Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 30 of 32

Full-Text Articles in Engineering

Automated Field Boundary Detection Using Modern Machine Learning Techniques, Rishikumar Suresh Kumar Jan 2020

Automated Field Boundary Detection Using Modern Machine Learning Techniques, Rishikumar Suresh Kumar

Creative Components

The Agricultural Conservation Planning Framework (ACPF) is a framework for watershed analysis that is supported by a unique land management database. Implementing the ACPF Framework comprises several steps. One of the most important steps in this framework is manually editing the United States Department of Agriculture (USDA) Farm Service Agency (FSA) Common Land Unit (CLU) boundaries to match cropping patterns per USDA National Agricultural Statistics Service (NASS) Cropland Data Layer (CDL) and National Agricultural Imagery Program (NAIP) aerial imagery. This step uses lot of man-hours and is highly susceptible to human errors. The use of latest deep-learning techniques will help ...


Towards Energy-Efficient Hardware Acceleration Of Memory-Intensive Event-Driven Kernels On A Synchronous Neuromorphic Substrate, Saunak Saha Jan 2019

Towards Energy-Efficient Hardware Acceleration Of Memory-Intensive Event-Driven Kernels On A Synchronous Neuromorphic Substrate, Saunak Saha

Graduate Theses and Dissertations

Spiking neural networks are increasingly becoming popular as low-power alternatives to deep learning architectures. To make edge processing possible in resource-constrained embedded devices, there is a requirement for reconfigurable neuromorphic accelerators that can cater to various topologies and neural dynamics typical to these networks. Subsequently, they also must consolidate energy consumption in emulating these dynamics. Since spike processing is essentially memory-intensive in nature, a significant proportion of the system's power consumption can be reduced by eliminating redundant memory traffic to off-chip storage that holds the large synaptic data for the network. In this work, I will present CyNAPSE, a ...


Deep Learning For Monitoring Cyber-Physical Systems, Tryambak Gangopadhyay Jan 2019

Deep Learning For Monitoring Cyber-Physical Systems, Tryambak Gangopadhyay

Graduate Theses and Dissertations

Different cyber-physical systems involving sequential data require accurate frameworks for predicting the state of the system leading to effective monitoring. If the framework is explanatory, the insights provided by the explanations can improve scientific understanding of the system. Detecting the transition to an impending instability is important to initiate effective control in a combustion system. Building robust frameworks is important in this context.

As one of the early applications of characterizing instability in a combustion system using Deep Neural Networks, we train our proposed deep convolutional neural network (CNN) model on sequential image frames extracted from hi-speed flame videos by ...


Freeway Traffic Incident Detection Using Large Scale Traffic Data And Cameras, Pranamesh Chakraborty Jan 2019

Freeway Traffic Incident Detection Using Large Scale Traffic Data And Cameras, Pranamesh Chakraborty

Graduate Theses and Dissertations

Automatic incident detection (AID) is crucial for reducing non-recurrent congestion caused by traffic incidents. In this paper, a data-driven AID framework is proposed that can leverage large-scale historical traffic data along with the inherent topology of the traffic networks to obtain robust traffic patterns. Such traffic patterns can be compared with the real-time traffic data to detect traffic incidents in the road network. Our AID framework consists of two basic steps for traffic pattern estimation. First, we estimate a robust univariate speed threshold using historical traffic information from individual sensors. This step can be parallelized using MapReduce framework thereby making ...


A Methodology For Rapid Hypersonic Flow Predictions Via Surrogate Modeling With Machine Learning And Deep Learning, Nathan Hemming Jan 2018

A Methodology For Rapid Hypersonic Flow Predictions Via Surrogate Modeling With Machine Learning And Deep Learning, Nathan Hemming

Graduate Theses and Dissertations

Generating and parsing through large amounts of wind tunnel,

ight test, or computational

uid dynamics (CFD) data can prove to be expensive. This makes, for example, the optimization

of aerothermal hypersonic components, which may contain a large number of independent variables,

challenging. Having a surrogate model to quickly and accurately approximate the data can help

with the optimal design process. A lower order model can be used instead of or in conjunction

with a higher order model to model a system with less computational eort. Typically, additional

assumptions are made to make a lower order model. These have the benet ...


A Study Of Interpretability Mechanisms For Deep Networks, Apurva Dilip Kokate Jan 2018

A Study Of Interpretability Mechanisms For Deep Networks, Apurva Dilip Kokate

Graduate Theses and Dissertations

Deep neural networks are traditionally considered to be “black-box” models where it is generally difficult to interpret a certain decision made by such models given a test instance. However, as deep learning is increasingly becoming the tool of choice in making many safety-critical and time-critical decisions such as perception for self-driving cars, the machine learning community has been extremely interested recently to build interpretation mechanisms for these so called black box deep learning models primarily to build users’ trust with the models. Many such mechanisms have been developed to explain behavior of deep models such as convolutional neural networks (CNNs ...


Reducing Labeling Complexity In Streaming Data Mining, Yesdaulet Izenov Jan 2018

Reducing Labeling Complexity In Streaming Data Mining, Yesdaulet Izenov

Graduate Theses and Dissertations

Supervised machine learning is an approach where an algorithm estimates a mapping

function by using labeled data i.e. utilizing data attributes and target values. One of the major

obstacles in supervised learning is the labeling step. Obtaining labeled data is an expensive

procedure since it typically requires human effort. Training a model with too little data tends

to overfit therefore in order to achieve a reasonable accuracy of prediction we need a minimum

number of labeled examples. This is also true for streaming machine learning models. Maintaining

a model without rebuilding and performing a prediction task without ever storing ...


Behavior-Grounded Multi-Sensory Object Perception And Exploration By A Humanoid Robot, Jivko Sinapov Jan 2013

Behavior-Grounded Multi-Sensory Object Perception And Exploration By A Humanoid Robot, Jivko Sinapov

Graduate Theses and Dissertations

Infants use exploratory behaviors to learn about the objects around them. Psychologists have theorized that behaviors such as touching, pressing, lifting, and dropping enable infants to form grounded object representations. For example, scratching an object can provide information about its roughness, while lifting it can provide information about its weight. In a sense, the exploratory behavior acts as a ``question'' to the object, which is subsequently ``answered" by the sensory stimuli produced during the execution of the behavior. In contrast, most object representations used by robots today rely solely on computer vision or laser scan data, gathered through passive observation ...


Intelligence Tests For Robots: Solving Perceptual Reasoning Tasks With A Humanoid Robot, Connor Schenck Jan 2013

Intelligence Tests For Robots: Solving Perceptual Reasoning Tasks With A Humanoid Robot, Connor Schenck

Graduate Theses and Dissertations

Intelligence test scores have long been shown to correlate with a wide variety of other abilities. The goal of this thesis is to enable a robot to solve some of the common tasks from intelligence tests with the intent of improving its performance on other real-world tasks. In other words, the goal of this thesis is to make robots more intelligent. We used an upper-torso humanoid robot to solve three common perceptual reasoning tasks: the object pairing task, the order completion task, and the matrix completion task. Each task consisted of a set of objects arranged in a specific configuration ...


A Study Of The Accuracy, Completeness, And Efficiency Of Artificial Neural Networks And Related Inductive Learning Techniques , Craig Garlin Carmichael Jan 2001

A Study Of The Accuracy, Completeness, And Efficiency Of Artificial Neural Networks And Related Inductive Learning Techniques , Craig Garlin Carmichael

Retrospective Theses and Dissertations

Artificial Neural Networks (ANNs) have been an intense topic of research in the last decade. They have been viewed as black boxes, where the inputs were known and the outputs were computed, but the underlying statistics and thus reliability of the networks were not fully understood. Because of this, there has been hesitation in utilizing ANNs in automated systems such as intelligent flight control. This hesitation is diminishing, however. Individual elements of a neural network can be probed and their decision-making power assessed. In this study, a neural network is trained and then various ranking methods are used to assess ...


Algorithms For Enhancing Pattern Separability, Feature Selection And Incremental Learning With Applications To Gas Sensing Electronic Nose Systems , Robi Polikar Jan 2000

Algorithms For Enhancing Pattern Separability, Feature Selection And Incremental Learning With Applications To Gas Sensing Electronic Nose Systems , Robi Polikar

Retrospective Theses and Dissertations

Three major issues in pattern recognition and data analysis have been addressed in this study and applied to the problem of identification of volatile organic compounds (VOC) for gas sensing applications. Various approaches have been proposed and discussed. These approaches are not only applicable to the VOC identification, but also to a variety of pattern recognition and data analysis problems. In particular, (1) enhancing pattern separability for challenging classification problems, (2) optimum feature selection problem, and (3) incremental learning for neural networks have been investigated;Three different approaches are proposed for enhancing pattern separability for classification of closely spaced, or ...


Knowledge Based Expert System Pavement Management Optimization , Omar Ghaleb Smadi Jan 2000

Knowledge Based Expert System Pavement Management Optimization , Omar Ghaleb Smadi

Retrospective Theses and Dissertations

Knowledge-based expert systems and dynamic programming are used for development of a comprehensive pavement management system tool to help engineers and planners to make objective, consistent, and cost effective decisions regarding pavement maintenance, rehabilitation, and reconstruction;Knowledge-based expert system provide a flexible tool to allow for acquisition of knowledge from experts in the field and incorporate that knowledge in building an efficient pavement management decision support tool. Knowledge-based expert systems are used to develop a pavement condition forecasting model and a treatment strategy selection model. The forecasting model is capable of predicting pavement condition in the future based on both ...


Power System Security Boundary Visualization Using Intelligent Techniques , Guozhong Zhou Jan 1998

Power System Security Boundary Visualization Using Intelligent Techniques , Guozhong Zhou

Retrospective Theses and Dissertations

In the open access environment, one of the challenges for utilities is that typical operating conditions tend to be much closer to security boundaries. Consequently, security levels for the transmission network must be accurately assessed and easily identified on-line by system operators;Security assessment through boundary visualization provides the operator with knowledge of system security levels in terms of easily monitorable pre-contingency operating parameters. The traditional boundary visualization approach results in a two-dimensional graph called a nomogram. However, an intensive labor involvement, inaccurate boundary representation, and little flexibility in integrating with the energy management system greatly restrict use of nomograms ...


Profiting From Competition: Financial Tools For Electric Generation Companies , Charles William Richter Jr. Jan 1998

Profiting From Competition: Financial Tools For Electric Generation Companies , Charles William Richter Jr.

Retrospective Theses and Dissertations

Regulations governing the operation of electric power systems in North America and many other areas of the world are undergoing major changes designed to promote competition. This process of change is often referred to as deregulation. Participants in deregulated electricity systems may find that their profits will greatly benefit from the implementation of successful bidding strategies. While the goal of the regulators may be to create rules which balance reliable power system operation with maximization of the total benefit to society, the goal of generation companies is to maximize their profit, i.e., return to their shareholders. The majority of ...


Pns Algorithm For Solving Supersonic Flows With Upstream Influences , James Hale Miller Jan 1997

Pns Algorithm For Solving Supersonic Flows With Upstream Influences , James Hale Miller

Retrospective Theses and Dissertations

The goal of this research is to produce a robust, parabolized Navier-Stokes (PNS) code that will significantly reduce the computer time required to calculate flows about complex vehicles with embedded subsonic/separated regions. The major drawback of "current day" PNS codes is that they cannot be used to compute separated regions which occur near canopies, wing-body junctures, etc. As a result, Navier-Stokes (NS) codes are often used to compute the entire flowfield despite the fact that a PNS code requires at least one order of magnitude less computer time and storage;An innovative approach has been developed to permit a ...


Development Of Four In-Process Surface Recognition Systems To Predict Surface Roughness In End Milling , Shi-Jer Lou Jan 1997

Development Of Four In-Process Surface Recognition Systems To Predict Surface Roughness In End Milling , Shi-Jer Lou

Retrospective Theses and Dissertations

Surface roughness is one of the important factors in tribology and in evaluating the quality of machining operations. To realize full automation and achieve zero defect production, an effective technique is needed for on-line, real-time monitoring of surface roughness during machining. An in-process surface recognition system (ISRS), was developed for predicting real-time surface roughness, Ra, in end-milling operations. The parameters are spindle speed, feed rate, depth of cut, and the cutting, vibration between tool and workpiece. The cutting vibration is measured by an accelerometer and a proximity sensor;The analyses of the data and the ISRS building model are carried ...


The Fuzzy-Nets Based Approach In Predicting The Cutting Power Of End Milling Operations , Chuan-Teh Chang Jan 1997

The Fuzzy-Nets Based Approach In Predicting The Cutting Power Of End Milling Operations , Chuan-Teh Chang

Retrospective Theses and Dissertations

Process planning is a major determinant of manufacturing cost. The selection of machining parameters is an important element of process planning. The development of a utility to show the cutting power on-line would be helpful to programmers and process planners in selecting machining parameters. The relationship between the cutting power and the machining parameters is nonlinear. Presently there is no accurate or simple algorithm to calculate the required cutting power for a selected set of parameters. Although machining data handbooks, machinability data systems, and machining databases have been developed to recommend machining parameters for efficient machining, they are basically for ...


Three-Dimensional Object Recognition , Kehang Chen Jan 1997

Three-Dimensional Object Recognition , Kehang Chen

Retrospective Theses and Dissertations

In the development of an object pattern recognition system, feature construction is always the problem issue. Due to the large amount of information contained in three dimensional (3D) objects, features extracted to efficiently and sufficiently represent 3D objects are difficult to obtain. Thus, current commercially available object recognition systems mostly emphasize the classification of two dimensional objects or patterns. This work presents a paradigm to develop a complete 3D object recognition system that uses simple and efficient features, and supports the integration of CAD/CAM models;In this research, several proposed algorithm for extracting features representing 3D objects are constructed ...


Invariance Transformations For Processing Nde Signals , Shreekanth Ammanji Mandayam Jan 1996

Invariance Transformations For Processing Nde Signals , Shreekanth Ammanji Mandayam

Retrospective Theses and Dissertations

The ultimate objective in nondestructive evaluation (NDE) is the characterization of materials, on the basis of information in the response from energy/material interactions. This is commonly referred to as the "inverse problem." Inverse problems are in general ill-posed and full analytical solutions to these problems are seldom tractable. Pragmatic approaches for solving them employ a constrained search technique by limiting the space of all possible solutions. A more modest goal is therefore to use the received signal for characterizing defects in objects in terms of the location, size and shape. However, the NDE signal received by the sensors is ...


Propagation Of Uncertainty In A Knowledge-Based System To Assess Energy Management Strategies For New Technologies , Chun-Yen Hsu Jan 1995

Propagation Of Uncertainty In A Knowledge-Based System To Assess Energy Management Strategies For New Technologies , Chun-Yen Hsu

Retrospective Theses and Dissertations

The goal of this project is to investigate the propagation of uncertainty in a knowledge-based system that assesses energy management strategies for new gas and electric technologies that can help reduce energy consumption and demand. The new technologies that have been investigated include lighting, electric heat pumps, motors, refrigerators, microwave clothes dryers, freeze concentration, electric vehicles, gas furnaces, gas heat pumps, engine-driven chillers, absorption chillers, and natural gas vehicles distributed throughout the residential, commercial, industrial, and transportation sectors;The description of a complex assessment system may be simplified by allowing some degree of uncertainty. A number of uncertainty-representing mechanisms, such ...


Automated Image Inspection Using Wavelet Decomposition And Fuzzy Rule-Based Classifier , Zhong Zhang Jan 1995

Automated Image Inspection Using Wavelet Decomposition And Fuzzy Rule-Based Classifier , Zhong Zhang

Retrospective Theses and Dissertations

A general purpose image inspecting system has been developed for automatic flaw detection in industrial applications. The system has a general purpose image understanding architecture that performs local feature extraction and supervised classification. Local features of an image are extracted from the compactly supported wavelet transform of the image. The features extracted from the wavelet transform provide local harmonic analysis and multi-resolution representation of the image. Image segmentation is achieved by classifying image pixels based on features extracted within a local area near each pixel. The supervised classifier used in the segmentation process is a fuzzy rule-based classifier which is ...


Nuclear Plant Diagnostics Using Neural Networks With Dynamic Input Selection , Anujit Basu Jan 1995

Nuclear Plant Diagnostics Using Neural Networks With Dynamic Input Selection , Anujit Basu

Retrospective Theses and Dissertations

The work presented in this dissertation explores the design and development of a large scale nuclear power plant (NPP) fault diagnostic system based on artificial neural networks (ANNs). The viability of detecting a large number of transients in a NPP using ANNs is demonstrated. A new adviser design is subsequently presented where the diagnostic task is divided into component parts, and each part is solved by an individual ANN. This new design allows the expansion of the diagnostic capabilities of an existing adviser by modifying the existing ANNs and adding new ANNs to the adviser;This dissertation also presents an ...


Medical Image Tomography: A Statistically Tailored Neural Network Approach , John Patrick Kerr Jan 1994

Medical Image Tomography: A Statistically Tailored Neural Network Approach , John Patrick Kerr

Retrospective Theses and Dissertations

In medical computed tomography (CT) the tomographic images are reconstructed from planar information collected 180∘ to 360∘ around the patient. In clinical applications, the reconstructions are typically produced using a filtered backprojection algorithm. Filtered backprojection methods have limitations that create a high percentage of statistical uncertainty in the reconstructed images. Many techniques have been developed which produce better reconstructions, but they tend to be computationally expensive, and thus, impractical for clinical use;Artificial neural networks (ANN) have been shown to be adept at learning and then simulating complex functional relationships. For medical tomography, a neural network can be trained to ...


Advanced Fuzzy Logic Controllers And Self-Tuning Strategy , Shou-Heng Huang Jan 1994

Advanced Fuzzy Logic Controllers And Self-Tuning Strategy , Shou-Heng Huang

Retrospective Theses and Dissertations

This study has concentrated on fuzzy logic controllers from the basic aspects to an advanced self-tuning strategy. Fuzzy logic provides a very good technique for knowledge representation which makes it possible to incorporate the experience of human operators in the design of controllers;The basic concepts of fuzzy set theory, fundamental definitions of fuzzy logic, and basic structure of fuzzy logic controllers are introduced and a guideline for building the fuzzy rule-based system is developed. The rule development and adjustment strategies for fuzzy logic controllers are presented and experimentally identified. The fuzzy logic control system is analyzed on a linguistic ...


Spline Network Modeling And Fault Classification Of A Heating Ventilation And Air-Conditioning System , Mathew Scaria Chackalackal Jan 1994

Spline Network Modeling And Fault Classification Of A Heating Ventilation And Air-Conditioning System , Mathew Scaria Chackalackal

Retrospective Theses and Dissertations

A spline network, that is an alternative to artificial neural networks, is introduced in this dissertation. This network has an input layer, a single hidden layer, and an output layer. Spline basis functions, with small support, are used as the activation functions. The network is used to model the steady state operation of a complex Heating Ventilation and Air-conditioning (HVAC) system. Real data was used to train the spline network. A neural network was also trained on the same set of data. Based on the training process, it is possible to conclude that when compared to artificial neural networks, the ...


Color Computer Vision For Characterization Of Corn Germplasm , Suranjan Panigrahi Jan 1992

Color Computer Vision For Characterization Of Corn Germplasm , Suranjan Panigrahi

Retrospective Theses and Dissertations

A color computer vision system was developed at Iowa State University, Ames, Iowa for morphological characterization of corn germplasm. The system consists of a color camera, a PC-AT host computer, a color frame digitizer, a video display monitor, a color video decoder and encoder, and a specially designed lighting chamber. The lighting chamber was specially designed and fabricated to provide uniform lighting for acquiring images of ear corn. The components of the system were matched and interfaced to configure the entire system. A study was conducted to calibrate each component and the entire system to ensure proper functioning of the ...


An Expert Fuzzy Logic Controller Employing Adaptive Learning For Servo Systems , Zong-Mu Yeh Jan 1992

An Expert Fuzzy Logic Controller Employing Adaptive Learning For Servo Systems , Zong-Mu Yeh

Retrospective Theses and Dissertations

An expert fuzzy logic controller with adaptive learning is proposed as an intelligent controller for servo systems. A key component of this controller is an adaptive learning mechanism which is used to self-regulate the scaling factors and the control action based on the error between the desired value and the plant output. The inference engine of this controller is based on the principle of approximate reasoning and the learning strategy is based on reinforcement learning. A novel approach of model reference adaptive control is also proposed for servo systems. The comparison of the performance between the proposed controller and PID ...


Knowledge Base Expert System Control Of Spatial Xenon Oscillations In Pressurized Water Reactors , Serhat Alten Jan 1992

Knowledge Base Expert System Control Of Spatial Xenon Oscillations In Pressurized Water Reactors , Serhat Alten

Retrospective Theses and Dissertations

Nuclear reactor operators are required to pay special attention to spatial xenon oscillations during the load-follow operation of pressurized water reactors. They are expected to observe the axial offset of the core, and to estimate the correct time and amount of necessary control action based on heuristic rules given in axial offset control strategies;Current control methods of axial xenon oscillations are knowledge intensive, and heuristic in nature. An expert system, ACES (Axial offset Control using Expert Systems) is developed to implement a heuristic constant axial offset control procedure to aid reactor operators in increasing the plant reliability by reducing ...


Neural Network Approach For Solving Inverse Problems, Ibrahim Mohamed Elshafiey Jan 1991

Neural Network Approach For Solving Inverse Problems, Ibrahim Mohamed Elshafiey

Retrospective Theses and Dissertations

No abstract provided.


A Microcomputer Based Combined Machine Vision And Expert System For Irregular Object Classification , Syed Azhar Saeed Zaidi Jan 1990

A Microcomputer Based Combined Machine Vision And Expert System For Irregular Object Classification , Syed Azhar Saeed Zaidi

Retrospective Theses and Dissertations

In recent years, much work has been reported on the development of microcomputer based machine vision systems. A substantial portion of this research assumes most of the items subjected for machine vision inspection, can be categorized by a regular geometrical shape. Most of the vision systems, and microcomputer-based vision systems in particular, are designed to perform singular tasks. They are niche oriented and designed to be used in an inflexible environment, and are designed to process regular objects. These systems are prohibitively expensive for small industrial concerns;The objective of the research was to develop and design a low cost ...