Electrical and Computer Engineering Commons^™

Fingerprint Recognition Using Neural Networks, Eng Hoe Kennie Yeoh

Student Works (2000-2009)

Traditional methods of fingerprint verification uses either complicated feature detection algorithms that are not specific to each fingerprint, or compare two fingerprint images directly using image processing toots. The former involves very complicated calculations and tedious algorithms, and the latter tend to work poorly. In this paper it is described a new method which takes the middle ground. This paper studies the implementation of the Fast Fourier Transform and Artificial Neural Networks into the recognition of fingerprints. With tests conducted on the implementation of the Fourier Transform as a method of fingerprint feature extraction, the use of the Fourier Transform …

Neural Networks Versus Nonparametric Neighbor-Based Classifiers For Semisupervised Classification Of Landsat Thematic Mapper Imagery, Perry J. Hardin

Faculty Publications

Semisupervised classification is one approach to converting multiband optical and infrared imagery into landcover maps. First, a sample of image pixels is extracted and clustered into several classes. The analyst next combines the clusters by hand to create a smaller set of groups that correspond to a useful landcover classification. The remaining image pixels are then assigned to one of the aggregated cluster groups by use of a per-pixel classifier. Since the cluster aggregation process frequently creates groups with multivariate shapes ill suited for parametric classifiers, there has been renewed interest in nonparametric methods for the task. This research reports …

Newton Parameter Update Algorithm For Recurrent Neural Networks Applied To Adaptive System Identification And Control, Donald Allen Gates

Electrical & Computer Engineering Theses & Dissertations

This paper shows that the combination of a second-order neural network parameter update algorithm and internal network feedback can be effectively used for adaptive, nonlinear, dynamical system identification and control. Adaptive neural identification and control algorithms are typically utilized for real-time applications where the rate of adaptation is often critical. A fast, adaptive network parameter update algorithm is presented.

Simulation results show that this algorithm is capable of quickly identifying and adapting to changes in system parameters, making it feasible to use for real-time control and fault accommodation applications.

Electromyography (Emg) Signal Classification By Artificial Neural Networks, Behnam Dashtipour

Electrical & Computer Engineering Theses & Dissertations

EMG signal processing is one of the active fields of biomedical signal processing. One unanswered question is how to determine whether a muscle is fatigued by analyzing the EMG signal. Fatigue detection could be useful in several different practical situations. There are several studies which show there are differences between EMG signal features before fatigue and after fatigue. Generally studies are based on an analytical analysis of the EMG signal instead of a quantitative analysis. In all previous studies in EMG signal processing for fatigue/nonfatigue detection, the result is that there exist some differences between the EMG signal before muscle …

Comparison Of Three Clustering Algorithms And An Application To Color Image Compression, Jihun Cha, Laurene V. Fausett

Electrical Engineering and Computer Science Faculty Publications

This paper investigates a traditional clustering algorithm (K-means) and two neural networks (SOM and ART-F). The characteristics of each algorithm are illustrated by simulating geometric space data clustering. Then each algorithm is applied to image data sets to compress the size by reducing the number of colors from 256 to 16.

Robust Partial Least-Squares Regression: A Modular Neural Network Approach, Thomas M. Mcdowall, Fredric M. Ham

Electrical Engineering and Computer Science Faculty Publications

We have developed a robust Partial Least-Squares Regression (PLSR) neural network approach to statistical calibration model development. Generalized neural network learning rules derived from a weighted statistical representation error criterion that grows less than quadratically are presented. This optimization criterion allows for higher-order statistics associated with the inputs to be taken into account and also serves to robustify the results when the empirical data contains impulsive and colored noise and outliers. The learning rules presented are considered generalized because they can be used to implement several specialized cases including: robust PLSR, linear PLSR, weighted least-squares, and variance scaling. The same …

Neural Network Approach To The Determination Of The Geophysical Model Function Of The Ers-1 C-Band Spaceborne Radar Scatterometer, Sami M. Alhumaidi, W. Linwood Jones

Electrical Engineering and Computer Science Faculty Publications

Geophysical Model Functions (GMF) describing the relationship between the scatterometer normalized radar cross section (sigma-0) and useful geophysical parameters such as sea-surface wind vectors, wave heights, and sea- surface temperatures have been undergoing extensive research and development during the last decade. In this study, we investigate the use of two feed-forward neural networks, Multilayer Perceptron and Radial Basis Functions, for developing a useful and accurate representation of the C- band GMF. Collocated radar sigma-0 cells with global wind vector models were used as the database of the study. The resulting well-known biharmonic relationship between the sigma-0 and the relative azimuth …

Navigation Satellite Selection Using Neural Networks, Daniel J. Simon, Hossny El-Sherief

Electrical and Computer Engineering Faculty Publications

The application of neural networks to optimal satellite subset selection for navigation use is discussed. The methods presented in this paper are general enough to be applicable regardless of how many satellite signals are being processed by the receiver. The optimal satellite subset is chosen by minimizing a quantity known as Geometric Dilution of Precision (GDOP), which is given by the trace of the inverse of the measurement matrix. An artificial neural network learns the functional relationships between the entries of a measurement matrix and the eigenvalues of its inverse, and thus generates GDOP without inverting a matrix. Simulation results …

Applying Neural Networks To Find The Minimum-Cost Coverage Of A Boolean Function, Pong P. Chu

Electrical and Computer Engineering Faculty Publications

To find a minimal expression of a boolean function includes a step to select the minimum cost cover from a set of implicants. Since the selection process is an NP-complete problem, to find an optimal solution is impractical for large input data size. Neural network approach is used to solve this problem. We first formalize the problem, and then define an ''energy function'' and map it to a modified Hopfield network, which will automatically search for the minima. Simulation of simple examples shows the proposed neural network can obtain good solutions most of the time.

Robust Linear Quadratic Regulation Using Neural Network, Kisuck Yoo, Michael Thursby

Electrical Engineering and Computer Science Faculty Publications

Using an Artificial Neural Network (ANN) trained with the Least Mean Square (LMS) algorithm we have designed a robust linear quadratic regulator for a range of plant uncertainty. Since there is a trade-off between performance and robustness in the conventional design techniques, we propose a design technique to provide the best mix of robustness and performance. Our approach is to provide different control strategies for different levels of uncertainty. We describe how to measure these uncertainties. We will compare our multiple strategies results with those of conventional techniques e.g. H∞ control theory. A Lyapunov equation is used to define stability …

Cepstral And Auditory Model Features For Speaker Recognition, John M. Colombi

Theses and Dissertations

The TIMIT and KING databases, as well as a ten day AFIT speaker corpus, are used to compare proven spectral processing techniques to an auditory neural representation for speaker identification. The feature sets compared were Linear Predictive Coding (LPC) cepstral coefficients and auditory nerve firing rates using the Payton model. This auditory model provides for the mechanisms found in the human middle and inner auditory periphery as well as neural transduction. Clustering algorithms were used to generate speaker specific codebooks - one statistically based and the other a neural approach. These algorithms are the Linde-Buzo-Gray (LBG) algorithm and a Kohonen …

Feature-Based Correlation Filters For Distortion Invariance, Samuel Peter Kozaitis, Robert Petrilak, Wesley E. Foor

Electrical Engineering and Computer Science Faculty Publications

In an optical correlator, binary phase-only filters (BPOFs) that recognize objects that vary in a nonrepeatable way are essential for recognizing objects from actual sensors. An approach is required that is as descriptive as a BPOF yet robust to object and background variations of an unknown or nonrepeatable type. We developed a BPOF that was more robust than a synthetic discriminant function (SDF) filter. This was done by creating a filter that retained the invariant features of a training set. By simulation, our feature-based filter offered a range of performance by setting a parameter to different values. As the value …

An Application Of Neural Networks In Data Communication Real-Time Resource Reallocation, Qing Fan

Electrical & Computer Engineering Theses & Dissertations

This thesis presents an application of artificial neural networks in real-time resource reallocation, a methodology used in the implementation of an intelligent interface node in the Computer Integrated Manufacturing (CIM) environment. In particular, the problem is formulated using a Hopfield neural network model. The real-time reallocation problem is mapped into a two-dimensional matrix of neurons similar to Hopfield and Tank's approach to the traveling salesman problem (TSP) . An energy function is formulated in terms of the hard constraints and the solution cost. The interconnection weights and the input biases are determined by the energy function. It is shown through …

Text-Independent Automatic Speaker Identification Using Partitioned Neural Networks, Laszlo Rudasi

Electrical & Computer Engineering Theses & Dissertations

This dissertation introduces a binary partitioned approach to statistical pattern classification which is applied to talker identification using neural networks. In recent years artificial neural networks have been shown to work exceptionally well for small but difficult pattern classification tasks. However, their application to large tasks (i.e., having more than ten to 20 categories) is limited by a dramatic increase in required training time. The time required to train a single network to perform N-way classification is nearly proportional to the exponential of N. In contrast, the binary partitioned approach requires training times on the order of N². …

Bounds On Constraint Weight Parameters Of Hopfield Networks For Stability Of Optimization Problem Solutions, Gursel Serpen

Electrical & Computer Engineering Theses & Dissertations

The purpose of the presented research is to study the convergence characteristics of Hopfield network dynamics. The relation between constraint weight parameter values and the stability of solutions of constraint satisfaction and optimization problems mapped to Hopfield networks is investigated. A theoretical development relating constraint weight parameter values to solution stability is presented. The dependency of solution stability on constraint weight parameter values is shown employing an abstract optimization problem. A theorem defining bounds on the constraint weight parameter magnitudes for solution stability of constraint satisfaction and optimization problems is proved. Simulation analysis on a set of optimization and constraint …