Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Air Force Institute of Technology

Discipline
Keyword
Publication Year
Publication
Publication Type

Articles 451 - 480 of 2678

Full-Text Articles in Physical Sciences and Mathematics

Neural Network Models For Nuclear Treaty Monitoring: Enhancing The Seismic Signal Pipeline With Deep Temporal Convolution, Joshua T. Dickey Jun 2020

Neural Network Models For Nuclear Treaty Monitoring: Enhancing The Seismic Signal Pipeline With Deep Temporal Convolution, Joshua T. Dickey

Theses and Dissertations

Seismic signal processing at the IDC is critical to global security, facilitating the detection and identification of covert nuclear tests in near-real time. This dissertation details three research studies providing substantial enhancements to this pipeline. Study 1 focuses on signal detection, employing a TCN architecture directly against raw real-time data streams and effecting a 4 dB increase in detector sensitivity over the latest operational methods. Study 2 focuses on both event association and source discrimination, utilizing a TCN-based triplet network to extract source-specific features from three-component seismograms, and providing both a complimentary validation measure for event association and a one-shot …

Go to article

Securing Photovoltaic (Pv) System Deployments With Data Diodes, Robert D. Larkin, Torrey J. Wagner, Barry E. Mullins Jun 2020

Securing Photovoltaic (Pv) System Deployments With Data Diodes, Robert D. Larkin, Torrey J. Wagner, Barry E. Mullins

Faculty Publications

A survey of a typical photovoltaic (PV) system with and without the cybersecurity protections of a data diode is explored. This survey includes a brief overview of Industrial Control Systems (ICS) and their relationship to the Internet of Things (IoT), Industrial Internet of Things (IIoT), and Industry 4.0 terminology. The cybersecurity features of eight data diodes are compared, and the cyber attack surface, attack scenarios, and mitigations of a typical PV system are discussed. After assessing cybersecurity, the economic considerations to purchase a data diode are considered. At 13.19 cents/kWh, the sale of 227,445 kWh is needed to fund one …

Go to article

A Physics-Based Machine Learning Study Of The Behavior Of Interstitial Helium In Single Crystal W–Mo Binary Alloys, Adib J. Samin May 2020

A Physics-Based Machine Learning Study Of The Behavior Of Interstitial Helium In Single Crystal W–Mo Binary Alloys, Adib J. Samin

Faculty Publications

In this work, the behavior of dilute interstitial helium in W–Mo binary alloys was explored through the application of a first principles-informed neural network (NN) in order to study the early stages of helium-induced damage and inform the design of next generation materials for fusion reactors. The neural network (NN) was trained using a database of 120 density functional theory (DFT) calculations on the alloy. The DFT database of computed solution energies showed a linear dependence on the composition of the first nearest neighbor metallic shell. This NN was then employed in a kinetic Monte Carlo simulation, which took into …

Go to article

Machine Learning Modeling Of Horizontal Photovoltaics Using Weather And Location Data, Christil Pasion, Torrey J. Wagner, Clay Koschnick, Steven J. Schuldt, Jada B. Williams, Kevin Hallinan May 2020

Machine Learning Modeling Of Horizontal Photovoltaics Using Weather And Location Data, Christil Pasion, Torrey J. Wagner, Clay Koschnick, Steven J. Schuldt, Jada B. Williams, Kevin Hallinan

Faculty Publications

Solar energy is a key renewable energy source; however, its intermittent nature and potential for use in distributed systems make power prediction an important aspect of grid integration. This research analyzed a variety of machine learning techniques to predict power output for horizontal solar panels using 14 months of data collected from 12 northern-hemisphere locations. We performed our data collection and analysis in the absence of irradiation data—an approach not commonly found in prior literature. Using latitude, month, hour, ambient temperature, pressure, humidity, wind speed, and cloud ceiling as independent variables, a distributed random forest regression algorithm modeled the combined …

Go to article

Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing [*], Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola Apr 2020

Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing [*], Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola

Faculty Publications

Atmospheric compensation of long-wave infrared (LWIR) hyperspectral imagery is investigated in this article using set representations learned by a neural network. This approach relies on synthetic at-sensor radiance data derived from collected radiosondes and a diverse database of measured emissivity spectra sampled at a range of surface temperatures. The network loss function relies on LWIR radiative transfer equations to update model parameters. Atmospheric predictions are made on a set of diverse pixels extracted from the scene, without knowledge of blackbody pixels or pixel temperatures. The network architecture utilizes permutation-invariant layers to predict a set representation, similar to the work performed …

Go to article

Single-Pulse, Kerr-Effect Mueller Matrix Lidar Polarimeter, Keyser, Christian K., Richard K. Martin, Helena Lopez-Aviles, Khanh Nguyen, Arielle M. Adams, Demetrios Christodoulides Apr 2020

Single-Pulse, Kerr-Effect Mueller Matrix Lidar Polarimeter, Keyser, Christian K., Richard K. Martin, Helena Lopez-Aviles, Khanh Nguyen, Arielle M. Adams, Demetrios Christodoulides

Faculty Publications

We present a novel light detection and ranging (LiDAR) polarimeter that enables measurement of 12 of 16 sample Mueller matrix elements in a single, 10 ns pulse. The new polarization state generator (PSG) leverages Kerr phase modulation in a birefringent optical fiber, creating a probe pulse characterized by temporally varying polarization. Theoretical expressions for the Polarization State Generator (PSG) Stokes vector are derived for birefringent walk-off and no walk-off and incorporated into a time-dependent polarimeter signal model employing multiple polarization state analyzers (PSA). Polarimeter modeling compares the Kerr effect and electro-optic phase modulator–based PSG using a single Polarization State Analyzer …

Go to article

Experimental Determination Of The (0/−) Level For Mg Acceptors In Β-Ga2O3 Crystals, Christopher A. Lenyk, Trevor A . Gustafson, Sergey A. Basun, Larry E. Halliburton, Nancy C. Giles Apr 2020

Experimental Determination Of The (0/−) Level For Mg Acceptors In Β-Ga2O3 Crystals, Christopher A. Lenyk, Trevor A . Gustafson, Sergey A. Basun, Larry E. Halliburton, Nancy C. Giles

Faculty Publications

Electron paramagnetic resonance (EPR) is used to experimentally determine the (0/−) level of the Mg acceptor in an Mg-doped β-Ga2O3 crystal. Our results place this level 0.65 eV (±0.05 eV) above the valence band, a position closer to the valence band than the predictions of several recent computational studies. The crystal used in this investigation was grown by the Czochralski method and contains large concentrations of Mg acceptors and Ir donors, as well as a small concentration of Fe ions and an even smaller concentration of Cr ions. Below room temperature, illumination with 325 nm laser light …

Go to article

Cyber-Physical System Intrusion: A Case Study Of Automobile Identification Vulnerabilities And Automated Approaches For Intrusion Detection, David R. Crow Mar 2020

Cyber-Physical System Intrusion: A Case Study Of Automobile Identification Vulnerabilities And Automated Approaches For Intrusion Detection, David R. Crow

Theses and Dissertations

Today's vehicle manufacturers do not tend to publish proprietary packet formats for the controller area network (CAN), a network protocol regularly used in automobiles and manufacturing. This is a form of security through obscurity -it makes reverse engineering efforts more difficult for would-be intruders -but obfuscating the CAN data in this way does not adequately hide the vehicle's unique signature, even if these data are unprocessed or limited in scope. To prove this, we train two distinct deep learning models on data from 11 different vehicles. Our results clearly indicate that one can determine which vehicle generated a given sample …

Go to article

One-Dimensional Multi-Frame Blind Deconvolution Using Astronomical Data For Spatially Separable Objects, Marc R. Brown Mar 2020

One-Dimensional Multi-Frame Blind Deconvolution Using Astronomical Data For Spatially Separable Objects, Marc R. Brown

Theses and Dissertations

Blind deconvolution is used to complete missions to detect adversary assets in space and to defend the nation's assets. A new algorithm was developed to perform blind deconvolution for objects that are spatially separable using multiple frames of data. This new one-dimensional approach uses the expectation-maximization algorithm to blindly deconvolve spatially separable objects. This object separation reduces the size of the object matrix from an NxN matrix to two singular vectors of length N. With limited knowledge of the object and point spread function the one-dimensional algorithm successfully deconvolved the objects in both simulated and laboratory data.

Go to article

Relational Database Design And Multi-Objective Database Queries For Position Navigation And Timing Data, Sean A. Mochocki Mar 2020

Relational Database Design And Multi-Objective Database Queries For Position Navigation And Timing Data, Sean A. Mochocki

Theses and Dissertations

Performing flight tests is a natural part of researching cutting edge sensors and filters for sensor integration. Unfortunately, tests are expensive, and typically take many months of planning. A sensible goal would be to make previously collected data readily available to researchers for future development. The Air Force Institute of Technology (AFIT) has hundreds of data logs potentially available to aid in facilitating further research in the area of navigation. A database would provide a common location where older and newer data sets are available. Such a database must be able to store the sensor data, metadata about the sensors, …

Go to article

Object Detection With Deep Learning To Accelerate Pose Estimation For Automated Aerial Refueling, Andrew T. Lee Mar 2020

Object Detection With Deep Learning To Accelerate Pose Estimation For Automated Aerial Refueling, Andrew T. Lee

Theses and Dissertations

Remotely piloted aircraft (RPAs) cannot currently refuel during flight because the latency between the pilot and the aircraft is too great to safely perform aerial refueling maneuvers. However, an AAR system removes this limitation by allowing the tanker to directly control the RP A. The tanker quickly finding the relative position and orientation (pose) of the approaching aircraft is the first step to create an AAR system. Previous work at AFIT demonstrates that stereo camera systems provide robust pose estimation capability. This thesis first extends that work by examining the effects of the cameras' resolution on the quality of pose …

Go to article

Sliver: Simulation-Based Logic Bomb Identification/Verification For Unmanned Aerial Vehicles, Jake M. Magness Mar 2020

Sliver: Simulation-Based Logic Bomb Identification/Verification For Unmanned Aerial Vehicles, Jake M. Magness

Theses and Dissertations

This research introduces SLIVer, a Simulation-based Logic Bomb Identification/Verification methodology, for finding logic bombs hidden within Unmanned Aerial Vehicle (UAV) autopilot code without having access to the device source code. Effectiveness is demonstrated by executing a series of test missions within a high-fidelity software-in-the-loop (SITL) simulator. In the event that a logic bomb is not detected, this methodology defines safe operating areas for UAVs to ensure to a high degree of confidence the UAV operates normally on the defined flight plan. SLIVer uses preplanned flight paths as the baseline input space, greatly reducing the input space that must be searched …

Go to article

Extracting Range Data From Images Using Focus Error, Erik M. Madden Mar 2020

Extracting Range Data From Images Using Focus Error, Erik M. Madden

Theses and Dissertations

Air-to-air refueling (AAR) has become a staple when performing long missions with aircraft. With modern technology, however, people have begun to research how to perform this task autonomously. Automated air-to-air refueling (A3R) is this exact concept. Combining many different systems, the idea is to allow computers on the aircraft to link up via the refueling boom, refuel, and detach before resuming pilot control. This document lays out one of the systems that is needed to perform A3R, namely, the system that extracts range data. While stereo cameras perform such tasks, there is interest in finding other ways of accomplishing the …

Go to article

Newhope: A Mobile Implementation Of A Post-Quantum Cryptographic Key Encapsulation Mechanism, Jessica A. Switzler Mar 2020

Newhope: A Mobile Implementation Of A Post-Quantum Cryptographic Key Encapsulation Mechanism, Jessica A. Switzler

Theses and Dissertations

NIST anticipates the appearance of large-scale quantum computers by 2036 [34], which will threaten widely used asymmetric algorithms, National Institute of Standards and Technology (NIST) launched a Post-Quantum Cryptography Standardization Project to find quantum-secure alternatives. NewHope post-quantum cryptography (PQC) key encapsulation mechanism (KEM) is the only Round 2 candidate to simultaneously achieve small key values through the use of a security problem with sufficient confidence its security, while mitigating any known vulnerabilities. This research contributes to NIST project’s overall goal by assessing the platform flexibility and resource requirements of NewHope KEMs on an Android mobile device. The resource requirements analyzed …

Go to article

A General Methodology To Optimize And Benchmark Edge Devices, Kyle J. Smathers Mar 2020

A General Methodology To Optimize And Benchmark Edge Devices, Kyle J. Smathers

Theses and Dissertations

The explosion of Internet Of Things (IoT), embedded and “smart” devices has also seen the addition of “general purpose” single board computers also referred to as “edge devices.” Determining if one of these generic devices meets the need of a new given task however can be challenging. Software generically written to be portable or plug and play may be too bloated to work properly without significant modification due to much tighter hardware resources. Previous work in this area has been focused on micro or chip-level benchmarking which is mainly useful for chip designers or low level system integrators. A higher …

Go to article

An Analysis Of A Lighting Prediction Threshold For 45th Weather Squadron Electric Field Mill Data, Charles A. Skrovan Mar 2020

An Analysis Of A Lighting Prediction Threshold For 45th Weather Squadron Electric Field Mill Data, Charles A. Skrovan

Theses and Dissertations

The mission of the 45th Weather Squadron (45 WS) is to “exploit the weather to assure safe access to air and space” for Patrick Air Force Base, Cape Canaveral Air Force Station (CCAFS), and Kennedy Space Center (KSC) in support of various operations (United States Air Force, n.d.). To support that mission the 45 WS hosts a suite of weather detection instruments that include a lightning warning system that consists of an array of 31 electric field mills (EFM) and a lightning detection and ranging system (Department of the Air Force, 1976). Electric field mills at Cape Canaveral continuously record …

Go to article

Validation Technique For Modeled Bottomside Ionospheres Via Ray Tracing, Kevin S. Burg Mar 2020

Validation Technique For Modeled Bottomside Ionospheres Via Ray Tracing, Kevin S. Burg

Theses and Dissertations

A new method for validating ionosphere models using High Frequency (HF) angle of arrival (AoA) data is presented. AoA measurements from a field campaign held at White Sands Missile Range, New Mexico, USA in January 2014 provide the actual elevation angle, azimuth and group delay results from 10 transmitter-receiver circuits. Simulated AoAs are calculated by ray tracing through the electron density profiles predicted from the ionosphere models hosted by NASA's Community Coordinated Modeling Center: IRI-2016, USU-GAIM, GITM, CTIPe, TIE-GCM, and SAMI3. Through the implementation of metrics including Mean Absolute Error, Prediction Efficiency, Correlation Coefficient, and others, we are able to …

Go to article

Comparison Of Visual Simultaneous Localization And Mapping Methods For Fixed-Wing Aircraft Using Slambench2, Patrick R. Latcham Mar 2020

Comparison Of Visual Simultaneous Localization And Mapping Methods For Fixed-Wing Aircraft Using Slambench2, Patrick R. Latcham

Theses and Dissertations

Visual Simultaneous Localization and Mapping (VSLAM) algorithms have evolved rapidly in the last few years, however there has been little research evaluating current algorithm's effectiveness and limitations when applied to tracking the position of a fixed-wing aerial vehicle. This research looks to evaluate current monocular VSLAM algorithms' performance on aerial vehicle datasets using the SLAMBench2 benchmarking suite. The algorithms tested are MonoSLAM, PTAM, OKVIS, LSDSLAM, ORB-SLAM2, and SVO, all of which are built into the SLAMBench2 software. The algorithms' performance is evaluated using simulated datasets generated in the AftrBurner Engine. The datasets were designed to test the quality of each …

Go to article

Applying Data Organizational Techniques To Enhance Air Force Learning, Jacob A. Orner Mar 2020

Applying Data Organizational Techniques To Enhance Air Force Learning, Jacob A. Orner

Theses and Dissertations

The USAF and the DoD use traditional schoolhouses to educate and train personnel. The physical aspects of these schoolhouses limit throughput. A method to increase throughput is to shift towards an asynchronous learning environment where students move through content at individually. This research introduces a methodology for transforming a set of unstructured documents into an organized TM students can use to orient themselves in a domain. The research identifies learning paths within the TM to create a directed KSAT. We apply this methodology in four case studies, each an education or training course. Using a graph comparison metric and the …

Go to article

Conceptualization And Application Of Deep Learning And Applied Statistics For Flight Plan Recommendation, Nicholas C. Forrest Mar 2020

Conceptualization And Application Of Deep Learning And Applied Statistics For Flight Plan Recommendation, Nicholas C. Forrest

Theses and Dissertations

The Air Forces Pilot Training Next (PTN) program seeks a more efficient pilot training environment emphasizing the use of virtual reality flight simulators alongside periodic real aircraft experience. The PTN program wants to accelerate the training pace and progress in undergraduate pilot training compared to traditional undergraduate pilot training. Currently, instructor pilots spend excessive time planning and scheduling flights. This research focuses on methods to auto-generate the planning of in-flight events using hybrid filtering and deep learning techniques. The resulting approach captures temporal trends of user-specific and program-wide student performance to recommend a feasible set of graded flight events for …

Go to article

Modeling Nonlinear Heat Transfer For A Pin-On-Disc Sliding System, Brian A. Boardman Mar 2020

Modeling Nonlinear Heat Transfer For A Pin-On-Disc Sliding System, Brian A. Boardman

Theses and Dissertations

The objective of this research is to develop a numerical method to characterize heat transfer and wear rates for samples of Vascomax® 300, or Maraging 300, steel. A pin-on-disc experiment was conducted in which samples were exposed to a high-pressure, high-speed, sliding contact environment. This sliding contact generates frictional heating that influences the temperature distribution and wear characteristics of the test samples. A two-dimensional nonlinear heat transfer equation is discretized and solved via a second-order explicit finite difference scheme to predict the transient temperature distribution of the pin. This schematic is used to predict the removal of material from the …

Go to article

Event-Based Visual-Inertial Odometry Using Smart Features, Zachary P. Friedel Mar 2020

Event-Based Visual-Inertial Odometry Using Smart Features, Zachary P. Friedel

Theses and Dissertations

Event-based cameras are a novel type of visual sensor that operate under a unique paradigm, providing asynchronous data on the log-level changes in light intensity for individual pixels. This hardware-level approach to change detection allows these cameras to achieve ultra-wide dynamic range and high temporal resolution. Furthermore, the advent of convolutional neural networks (CNNs) has led to state-of-the-art navigation solutions that now rival or even surpass human engineered algorithms. The advantages offered by event cameras and CNNs make them excellent tools for visual odometry (VO). This document presents the implementation of a CNN trained to detect and describe features within …

Go to article

Honeyhive - A Network Intrusion Detection System Framework Utilizing Distributed Internet Of Things Honeypot Sensors, Zachary D. Madison Mar 2020

Honeyhive - A Network Intrusion Detection System Framework Utilizing Distributed Internet Of Things Honeypot Sensors, Zachary D. Madison

Theses and Dissertations

Exploding over the past decade, the number of Internet of Things (IoT) devices connected to the Internet jumped from 3.8 billion in 2015 to 17.8 billion in 2018. Because so many IoT devices remain upatched, unmonitored, and left on, they have become a tantalizing target for attackers to gain network access or add another device to their botnet. HoneyHive is a framework that uses distributed IoT honeypots as Network Intrusion Detection Systems (NIDS) sensors that beacon back to a centralized Command and Control (C2) server. The tests in this experiment involve four types of scans and four levels of active …

Go to article

Near Real-Time Zigbee Device Discrimination Using Cb-Dna Features, Yousuke Z. Matsui Mar 2020

Near Real-Time Zigbee Device Discrimination Using Cb-Dna Features, Yousuke Z. Matsui

Theses and Dissertations

Currently, Low-Rate Wireless Personal Area Networks (LR-WPAN) based on the Institute of Electrical and Electronics Engineers (IEEE) 802.15.4 standard are at risk due to open-source tools which allow bad actors to exploit unauthorized network access through various cyberattacks by falsifying bit-level credentials. This research investigates implementing a Radio Frequency (RF) air monitor to perform Near RealTime (NRT) discrimination of Zigbee devices using the IEEE 802.15.4 standard. The air monitor employed a Multiple Discriminant Analysis/Euclidean Distance classifier to discriminate Zigbee devices based upon Constellation-Based Distinct Native Attribute (CB-DNA) fingerprints. Through the use of CB-DNA fingerprints, Physical Layer (PHY) characteristics unique to …

Go to article

Ground Weather Radar Signal Characterization Through Application Of Convolutional Neural Networks, Stephen M. Lee Mar 2020

Ground Weather Radar Signal Characterization Through Application Of Convolutional Neural Networks, Stephen M. Lee

Theses and Dissertations

The 45th Weather Squadron supports the space launch efforts out of the Kennedy Space Center and Cape Canaveral Air Force Station for the Department of Defense, NASA, and commercial customers through weather assessments. Their assessment of the Lightning Launch Commit Criteria (LLCC) for avoidance of natural and rocket triggered lightning to launch vehicles is critical in approving space shuttle and rocket launches. The LLCC includes standards for cloud formations, which requires proper cloud identification and characterization methods. Accurate reflectivity measurements for ground weather radar are important to meet the LLCC for rocket triggered lightning. Current linear interpolation methods for ground …

Go to article

Developing A Serious Game To Explore Joint All Domain Command And Control, Nathaniel W. Flack Mar 2020

Developing A Serious Game To Explore Joint All Domain Command And Control, Nathaniel W. Flack

Theses and Dissertations

Changes in the geopolitical landscape and increasing technological complexity have prompted the U.S. Military to coin Multi-Domain Operations (MDO) and Joint All-Domain Command and Control as terms to describe an over-arching strategy that frames the complexity of warfare across both traditional and emerging warfighting domains. Teaching new and advanced concepts associated with these terms requires both innovation as well as distinct education and training tools in order to realize the cultural change advocated by senior military leaders. BSN, a Collectible Card Game, was developed to teach concepts integral to MDO and initiate discussion on military strategy.

Go to article

Maximizing Accuracy Through Stereo Vision Camera Positioning For Automated Aerial Refueling, Kirill A. Sarantsev Mar 2020

Maximizing Accuracy Through Stereo Vision Camera Positioning For Automated Aerial Refueling, Kirill A. Sarantsev

Theses and Dissertations

Aerial refueling is a key component of the U.S. Air Force strategic arsenal. When two aircraft interact in an aerial refueling operation, the accuracy of relative navigation estimates are critical for the safety, accuracy and success of the mission. Automated Aerial Refueling (AAR) looks to improve the refueling process by creating a more effective system and allowing for Unmanned Aerial Vehicle(s) (UAV) support. This paper considers a cooperative aerial refueling scenario where stereo cameras are used on the tanker to direct a \boom" (a large, long structure through which the fuel will ow) into a port on the receiver aircraft. …

Go to article

Comparison Of The Accuracy Of Rayleigh-Rice Polarization Factors To Improve Microfacet Brdf Models, Rachel L. Wolfgang Mar 2020

Comparison Of The Accuracy Of Rayleigh-Rice Polarization Factors To Improve Microfacet Brdf Models, Rachel L. Wolfgang

Theses and Dissertations

Microfacet BRDF models assume that a surface has many small microfacets making up the roughness of the surface. Despite their computational simplicity in applications in remote sensing and scene generation, microfacet models lack the physical accuracy of wave optics models. In a previous work, Butler proposed to replace the Fresnel reflectance term of microfacet models with the Rayleigh-Rice polarization factor, Q, to create a more accurate model. This work examines the novel model that combines microfacet and wave optics terms for its accuracy in the pp and ss polarized cases individually. The model is fitted to the polarized data in …

Go to article

A Method For Routine Pm2.5 Obsercation And Incorporation Into Numerical Weather Prediction, Daniel B. Jagoda Mar 2020

A Method For Routine Pm2.5 Obsercation And Incorporation Into Numerical Weather Prediction, Daniel B. Jagoda

Theses and Dissertations

Operational numerical weather prediction (NWP) simulates aerosol abundance using climatic emission inventories due to a lack of available real-time observation. An advocation to monitor aerosol number concentration with a standardized global sensor network is defended. A comparison between observations from the existing network “PurpleAir” and condensation particle counters (CPC) reveals the necessity of regulated instrumentation when measuring aerosol number concentration. NWP initialization by the Goddard Chemistry Aerosol Radiation and Transport (GOCART) module is capable of augmentation by hourly aerosol observation. The disparity between observed in-situ particulate matter smaller than 2.5-μm in diameter (PM2.5) and Weather Research and Forecasting …

Go to article

Quantitative Analysis Of Evaluation Criteria For Generative Models, Marvin W. Newlin Mar 2020

Quantitative Analysis Of Evaluation Criteria For Generative Models, Marvin W. Newlin

Theses and Dissertations

Machine Learning (ML) is rapidly becoming integrated in critical aspects of cybersecurity today, particularly in the area of network intrusion/anomaly detection. However, ML techniques require large volumes of data to be effective. The available data is a critical aspect of the ML process for training, classification, and testing purposes. One solution to the problem is to generate synthetic data that is realistic. With the application of ML to this area, one promising application is the use of ML to perform the data generation. With the ability to generate synthetic data comes the need to evaluate the “realness” of the generated …

Go to article

First Prev Next Last