Engineering Commons^™

Finding A Viable Neural Network Architecture For Use With Upper Limb Prosthetics, Maxwell Lavin

Master of Science in Computer Science Theses

This paper attempts to answer the question of if it’s possible to produce a simple, quick, and accurate neural network for the use in upper-limb prosthetics. Through the implementation of convolutional and artificial neural networks and feature extraction on electromyographic data different possible architectures are examined with regards to processing time, complexity, and accuracy. It is found that the most accurate architecture is a multi-entry categorical cross entropy convolutional neural network with 100% accuracy. The issue is that it is also the slowest method requiring 9 minutes to run. The next best method found was a single-entry binary cross entropy …

An Application Of Clustering And Cluster Update Methods To Boiler Sensor Prediction And Case-Based-Reasoning To Boiler Repair, Timothy Edward Rooney

Theses and Dissertations

Driven by demand from both consumers and manufacturers alike, Internet of Things (IoT)

capabilities are being built into more products. Consumers want more control and access to their

devices, while manufacturers can find data gathered from IoT-capable products invaluable. In

this thesis, we use data from a growing fleet of IoT-connected boilers in the residential, lightcommercial, and medium-commercial ranges to demonstrate a framework for cluster initialization

and updating. We compare two methods of dynamically updating clusters: a sequential method

inspired by sequential K-means clustering and a cohesion-based method called DYNC. A predictive

artificial neural network system demonstrates the effectiveness of …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

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 …

Modern Methods In Machine Learning As Applied To The Study Of A Complex Supersonic Jet Flow, Andrew Steven Tenney

Dissertations - ALL

The desire for aircraft to fly higher, farther, and faster has led to the use of more complex nozzle geometries over the last several decades. These nozzles often take advantage of multiple high-velocity streams issuing from non-axisymmetric exit areas and can be optimized for airframe integration and stealth performance. The associated turbulent jet physics and the aeroacoustic phenomena have been studied thoroughly over the past 80 years; however, the complex non-linear interactions between multiple merging canonical flows are not well understood. In this study, we seek to gain a better understanding of the flow physics in the near-field of a …

Synchrophasor-Based Fault Location Detection And Classification, In Power Systems, Using Artificial Intelligence, Hemal Falak

Graduate Theses and Dissertations

With the introduction of sophisticated electronic gadgets which cannot sustain interruption in the provision of electricity, the need to supply uninterrupted and reliable power supply, to the consumers, has become a crucial factor in the present-day world. Therefore, it is customary to correctly identify fault locations in an electrical power network, in order to rectify faults and restore power supply in the minimum possible time. Many automated fault location detection algorithms have been proposed, however, prior art requires topological and physical information of the electrical power network. This thesis presents a new method of detecting fault locations, in transmission as …

Optimal And Robust Neural Network Controllers For Proximal Spacecraft Maneuvers, B. Cole George

Theses and Dissertations

Recent successes in machine learning research, buoyed by advances in computational power, have revitalized interest in neural networks and demonstrated their potential in solving complex controls problems. In this research, the reinforcement learning framework is combined with traditional direct shooting methods to generate optimal proximal spacecraft maneuvers. Open-loop and closed-loop feedback controllers, parameterized by multi-layer feed-forward artificial neural networks, are developed with evolutionary and gradient-based optimization algorithms. Utilizing Clohessy- Wiltshire relative motion dynamics, terminally constrained fixed-time, fuel-optimal trajectories are solved for intercept, rendezvous, and natural motion circumnavigation transfer maneuvers using three different thrust models: impulsive, finite, and continuous. In addition …

Neuroengineering Of Clustering Algorithms, Leonardo Enzo Brito Da Silva

Doctoral Dissertations

"Cluster analysis can be broadly divided into multivariate data visualization, clustering algorithms, and cluster validation. This dissertation contributes neural network-based techniques to perform all three unsupervised learning tasks. Particularly, the first paper provides a comprehensive review on adaptive resonance theory (ART) models for engineering applications and provides context for the four subsequent papers. These papers are devoted to enhancements of ART-based clustering algorithms from (a) a practical perspective by exploiting the visual assessment of cluster tendency (VAT) sorting algorithm as a preprocessor for ART offline training, thus mitigating ordering effects; and (b) an engineering perspective by designing a family of …