Digital Commons Network^™

A Portable Computer System For Recording Heart Sounds And Data Modeling Using A Backpropagation Neural Network, Erik Mark Hudson

UNF Graduate Theses and Dissertations

Cardiac auscultation is the primary tool used by cardiologists to diagnose heart problems. Although effective, auscultation is limited by the effectiveness of human hearing. Digital sound technology and the pattern classification ability of neural networks may offer improvements in this area. Digital sound technology is now widely available on personal computers in the form of sound cards. A good deal of research over the last fifteen years has shown that neural networks can excel in diagnostic problem solving. To date, most research involving cardiology and neural networks has focussed on ECG pattern classification. This thesis explores the prospects of recording …

Multiple Query Optimization With Depth-First Branch-And-Bound And Dynamic Query Ordering, Ee Peng Lim, Ahmet Cosar, Jaideep Srivastava

Research Collection School Of Computing and Information Systems

In certain database applications such as deductive databases, batch query processing, and recursive query processing etc., usually a single query gets transformed into a set of closely related database queries. Also, great benefits can be obtained by executing a group of related queries all together in a single unified multi-plan instead of executing each query separately. In order to achieve this Multiple Query Optimization (MQO) identifies common task(s) (e.g. common subexpressions, joins, etc.) among a set of query plans and creates a single unified plan (multi-plan) which can be executed to obtain the required outputs for all queries at once. …

A Study Of Voluntary Participation In Computer User Groups, Alan Engels

Electronic Theses & Dissertations

The purpose of this study was to determine ways to increase participation of members in Computer User Groups. The problem addressed was that a small select group, less than ten percent, in the Parsons Apple/Macintosh Users Group was doing ninety-five percent or more of the work. If this scenario does not change soon, the overworked and overburdened select few may suffer burnout and quit. Case in point, Joplin, MO, had a large Computer User Group, but about seven years ago, it vanished when the select few refused to serve anymore. The same process of decay and erosion has happened in …

Quantitative Object Motion Prediction By An Art2 And Madaline Combined Neural Network: Concepts And Experiments, Qiuming Zhu, Ahmed Y. Tawfik

Computer Science Faculty Publications

An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.

An Optimal Path Cover Algorithm For Cographs, R. Lin, S. Olariu

Computer Science Faculty Publications

The class of cographs, or complement-reducible graphs, arises naturally in many different areas of applied mathematics and computer science. In this paper, we present an optimal algorithm for determining a minimum path cover for a cograph G. In case G has a Hamiltonian path (cycle) our algorithm exhibits the path (cycle) as well.

A Linear-Time Recognition Algorithm For P4-Reducible Graphs, B. Jamison, S. Olariu

Computer Science Faculty Publications

The P₄-reducible graphs are a natural generalization of the well-known class of cographs, with applications to scheduling, computational semantics, and clustering. More precisely, the P₄-reducible graphs are exactly the graphs none of whose vertices belong to more than one chordless path with three edges. A remarkable property of P₄-reducible graphs is their unique tree representation up to isomorphism. In this paper we present a linear-time algorithm to recognize P₄-reducible graphs and to construct their corresponding tree representation.

Linear Time Optimization Algorithms For P4-Sparse Graphs, Beverly Jamison, Stephan Olariu

Computer Science Faculty Publications

Quite often, real-life applications suggest the study of graphs that feature some local density properties. In particular, graphs that are unlikely to have more than a few chordless paths of length three appear in a number of contexts. A graph G is P₄-sparse if no set of five vertices in G induces more than one chordless path of length three. P₄-sparse graphs generalize both the class of cographs and the class of P₄-reducible graphs. It has been shown that P₄-sparse graphs can be recognized in time linear in the size of the …

Finding Connected Components On A Scan Line Array Processor, Ronald I. Greenberg

Computer Science: Faculty Publications and Other Works

This paper provides a new approach to labeling the connected components of an n x n image on a scan line array processor (comprised of n processing elements). Variations of this approach yield an algorithm guaranteed to complete in o(n lg n) time as well as algorithms likely to approach O(n) time for all or most images. The best previous solutions require using a more complicated architecture or require Omega(n lg n) time. We also show that on a restricted version of the architecture, any algorithm requires Omega(n lg n) time in the worst case.

Biometric Imaging: Three Dimensional Imaging Of The Human Hand Using Coded Structured Lighting, T. A. Vuori, C. L. Smith

Research outputs pre 2011

In this report the results of applying a three dimensional range imaging system, based on coded structured light, are presented. This includes a description of a new improved spatial coding scheme. This new scheme increases the number of reference points available and provides a basis for more accurate calculation of their location. A detailed description of the image processing methods used to extract structural information and to identify structural objects from the camera image are given. In addition the method used to calculate the locations of reference points with 'subpixel' accuracy is described. Finally, the results of experiments with synthesised …

Using Neural Networks For Aerodynamic Parameter Modeling, Gerald E. Peterson, William E. Bond, Roger Germann, Barry Streeter, James Urnes

Computer Science Faculty Research & Creative Works

Neural networks are being developed at McDonnell Douglas Corporation to provide an onboard model of an aircraft's aerodynamics to support advanced flight control systems. These flight control systems, constructed using neural networks and advanced controllers, have the potential to reduce flight control development costs and to improve inflight performance. Neural networks are useful in this situation because they can compactly represent the data and operate in real-time

An Interactive Model Of Teaching, H. David Mathias

All Computer Science and Engineering Research

Previous teaching models in the learning theory community have been batch models. That is, in these models the teacher has generated a single set of helpful examples to present to the learner. In this paper we present an interactive model in which the learner has the ability to ask queries as in the query learning model of Angluin [1]. We show that this model is at least as powerful as previous teaching models. We also show that anything learnable with queries, even by a randomized learner, is teachable in our model. In all previous teaching models, all classes shown to …

Formal Specification Of A Dynamically Configurable Distributed System, Ram Sethuraman, Kenneth J. Goldman

All Computer Science and Engineering Research

The Programmers' Playground is a programming environment that supports end-user construction of distributed multimedia applications. The system implements a new programming model that is based, in part, upon ideas from the formal I/O automaton model of Lynch and Tuttle. Important features of The Programmers' Playground are a separation of communication and computation and graphical support for dynamic reconfiguration. This paper provides a formal specification of the Playground programming model and runtime system in terms of the I/O automaton model on which it is based. Exploiting the compositionality properties of the I/O automaton model, the formal specification is describd as a …

Euphoria Reference Manual, T. Paul Mccartney, Kenneth J. Goldman

All Computer Science and Engineering Research

No abstract provided.

Building Interactive Distributed Applications In C++ With The Programmers' Playground, Kenneth J. Goldman, T. Paul Mccartney, Ram Sethuraman, Bala Swaminathan And Todd Rogers

All Computer Science and Engineering Research

No abstract provided.

A Single-Stroke Orientation-Orient Gesture System, Yike Hu

All Computer Science and Engineering Research

No abstract provided.

Using Multiple Statistical Prototypes To Classify Continuously Valued Data, Tony R. Martinez, Dan A. Ventura

Faculty Publications

Multiple Statistical Prototypes (MSP) is a modification of a standard minimum distance classification scheme that generates muItiple prototypes per class using a modified greedy heuristic. Empirical comparison of MSP with other well-known learning algorithms shows MSP to be a robust algorithm that uses a very simple premise to produce good generalization and achieve parsimonious hypothesis representation.

Error Estimates And Lipschitz Constants For Best Approximation In Continuous Function Spaces, M. Bartelt, W. Li

Mathematics & Statistics Faculty Publications

We use a structural characterization of the metric projection PG(f), from the continuous function space to its one-dimensional subspace G, to derive a lower bound of the Hausdorff strong unicity constant (or weak sharp minimum constant) for PG and then show this lower bound can be attained. Then the exact value of Lipschitz constant for PG is computed. The process is a quantitative analysis based on the Gâteaux derivative of PG, a representation of local Lipschitz constants, the equivalence of local and global Lipschitz constants for lower semicontinuous mappings, and construction …

A Mathematical Model Of Cycle Chemotherapy, J. C. Panetta, J. Adam

Mathematics & Statistics Faculty Publications

A mathematical model is used to discuss the effects of cycle-specific chemotherapy. The model includes a constraint equation which describes the effects of the drugs on sensitive normal tissue such as bone marrow. This model investigates both pulsed and piecewise-continuous chemotherapeutic effects and calculates the parameter regions of acceptable dose and period. It also identifies the optimal period needed for maximal tumor reduction. Examples are included concerning the use of growth factors and how they can enhance the cell kill of the chemotherapeutic drugs.

Object Interactions As First Class Objects: From Design To Implementation, Mahesh Dodani, Benjamin Kok Siew Gan, Lizette Velazquez

Research Collection School Of Computing and Information Systems

Collaborations between objects make up the dynamic behavior of OO software. These collaborations among objects require careful design and implementation. Treating the interactions as responsibilities that are integrated in the participating objects, results in tight coupling between objects. Tight coupling increases complexity and reduces reusability. Object interactions need to be first class objects from design to implementation. Our research provides a unified approach to model and implement these interactions as first class objects. During analysis and design, they are modeled using DynaSpecs. During implementation, they are coded with a new language construct called Compositions. DynaSpecs and Compositions provide a consistent …

Rule Extraction: From Neural Architecture To Symbolic Representation, Gail A. Carpenter, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

This paper shows how knowledge, in the form of fuzzy rules, can be derived from a supervised learning neural network called fuzzy ARTMAP. Rule extraction proceeds in two stages: pruning, which simplifies the network structure by removing excessive recognition categories and weights; and quantization of continuous learned weights, which allows the final system state to be translated into a usable set of descriptive rules. Three benchmark studies illustrate the rule extraction methods: (1) Pima Indian diabetes diagnosis, (2) mushroom classification and (3) DNA promoter recognition. Fuzzy ARTMAP and ART-EMAP are compared with the ADAP algorithm, the k nearest neighbor system, …

Comparing Traditional Statistical Models With Neural Network Models: The Case Of The Relation Of Human Performance Factors To The Outcomes Of Military Combat, William Oliver Hedgepeth

Engineering Management & Systems Engineering Theses & Dissertations

Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.

Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.

The …

Software Reliability Issues: An Experimental Approach, Mary Ann Hoppa

Computer Science Theses & Dissertations

In this thesis, we present methodologies involving a data structure called the debugging graph whereby the predictive performance of software reliability models can be analyzed and improved under laboratory conditions. This procedure substitutes the averages of large sample sets for the single point samples normally used as inputs to these models and thus supports scrutiny of their performances with less random input data.

Initially, we describe the construction of an extensive database of empirical reliability data which we derived by testing each partially debugged version of subject software represented by complete or partial debugging graphs. We demonstrate how these data …

Multicriteria Mission Route Planning Using A Parallel A* Search, Michael S. Gudaitis

Theses and Dissertations

The Mission Route Planning (MRP) Problem falls into the general class of multicriteria path search problems. Multiple criteria are evaluated to select an optimal aircraft mission route through a hostile environment. Criteria for distance travelled and radar exposure are combined into a single cost function for route evaluation. Radar calculations are performed dynamically. The A* search algorithm is applied to the MRP problem, and a parallel implementation is developed and tested. A unique combination of distributed OPEN lists with a global CLOSED list strategy produced fast execution times on the Paragon. Test cases for scenarios with 15 radars took less …

Computing Χ² Values, John F. Dooley, Daniel C. St Clair, William E. Bond

Mathematics and Statistics Faculty Research & Creative Works

Textbooks and courses on numerical algorithms contain numerous examples which lead students to believe that the algorithm of choice for computing the zeros of a function f1994 is Newton's algorithm. In many of these courses little or no time is spent in providing students with "real world" experiences where Newton's method fails. The work presented in this paper describes a slow convergence problem encountered while trying to use Newton to estimate values for the 2 distributions. The problem occurred while the authors were trying to implement a well-known machine learning algorithm from the field of artificial intelligence. The function being …

Program Modeling And Control Synthesis For Robotic Manipulators, Ramiz N. Ballou, Arlan R. Dekock, David D. Ardayfio

Computer Science Technical Reports

The control and programming methodology of industrial robots is becoming increasingly important. The speed and accuracy of data generation, and the performance of the robot are considered the most important factors in robotics control. This paper presents and discusses algorithms that solve for the inverse solution for a given point in space at a very high speed based on the top down abstract method. The algorithms are independent of any specific type of manipulator configuration or programming language. The algorithms were implemented for the IBM-PC™ using the FORTRAN language to control the Armdroid™ robot. The program generates 500 sets of …

Wright State University College Of Engineering And Computer Science Bits And Pcs Newsletter, Volume 10, Number 10, December 1994, College Of Engineering And Computer Science, Wright State University

BITs and PCs Newsletter

A fourteen page newsletter created by the Wright State University College of Engineering and Computer Science that addresses the current affairs of the college.

Generalized Probabilistic Reasoning And Empirical Studies On Computational Efficiency And Scalability, Eric P. Baenen

Theses and Dissertations

Expert Systems are tools that can be very useful for diagnostic purposes, however current methods of storing and reasoning with knowledge have significant limitations. One set of limitations involves how to store and manipulate uncertain knowledge: much of the knowledge we are dealing with has some degree of uncertainty. These limitations include lack of complete information, not being able to model cyclic information and limitations on the size and complexity of the problems to be solved. If expert systems are ever going to be able to tackle significant real world problems then these deficiencies must be corrected. This paper describes …

A New Approach To Automatic Target Recognition Using Wavelet Transforms, Anitha Panapakkam, S. N. Balakrishnan, Daniel St. Clair

Computer Science Technical Reports

Automatic Target Recognition (ATR) systems have significant impact in defense applications. There is a continuing need to develop new and robust techniques to handle the increasingly complex ATR problem. The objectives of this thesis are two-fold. First a new technique to be used for ATR is developed and secondly an integrated ATR system to investigate and combine all subsystems is developed. In this thesis, we have developed a new technique for the feature extraction stage of ATR problem using wavelet transforms. Wavelet transforms have been one of the widely investigated areas of research in the past few years. The promising …

Toward Scalable Parallel Software: An Active Object Model And Library To Support Von Neumann Languages, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

Scalable parallel processing has been proposed as the technology scientists and engineers can use today to solve the problems of tomorrow. Many computational Grand Challenge problems require between two and three orders of magnitude than can be provided with the scalable parallel hardware of the early nineteen-nineties. While hardware continues to become more scalable and cheaper, software is not advancing at the same pace and remains a very expensive part of systems development.

A great deal of emphasis on software technology to support scalable parallel processing is placed on von Neumann languages. One of two approaches is common: (a) augment …

Autonomous Robot Navigation In Unknown Terrains Using Parallel Numerical Artificial Potential Fields, John C. Schneider

Computer Science Theses & Dissertations

We present a new artificial potential field formulation for resolution complete robot navigation that unifies the purely geometric path planning problem with the lower level force control problem. Our formulation is designed for numerical computation over a massively parallel mesh of processors and is responsive to newly discovered terrain features. It does not suffer from many of the problems commonly associated with potential fields and with adequate resolution provides provably correct, collision free convergence to the goal. In addition, our formulation supports many desirable, practical features required for implementation, such as bounded actuator torques, attainable incremental constructability, realizable computation and …