Engineering Commons^™

Vessel Trajectory Prediction Using Historical Ais Data, Jagir Laxmichand Charla

Dissertations and Theses

Maritime vessel position coordinates are important information for maritime situational planning and organization. A better estimate of future locations of the maritime vessels, from their current locations, can help maritime authorities to make planned decisions, which can be helpful to avoid traffic congestion and longer waiting times. This thesis develops a method for estimating future locations of the vessels using their current and previous locations and other data.

The motivating scenario for this work is that of determining the future locations of the vessels based on their current location and previous locations for accurate modelling of underwater acoustic noise. As …

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also …

Communications Using Deep Learning Techniques, Priti Gopal Pachpande

Legacy Theses & Dissertations (2009 - 2024)

Deep learning (DL) techniques have the potential of making communication systems

Architectures And Algorithms For Intrinsic Computation With Memristive Devices, Jens Bürger

Dissertations and Theses

Neuromorphic engineering is the research field dedicated to the study and design of brain-inspired hardware and software tools. Recent advances in emerging nanoelectronics promote the implementation of synaptic connections based on memristive devices. Their non-volatile modifiable conductance was shown to exhibit the synaptic properties often used in connecting and training neural layers. With their nanoscale size and non-volatile memory property, they promise a next step in designing more area and energy efficient neuromorphic hardware.

My research deals with the challenges of harnessing memristive device properties that go beyond the behaviors utilized for synaptic weight storage. Based on devices that exhibit …

Intelligent Controls For A Semi-Active Hydraulic Prosthetic Knee, Timothy Allen Wilmot

ETD Archive

We discuss open loop control development and simulation results for a semi-active above-knee prosthesis. The control signal consists of two hydraulic valve settings. These valves control a rotary actuator that provides torque to the prosthetic knee. We develop open loop control using biogeography-based optimization (BBO), which is a recently developed evolutionary algorithm, and gradient descent. We use gradient descent to show that the control generated by BBO is locally optimal. This research contributes to the field of evolutionary algorithms by demonstrating that BBO is successful at finding optimal solutions to complex, real-world, nonlinear, time varying control problems. The research contributes …

Design And Operation Of Stationary Distributed Battery Micro-Storage Systems, Ala R. Al-Haj Hussein

Electronic Theses and Dissertations

Due to some technical and environmental constraints, expanding the current electric power generation and transmission system is being challenged by even increasing the deployment of distributed renewable generation and storage systems. Energy storage can be used to store energy from utility during low-demand (off-peak) hours and deliver this energy back to the utility during high-demand (on-peak) hours. Furthermore, energy storage can be used with renewable sources to overcome some of their limitations such as their strong dependence on the weather conditions, which cannot be perfectly predicted, and their unmatched or out-of-synchronization generation peaks with the demand peaks. Generally, energy storage …

Voice Command Controller, Hoang Nghia Nguyen

Theses : Honours

Signal processing technology has been strongly developed and it has attracted interest from scientists and engineers around the world from the last decade. Speech synthesis and speech recognition are particular topic in the field that have been widely used and developed in many different area such as business, controlling, education and entertainment. The project's main objective is to study and develop an application program with the Speech SDK through design and implementation of Tele-Control system based on the commercial product of National Semiconductor: Carrier-Current Transceiver (LM 1893) and Speech development kit (Speech SDK4.0) from Microsoft Corporation. The project is suitable …

Training Strategies For Critic And Action Neural Networks In Dual Heuristic Programming Method, Christian Peter Paintz

Dissertations and Theses

This thesis discusses strategies for and details of training procedures for the Dual Heuristic Programming (DHP) methodology. This and other approximate dynamic programming approaches (HDP, DHP, GDHP) have been discussed in some detail in the literature, all being members of the Adaptive Critic Design (ACD) family. The example applications used here are the inverted pendulum problem and a fully nonlinear constant velocity bicycle steering model. The inverted pendulum has been successfully controlled using DHP, as reported in the literature. This thesis suggests and investigates several alternative D HP training procedures and compares their performance with respect to convergence speed and …

Adaptive Neural Network Controller For Atm Traffic, Jeffrey E. Larson

Theses and Dissertations

Broadband-Integrated Services Digital Networks (B-ISDN), along with Asynchronous Transfer Mode (ATM), were designed to meet the requirements of modern communication networks to handle multiple users and a wide variety of diverse traffic including voice, data and video. ATM responds to requests for admission to the network by analyzing whether or not the grade of service (GOS) requirement, specified in the admission request, can be guaranteed without violating the GOS guaranteed to traffic already accepted into the network. The GOS is typically a parameter such as cell loss rate (CLR), average delay, or some other measurement associated with network performance. In …

An Investigation Of Preliminary Feature Screening Using Signal-To-Noise Ratios, David B. Sumrell

Theses and Dissertations

A new saliency metric and a new saliency screening method are developed. This new metric, the SN saliency metric, is based upon signal-to-noise ratios, where the signal is provided by a sum of squared weights associated with a given feature, and the noise is based upon a sum of squared weights associated with a reference noise feature which is injected into the data. The resultant metric allows for a direct comparison of the feature of interest with a reference noise feature which is known to be nonsalient. The SN saliency screening method, which uses the SN saliency metric, offers the …

Configuring The Radial Basis Function Neural Network, Insoo Sohn

Theses

The most important factor in configuring an optimum radial basis function (RBF) network is the training of neural units in the hidden layer. Many algorithms have been proposed, e.g., competitive learning (CL), to train the hidden units. CL suffers from producing "dead-units." The other major factor Which was ignored in the past is the appropriate selection of the number of neural units in the hidden layer. The frequency sensitive competitive learning (FSCL) algorithm was proposed to alleviate the problem of dead-units, but it does not alleviate the latter problem. The rival penalized competitive learning (RPCL) algorithm is an improved version …

Adaptive And Fixed Wavelet Features For Narrowband Signal Classification, Anthony J. Pohl

Theses and Dissertations

The application of the multiresolution analysis developed by Mallat to signal classification by Pati and Krishnaprasad and Szu, et al, is further explored in this thesis. Several different wavelet based feature extraction and classification systems are developed and implemented. Methods which rely on the traditional dyadic wavelet decomposition and on the adaptive wavelet representation are presented. Each of the classification systems is implemented for a labeled data set of narrowband signals. Finally, classification results on the full data set and on low frequency Fourier coefficients are provided as baseline comparisons for our work.

Space Object Identification Using Spatio-Temporal Pattern Recognition, Gary W. Brandstrom

Theses and Dissertations

This thesis is part of a research effort to automate the task of characterizing space objects or satellites based on a sequence of images. The goal is to detect space object anomalies. Two algorithms are considered - the feature space trajectory neural network (FST NN) and hidden Markov model (HMM) classifier. The FST NN was first presented by Leonard Neiberg and David P. Casasent in 1994 as a target identification tool. Kenneth H. Fielding and Dennis W. Ruck recently applied the hidden Markov model classifier to a 3D moving light display identification problem and a target recognition problem, using time …

Time-Frequency Shift-Tolerance And Counterpropagation Network With Applications To Phoneme Recognition, Li-Minn Ang

Theses : Honours

Human speech signals are inherently multi-component non-stationary signals. Recognition schemes for classification of non-stationary signals generally require some kind of temporal alignment to be performed. Examples of techniques used for temporal alignment include hidden Markov models and dynamic time warping. Attempts to incorporate temporal alignment into artificial neural networks have resulted in the construction of time-delay neural networks. The nonstationary nature of speech requires a signal representation that is dependent on time. Time-frequency signal analysis is an extension of conventional time-domain and frequency-domain analysis methods. Researchers have reported on the effectiveness of time-frequency representations to reveal the time-varying nature of …

Head Related Transfer Function Approximation Using Neural Networks, John K. Millhouse

Theses and Dissertations

This thesis determines whether an artificial neural network (ANN) can approximate the Armstrong Aerospace Medical Research Laboratories (AAMRL) head related transfer functions (HRTF) data obtained from research at AAMRL during the fall of 1988. The first test determines whether HRTF lends any support in sound localization when compared to no HRTF (Interaural Time Delay only). There is a statistically significant interaction between the location of the sound and whether the HRTF or no HRTF is used. When this interaction is removed using the alternate F.Value, the statistics give the result of equal means for the filters and azimuth. This means …

Embedology And Neural Estimation For Time Series Prediction, Robert E. Garza

Theses and Dissertations

Time series prediction has widespread application, ranging from predicting the stock market to trying to predict future locations of scud missiles. Recent work by Sauer and Casdagli has developed into the embedology theorem, which sets forth the procedures for state space manipulation and reconstruction for time series prediction. This includes embedding the time series into a higher dimensional space in order to form an attractor, a structure defined by the embedded vectors. Embedology is combined with neural technologies in an effort to create a more accurate prediction algorithm. These algorithms consist of embedology, neural networks, Euclidean space nearest neighbors, and …

Neural Networks For Dynamic Flight Control, Ronald E. Setzer

Theses and Dissertations

This thesis examines the application of artificial neural networks (NNs) to the problem of dynamic flight control. The specific application is the control of a flying model helicopter. The control interface is provided through a hardware and software test bed called the Fast Adaptive Maneuvering Experiment (FAME). The NN design approach uses two NNs: one trained as an emulator of the plant and the other trained to control the emulator. The emulator neural network is designed to reproduce the flight dynamics of the experimental plant. The controller is then designed to produce the appropriate control inputs to drive the emulator …

Color Image Segmentation, Kimberley A. Mccrae

Theses and Dissertations

The most difficult stage of automated target recognition ATR is segmentation. Current AFIT segmentation problems include faces and tactical targets previous efforts to segment these objects have used intensity and motion cues. This thesis develops a color preprocessing scheme to be used with the other segmentation techniques. A neural network is trained to identify the color of a desired object, eliminating all but that color from the scene. Gabor correlations and 2D wavelet transformations will be performed on stationary images and 3D wavelet transforms on multispectral data will incorporate color and motion detection into the machine visual system. The thesis …

Automatic Tuning Of Integrated Filters Using Neural Networks, Lutz Henning Lenz

Dissertations and Theses

Component values of integrated filters vary considerably due to· manufacturing tolerances and environmental changes. Thus it is of major importance that the components of an integrated filter be electronically tunable. The method explored in this thesis is the transconductance-C-method.

A method of realizing higher-order filters is to use a cascade structure of second-order filters. In this context, a method of tuning second-order filters becomes important.

The research objective of this thesis is to determine if the Neural Network methodology can be used to facilitate the filter tuning process for a second-order filter (realized via the transconductance-C-method). Since this thesis is, …

Etann Hardware Implementation For Radar Emitter Identification, James B. Calvin Jr.

Theses and Dissertations

This study investigated classification of 30 radar emitters with 16 signal features using Intel's 80170NX chip, the Electronically Trainable Analog Neural Network (ETANN). Software tools were developed to characterize the ETANN sigmoidal transfer function for use in a custom simulator, known as Neural Graphics. Neural Graphics operates on a Silicon Graphics workstation. The Intel Neural Network Training System simulators were used in early experiments, but were found to be inefficient in training on data used in this research. Using a modified Neural Graphics simulator, single chip and multi-chip experiments were performed to provide benchmark results prior to performing chip-in-loop training. …

Face Recognition With Neural Networks, Dennis L. Krepp

Theses and Dissertations

This study investigated neural networks for face verification and classification. The research concentrated on developing a neural network based feature extractor and/or classifier to perform authorized user verification in a realistic work environment. Recognition accuracy, system assumptions, training time, and execution time were analyzed to determine the feasibility of a neural network approach. Data was collected using a camcorder and two segmentation schemes: manual segmentation and motion-based, automatic segmentation. Data consisted of over 2000. 32x32 pixel, 8 bit gray scale images of 52 subjects; each subject had two to ten days worth of images collected. Several training and test sets …

Signal Approximation With A Wavelet Neural Network, Charles M. Westphal

Theses and Dissertations

This study investigated the use of Wavelet Neural Networks (WNN) for signal approximation. The particular wavelet function used in this analysis consisted of a summation of sigmoidal functions (a sigmoidal wavelet). The sigmoidal wavelet has the advantage of being easily implemented in hardware via specialized electronic devices like the Intel Electronically Trainable Analog Neural Network (ETANN) chip. The WNN representation allows the determination of the number of hidden-layer nodes required to achieve a desired level of approximation accuracy. Results show that a bandlimited signal can be accurately approximated with a WNN trained with irregularly sampled data. Signal approximation, Wavelet neural …

A Gaze-Addressing Communication System Using Artificial Neural Networks, Gabriel Baud-Bovy

Dissertations and Theses

Severe motor disabilities can render a person almost completely incapable of communication. Nevertheless, in many cases, the sensory systems are intact and the eye movements are still under good control. In these cases, one can use a device such as the Brain Response Interface (BRI) to command a remote control (e.g. room temperature, bed position), a word-processor, a speech synthesizer, and so on.

The BRI is a gaze-addressing communication system that was developed by Dr. Erik E. Sutter at the Smith-Kettlewell Eye Research Institute, San-Francisco: a menu of communication objects (e.g. letter, word, command) is displayed on a TV screen; …

Design Of An Artificial Neural Network Based Tactile Sensor For The Utah/Mit Dexterous Hand, Jeffery D. Nering

Theses and Dissertations

The Neural Tactile Sensor (NTS) is a high resolution, easily manufactured tactile sensor consisting of electrodes, a thin resistive 'skin', and pattern recognition circuitry that is capable of resolving dynamic and static contact location, force, and slip throughout the continuum of the sensor's active region. The sensor operates by means of a resistive 'skin' harboring the electric field generated when a current is injected into it, and a plurality of electrodes for taking measurements of said electric field. When current flows through the resistive medium from the location of tactile contact, an electric field within the resistive medium is established, …

A New Method To Optimize The Satellite Broadcasting Schedules Using The Mean Field Annealing Of A Neural Network, Youyi Yu

Theses

This thesis reports a new method for optimizing satellite broadcasting schedules based on the Hopfield neural model in combination with the mean field annealing theory. A clamping technique is used with an associative matrix, thus reducing the dimensions of the solution space. A formula for estimating the critical temperature for the mean field annealing procedure is derived, hence enabling the updating of the mean field theory equations to be more economical. Several factors on the numerical implementation of the mean field equations using a straightforward iteration method that may cause divergence are discussed; methods to avoid this kind of divergence …

Feature Extraction For Pose Estimation. A Comparison Between Synthetic And Real Ir Imagery, Donald J. Willis

Theses and Dissertations

This research addressed the problem of pose estimation of three- dimensional objects given their two-dimensional IR imagery and corresponding synthetic (computer-generated) IR imagery. Features and techniques were investigated to find those which may be extendable from computer models to real- world IR imagery. GTSIG and SCNGEN were used to create the synthetic imagery. Silhouette and outline shape moments were explored as optimum features for the comparison. Employing back-propagation with momentum as the training paradigm, a two-hidden-layer neural network was able to determine the base-plane orientation of the synthetic imagery to within 7.5 degrees with better than 90% accuracy. (No conclusive …

Function Prediction Using Recurrent Neural Networks, Randall L. Lindsey

Theses and Dissertations

A fully recurrent neural network was applied to the function prediction problem. The real-time recurrent learning (RTRL) algorithm was modified and tested for use as a viable function predictor. The modification gave the algorithm a variable learning rate and a linear/sigmoidal output selection. Verifying the networks ability to temporally learn both the classic exclusive-OR (XOR) problem and the internal state problem, the network was then used to simulate the frequency response of a second order IIR lowpass Butterworth filter. The recurrent network was then applied to two problems: head position tracking, and voice date reconstruction. The accuracy at which the …

Binaural Sound Localization Using Neural Networks, Rushby C. Craig

Theses and Dissertations

The purpose of this study was to investigate the use of Artificial Neural Networks to localize sound sources from simulated, human binaural signals. Only sound sources originating from a circle on the horizontal plane were considered. Experiments were performed to examine the ability of the networks to localize using three-different feature sets. The feature sets used were: time-samples of the signals, mena Fast Fourier Transform magnitude and cross correlation data, and auto-correlation and cross correlation data. The two different types of sound source signals considered were tones and gaussian noise. The feature set which yielded the best results in terms …

Infrared Target Recognition, Brian D. Singstock

Theses and Dissertations

In this thesis, three approaches were used for Automatic Target Recognition (ATR). These approaches were shape, moment and Fourier generated features, Karhunen-Loeve transform (KLT) generated features and Discrete Cosine Transform (DCT) generated features. The KLT approach was modelled after the face recognition research by Suarez, AFIT, and Turk and Pentland, MIT. A KLT is taken of a reduced covariance matrix, composed all three classes of targets, and the resulting eigenimages are used to reconstruct the original images. The reconstruction coefficients for each original image are found by taking the dot product of the original image with each eigenimage. These reconstruction …

An Investigation Of The Application Of Artificial Neural Networks To Adaptive Optics Imaging Systems, Andrew H. Suzuki

Theses and Dissertations

Recurrent and feedforward artificial neural networks are developed as wavefront reconstructors. The recurrent neural network studied is the Hopfield neural network and the feedforward neural network studied is the single layer perceptron artificial neural network. The recurrent artificial neural network input features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input features are just the wavefront sensor slope outputs. Both artificial neural networks use their inputs to calculate deformable mirror actuator commands. The effects of training are examined.