Computer Engineering Commons^™

A Triangulation-Based Approach To Nonrigid Image Registration, Timothy R. Linden

Browse all Theses and Dissertations

A triangulation-based approach to nonrigid image registration is presented. This method builds upon control point projective registration methods. Control points for this method are located using the Harris point detector. An analysis is presented for this detector to show its properties. Projective registration is used as the basis for this non-rigid registration method. Details of the projective registration method used are presented. Nonrigid registration is used to spatially align images of a 3-D scene taken from different views. Projective registration approximates the scene geometry as a plane. This nonrigid approach subdivides the images into small corresponding triangles, to improve the …

Large Scale Distributed Semantic N-Gram Language Model, Yuandong Jiang

Browse all Theses and Dissertations

Language model is a crucial component in statistical machine translation system. The basic language model is N-gram which predicts the next word based on previous N-1 words. It has been used in the state-of-the-art commercial machine translation systems over years. However, the N-gram model ignores the rich syntactic and semantic structure in natural languages. We propose a composite semantic N-gram language model which combines probabilistic latent semantic analysis model with N-gram as a generative model. We have implemented the proposed composite language model in a super-computer with thousand processors that is trained by 1.3 billion tokens corpus. Comparing with simple …

Measuring Uncertainty Of Protein Secondary Structure, Alan Eugene Herner

Browse all Theses and Dissertations

This dissertation develops and demonstrates a method to measure the uncertainty of secondary structure of protein sequences using Shannon's information theory. This method is applied to a newly developed large dataset of chameleon sequences and to several protein hinges culled from the Hinge Atlas. The uncertainty of the central residue in each tripeptide is computed for each amino acid in a sequence using Cuff and Barton's CB513 as the reference set. It is shown that while secondary structure uncertainty is relatively high in chameleon regions [avg = 1.27 bits] it is relatively low in the regions 1-7 residues nearest a …

A User Centered Design And Prototype Of A Mobile Reading Device For The Visually Impaired, Robert B. Keefer

Browse all Theses and Dissertations

While mobile reading devices have been on the market and investigated by researchers in recent years, there is still work required to make these devices highly accessible to the visually impaired. A usability test with one such device revealed gaps in the current state of the art devices. These gaps focus mostly on the user interaction and his or her ability to quickly consume written reading material. In this dissertation a voice user interface (VUI) is presented that improves the ability of a blind user of a mobile reading device to interact with written material. The image processing techniques required …

Weapon Engagement Zone Maximum Launch Range Approximation Using A Multilayer Perceptron, Brian Michael Birkmire

Browse all Theses and Dissertations

This thesis investigates the use of an artificial neural network (ANN), in particular a Multi-Layer Perceptron (MLP), to perform function approximation on truth data representing a weapon engagement zone's (WEZ) maximum launch range. The WEZ of an air-to-air missile represents the boundaries and zones of effectiveness for a one-vs-one air-to-air combat engagement [13]. The intent is for the network to fuse table lookup and interpolation functionality into a physically compact and computationally efficient package, while improving approximation accuracy over conventional methods. Data was collected from simulated firings of a notional air-to-air missile model and used to train a two layer …

Design And Development Of A Fall Detection Device With Infrared Receiving Capabilities, Ammari Ramzi

Browse all Theses and Dissertations

Fall related injuries are the leading cause of death and hospitalization among the elderly. Falls among older people become a major problem facing hospitals and nursing homes. In this study we put an effort to design a wireless device capable of detecting falls with the hope that this study will provide a path towards better healthcare monitoring and better independent living for the elderly.

In this project I showed how the fall detection device can be interfaced with different systems to achieve functionality without adding extra cost. For seniors who prefer to stay at their homes and live independently, the …

3-D Model Characterization And Identification From Intrinsic Landmarks, John L. Camp

Browse all Theses and Dissertations

A method to automatically characterize and identify 3-D range scans based on intrinsic landmarks is presented. Intrinsic landmarks represent locally unique, intrinsic properties of a scanned surface, regardless of scale or rotation. The number, location, and characteristics of landmarks are used to characterize the scanned models. This method contains a selection process to identify stable, intrinsic landmarks for range scans as well as the identification of those scans. The selection process requires no user interaction or surface assumptions. It uses the principal curvatures at the range points to select the landmarks. First, a large number of landmarks are generated by …

A Domain Specific Language Based Approach For Developing Complex Cloud Computing Applications, Ashwin Kumar Manjunatha

Browse all Theses and Dissertations

Computing has changed. Lately, a slew of cheap, ubiquitous, connected mobile devices as well as seemingly unlimited, utility style, pay as you go computing resources has become available at the disposal of the common man. The latter commonly called Cloud Computing (or just Cloud) is democratizing computing by making large computing power accessible to people and corporations around the world easily and economically.

However, taking full advantage of this computing landscape, especially for the data intensive domains, has been hampered by many factors, the primary one being the complexity in developing applications for the variety of available platforms.

This thesis …