Browsing by Subject "pattern recognition"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item An Analysis Tool for Flight Dynamics Monte Carlo Simulations(2011-05-20) Restrepo, Carolina 1982-Spacecraft design is inherently difficult due to the nonlinearity of the systems involved as well as the expense of testing hardware in a realistic environment. The number and cost of flight tests can be reduced by performing extensive simulation and analysis work to understand vehicle operating limits and identify circumstances that lead to mission failure. A Monte Carlo simulation approach that varies a wide range of physical parameters is typically used to generate thousands of test cases. Currently, the data analysis process for a fully integrated spacecraft is mostly performed manually on a case-by-case basis, often requiring several analysts to write additional scripts in order to sort through the large data sets. There is no single method that can be used to identify these complex variable interactions in a reliable and timely manner as well as be applied to a wide range of flight dynamics problems. This dissertation investigates the feasibility of a unified, general approach to the process of analyzing flight dynamics Monte Carlo data. The main contribution of this work is the development of a systematic approach to finding and ranking the most influential variables and combinations of variables for a given system failure. Specifically, a practical and interactive analysis tool that uses tractable pattern recognition methods to automate the analysis process has been developed. The analysis tool has two main parts: the analysis of individual influential variables and the analysis of influential combinations of variables. This dissertation describes in detail the two main algorithms used: kernel density estimation and nearest neighbors. Both are non-parametric density estimation methods that are used to analyze hundreds of variables and combinations thereof to provide an analyst with insightful information about the potential cause for a specific system failure. Examples of dynamical systems analysis tasks using the tool are provided.Item Anisotropic Characterization and Performance Prediction of Chemically and Hydraulically Bounded Pavement Foundations(2010-10-12) Salehi Ashtiani, RezaThe aggregate base layer is a vital part of the flexible pavement system. Unlike rigid pavements, the base layer provides a substantial contribution to the load bearing capacity in flexible pavements, and this contribution is complex: stress dependent, moisture dependent, particle size dependent, and is anisotropic in nature. Furthermore, the response of the aggregate layer in the pavement structure is defined not only by resilient properties of the base layer but also by permanent deformation properties of the aggregate layer. Before the benefits of revolutionary changes in the typical pavement structures, such as deep unbound aggregate base (UAB) layers under thin hot mix asphalt surfaces and inverted pavement systems can be justified, an accurate assessment of the UAB is required. Several researchers identified that in order to properly assess the contribution of the UAB in the pavement structure, it is necessary to consider not only the vertical modulus but also the horizontal modulus as this substantially impacts the distribution of stresses within the pavement structure. Anisotropy, which is defined as the directional dependency of the material properties in unbound granular bases, is inherent even before the aggregate layer is subjected to traffic loads due to random arrangement of particles upon compaction. Distribution of particle contacts is dominated by the geometry of the aggregates as well as the compaction effort at the time of construction. Critical pavement responses and therefore performance of flexible pavements are significantly influenced by the level of anisotropy of aggregate layers. There are several ways to characterize the level of anisotropy in unbound aggregate systems. Previous research at Texas A&M University suggests functions of fitting parameters in material models (kvalues) as characterizers of the level of anisotropy. In the realm of geotechnical engineering, the ratio of the horizontal modulus to vertical modulus is commonly referred to as the level of anisotropy. When the vertical and horizontal moduli are equal, the system is isotropic, but when they differ, the system is anisotropic. This research showed that the level of anisotropy can vary considerably depending on aggregate mix properties such as gradation, saturation level, and the geometry of the aggregate particles. Cross anisotropic material properties for several unbound and stabilized aggregate systems were determined. A comprehensive aggregate database was developed to identify the contribution level of aggregate features to the directional dependency of material properties. Finally a new mechanistic performance protocol based on plasticity theory was developed to ensure the stability of the pavement foundations under traffic loads.Item Fuzzy neural network pattern recognition algorithm for classification of the events in power system networks(Texas A&M University, 2004-09-30) Vasilic, SlavkoThis dissertation introduces advanced artificial intelligence based algorithm for detecting and classifying faults on the power system transmission line. The proposed algorithm is aimed at substituting classical relays susceptible to possible performance deterioration during variable power system operating and fault conditions. The new concept relies on a principle of pattern recognition and detects the existence of the fault, identifies fault type, and estimates the transmission line faulted section. The approach utilizes self-organized, Adaptive Resonance Theory (ART) neural network, combined with fuzzy decision rule for interpretation of neural network outputs. Neural network learns the mapping between inputs and desired outputs through processing a set of example cases. Training of the neural network is based on the combined use of unsupervised and supervised learning methods. During training, a set of input events is transformed into a set of prototypes of typical input events. During application, real events are classified based on the interpretation of their matching to the prototypes through fuzzy decision rule. This study introduces several enhancements to the original version of the ART algorithm: suitable preprocessing of neural network inputs, improvement in the concept of supervised learning, fuzzyfication of neural network outputs, and utilization of on-line learning. A selected model of an actual power network is used to simulate extensive sets of scenarios covering a variety of power system operating conditions as well as fault and disturbance events. Simulation results show improved recognition capabilities compared to a previous version of ART neural network algorithm, Multilayer Perceptron (MLP) neural network algorithm, and impedance based distance relay. Simulation results also show exceptional robustness of the novel ART algorithm for all operating conditions and events studied, as well as superior classification capabilities compared to the other solutions. Consequently, it is demonstrated that the proposed ART solution may be used for accurate, high-speed distinction among faulted and unfaulted events, and estimation of fault type and fault section.Item Rethinking Pen Input Interaction: Enabling Freehand Sketching Through Improved Primitive Recognition(2011-08-08) Paulson, Brandon C.Online sketch recognition uses machine learning and artificial intelligence techniques to interpret markings made by users via an electronic stylus or pen. The goal of sketch recognition is to understand the intention and meaning of a particular user's drawing. Diagramming applications have been the primary beneficiaries of sketch recognition technology, as it is commonplace for the users of these tools to rst create a rough sketch of a diagram on paper before translating it into a machine understandable model, using computer-aided design tools, which can then be used to perform simulations or other meaningful tasks. Traditional methods for performing sketch recognition can be broken down into three distinct categories: appearance-based, gesture-based, and geometric-based. Although each approach has its advantages and disadvantages, geometric-based methods have proven to be the most generalizable for multi-domain recognition. Tools, such as the LADDER symbol description language, have shown to be capable of recognizing sketches from over 30 different domains using generalizable, geometric techniques. The LADDER system is limited, however, in the fact that it uses a low-level recognizer that supports only a few primitive shapes, the building blocks for describing higher-level symbols. Systems which support a larger number of primitive shapes have been shown to have questionable accuracies as the number of primitives increase, or they place constraints on how users must input shapes (e.g. circles can only be drawn in a clockwise motion; rectangles must be drawn starting at the top-left corner). This dissertation allows for a significant growth in the possibility of free-sketch recognition systems, those which place little to no drawing constraints on users. In this dissertation, we describe multiple techniques to recognize upwards of 18 primitive shapes while maintaining high accuracy. We also provide methods for producing confidence values and generating multiple interpretations, and explore the difficulties of recognizing multi-stroke primitives. In addition, we show the need for a standardized data repository for sketch recognition algorithm testing and propose SOUSA (sketch-based online user study application), our online system for performing and sharing user study sketch data. Finally, we will show how the principles we have learned through our work extend to other domains, including activity recognition using trained hand posture cues.Item Steganalysis of video sequences using collusion sensitivity(Texas A&M University, 2006-08-16) Budhia, UditIn this thesis we present an effective steganalysis technique for digital video sequences based on the collusion attack. Steganalysis is the process of detecting with a high probability the presence of covert data in multimedia. Existing algorithms for steganalysis target detecting covert information in still images. When applied directly to video sequences these approaches are suboptimal. In this thesis we present methods that overcome this limitation by using redundant information present in the temporal domain to detect covert messages in the form of Gaussian watermarks. In particular we target the spread spectrum steganography method because of its widespread use. Our gains are achieved by exploiting the collusion attack that has recently been studied in the field of digital video watermarking and more sophisticated pattern recognition tools. Through analysis and simulations we, evaluate the effectiveness of the video steganalysis method based on averaging based collusion scheme. Other forms of collusion attack in the form of weighted linear collusion and block-based collusion schemes have been proposed to improve the detection performance. The proposed steganalsyis methods were successful in detecting hidden watermarks bearing low SNR with high accuracy. The simulation results also show the improved performance of the proposed temporal based methods over the spatial methods. We conclude that the essence of future video steganalysis techniques lies in the exploitation of the temporal redundancy.