Engineering Commons^™

Mobile Ad Hoc Networks In Transportation Data Collection And Dissemination, Kardigue Konte

Theses and Dissertations

The field of transportation is rapidly changing with new opportunities for systems solutions and emerging technologies. The global economic impact of congestion and accidents are significant. Improved means are needed to solve them. Combined with the increasing numbers of vehicles on the road, the net economic impact is measured in the many billions of dollars. Promising methodologies explored in this thesis include the use of the Internet of Things (IoT) and Mobile Ad Hoc Networks (MANET). Interconnecting vehicles using Dedicated Short Range Communication technology (DSRC) brings many benefits. Integrating DSRC into roadway vehicles offers the promise of reducing the problems …

The Trust-Based Interactive Partially Observable Markov Decision Process, Richard S. Seymour

Theses and Dissertations

Cooperative agent and robot systems are designed so that each is working toward the same common good. The problem is that the software systems are extremely complex and can be subverted by an adversary to either break the system or potentially worse, create sneaky agents who are willing to cooperate when the stakes are low and take selfish, greedy actions when the rewards rise. This research focuses on the ability of a group of agents to reason about the trustworthiness of each other and make decisions about whether to cooperate. A trust-based interactive partially observable Markov decision process (TI-POMDP) is …

Way-Finding: A New Approach To Studying Digital Communications, William Daniel Glade

Theses and Dissertations

This work further develops the way-finding model first proposed by Pearson and Kosicki (2017) which examines the flow of information in the digital age. Way-finding systems are online systems that help individuals find information—i.e. social media, search engines, email, etc. Using a grounded theory methodology, this new framework was explored in greater detail. Way-finding theory was created using the context of the elaboration likelihood model, gatekeeping theory, algorithmic gatekeepers, and the existence of the filter bubble phenomenon. This study establishes the three basic pillars of way-finding theory: the user’s mindset when accessing way-finding systems, the perception of how popular way-finding …

Machine Learning Models Of C-17 Specific Range Using Flight Recorder Data, Marcus Catchpole

Theses and Dissertations

Fuel is a significant expense for the Air Force. The C-17 Globemaster eet accounts for a significant portion. Estimating the range of an aircraft based on its fuel consumption is nearly as old as flight itself. Consideration of operational energy and the related consideration of fuel efficiency is increasing. Meanwhile machine learning and data-mining techniques are on the rise. The old question, "How far can my aircraft y with a given load cargo and fuel?" has given way to "How little fuel can I load into an aircraft and safely arrive at the destination?" Specific range is a measure of …

Examining Effectiveness Of Web-Based Internet Of Things Honeypots, Lukas A. Stafira

Theses and Dissertations

The Internet of Things (IoT) is growing at an alarming rate. It is estimated that there will be over 25 billion IoT devices by 2020. The simplicity of their function usually means that IoT devices have low processing power, which prevent them from having intricate security features, leading to vulnerabilities. This makes IoT devices the prime target of attackers in the coming years. Honeypots are intentionally vulnerable machines that run programs which appear as a vulnerable device to a would-be attacker. They are placed on a network to entice and trap an attacker and then gather information on them, including …

Confidence Inference In Defensive Cyber Operator Decision Making, Graig S. Ganitano

Theses and Dissertations

Cyber defense analysts face the challenge of validating machine generated alerts regarding network-based security threats. Operations tempo and systematic manpower issues have increased the importance of these individual analyst decisions, since they typically are not reviewed or changed. Analysts may not always be confident in their decisions. If confidence can be accurately assessed, then analyst decisions made under low confidence can be independently reviewed and analysts can be offered decision assistance or additional training. This work investigates the utility of using neurophysiological and behavioral correlates of decision confidence to train machine learning models to infer confidence in analyst decisions. Electroencephalography …

High Resolution Low-Bandwidth Real-Time Reconnaissance Using Structure From Motion With Planar Homography Estimation, Christian M.A. Arnold

Theses and Dissertations

Aerial real-time surveillance exists in a paradigm balancing the constraints of delivering high quality data and transporting data quickly. Typically, to have more of one, sacrifices must be made to the other. This is true of the environment in which an Unmanned Aerial Vehicle (UAV) operates, where real-time communication may be done through a low-bandwidth satellite connection resulting in low-resolution data, and serves as the primary limiting factor in all intelligence operations. Through the use of efficient computer vision techniques, we propose a new Structure from Motion (SfM) method capable of compressing high-resolution data, and delivering that data in real-time. …

Modeling A Consortium-Based Distributed Ledger Network With Applications For Intelligent Transportation Infrastructure, Luis A. Cintron

Theses and Dissertations

Emerging distributed-ledger networks are changing the landscape for environments of low trust among participating entities. Implementing such technologies in transportation infrastructure communications and operations would enable, in a secure fashion, decentralized collaboration among entities who do not fully trust each other. This work models a transportation records and events data collection system enabled by a Hyperledger Fabric blockchain network and simulated using a transportation environment modeling tool. A distributed vehicle records management use case is shown with the capability to detect and prevent unauthorized vehicle odometer tampering. Another use case studied is that of vehicular data collected during the event …

Near Real-Time Rf-Dna Fingerprinting For Zigbee Devices Using Software Defined Radios, Frankie A. Cruz

Theses and Dissertations

Low-Rate Wireless Personal Area Network(s) (LR-WPAN) usage has increased as more consumers embrace Internet of Things (IoT) devices. ZigBee Physical Layer (PHY) is based on the Institute of Electrical and Electronics Engineers (IEEE) 802.15.4 specification designed to provide a low-cost, low-power, and low-complexity solution for Wireless Sensor Network(s) (WSN). The standard’s extended battery life and reliability makes ZigBee WSN a popular choice for home automation, transportation, traffic management, Industrial Control Systems (ICS), and cyber-physical systems. As robust and versatile as the standard is, ZigBee remains vulnerable to a myriad of common network attacks. Previous research involving Radio Frequency-Distinct Native Attribute …

A Multi-Vehicle Cooperative Localization Approach For An Autonomy Framework, Edwin A. Mora

Theses and Dissertations

Offensive techniques produced by technological advancement present opportunities for adversaries to threaten the operational advantages of our joint and allied forces. Combating these new methodologies requires continuous and rapid development towards our own set of \game-changing" technologies. Through focused development of unmanned systems and autonomy, the Air Force can strive to maintain its technological superiority. Furthermore, creating a robust framework capable of testing and evaluating the principles that define autonomy allows for the exploration of future capabilities. This research presents development towards a hybrid reactive/deliberative architecture that will allow for the testing of the principles of task, cognitive, and peer …

A Blockchain-Based Anomalous Detection System For Internet Of Things Devices, Joshua K. Mosby

Theses and Dissertations

Internet of Things devices are highly susceptible to attack, and owners often fail to realize they have been compromised. This thesis describes an anomalous-based intrusion detection system that operates directly on Internet of Things devices utilizing a custom-built Blockchain. In this approach, an agent on each node compares the node's behavior to that of its peers, generating an alert if they are behaving differently. An experiment is conducted to determine the effectiveness at detecting malware. Three different code samples simulating common malware are deployed against a testbed of 12 Raspberry Pi devices. Increasing numbers are infected until two-thirds of the …

Autonomous Association Of Geo Rso Observations Using Deep Neural Networks, Ian W. Mcquaid

Theses and Dissertations

Ground-based non-resolved optical observations of resident space objects (RSOs) in geosynchronous orbit (GEO) represent the majority of the space surveillance network’s (SSN’s) deep-space tracking. Reliable and accurate tracking necessitates temporal separation of the observations. This requires that subsequent observations be associated with prior observations of a given RSO before they can be used to create or refine that RSO’s ephemeris. The use of astrometric data (e.g. topocentric angular position) alone for this association task is complicated by RSO maneuvers between observations, and by RSOs operating in close proximity. Accurately associating an observation with an RSO thus motivates the use of …

Unresolved Object Detection Using Synthetic Data Generation And Artificial Neural Networks, Yong U. Sinn

Theses and Dissertations

This research presents and solves constrained real-world problems of using synthetic data to train artificial neural networks (ANNs) to detect unresolved moving objects in wide field of view (WFOV) electro-optical/infrared (EO/IR) satellite motion imagery. Objectives include demonstrating the use of the Air Force Institute of Technology (AFIT) Sensor and Scene Emulation Tool (ASSET) as an effective tool for generating EO/IR motion imagery representative of real WFOV sensors and describing the ANN architectures, training, and testing results obtained. Deep learning using a 3-D convolutional neural network (3D ConvNet), long short term memory (LSTM) network, and U-Net are used to solve the …

Let’S Face It: The Effect Of Orthognathic Surgery On Facial Recognition Algorithm Analysis, Carolyn Bradford Dragon

Theses and Dissertations

Aim: To evaluate the ability of a publicly available facial recognition application program interface (API) to calculate similarity scores for pre- and post-surgical photographs of patients undergoing orthognathic surgeries. Our primary objective was to identify which surgical procedure(s) had the greatest effect(s) on similarity score.

Methods: Standard treatment progress photographs for 25 retrospectively identified, orthodontic-orthognathic patients were analyzed using the API to calculate similarity scores between the pre- and post-surgical photographs. Photographs from two pre-surgical timepoints were compared as controls. Both relaxed and smiling photographs were included in the study to assess for the added impact of facial pose on …