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

Engineering Commons

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

Theses/Dissertations

Artificial Intelligence and Robotics

Institution
Keyword
Publication Year
Publication

Articles 1 - 30 of 181

Full-Text Articles in Engineering

Image Restoration Using Automatic Damaged Regions Detection And Machine Learning-Based Inpainting Technique, Chloe Martin-King Dec 2019

Image Restoration Using Automatic Damaged Regions Detection And Machine Learning-Based Inpainting Technique, Chloe Martin-King

Computational and Data Sciences (Ph.D.) Dissertations

In this dissertation we propose two novel image restoration schemes. The first pertains to automatic detection of damaged regions in old photographs and digital images of cracked paintings. In cases when inpainting mask generation cannot be completely automatic, our detection algorithm facilitates precise mask creation, particularly useful for images containing damage that is tedious to annotate or difficult to geometrically define. The main contribution of this dissertation is the development and utilization of a new inpainting technique, region hiding, to repair a single image by training a convolutional neural network on various transformations of that image. Region hiding is also ...


Function And Dissipation In Finite State Automata - From Computing To Intelligence And Back, Natesh Ganesh Oct 2019

Function And Dissipation In Finite State Automata - From Computing To Intelligence And Back, Natesh Ganesh

Doctoral Dissertations

Society has benefited from the technological revolution and the tremendous growth in computing powered by Moore's law. However, we are fast approaching the ultimate physical limits in terms of both device sizes and the associated energy dissipation. It is important to characterize these limits in a physically grounded and implementation-agnostic manner, in order to capture the fundamental energy dissipation costs associated with performing computing operations with classical information in nano-scale quantum systems. It is also necessary to identify and understand the effect of quantum in-distinguishability, noise, and device variability on these dissipation limits. Identifying these parameters is crucial to ...


Demonstration Of Visible And Near Infrared Raman Spectrometers And Improved Matched Filter Model For Analysis Of Combined Raman Signals, Alexander Matthew Atkinson Oct 2019

Demonstration Of Visible And Near Infrared Raman Spectrometers And Improved Matched Filter Model For Analysis Of Combined Raman Signals, Alexander Matthew Atkinson

Electrical & Computer Engineering Theses & Disssertations

Raman spectroscopy is a powerful analysis technique that has found applications in fields such as analytical chemistry, planetary sciences, and medical diagnostics. Recent studies have shown that analysis of Raman spectral profiles can be greatly assisted by use of computational models with achievements including high accuracy pure sample classification with imbalanced data sets and detection of ideal sample deviations for pharmaceutical quality control. The adoption of automated methods is a necessary step in streamlining the analysis process as Raman hardware becomes more advanced. Due to limits in the architectures of current machine learning based Raman classification models, transfer from pure ...


Big-Data Talent Analytics In The Public Sector: A Promotion And Firing Model Of Employees At Federal Agencies, Rabih Neouchi Oct 2019

Big-Data Talent Analytics In The Public Sector: A Promotion And Firing Model Of Employees At Federal Agencies, Rabih Neouchi

Engineering Management, Information, and Systems Research Theses and Dissertations

Talent analytics is a relatively new area of focus to researchers working in analytics and data science. Talent Analytics has the potential to help companies make many informed critical decisions around talent acquisition, promotion and retention. This work investigates data science to predict “shiny star” employees in the U.S. public sector, defined as top-notch performers over the years of a given time span. Its scope falls within talent analytics, also called people analytics, a relatively new research area.

We clean a data set made available by the U.S. Office of Personnel Management (OPM) and present two models to ...


Optimal Sampling Paths For Autonomous Vehicles In Uncertain Ocean Flows, Andrew J. De Stefan Aug 2019

Optimal Sampling Paths For Autonomous Vehicles In Uncertain Ocean Flows, Andrew J. De Stefan

Dissertations

Despite an extensive history of oceanic observation, researchers have only begun to build a complete picture of oceanic currents. Sparsity of instrumentation has created the need to maximize the information extracted from every source of data in building this picture. Within the last few decades, autonomous vehicles, or AVs, have been employed as tools to aid in this research initiative. Unmanned and self-propelled, AVs are capable of spending weeks, if not months, exploring and monitoring the oceans. However, the quality of data acquired by these vehicles is highly dependent on the paths along which they collect their observational data. The ...


Developing Algorithms To Detect Incidents On Freeways From Loop Detector And Vehicle Re-Identification Data, Biraj Adhikari Jul 2019

Developing Algorithms To Detect Incidents On Freeways From Loop Detector And Vehicle Re-Identification Data, Biraj Adhikari

Civil & Environmental Engineering Theses & Dissertations

A new approach for testing incident detection algorithms has been developed and is presented in this thesis. Two new algorithms were developed and tested taking California #7, which is the most widely used algorithm to date, and SVM (Support Vector Machine), which is considered one of the best performing classifiers, as the baseline for comparisons. Algorithm #B in this study uses data from Vehicle Re-Identification whereas the other three algorithms (California #7, SVM and Algorithm #A) use data from a double loop detector for detection of an incident. A microscopic traffic simulator is used for modeling three types of incident ...


Field Drilling Data Cleaning And Preparation For Data Analytics Applications, Daniel Cardoso Braga Jun 2019

Field Drilling Data Cleaning And Preparation For Data Analytics Applications, Daniel Cardoso Braga

LSU Master's Theses

Throughout the history of oil well drilling, service providers have been continuously striving to improve performance and reduce total drilling costs to operating companies. Despite constant improvement in tools, products, and processes, data science has not played a large part in oil well drilling. With the implementation of data science in the energy sector, companies have come to see significant value in efficiently processing the massive amounts of data produced by the multitude of internet of thing (IOT) sensors at the rig. The scope of this project is to combine academia and industry experience to analyze data from 13 different ...


Exploring The Behavior Repertoire Of A Wireless Vibrationally Actuated Tensegrity Robot, Zongliang Ji Jun 2019

Exploring The Behavior Repertoire Of A Wireless Vibrationally Actuated Tensegrity Robot, Zongliang Ji

Honors Theses

Soft robotics is an emerging field of research due to its potential to explore and operate in unstructured, rugged, and dynamic environments. However, the properties that make soft robots compelling also make them difficult to robustly control. Here at Union, we developed the world’s first wireless soft tensegrity robot. The goal of my thesis is to explore effective and efficient methods to explore the diverse behavior our tensegrity robot. We will achieve that by applying state-of-art machine learning technique and a novelty search algorithm.


Identifying Hourly Traffic Patterns With Python Deep Learning, Christopher L. Leavitt Jun 2019

Identifying Hourly Traffic Patterns With Python Deep Learning, Christopher L. Leavitt

Computer Engineering

This project was designed to explore and analyze the potential abilities and usefulness of applying machine learning models to data collected by parking sensors at a major metro shopping mall. By examining patterns in rates at which customer enter and exit parking garages on the campus of the Bellevue Collection shopping mall in Bellevue, Washington, a recurrent neural network will use data points from the previous hours will be trained to forecast future trends.


Labeling Paths With Convolutional Neural Networks, Sean Wallace, Kyle Wuerch Jun 2019

Labeling Paths With Convolutional Neural Networks, Sean Wallace, Kyle Wuerch

Computer Engineering

With the increasing development of autonomous vehicles, being able to detect driveable paths in arbitrary environments has become a prevalent problem in multiple industries. This project explores a technique which utilizes a discretized output map that is used to color an image based on the confidence that each block is a driveable path. This was done using a generalized convolutional neural network that was trained on a set of 3000 images taken from the perspective of a robot along with matching masks marking which portion of the image was a driveable path. The techniques used allowed for a labeling accuracy ...


Probabilistic Spiking Neural Networks : Supervised, Unsupervised And Adversarial Trainings, Alireza Bagheri May 2019

Probabilistic Spiking Neural Networks : Supervised, Unsupervised And Adversarial Trainings, Alireza Bagheri

Dissertations

Spiking Neural Networks (SNNs), or third-generation neural networks, are networks of computation units, called neurons, in which each neuron with internal analogue dynamics receives as input and produces as output spiking, that is, binary sparse, signals. In contrast, second-generation neural networks, termed as Artificial Neural Networks (ANNs), rely on simple static non-linear neurons that are known to be energy-intensive, hindering their implementations on energy-limited processors such as mobile devices. The sparse event-based characteristics of SNNs for information transmission and encoding have made them more feasible for highly energy-efficient neuromorphic computing architectures. The most existing training algorithms for SNNs are based ...


Differential Estimation Of Audiograms Using Gaussian Process Active Model Selection, Trevor Larsen May 2019

Differential Estimation Of Audiograms Using Gaussian Process Active Model Selection, Trevor Larsen

Engineering and Applied Science Theses & Dissertations

Classical methods for psychometric function estimation either require excessive resources to perform, as in the method of constants, or produce only a low resolution approximation of the target psychometric function, as in adaptive staircase or up-down procedures. This thesis makes two primary contributions to the estimation of the audiogram, a clinically relevant psychometric function estimated by querying a patient’s for audibility of a collection of tones. First, it covers the implementation of a Gaussian process model for learning an audiogram using another audiogram as a prior belief to speed up the learning procedure. Second, it implements a use case ...


Autonomous Watercraft Simulation And Programming, Nicholas J. Savino May 2019

Autonomous Watercraft Simulation And Programming, Nicholas J. Savino

Undergraduate Theses and Capstone Projects

Automation of various modes of transportation is thought to make travel more safe and efficient. Over the past several decades advances to semi-autonomous and autonomous vehicles have led to advanced autopilot systems on planes and boats and an increasing popularity of self-driving cars. We simulated the motion of an autonomous vehicle using computational models. The simulation models the motion of a small-scale watercraft, which can then be built and programmed using an Arduino Microcontroller. We examined different control methods for a simulated rescue craft to reach a target. We also examined the effects of different factors, such as various biases ...


Machine Intelligence For Advanced Medical Data Analysis: Manifold Learning Approach, Fereshteh S Bashiri May 2019

Machine Intelligence For Advanced Medical Data Analysis: Manifold Learning Approach, Fereshteh S Bashiri

Theses and Dissertations

In the current work, linear and non-linear manifold learning techniques, specifically Principle Component Analysis (PCA) and Laplacian Eigenmaps, are studied in detail. Their applications in medical image and shape analysis are investigated.

In the first contribution, a manifold learning-based multi-modal image registration technique is developed, which results in a unified intensity system through intensity transformation between the reference and sensed images. The transformation eliminates intensity variations in multi-modal medical scans and hence facilitates employing well-studied mono-modal registration techniques. The method can be used for registering multi-modal images with full and partial data.

Next, a manifold learning-based scale invariant global shape ...


Motor Control Systems Analysis, Design, And Optimization Strategies For A Lightweight Excavation Robot, Austin Jerold Crawford May 2019

Motor Control Systems Analysis, Design, And Optimization Strategies For A Lightweight Excavation Robot, Austin Jerold Crawford

Theses and Dissertations

This thesis entails motor control system analysis, design, and optimization for the University of Arkansas NASA Robotic Mining Competition robot. The open-loop system is to be modeled and simulated in order to achieve a desired rapid, yet smooth response to a change in input. The initial goal of this work is to find a repeatable, generalized step-by-step process that can be used to tune the gains of a PID controller for multiple different operating points. Then, sensors are to be modeled onto the robot within a feedback loop to develop an error signal and to make the control system self-corrective ...


Fault Adaptive Workload Allocation For Complex Manufacturing Systems, Charlie B. Destefano May 2019

Fault Adaptive Workload Allocation For Complex Manufacturing Systems, Charlie B. Destefano

Theses and Dissertations

This research proposes novel fault adaptive workload allocation (FAWA) strategies for the health management of complex manufacturing systems. The primary goal of these strategies is to minimize maintenance costs and maximize production by strategically controlling when and where failures occur through condition-based workload allocation.

For complex systems that are capable of performing tasks a variety of different ways, such as an industrial robot arm that can move between locations using different joint angle configurations and path trajectories, each option, i.e. mission plan, will result in different degradation rates and life-expectancies. Consequently, this can make it difficult to predict when ...


Classification Of Vegetation In Aerial Imagery Via Neural Network, Gevand Balayan May 2019

Classification Of Vegetation In Aerial Imagery Via Neural Network, Gevand Balayan

UNLV Theses, Dissertations, Professional Papers, and Capstones

This thesis focuses on the task of trying to find a Neural Network that is best suited for identifying vegetation from aerial imagery. The goal is to find a way to quickly classify items in an image as highly likely to be vegetation(trees, grass, bushes and shrubs) and then interpolate that data and use it to mark sections of an image as vegetation. This has practical applications as well. The main motivation of this work came from the effort that our town takes in conserving water. By creating an AI that can easily recognize plants, we can better monitor ...


Multi-Resolution Spatio-Temporal Change Analyses Of Hydro-Climatological Variables In Association With Large-Scale Oceanic-Atmospheric Climate Signals, Kazi Ali Tamaddun May 2019

Multi-Resolution Spatio-Temporal Change Analyses Of Hydro-Climatological Variables In Association With Large-Scale Oceanic-Atmospheric Climate Signals, Kazi Ali Tamaddun

UNLV Theses, Dissertations, Professional Papers, and Capstones

The primary objective of the work presented in this dissertation was to evaluate the change patterns, i.e., a gradual change known as the trend, and an abrupt change known as the shift, of multiple hydro-climatological variables, namely, streamflow, snow water equivalent (SWE), temperature, precipitation, and potential evapotranspiration (PET), in association with the large-scale oceanic-atmospheric climate signals. Moreover, both observed datasets and modeled simulations were used to evaluate such change patterns to assess the efficacy of the modeled datasets in emulating the observed trends and shifts under the influence of uncertainties and inconsistencies. A secondary objective of this study was ...


The Affective Perceptual Model: Enhancing Communication Quality For Persons With Pimd, Jadin Tredup May 2019

The Affective Perceptual Model: Enhancing Communication Quality For Persons With Pimd, Jadin Tredup

UNLV Theses, Dissertations, Professional Papers, and Capstones

Methods for prolonged compassionate care for persons with Profound Intellectual and Multiple Disabilities (PIMD) require a rotating cast of import people in the subjects life in order to facilitate interaction with the external environment. As subjects continue to age, dependency on these people increases with complexity of communications while the quality of communication decreases. It is theorized that a machine learning (ML) system could replicate the attuning process and replace these people to promote independence. This thesis extends this idea to develop a conceptual and formal model and system prototype.

The main contributions of this thesis are: (1) proposal of ...


Predicting Chaotic Behavior In Electrical Circuits, Trey Scofield Apr 2019

Predicting Chaotic Behavior In Electrical Circuits, Trey Scofield

Mathematics, Engineering and Computer Science Undergraduate Theses

Chaotic behavior is a natural phenomenon that can be found all around us in our daily lives. This project is focused on analyzing the behavior in forced RL-Diode (resistor, inductor, and diode) electrical circuits. We determined that when the sinusoidal input voltage of the circuit was increased, the voltage across the diode experienced period doubling, quadrupling, and then eventually chaos. Furthermore, this project is focused on predicting when and how these chaotic properties emerged from data that we collected. The primary machine learning technique that is used to predict chaos properties is a recurring neural network called an echo state ...


Variable Speed Limit Control At Sag Curves Through Connected Vehicles: Implications Of Alternative Communications And Sensing Technologies, Reza Vatani Nezafat Apr 2019

Variable Speed Limit Control At Sag Curves Through Connected Vehicles: Implications Of Alternative Communications And Sensing Technologies, Reza Vatani Nezafat

Civil & Environmental Engineering Theses & Dissertations

Connected vehicles (CVs) will enable new applications to improve traffic flow. This study’s focus is to investigate how potential implementation of variable speed limit (VSL) through different types of communication and sensing technologies on CVs may improve traffic flow at a sag curve. At sag curves, the gradient changes from negative to positive values which causes a reduction in the roadway capacity and congestion. A VSL algorithm is developed and implemented in a simulation environment for controlling the inflow of vehicles to a sag curve on a freeway to minimize delays and increase throughput. Both vehicle-to-vehicle (V2V) and infrastructure-to-vehicle ...


Development And Initial Evaluation Of A Reinforced Cue Detection Model To Assess Situation Awareness In Commercial Aircraft Cockpits, Aysen K. Taylor Apr 2019

Development And Initial Evaluation Of A Reinforced Cue Detection Model To Assess Situation Awareness In Commercial Aircraft Cockpits, Aysen K. Taylor

Engineering Management & Systems Engineering Theses & Dissertations

Commercial transport aircraft of today vary greatly from early aircraft with regards to how the aircraft are controlled and the feedback provided from the machine to the human operator. Over time, as avionics systems became more automated, pilots had less direct control over their aircraft. Much research exists in the literature about automation issues, and several major accidents over the last twenty years spurred interest about how to maintain the benefits of automation while improving the overall human-machine interaction as the pilot is considered the last line of defense.

An important reason for maintaining or even improving overall pilot situation ...


Image-Based Roadway Assessment Using Convolutional Neural Networks, Weilian Song Jan 2019

Image-Based Roadway Assessment Using Convolutional Neural Networks, Weilian Song

Theses and Dissertations--Computer Science

Road crashes are one of the main causes of death in the United States. To reduce the number of accidents, roadway assessment programs take a proactive approach, collecting data and identifying high-risk roads before crashes occur. However, the cost of data acquisition and manual annotation has restricted the effect of these programs. In this thesis, we propose methods to automate the task of roadway safety assessment using deep learning. Specifically, we trained convolutional neural networks on publicly available roadway images to predict safety-related metrics: the star rating score and free-flow speed. Inference speeds for our methods are mere milliseconds, enabling ...


Dedicated Hardware For Machine/Deep Learning: Domain Specific Architectures, Angel Izael Solis Jan 2019

Dedicated Hardware For Machine/Deep Learning: Domain Specific Architectures, Angel Izael Solis

Open Access Theses & Dissertations

Artificial intelligence has come a very long way from being a mere spectacle on the silver screen in the 1920s [Hml18]. As artificial intelligence continues to evolve, and we begin to develop more sophisticated Artificial Neural Networks, the need for specialized and more efficient machines (less computational strain while maintaining the same performance results) becomes increasingly evident. Though these “new” techniques, such as Multilayer Perceptron’s, Convolutional Neural Networks and Recurrent Neural Networks, may seem as if they are on the cutting edge of technology, many of these ideas are over 60 years old! However, many of these earlier models ...


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 ...


Visual Perception For Robotic Spatial Understanding, Jason Lawrence Owens Jan 2019

Visual Perception For Robotic Spatial Understanding, Jason Lawrence Owens

Publicly Accessible Penn Dissertations

Humans understand the world through vision without much effort. We perceive the structure, objects, and people in the environment and pay little direct attention to most of it, until it becomes useful. Intelligent systems, especially mobile robots, have no such biologically engineered vision mechanism to take for granted. In contrast, we must devise algorithmic methods of taking raw sensor data and converting it to something useful very quickly. Vision is such a necessary part of building a robot or any intelligent system that is meant to interact with the world that it is somewhat surprising we don't have off-the-shelf ...


Learning Probabilistic Generative Models For Fast Sampling-Based Planning, Jinwook Huh Jan 2019

Learning Probabilistic Generative Models For Fast Sampling-Based Planning, Jinwook Huh

Publicly Accessible Penn Dissertations

Due to their simplicity and efficiency in high dimensional space, sampling-based motion planners have been gaining interest for robotic manipulation in recent years. We present several new learning approaches using probabilistic generative models for fast sampling-based planning. First, we propose fast collision detection in high dimensional configuration spaces based on Gaussian Mixture Models (GMMs) for Rapidly-exploring Random Trees (RRT). In addition, we introduce a new probabilistically safe local steering primitive based on the probabilistic model. Our local steering procedure is based on a new notion of a convex probabilistically safety corridor that is constructed around a configuration using tangent hyperplanes ...


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 ...


Event-Based Algorithms For Geometric Computer Vision, Alex Zihao Zhu Jan 2019

Event-Based Algorithms For Geometric Computer Vision, Alex Zihao Zhu

Publicly Accessible Penn Dissertations

Event cameras are novel bio-inspired sensors which mimic the function of the human retina. Rather than directly capturing intensities to form synchronous images as in traditional cameras, event cameras asynchronously detect changes in log image intensity. When such a change is detected at a given pixel, the change is immediately sent to the host computer, where each event consists of the x,y pixel position of the change, a timestamp, accurate to tens of microseconds, and a polarity, indicating whether the pixel got brighter or darker. These cameras provide a number of useful benefits over traditional cameras, including the ability ...