A Dynamic Programming Approach To Determine Optimum Modularity Level In Industrial Packaging,
2021
Anna University
A Dynamic Programming Approach To Determine Optimum Modularity Level In Industrial Packaging, Marshal Louie, Kumar B
Journal of Applied Packaging Research
Modular packaging facilitate customization for accommodating variable product sizes in a product family. When determining package sizes for product variability, packaging engineers does not find difficulty to determine package dimension for less product variety whereas if the product variety is more, then determining the dimension of modular package involves complex decision-making and time-consuming process to find the optimal solution. This in turn directly impacts the overall lead time of the supply chain. Thus, in this paper a dynamic programming is developed to determine the quantity and dimension of modular packages for every demand of assorted products sizes. The program helps …
Meta-Heuristic Optimization Methods For Quaternion-Valued Neural Networks,
2021
Air Force Institute of Technology
Meta-Heuristic Optimization Methods For Quaternion-Valued Neural Networks, Jeremiah P. Bill
Theses and Dissertations
In recent years, real-valued neural networks have demonstrated promising, and often striking, results across a broad range of domains. This has driven a surge of applications utilizing high-dimensional datasets. While many techniques exist to alleviate issues of high-dimensionality, they all induce a cost in terms of network size or computational runtime. This work examines the use of quaternions, a form of hypercomplex numbers, in neural networks. The constructed networks demonstrate the ability of quaternions to encode high-dimensional data in an efficient neural network structure, showing that hypercomplex neural networks reduce the number of total trainable parameters compared to their real-valued …
Exploring The Limits Of Strategic Thought: Evaluating How Different Communication Modalities Affect The Nature Of Strategic Decision-Making Using Cognitive Hierarchy,
2021
Air Force Institute of Technology
Exploring The Limits Of Strategic Thought: Evaluating How Different Communication Modalities Affect The Nature Of Strategic Decision-Making Using Cognitive Hierarchy, Stephen D. Donnel
Theses and Dissertations
This research examines and quantifies the degree to which both information communication modality and the situational complexity affect individuals' ability to process the provided information and determine an effective strategy. Human subject testing herein consists of benign benevolent intervention involving the presentation of a series of strategic situations. For each situation, a participant attempts to identify their best response for a two-player, normal-form game with complete information. In each such game, players seek to maximize their own utility while considering their own actions, their opponent's actions, and each player's respective preferences over outcomes resulting from the possible combinations of actions. …
Air Combat Maneuvering Via Operations Research And Artificial Intelligence Methods,
2021
Air Force Institute of Technology
Air Combat Maneuvering Via Operations Research And Artificial Intelligence Methods, James B. Crumpacker
Theses and Dissertations
Within visual range air combat requires rapid, sequential decision-making to survive and defeat the adversary. Fighter pilots spend years perfecting maneuvers for these types of engagements, yet the emergence of unmanned, autonomous vehicle technologies elicits a natural question - can an autonomous unmanned combat aerial vehicle (AUCAV) be imbued with the necessary artificial intelligence to perform air combat maneuvering tasks independently? We formulate and solve the air combat maneuvering problem to examine this question, developing a Markov decision process model to control an AUCAV seeking to destroy a maneuvering adversarial vehicle. An approximate dynamic programming (ADP) approach implementing neural network …
The Autonomous Attack Aviation Problem,
2021
Air Force Institute of Technology
The Autonomous Attack Aviation Problem, John C. Goodwill
Theses and Dissertations
An autonomous unmanned combat aerial vehicle (AUCAV) performing an air-to-ground attack mission must make sequential targeting and routing decisions under uncertainty. We formulate a Markov decision process model of this autonomous attack aviation problem (A3P) and solve it using an approximate dynamic programming (ADP) approach. We develop an approximate policy iteration algorithm that implements a least squares temporal difference learning mechanism to solve the A3P. Basis functions are developed and tested for application within the ADP algorithm. The ADP policy is compared to a benchmark policy, the DROP policy, which is determined by repeatedly solving a deterministic orienteering problem as …
Bayesian Augmentation Of Cnn-Lstm For Video Classification With Uncertainty Measures,
2021
Air Force Institute of Technology
Bayesian Augmentation Of Cnn-Lstm For Video Classification With Uncertainty Measures, Emmie K. Swize
Theses and Dissertations
The success of Department of Defense (DoD) missions rely heavily on intelligence, surveillance, and reconnaissance (ISR) capabilities, which supply information about the activities and resources of an enemy or adversary. To secure this information, satellites and unmanned aircraft systems collect video data to be classified by either humans or machine learning networks. Traditional automated video classification methods lack measures of uncertainty, meaning the network is unable to identify those cases in which it predictions are made with significant uncertainty. This leads to misclassification, as the traditional network classifies each observation with same amount of certainty, no matter what the observation …
The Impact Of Threat Levels At The Casualty Collection Point On Military Medical Evacuation System Performance,
2021
Air Force Institute of Technology
The Impact Of Threat Levels At The Casualty Collection Point On Military Medical Evacuation System Performance, Nathaniel C. Dennie
Theses and Dissertations
One of the primary duties of the Military Health System is to provide effective and efficient medical evacuation (MEDEVAC) to injured battlefield personnel. To accomplish this, military medical planners seek to develop high-quality dispatching policies that dictate how deployed MEDEVAC assets are utilized throughout combat operations. This thesis seeks to determine dispatching policies that improve the performance of the MEDEVAC system. A discounted, infinite-horizon continuous-time Markov decision process (MDP) model is developed to examine the MEDEVAC dispatching problem. The model incorporates problem features that are not considered under the current dispatching policy (e.g., myopic policy), which tasks the closest-available MEDEVAC …
Strategic Upgrade Scheduling And Portfolio Management To Fortify Contested Networks,
2021
Air Force Institute of Technology
Strategic Upgrade Scheduling And Portfolio Management To Fortify Contested Networks, Justin L. Anderson
Theses and Dissertations
The nuclear command, control, and communication (NC3) network provides an effective deterrent against adversaries by maintaining robust communication between assets, operators, and decision makers. NC3 must receive a series of upgrades to remain an effective deterrent against evolving threats around the globe. Given a contested network and a portfolio of network upgrades, this research seeks an optimal upgrade schedule to maximize network resilience in support of NC3 modernization. Our research contributes a model that solves a budget-constrained network upgrade scheduling problem (NUSP). The NUSP is a defender-attacker-defender tri-level optimization model that achieves fortification via selecting and scheduling network upgrades. The …
Reducing Military Personnel Flight Wait Times Using A Simulation,
2021
Air Force Institute of Technology
Reducing Military Personnel Flight Wait Times Using A Simulation, Matthew D. Cornman
Theses and Dissertations
A shortage of resources and system failures have put a strain on Military Personnel Flights (MPFs) being able to service their customers in a timely manner. Prolonged customer wait times are becoming a common problem in most MPFs creating problems between the relationship of the customers and leadership. This research uses historical data of an MPF to develop a simulation model of daily operations in an MPF. Subject matter expertise of current MPF operations and resource levels were used to provide a baseline model of the MPF queuing system. The analysis examines the effects of number of Defense Enrollment Eligibility …
Improving Air Battle Management Target Assignment Processes Via Approximate Dynamic Programming,
2021
Air Force Institute of Technology
Improving Air Battle Management Target Assignment Processes Via Approximate Dynamic Programming, Joseph M. Liles Iv
Theses and Dissertations
Military air battle managers face many challenges when directing operations in quickly evolving combat scenarios. These scenarios require rapid decisions to engage moving and unpredictable targets. In defensive operations, the success of a sequence of air battle management decisions is reflected by the friendly force's ability to maintain air superiority by defending friendly assets. We develop a Markov decision process (MDP) model of the air battle management (ABM)problem, wherein a set of unmanned combat aerial vehicles (UCAV) is tasked to defend a central asset from cruise missiles that arrive stochastically over time.
The Impact Of Triage Classification Errors On Military Medical Evacuation System Performance,
2021
Air Force Institute of Technology
The Impact Of Triage Classification Errors On Military Medical Evacuation System Performance, Emily S. Graves
Theses and Dissertations
In a deployed environment, evacuation requests of injured personnel are serviced by multiple forms of evacuation including medical evacuation (MEDEVAC) and casualty evacuation (CASEVAC). This thesis focuses on the optimal dispatching policy for MEDEVAC units when triage classification errors and blood transfusion kits are considered. A discounted, infinite-horizon Markov decision process (MDP) model is formulated to analyze the MEDEVAC dispatching problem and determine the optimal policy based on the status of the MEDEVAC units in the system, the priority level of incoming requests, and the locations from which requests originate. A notional, representational scenario based in Azerbaijan is utilized to …
Resupply Operations Of A Dispersed Infantry Brigade Combat Team Using Approximate Dynamic Programming,
2021
Air Force Institute of Technology
Resupply Operations Of A Dispersed Infantry Brigade Combat Team Using Approximate Dynamic Programming, Camero K. Song
Theses and Dissertations
Military sustainment planners must consider the effective employment of Cargo Unmanned Aerial Vehicles (CUAVs) into resupply operations under austere threat conditions. Viewed as an inventory routing problem, the complexities of resupplying dislocated Forward Operating Bases (FOBs) under dangerous and dynamic conditions warrant additional features to the baseline problem. This research models a military stochastic inventory routing problem with multiple routing (MIL SIRP- MR) as a Markov decision process (MDP) model and provides high-quality policy solutions using a combination of approximate dynamic programming and ordinal optimization techniques.
Allocation Of Scarce Healthcare Resources In A Military Treatment Facility During A Pandemic: A Comparison Of Goal Programming And Portfolio Decision Analysis Methods,
2021
Air Force Institute of Technology
Allocation Of Scarce Healthcare Resources In A Military Treatment Facility During A Pandemic: A Comparison Of Goal Programming And Portfolio Decision Analysis Methods, Donald B. Hale
Theses and Dissertations
In a pandemic, healthcare decisionmakers face the challenge of allocating critical, but scarce healthcare resources in a dynamic, uncertain environment. Their decisions will not only affect the patients coming to the hospital for treatment, but also the Military Treatment Facility's personnel responsible. The decisionmaker must decide how to allocate these resources to achieve multiple, conflicting objectives under multiple constraints. In response, we propose a methodology for the implementation of both Portfolio Decision Analysis and Goal Programming. The steps of this methodology provide a framework with which the decisionmaker can develop optimal allocation of resources. This framework was then applied to …
Automated Sentiment Analysis For Personnel Survey Data In The Us Air Force Context,
2021
Air Force Institute of Technology
Automated Sentiment Analysis For Personnel Survey Data In The Us Air Force Context, Julia M. Haines
Theses and Dissertations
When surveys are distributed across the Air Force (AF), whether it be an employee engagement survey, a climate survey, or similar, significant resources are put towards the development, distribution and analysis of the survey. However, when open ended questions are included on these surveys, respondent comments are generally underutilized, more often treated as a source for pull-quotes rather than a data source in and of themselves. This is due to a lack of transparency and confidence in the accuracy of machine-aided methods such as sentiment analysis and topic modeling. This confidence reduces further when the text has special context, such …
An Examination Of Potential Training Regression Recognition Algorithms For Pilot Training Next,
2021
Air Force Institute of Technology
An Examination Of Potential Training Regression Recognition Algorithms For Pilot Training Next, Alex R. Gaines
Theses and Dissertations
The initiative to reduce the Air Forces serious pilot shortage lead to the Pilot Training Next (PTN) program. Under PTN, student pilots progress at an individual rate while making increased use of simulator-based training resources. A previous thesis used data from the first PTN class to conceptualize and prototype a student training flight scheduler. This scheduler did not consider training events required to bring students back to achieved levels of performance if in fact that student performance had regressed. This thesis examines three classes of PTN student data to determine whether student regression in training progression can be detected. A …
Predicting F-16 Cause Code H Micap Hours Using Jmp Regression Analysis,
2021
Air Force Institute of Technology
Predicting F-16 Cause Code H Micap Hours Using Jmp Regression Analysis, Scott E. Carr
Theses and Dissertations
Emergency demands for aircraft parts, MICAPs (Mission Impaired Capability Awaiting Parts) are one of the leading issues affecting mission capability supply rates for fighter aircraft. Cause code H MICAPS, those with a known demand level, but no supply available, are particularly troublesome and difficult to resolve. These MICAPS are due to failures by the supply chain to replenish stock levels within acceptable time limits. Numerous studies have identified a clear need for proactive measures to reduce MICAP hours. This would significantly improve aircraft availability. This study uses regression analysis implemented in JMP software to build models with a goal of …
Ccsfs/Ksc Total Lightning Warning Radii Optimization For Merlin Using Preexisting Lightning Areas,
2021
Air Force Institute of Technology
Ccsfs/Ksc Total Lightning Warning Radii Optimization For Merlin Using Preexisting Lightning Areas, Kimberly G. Holland
Theses and Dissertations
The purpose of this research is to optimize lightning warning radii specifications for the 45th Space Wing (45 SW), thus reducing the number of unnecessary warnings that delay ground processing needed for space launch execution at Kennedy Space Center and Cape Canaveral Space Force Station. This thesis sought to answer two key research questions addressing: 1) What radius reduction effectively balances both safety and operations and do reduction recommendations from previous research align with results from the new detection system? 2) What insights can be gained from comparing measurement results for seasonal lightning events as well as lightning types? This …
Examining Crucial Demographic Trends In General Aviation,
2021
Air Force Institute of Technology
Examining Crucial Demographic Trends In General Aviation, Joshua D. Meyer
Theses and Dissertations
America's General Aviation sector has witnessed significant demographic shifts since the turn of the century. The number of certified, private pilots, non-fatal aircraft accidents, fatal aircraft accidents, and number of general aviation hours flown are all in decline. Meanwhile, the average age of an American private pilot has increased by several years. All of these factors indicate that the industry is in decline. This study determined via mathematical, linear regression that times relationship to the number of annual, fatal General Aviation accidents and the number of certified private pilots is negative. It also proved that the average age of the …
Defensive Counterair For Air Base Air Defense Using Directed Energy And Kinetic Energy Weapons,
2021
Air Force Institute of Technology
Defensive Counterair For Air Base Air Defense Using Directed Energy And Kinetic Energy Weapons, Andrew S. Wilson
Theses and Dissertations
Air bases in key locations provide a strategic advantage to the countries that access them, and are at constant threat from adversaries. This research seeks to determine the optimal maneuvering of a fixed number of fighter aircraft in a combat air patrol for defensive counterair to maximally and effectively attrit the inbound cruise missile threat to a stationary high value asset such as an air base. The problem formulation identifies multiple objectives for the model: minimize the distance traveled for the fighters, minimize the time utilized to engage the incoming cruise missiles, and maximize the number of cruise missiles destroyed. …
Stochastic Programming Design For West Africa Logistics Networks,
2021
Air Force Institute of Technology
Stochastic Programming Design For West Africa Logistics Networks, Julius C. Walker
Theses and Dissertations
The USAFRICOM is studying methods to increase the resiliency of its West African Logistic Network, a hub-and-spoke network design responsible for sustaining long term humanitarian and security missions in the West Africa region. This paper employs a two-stage stochastic programming network design modeled on the WALN that builds a flexible supply chain capable of responding to periodic disruptions while maintaining peak resiliency. Elements such as cost, probability, and event-based disruption are integrated into the model to mirror challenges the WALN faces. We demonstrate that incorporating resilient based response mechanism provide a 90% reduction in cost compared to meeting the logistical …
