally display low-frequency Raman features related to the phonon density of states resulting in a broad disorder band for Raman shifts below 100 cm-1, which is related to the conformational entropy and the modulus. This disorder band is dominated by the Boson peak, a feature due to phonon scattering because of disorder and can be related to the transverse sound velocity of the material, and a …
Tunable Dual-Phase Dual-Drug Delivery System Using A Plga Microparticle/Pva Hydrogel Composite, Timothy John Eck
Tunable Dual-Phase Dual-Drug Delivery System Using A Plga Microparticle/Pva Hydrogel Composite, Timothy John Eck
Theses and Dissertations
Current drug-eluting coatings have demonstrated controlled long-term, sustained release but have only tried to mitigate short-term burst release as a negative side effect. For applications like wound healing, there is a need for a drug-eluting coating which is adjustable in both short- and long-term release, independent of each other. We present a tunable dual-phase dual-drug delivery coating composed of drug-loaded polymer microparticles and drug-loaded hydrogel which can control short term and long term release individually in this study. This coating was created using lidocaine and dexamethasone encapsulated in poly(D,L-lactide-co-glycolide) particles combined with lidocaine- and dexamethasone-loaded poly(vinyl alcohol) hydrogel. Hydrogel drug …
Mri Image Regression Cnn For Bone Marrow Lesion Volume Prediction, Kevin Yanagisawa
Mri Image Regression Cnn For Bone Marrow Lesion Volume Prediction, Kevin Yanagisawa
Theses and Dissertations
Bone marrow lesions (BMLs), occurs from fluid build up in the soft tissues inside your bone. This can be seen on magnetic resonance imaging (MRI) scans and is characterized by excess water signals in the bone marrow space. This disease is commonly caused by osteoarthritis (OA), a degenerative join disease where tissues within the joint breakdown over time [1]. These BMLs are an emerging target for OA, as they are commonly related to pain and worsening of the diseased area until surgical intervention is required [2]–[4]. In order to assess the BMLs, MRIs were utilized as input into a regression …
Laboratory Evaluation Of Warm Mix Additives At Lower Than Traditional Compaction Temperatures, Abdelrahman Mahmoud Waheish Ali
Laboratory Evaluation Of Warm Mix Additives At Lower Than Traditional Compaction Temperatures, Abdelrahman Mahmoud Waheish Ali
Theses and Dissertations
The study aims to evaluate the impact of warm mix additives (WMA) on the rheological and performance properties of asphalt binders and mixtures. For this purpose, PG 76-28 and PG 58-28 were obtained with one organic (Sasobit Redux) and three chemical WMA (Rediset, Evotherm, and Zycotherm). All WMA-modified asphalt binders were aged at three different aging levels. Laboratory tests such as performance grade (PG), critical temperature differential (ΔTc), asphalt binder cracking device (ABCD), linear amplitude sweep test (LAS), and Fourier transform infrared spectroscopy (FTIR) were performed. In addition to the binder testing plan, this study also evaluated the impact of …
Development Of A Xenograft For Annular Repair Using Pulsed Electric Field Exposures For Enhanced Decellularization, Prince Mensah Kwaku Atsu
Development Of A Xenograft For Annular Repair Using Pulsed Electric Field Exposures For Enhanced Decellularization, Prince Mensah Kwaku Atsu
Theses and Dissertations
Severe back injuries and chronic pain necessitate surgical replacement of damaged intervertebral disc (IVD) cartilage in advanced disease stages. Bovine IVD tissue has been exposed to an upper threshold pulsed electric field (PEF) dose, causing cell death without thermal damage to the tissue. Subsequent PEF exposures at lower magnitudes have accelerated the removal of immunogenic biomolecules though electrokinetic extraction using optimized aqueous solutions. This approach yields a natural scaffold, ready for biocompatibility and mechanical strength assessment. The effects of microsecond pulsed electric fields (µsPEF) on primary bovine AF fibroblast-like cells have been characterized in vitro. PEFs of 10 and 100 …
Cancer Treatment By Targeting Hdac4 Translocation Induced By Microsecond Pulsed Electric Field Exposure: Mechanistic Insights Through Kinases And Phosphatases, Zahra Safaei
Theses and Dissertations
Epigenetic modifications, arising from sub-cellular shifts in histone deacetylase (HDAC) activity and localization, present promising strategies for diverse cancer treatments. HDACs, enzymes responsible for post-translational histone modifications, induce these epigenetic changes by removing acetyl groups from ε-N-acetyl-lysine residues on histones, thereby suppressing gene transcription. Within the HDAC group, class IIa HDACs are notable for their responsiveness to extracellular signals, bridging the gap between external stimuli, plasma membrane, and genome through nuclear-cytoplasmic translocation. This localization offers two significant mechanisms for cancer treatment: nuclear accumulation of HDACs represses oncogenic transcription factors, such as myocyte-specific enhancer factor 2C (MEF2C), triggering various cell death …
Integrated Computer-Aided Design, Experimentation, And Optimization Approach For Perovskites And Petroleum Packaging Processes, Swapana Subbarao Jerpoth
Integrated Computer-Aided Design, Experimentation, And Optimization Approach For Perovskites And Petroleum Packaging Processes, Swapana Subbarao Jerpoth
Theses and Dissertations
According to the World Economic Forum report, the U.S. currently has an energy efficiency of just 30%, thus illustrating the potential scope and need for efficiency enhancement and waste minimization. In the U.S. energy sector, petroleum and solar energy are the two key pillars that have the potential to create research opportunities for transition to a cleaner, greener, and sustainable future. In this research endeavor, the focus is on two pivotal areas: (i) Computer-aided perovskite solar cell synthesis; and (ii) Optimization of flow processes through multiproduct petroleum pipelines. In the area of perovskite synthesis, the emphasis is on the enhancement …
A Systems Approach To Process Design And Sustainability - Synergy Via Pollution Prevention, Control, And Source Reduction, Emmanuel Apau Aboagye
A Systems Approach To Process Design And Sustainability - Synergy Via Pollution Prevention, Control, And Source Reduction, Emmanuel Apau Aboagye
Theses and Dissertations
Historically, process design prioritized efficiency and profitability, often overlooking environmental and societal implications. However, given the global challenges like climate change and resource scarcity, there is a growing emphasis on embedding sustainability into process design. Adopting a systems-oriented approach provides a comprehensive view, spanning from raw material acquisition to end-of-life product management. Such an approach not only identifies potential sustainability challenges but ensures that solutions foster both environmental responsibility and economic viability. In this study, a comprehensive framework for designing industrial systems is introduced, aiming to encompass the entire lifecycle impacts of chemical processes. The research initially delves into two …
Optimal Control Of Ion Exchange Process For Chromate Removal And Protein A Chromatography For Antibody Extraction, Fadi Ghanem
Optimal Control Of Ion Exchange Process For Chromate Removal And Protein A Chromatography For Antibody Extraction, Fadi Ghanem
Theses and Dissertations
Ion exchange resins are widely used in the extraction of hazardous chemicals as well as the recovery of precious molecules. Therefore, an early breakthrough from the resin system can lead to toxic compounds affecting the drinking water quality or inefficient use of costly resins. Hence, accurate modeling of the ion exchange process and control strategy can enable decisions that assist in avoiding leakage when facing fluctuations in the inlet contaminant concentrations. In this work, the ion exchange process is modeled via the method of moments where the system uncertainties are captured via stochastic modeling using Ito processes. The flow rate …
A New Algorithm For Encounter Generation: Encounters From Actual Trajectories (Enact), James Anthony Ritchie Iii
A New Algorithm For Encounter Generation: Encounters From Actual Trajectories (Enact), James Anthony Ritchie Iii
Theses and Dissertations
There is ongoing research at the Federal Aviation Administration (FAA) and other private industries to examine a concept for delegated separation in multiple classes of airspace to allow unmanned aircraft systems (UAS) to remain well clear of other aircraft. Detect and Avoid (DAA) capabilities are one potential technology being examined to maintain separation. To evaluate these DAA capabilities, input traffic scenarios are needed, but current approaches are limited by the breadth of the traffic recordings available. This thesis derives a new mathematical algorithm that uses great circle navigation equations in an Earth spherical model and an accurate aircraft performance model …
Evolutionary Conservation And Times Of Action Of Heterochronic Genes, Maria Ivanova
Evolutionary Conservation And Times Of Action Of Heterochronic Genes, Maria Ivanova
Theses and Dissertations
The heterochronic pathway of C. elegans is the most well-characterized system to date for controlling the sequence and timing of developmental events. However, we still have critical unanswered questions to address. First, little is known about the evolution of the heterochronic pathway, and of developmental timing in general. To determine if the roles of major heterochronic genes are conserved, I made mutants in orthologs of these genes in C. briggsae, using CRISPR/Cas9. My studies revealed a significant drift in the roles of some of the genes, although all of them are still involved in the developmental timing regulation, and several …
Advanced Processing Techniques For Electrospun Nanofibers: Investigating Annealing And Laser Zone-Drawing Effects On Material Characteristics, Matthew D. Flamini
Advanced Processing Techniques For Electrospun Nanofibers: Investigating Annealing And Laser Zone-Drawing Effects On Material Characteristics, Matthew D. Flamini
Theses and Dissertations
Electrospun nanofibers hold potential for a wide range of commercial and scientific applications; however, their properties must be optimized through post-processing treatments to achieve optimal performance. This dissertation investigates the effects of annealing and laser zone-drawing on electrospun nanofiber properties. Annealing polycaprolactone nanofibers at 70°C results in the highest rate of crystallization and molecular alignment, impacting long-term stability and mechanical properties. A multivariate linear model incorporating crystallinity and molecular alignment predicts the material properties resulting from annealing under different conditions. Laser zone-drawing experiments reveal that polylactide fiber thinning under laser irradiation primarily occurs due to drawing rather than ablation. Steady-state …
Developing A Smart And Sustainable Public Transportation System: A Case Study In Camden, New Jersey, Zahra Vafakhah
Developing A Smart And Sustainable Public Transportation System: A Case Study In Camden, New Jersey, Zahra Vafakhah
Theses and Dissertations
The transportation sector is a major contributor to air pollution and Greenhouse Gas (GHG) emissions. As a significant source of emissions, public transportation presents an opportunity for mitigation through electrification. However, transitioning to an electric bus fleet necessitates substantial investments in bus procurement and charging infrastructure. To address the associated costs, this study introduces a mixed-integer linear mathematical model developed to optimize the location of on-route fast charging stations within bus networks. The central objective of this optimization formulation is to minimize the overall cost of establishing the charging infrastructure. The study employs a real-world case study focusing on a …
Evaluation Of Digital Twin Approaches For Thermal Modeling And Energy Optimization For Existing Buildings, Jason Bastie Muermann
Evaluation Of Digital Twin Approaches For Thermal Modeling And Energy Optimization For Existing Buildings, Jason Bastie Muermann
Theses and Dissertations
Residential, commercial, and industrial building sectors in the United States were responsible for 42% of the nation’s consumption of 100.2 quadrillion BTUs of energy in 2019 [1]. 80% of the nation’s energy is sourced from fossil fuels, including coal, natural gas, and petroleum. Fossil fuels are known contributors to carbon emissions and climate change, making energy reduction vital. Consequently, New Jersey Department of Military and Veterans Affairs (NJDMAVA) is tasked with evaluating energy consumption and efficiency in all New Jersey Army National Guard (NJARNG) facilities, as mandated by TAG Policy Letter 18-5, Executive Order 13990, and the Energy Independence and …
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 …
Evaluating Frozen Soil Properties With Electrical Resistivity Measurement And Electro-Magnetic Induction Methods, Rui Liu
Theses and Dissertations
Electromagnetic induction was utilized in the past by the United States Army Corps of Engineers as a method of detecting unexploded ordinance, while it has the potential to act as a novel method of investigating frozen soils in cold regions. In this study, we performed lab-scale 1D electrical resistivity measurements under freeze-thaw circumstances on frost-susceptible soils with varied soil properties. We implemented an empirical model from our experiments into a COMSOL finite element model at both laboratory and field scales to simulate soil electrical resistivity response under both short-term and long-term sub-freezing conditions. Dynamic temperature-dependent soil properties, most notably unfrozen …
Evaluating The Permeability Of Porous Aggregate Concrete Using Electrical Resistivity-Based Measurements, Ariel Miguel Mendez Aragoncillo
Evaluating The Permeability Of Porous Aggregate Concrete Using Electrical Resistivity-Based Measurements, Ariel Miguel Mendez Aragoncillo
Theses and Dissertations
Recycled concrete aggregates (RCA) and lightweight aggregates (LWA) are popular alternative aggregates for concrete. However, due to their highly porous structure, concrete with RCA and LWA shows a different microstructure and higher permeability than conventional concrete. Thus, the existing relationships used to evaluate the permeability and, consequently, the durability of concrete are not applicable in concretes with RCA and LWA. This research examined the permeation properties of recycled aggregate concrete (RAC) and lightweight aggregate concrete (LWAC). The relationships between electrical resistivity-based measurements in RAC and LWAC and their permeation properties were determined and compared to that of normal weight aggregate …
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 …