Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 8 of 8
Full-Text Articles in Engineering
Determination Of Fire Control Policies Via Approximate Dynamic Programming, Michael T. Davis
Determination Of Fire Control Policies Via Approximate Dynamic Programming, Michael T. Davis
Theses and Dissertations
Given the ubiquitous nature of both offensive and defensive missile systems, the catastrophe-causing potential they represent, and the limited resources available to countries for missile defense, optimizing the defensive response to a missile attack is a necessary endeavor. For a single salvo of offensive missiles launched at a set of targets, a missile defense system protecting those targets must decide how many interceptors to fire at each incoming missile. Since such missile engagements often involve the firing of more than one attack salvo, we develop a Markov decision process (MDP) model to examine the optimal fire control policy for the …
Contextual Detection Of Anomalies In Hyperspectral Images, Adam J. Messer
Contextual Detection Of Anomalies In Hyperspectral Images, Adam J. Messer
Theses and Dissertations
The majority of anomaly detectors in Hyperspectral Imaging use only the statistical aspects of the spectral readings in the image. These detectors fail to use the spatial context that is contained in the images. The use of this information can yield detectors that out perform their spatially myopic counterparts. To demonstrate this, we will use an independent component analysis based detector, autonomous global anomaly detector (AutoGAD), developed at AFIT augmented to account for the spatial context of the detected anomalies. Through the use of segmentation algorithms, the anomalies identified are formed into regions. The size and shape of these regions …
Using Multiple Robust Parameter Design Techniques To Improve Hyperspectral Anomaly Detection Algorithm Performance, Matthew T. Davis
Using Multiple Robust Parameter Design Techniques To Improve Hyperspectral Anomaly Detection Algorithm Performance, Matthew T. Davis
Theses and Dissertations
Detecting and identifying objects of interest is the goal of all remote sensing. New advances, specifically in hyperspectral imaging technology have provided the analyst with immense amounts of data requiring evaluation. Several filtering techniques or anomaly detection algorithms have been proposed. However, most new algorithms are insufficiently verified to be robust to the broad range of hyperspectral data being made available. One such algorithm, AutoGAD, is tested here via two separate robust parameter design techniques to determine optimal parameters for consistent performance on a range of data with large attribute variances. Additionally, the results of the two techniques are compared …
Combat Identification Using Multiple Tuav Swarm, Younin Kang
Combat Identification Using Multiple Tuav Swarm, Younin Kang
Theses and Dissertations
In modern warfare, Tactical Unmanned Aerial Vehicles (TUAVs) are rapidly taking on a leading role in traditional and non-traditional ISR, to include Automatic Target Recognition (ATR). However, additional advancements in processors and sensors on TUAVs are still needed before they can be widely employed as a primary source for positive identification in the Combat Identification (CID) process. Cost is a driving factor for operating an ATR system using multiple TUAVs. The cost of high quality sensors appropriate for a single TUAV can be significantly higher than less sophisticated sensors suitable for deployment on a group, or swarm, of coordinated TUAVs. …
Hyperspectral Imagery Target Detection Using Improved Anomaly Detection And Signature Matching Methods, Timothy E. Smetek
Hyperspectral Imagery Target Detection Using Improved Anomaly Detection And Signature Matching Methods, Timothy E. Smetek
Theses and Dissertations
This research extends the field of hyperspectral target detection by developing autonomous anomaly detection and signature matching methodologies that reduce false alarms relative to existing benchmark detectors, and are practical for use in an operational environment. The proposed anomaly detection methodology adapts multivariate outlier detection algorithms for use with hyperspectral datasets containing tens of thousands of non-homogeneous, high-dimensional spectral signatures. In so doing, the limitations of existing, non-robust, anomaly detectors are identified, an autonomous clustering methodology is developed to divide an image into homogeneous background materials, and competing multivariate outlier detection methods are evaluated for their ability to uncover hyperspectral …
An Investigation Of The Effects Of Correlation And Autocorrelation In Classifier Fusion With Non-Declarations, Frank M. Mindrup
An Investigation Of The Effects Of Correlation And Autocorrelation In Classifier Fusion With Non-Declarations, Frank M. Mindrup
Theses and Dissertations
Air Force doctrine requires reliable and accurate information when striking targets. Further, this doctrine states that fusion should be utilized whenever possible to ensure the best possible information is conveyed; there is no specific guidance as to how to fuse this information. This thesis extends the research found in Leap, Bauer, and Oxley (2004) to include a non-declared class. The Identification system operating characteristic (ISOC) was adapted to allow for non-declarations both at the individual sensor level as well as the fused output level. A probabilistic neural network (PNN) was also used as a fusion technique. A cost function was …
An Investigation Of The Effects Of Correlation, Autocorrelation, And Sample Size In Classifier Fusion, Nathan J. Leap
An Investigation Of The Effects Of Correlation, Autocorrelation, And Sample Size In Classifier Fusion, Nathan J. Leap
Theses and Dissertations
This thesis extends the research found in Storm, Bauer, and Oxley, 2003. Data correlation effects and sample size effects on three classifier fusion techniques and one data fusion technique were investigated. Identification System Operating Characteristic Fusion (Haspert, 2000), the Receiver Operating Characteristic Within Fusion method (Oxley and Bauer, 2002), and a Probabilistic Neural Network were the three classifier fusion techniques; a Generalized Regression Neural Network was the data fusion technique. Correlation was injected into the data set both within a feature set (autocorrelation) and across feature sets for a variety of classification problems, and sample size was varied throughout. Total …
Embedding A Reactive Tabu Search Heuristic In Unmanned Aerial Vehicle Simulations, Joel L. Ryan
Embedding A Reactive Tabu Search Heuristic In Unmanned Aerial Vehicle Simulations, Joel L. Ryan
Theses and Dissertations
We apply a Reactive Tabu Search (RTS) heuristic within a discrete event simulation to solve routing problems for Unmanned Aerial Vehicles (UAVs). Our formulation represents this problem as a multiple Traveling Salesman Problem with time windows (mTSPTW), with the objective of attaining a specified level of target coverage using a minimum number of vehicles. Incorporating weather and probability of UAV survival at each target as random inputs, the RTS heuristic in the simulation searches for the best solution in each realization of the problem scenario in order to identify those routes that are robust to variations in weather, threat, or …