Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 7 of 7
Full-Text Articles in Entire DC Network
Simulation Of A Neural Network-Driven Fuzzy Controller, Karl Ver Schneider
Simulation Of A Neural Network-Driven Fuzzy Controller, Karl Ver Schneider
Theses
A software simulation package was developed to facilitate the analysis of a fuzzy logic tracking system constructed by first training a neural network. The adaptive vector quantization neural network used a competitive learning algorithm to classify control data from a controller in a noisy environment. The neural network memory generated rules for a fuzzy controller by mapping the state of the network into a predetermined fuzzy database. The software is intended to be expanded to allow further analysis of neural dynamics and to compare the performance of the resulting fuzzy controller to conventional controllers.
Features And Neural Net Recognition Strategies For Hand Printed Digits, Jeffrey R. Pink
Features And Neural Net Recognition Strategies For Hand Printed Digits, Jeffrey R. Pink
Theses
The thesis goal is to develop a computer system for hand printed digit recognition based on an investigation into various feature extractors and neural network strategies. Features such as subwindow pixel summation, moments, and orientation vectors will be among those investigated. Morphological thinning of characters prior to feature extraction will be used to assess the impact on network training and testing. Different strategies for implementing a multilayer perceptron neural network will be investigated. A high-level language called MatLab will be used for neural network algorithm development and quick prototyping. The feature extractors will be developed to operate on small (less …
Characterization Of Digital Film Scanner Systems For Use With Digital Scene Algorithms, Mark Vernacotola
Characterization Of Digital Film Scanner Systems For Use With Digital Scene Algorithms, Mark Vernacotola
Theses
Digital film scanners have been used in the photographic industry for more than a decade. The existence of digital image data has made possible the use of computer-based scene enhancement algorithms to improve image quality. These algorithms are usually device-dependent, functioning properly only for data generated by one scanner system. The complexity of most enhancement algorithms make them costly to develop, thus device-independent scene enhancement algorithms would be valuable. The computation of mathematical transformations to convert scanner data to a device-independent space is possible. The data created using these transformations should serve as the input for device-independent enhancement algorithms. A …
Statistical Spice Parameter Extraction For An N-Well Cmos Process, Scott Hildreth
Statistical Spice Parameter Extraction For An N-Well Cmos Process, Scott Hildreth
Theses
The purpose of this thesis is to demonstrate one method of statistical parameter extraction and show some of the advantages of statistical models. The method of extraction discussed, parameter domain statistics, is ideal for use in the classroom, due to its simplicity and ease of implementation. Another advantage is the minimal statistical knowledge required to understand this process. The test chip design was a modification of the test chip designed by Bert Berends. An N-Well CMOS lot was processed and models extracted using IC-CAP From these models, parameter domain statistics were performed - the model parameters were used to create …
Implementation Of Fractal Image Coding, Peter Stubler
Implementation Of Fractal Image Coding, Peter Stubler
Theses
The goal of this project is to implement a digital image encoder and decoder using a Fractal Block Coding compression algorithm for grayscale images, and to compare its performance to currendy popular algorithms such as JPEG. The algorithm used here is based on the published papers [1] - [3] ofA E. Jacquin, and in part, a paper [4] by B. Ramamurthi and A. Gersho. As stated in the project proposal, this algorithm has been simplified to enable the timely completion of the project.
Asic Design Of An Iir Digital Filter: Using Mentor Graphics Dsp Station Tools, Robert Panek
Asic Design Of An Iir Digital Filter: Using Mentor Graphics Dsp Station Tools, Robert Panek
Theses
Automation in VLSI design is a powerful way to simplify the VLSI layout process and will allow for faster time to market for integrated circuit designs. One means of automation is VHDL, a hardware description language for integrated circuit designs. A structured VHDL description can be used to describe the hardware design at the logic-gate level, and automated software is available that will use this gate-level design to generate the VLSI layout. A more recent type of automation occurs at a level above this. The Mentor Graphics DSP Station tools use a high-level algorithmic description to generate the gate-level VHDL …
A Vhdl Model Of A Digi-Neocognitron Neural Network For Vlsi, Troy Brewster
A Vhdl Model Of A Digi-Neocognitron Neural Network For Vlsi, Troy Brewster
Theses
Optical character recognition is useful in many aspects of business. However, the use of conventional computers to provide a solution to this problem has not been very effective. Over the past two decades, researchers have utilized artificial neural networks for optical character recognition with considerable success. One such neural network is the neocognitron, a real-valued, multi-layered hierarchical network that simulates the human visual system. The neocognitron was shown to have the capability for pattern recognition despite variations in size, shape or the presence of deformations from the trained patterns. Unfortunately, the neocognitron is an analog network which prevents it from …