Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Linear programming (2)
- Machine learning (2)
- Reinforcement learning (2)
- Value hierarchy (2)
- Active Shooting (1)
-
- Air combat (1)
- Analysis of variance (1)
- Applicant processing (1)
- Applied statistics (1)
- Approximate dynamic programming (1)
- Approximate dynamic programming (ADP) (1)
- Artificial intelligence (1)
- Artificial neural network (1)
- Assignment optimization (1)
- Audit (1)
- Bayesian networks (1)
- Casualty Minimization (1)
- Choice Model (1)
- Container transportation (1)
- Cost function approximation (CFA) (1)
- Cyberspace operations (1)
- Decision analysis (1)
- Descriptive analysis (1)
- Detector Placement (1)
- Difference equations (1)
- Discrete-event simulation (1)
- Eglin Air Force Base (Florida) (1)
- Emotion classification (1)
- Employee retention (1)
- Foreign assistance analysis (1)
Articles 1 - 22 of 22
Full-Text Articles in Engineering
Optimal Scheduling Of Aircraft Test And Evaluation Fleets To Balance Availability For Testing And Training, Sarah E. Hoops
Optimal Scheduling Of Aircraft Test And Evaluation Fleets To Balance Availability For Testing And Training, Sarah E. Hoops
Theses and Dissertations
The 96th Test Wing at Eglin Air Force Base manually schedules a fleet of approximately 26 aircraft to conduct a range of missions over a one-to-two year planning period. This study automates the scheduling process, does so in a manner that optimizes multiple planning goals related to aircraft availability for training, and provides the 96th Test Wing with a software tool for the implementation that can be used by operational analysts within the command. We formulate the scheduling problem as a multiobjective, nonlinear, binary integer math program that seeks to maximize both the lowest percent of time any aircraft is …
Retention Prediction And Policy Optimization For United States Air Force Personnel Management, Joseph C. Hoecherl
Retention Prediction And Policy Optimization For United States Air Force Personnel Management, Joseph C. Hoecherl
Theses and Dissertations
Effective personnel management policies in the United States Air Force (USAF) require methods to predict the number of personnel who will remain in the USAF as well as to replenish personnel with different skillsets over time as they depart. To improve retention predictions, we develop and test traditional random forest models and feedforward neural networks as well as partially autoregressive forms of both, outperforming the benchmark on a test dataset by 62.8% and 34.8% for the neural network and the partially autoregressive neural network, respectively. We formulate the workforce replenishment problem as a Markov decision process for active duty enlisted …
Developing Novel Optimization And Machine Learning Frameworks To Improve And Assess The Safety Of Workplaces, Amin Aghalari
Developing Novel Optimization And Machine Learning Frameworks To Improve And Assess The Safety Of Workplaces, Amin Aghalari
Theses and Dissertations
This study proposes several decision-making tools utilizing optimization and machine learning frameworks to assess and improve the safety of the workplaces. The first chapter of this study presents a novel mathematical model to optimally locate a set of detectors to minimize the expected number of casualties in a given threat area. The problem is formulated as a nonlinear binary integer programming model and then solved as a linearized branch-and-bound algorithm. Several sensitivity analyses illustrate the model's robustness and draw key managerial insights. One of the prevailing threats in the last decades, Active Shooting (AS) violence, poses a serious threat to …
Reconciliation, Restoration And Reconstruction Of A Conflict Ridden Country, Muhammad S. Riaz
Reconciliation, Restoration And Reconstruction Of A Conflict Ridden Country, Muhammad S. Riaz
Theses and Dissertations
Conflict has sadly been a constant part of history. Winning a conflict and making a lasting peace are often not the same thing. While a peace treaty ends a conflict and often dictates terms from the winners’ perspective, it may not create a lasting peace. Short of unconditional surrender, modern conflict ends with a negotiated cessation of hostilities. Such accords may have some initial reconstruction agreements, but Reconciliation, Restoration and Reconstruction (RRR) is a long term process. This study maintains that to achieve a lasting peace: 1) The culture and beliefs of the conflict nation must be continuously considered and …
Bayesian Convolutional Neural Network With Prediction Smoothing And Adversarial Class Thresholds, Noah M. Miller
Bayesian Convolutional Neural Network With Prediction Smoothing And Adversarial Class Thresholds, Noah M. Miller
Theses and Dissertations
Using convolutional neural networks (CNNs) for image classification for each frame in a video is a very common technique. Unfortunately, CNNs are very brittle and have a tendency to be over confident in their predictions. This can lead to what we will refer to as “flickering,” which is when the predictions between frames jump back and forth between classes. In this paper, new methods are proposed to combat these shortcomings. This paper utilizes a Bayesian CNN which allows for a distribution of outputs on each data point instead of just a point estimate. These distributions are then smoothed over multiple …
Military Personnel Flight Customer Wait Time Reduction Model Using Simulation, Nicholas C. Anderson
Military Personnel Flight Customer Wait Time Reduction Model Using Simulation, Nicholas C. Anderson
Theses and Dissertations
Customers at Military Personnel Flights (MPFs) have been experiencing long wait times. These customers are typically employees of the United States Air Force and every moment spent waiting for service is a moment they are away from their actual jobs. By reducing the mean wait time of MPF customers, manhours can be saved and customer complaints may be alleviated. This research uses data collected from an MPF to build a discrete-event simulation model of an MPF. A full factorial experimental design was conducted in the model using five factors. The factors included the total number of employees, the total number …
Inverse Optimization: Inferring Unknown Instance Parameters From Observed Decisions, Keith Batista
Inverse Optimization: Inferring Unknown Instance Parameters From Observed Decisions, Keith Batista
Theses and Dissertations
The objective of this research is to develop procedures that estimate selected, unknown parameters over an adversary's investment portfolio across a set of new or existing technologies. To solve for the selected unknown parameters, it is assumed that the adversary is maximizing the portfolio optimization problem and investing along the efficient frontier. The first technique is when an unknown risk attitude exists but all other parameters were known (i.e. expected return, variance, covariance). An adaptive line search technique that iteratively solved the portfolio optimization problem until the adversary's risk parameter was found. The second problem that was solved was when …
A Decision Support Simulation To Analyze Scheduling Alternatives For Applicant Processing At Military Entrance Processing Stations (Meps), Jonathan M. Escamilla
A Decision Support Simulation To Analyze Scheduling Alternatives For Applicant Processing At Military Entrance Processing Stations (Meps), Jonathan M. Escamilla
Theses and Dissertations
Applicant processing at Military Entrance Processing Stations (MEPS) is conducted via a batch arrival process by which all applicants arrive at the beginning of the processing day. Pursuit of alternate processing scenarios has never progressed beyond the pilot stage, possibly because the Command lacks a general decision support model to evaluate the impacts of proposed policies on applicant processing operations. This research creates a discrete event simulation of MEPS applicant processing operations and applies the model to three alternative applicant processing scenarios: split-shift, appointment- based, and express-lane. Results are examined and compared to benchmarks using multiple performance measurements.
Narrative Analysis Of Open-Source Social Media Activity In The Indopacom Aor, Aaron K. Glenn
Narrative Analysis Of Open-Source Social Media Activity In The Indopacom Aor, Aaron K. Glenn
Theses and Dissertations
Emotion classification can be a powerful tool to derive narratives from social media data. Recurrent Neural Networks (RNN) can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that RNN variants can produce more than an 8% gain in accuracy in comparison to Logistic Regression and SVM techniques and a 15% gain over Random Forest when using FastText embeddings. This research found a statistical significance in the performance of a single layer Bi-directional Long Short-Term Memory (Bi-LSTM) model over a 2-layer stacked Bi-LSTM model. This research also found …
Approximate Dynamic Programming For An Unmanned Aerial Vehicle Routing Problem With Obstacles And Stochastic Target Arrivals, Kassie M. Gurnell
Approximate Dynamic Programming For An Unmanned Aerial Vehicle Routing Problem With Obstacles And Stochastic Target Arrivals, Kassie M. Gurnell
Theses and Dissertations
The United States Air Force is investing in artificial intelligence (AI) to speed analysis in efforts to modernize the use of autonomous unmanned combat aerial vehicles (AUCAVs) in strike coordination and reconnaissance (SCAR) missions. This research examines an AUCAVs ability to execute target strikes and provide reconnaissance in a SCAR mission. An orienteering problem is formulated as anMarkov decision process (MDP) model wherein a single AUCAV must optimize its target route to aid in eliminating time-sensitive targets and collect imagery of requested named areas of interest while evading surface-to-air missile (SAM) battery threats imposed as obstacles. The AUCAV adjusts its …
Optimal Aircraft Maneuvering Models For Cruise Missile Engagement: A Modeling And Computational Study, Izaiah G. Laduke
Optimal Aircraft Maneuvering Models For Cruise Missile Engagement: A Modeling And Computational Study, Izaiah G. Laduke
Theses and Dissertations
Given the increased threat and proliferation of adversary military capabilities, this research seeks to develop reasonably accurate and computationally tractable models to optimally maneuver aircraft to intercept cruise missile attacks. The research leveraged mathematical programming to model the problem, informed by constraints representing a system of (temporal) difference equations. The research began by comparing six models having alternative representations of velocity and acceleration constraints while analyzing situations with stationary targets. The Multiple Aircraft, Multiple Stationary Target Engagement Problem with Box Constraint Bounds (MAMSTEP-BC) Model yielded superior overall performance and was further analyzed through alternative mathematical programming model enhancements to create …
Comparison Of Lightning Warning Radii Distributions, Michael M. Maestas
Comparison Of Lightning Warning Radii Distributions, Michael M. Maestas
Theses and Dissertations
Previous research investigating lightning warning radii about the Cape Canaveral space launch facilities have focused on reducing these radii from either 5 nautical miles (NM) to 4 NM or from 6 NM to 5 NM depending on the structures being protected. Some of these findings have suggested the possibility of both a seasonal difference (warm versus cold) and lightning detection events (cloud-to-ground lightning (CG) or total lightning (TL)) impacting these radii and associated risk levels. Utilizing the 2017-2020 data provided by the 45th Weather Squadron at Patrick Space Force Base via the Mesoscale Eastern Range Lightning Information System (MERLIN), this …
An Exploratory Analysis Of Time Series Econometric Data For Retention Forecasting Using Deep Learning, John C. O'Donnell
An Exploratory Analysis Of Time Series Econometric Data For Retention Forecasting Using Deep Learning, John C. O'Donnell
Theses and Dissertations
Officer retention in the Air Force has been researched many times in an attempt to better predict the personnel needs of the Air Force for the future. There has been previous work done in regards to specific AFSCs and how their retention compares to specific yet similar private sector jobs. This study considers different econometric time series statistics as a feature space and an average Air Force officer separation rate as the response variable for the multivariate time series analysis deep learning techniques. The econometric indicators used in this study are New Business Formations, New Durable Good Orders, and the …
Multiagent Routing Problem With Dynamic Target Arrivals Solved Via Approximate Dynamic Programming, Andrew E. Mogan
Multiagent Routing Problem With Dynamic Target Arrivals Solved Via Approximate Dynamic Programming, Andrew E. Mogan
Theses and Dissertations
This research formulates and solves the multiagent routing problem with dynamic target arrivals (MRP-DTA), a stochastic system wherein a team of autonomous unmanned aerial vehicles (AUAVs) executes a strike coordination and reconnaissance (SCAR) mission against a notional adversary. Dynamic target arrivals that occur during the mission present the team of AUAVs with a sequential decision-making process which we model via a Markov Decision Process (MDP). To combat the curse of dimensionality, we construct and implement a hybrid approximate dynamic programming (ADP) algorithmic framework that employs a parametric cost function approximation (CFA) which augments a direct lookahead (DLA) model via a …
Assessing The United States Foreign Assistance Activities Impact On Violent Conflicts, Daniel F. Feze
Assessing The United States Foreign Assistance Activities Impact On Violent Conflicts, Daniel F. Feze
Theses and Dissertations
The Global Fragility Act, H.R.2116 116th Cong. (2019), “directs the Department of State to establish the interagency Global Fragility Initiative to stabilize conflict-affected areas and prevent violence globally, and establishes funds to support such efforts”. The United States Agency for International Development (USAID) has identified deteriorating economies, weak or illegitimate political institutions, and competition over natural resources as causes of violence, extremism and instability (USAID, 2021). The agency gives priority to mitigating the causes and consequences of violent conflicts, instability and extremism and funds programs and activities to accomplish that (USAID, 2021). With this study, we aim to quantitatively assess …
Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice
Team Air Combat Using Model-Based Reinforcement Learning, David A. Mottice
Theses and Dissertations
We formulate the first generalized air combat maneuvering problem (ACMP), called the MvN ACMP, wherein M friendly AUCAVs engage against N enemy AUCAVs, developing a Markov decision process (MDP) model to control the team of M Blue AUCAVs. The MDP model leverages a 5-degree-of-freedom aircraft state transition model and formulates a directed energy weapon capability. Instead, a model-based reinforcement learning approach is adopted wherein an approximate policy iteration algorithmic strategy is implemented to attain high-quality approximate policies relative to a high performing benchmark policy. The ADP algorithm utilizes a multi-layer neural network for the value function approximation regression mechanism. One-versus-one …
A Decision Analysis Framework To Consider Space Congestion In Orbit Selection, Anthony J. Correale
A Decision Analysis Framework To Consider Space Congestion In Orbit Selection, Anthony J. Correale
Theses and Dissertations
Low Earth Orbit (LEO) is becoming more congested, which increases the risk to space missions. Decision makers will need to consider this increase in congestion as an increased risk within their mission engineering process. This thesis proposes a methodology to create and implement a value structure that quantitatively scores a range of orbits based on congestion factors of each orbit and how well each orbit meets mission requirements. This thesis demonstrates this methodology on a set of circular LEO orbits defined by altitude and inclination, and scores this illustrative scenario based on notional mission measures and expected number of encounters …
Screening Heuristics For The Evaluation Of Covert Network Node Insertion Scenarios, Andrew E. Pekarek
Screening Heuristics For The Evaluation Of Covert Network Node Insertion Scenarios, Andrew E. Pekarek
Theses and Dissertations
The majority of research on covert networks uses social network analysis (SNA) to determine critical members of the network to either kill or capture for the purpose of network destabilization. This thesis takes the opposite approach and evaluates potential scenarios for inserting an agent into a covert network for information gathering purposes or future disruption operations. Due to the substantial number of potential insertion scenarios in a large network, this research proposes three screening heuristics that leverage SNA measures to reduce the solution space before applying a simple search heuristic.
Analysis Of Container Shipments For Ustranscom, John N. Campos Y Campos
Analysis Of Container Shipments For Ustranscom, John N. Campos Y Campos
Theses and Dissertations
USTRANSCOM (United States Transportation Command) sends containers to various overseas destinations, mainly commercial container shipping companies. Delivering the containers to the destinations on time is important to support the United States (US) Forces deployed in foreign countries. This study analyzes container shipment records for two years from 2019 to 2021 and prepares insights for USTRANSCOM. This study utilizes descriptive statistics, data visualization, and one-way analysis of variance (ANOVA). According to the records, almost half of the containers (41.25%) were delivered late for one day or longer. The container with the longest delay took 408 days. Major reasons for delays included …
Air Force Specialty Code Assignment Optimization, Rebecca L. Reynolds
Air Force Specialty Code Assignment Optimization, Rebecca L. Reynolds
Theses and Dissertations
Each year, the Air Force Personnel Center determines which career field newly commissioned officers will serve under during their time in the Air Force. The career fields are assigned while considering five priorities, dictated by Headquarters Air Force, Manpower and Personnel: target number of cadets, education requirements, average cadet percentile, cadet source of commissioning, and cadet preference. A mixed-integer linear program with elasticized constraints is developed to generate cadet assignments according to these priorities. Each elasticized constraint carries an associated reward and penalty, which is used to dictate the importance of the constraint within the model. A subsequent analysis is …
The Cyber Wargame Commodity Course Of Action Automated Analysis Method, Alex Hoffendahl
The Cyber Wargame Commodity Course Of Action Automated Analysis Method, Alex Hoffendahl
Theses and Dissertations
In the modern operational landscape, strategic decisions are made and executed, under uncertain conditions, with many potential constraints and limited information. The end goal of these decisions is to minimize and mitigate the effect of adversarial threats, which may or may not act in line with previous assumptions. Wargaming is a powerful tool that allows for the practical implementation of theoretical knowledge into real-world scenarios, enhancing decision-makers critical thinking and problem solving skills. Furthermore, including cyber-effects in a wargame leads to a broader decision scope for an entire operation. This research aims to enhance the analytical capabilities and overall usability …
Training Logic And Random Forest Models To Predict It Spending, Jacob P. Batt
Training Logic And Random Forest Models To Predict It Spending, Jacob P. Batt
Theses and Dissertations
The Air Force must modernize, but the distribution of funds for technology remains as tight as ever. To this end, the Air Force Audit Agency is looking to utilize machine learning techniques to enhance their capabilities. This research explores Logistic Regression and Random Forest modeling to streamline data collection and cost classification. The final Logistic Regression model identified 4 significant attributes out of the 36 given and was 85 accurate in predicting whether a purchase amount was over or under $10,000. To expand beyond binary classification, a six-category classification Random Forest model was developed. It identified 6 significant attributes and …