Other Computer Engineering Commons^™

An Algorithm For Reconstructing Three-Dimensional Images From Overlapping Two-Dimensional Intensity Measurements With Relaxed Camera Positioning Requirements, With Application To Additive Manufacturing, Siranee Nuchitprasitchai

Dissertations, Master's Theses and Master's Reports

Cameras are everywhere for security purposes and there are often many cameras installed close to each other to cover areas of interest, such as airport passenger terminals. These systems are often designed to have overlapping fields of view to provide different aspects of the scene to review when, for example, law enforcement issues arise. However, these cameras are rarely, if ever positioned in a way that would be conducive to conventional stereo image processing. To address this, issue an algorithm was developed to rectify images measured under such conditions, and then perform stereo image reconstruction. The initial experiments described here …

Design Automation For Carbon Nanotube Circuits Considering Performance And Security Optimization, Lin Liu

Dissertations, Master's Theses and Master's Reports

As prevailing copper interconnect technology advances to its fundamental physical limit, interconnect delay due to ever-increasing wire resistivity has greatly limited the circuit miniaturization. Carbon nanotube (CNT) interconnects have emerged as promising replacement materials for copper interconnects due to their superior conductivity. Buffer insertion for CNT interconnects is capable of improving circuit timing of signal nets with limited buffer deployment. However, due to the imperfection of fabricating long straight CNT, there exist significant unidimensional-spatially correlated variations on the critical CNT geometric parameters such as the diameter and density, which will affect the circuit performance.

This dissertation develops a novel timing …

Low-Cost Open-Source Gmaw-Based Metal 3-D Printing: Monitoring, Slicer, Optimization, And Applications, Yuenyong Nilsiam

Dissertations, Master's Theses and Master's Reports

Low-cost and open-source gas metal arc welding (GMAW)-based 3-D printing has been demonstrated yet the electrical design and software was not developed enough to enable wide-spread adoption. This thesis provides three novel technical improvements based on the application of mechatronic and software theory that when combined demonstrate the ability for distributed digital manufacturing at the small and medium enterprise scale of steel and aluminum parts. First, low cost metal inert gas welders contain no power monitoring needed to tune GMAW 3-D printers. To obtain this data about power and energy usage during the printing, an integrated monitoring system was developed …

Performance Comparison Of Binarized Neural Network With Convolutional Neural Network, Lopamudra Baruah

Dissertations, Master's Theses and Master's Reports

Deep learning is a trending topic widely studied by researchers due to increase in the abundance of data and getting meaningful results with them. Convolutional Neural Networks (CNN) is one of the most popular architectures used in deep learning. Binarized Neural Network (BNN) is also a neural network which consists of binary weights and activations. Neural Networks has large number of parameters and overfitting is a common problem to these networks. To overcome the overfitting problem, dropout is a solution. Randomly dropping some neurons along with its connections helps to prevent co-adaptations which finally help in reducing overfitting. Many researchers …