Browsing 2016 Theses (MU) by Thesis Department "Computer engineering (MU)"
Now showing items 1-15 of 15
-
Analysis of performance/accuracy tradeoffs for floating point applications on GPUS
(University of Missouri--Columbia, 2016)Floating-point computations produce approximate results, which can lead to inaccuracy problems. Existing work addresses two issues: first, the design of high precision floatingpoint representations; second, the study of ... -
Convolutional Neural Network architectures for digit recognition system
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Rapidly evolving of Convolutional Neural Networks (CNNs) appeals and endeavors us to explore and discover various CNN model's robustness leading to ... -
Critical analysis and evaluation of different automata processing accelerators on large-scale datasets
(University of Missouri--Columbia, 2016)Many established and emerging applications perform at their core some form of pattern matching, a computation that maps naturally onto finite automata abstractions. As a consequence, in recent years there has been a ... -
A data acquisition system that uses signal scavenging to detect activity on floor pads
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] We designed a data acquisition system to scan data from four sensors on a pad using the smart carpet technology. We constructed and tested four data ... -
Design of runtime libraries to improve programmability and efficiency of heterogeneous CPU-GPU nodes
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] As computers began to reach their limit on how fast a single processor could execute code, computer developers began to devise methods to process more ... -
Dynamic construction of trie-based automata for approximate K-mer matching on heterogeneous CPU-GPU systems
(University of Missouri--Columbia, 2016)In recent decades, mapping of a variety of species' genomes has taken place. With the proliferation of advanced and specialized hardware architectures such as GPUs, the process has been greatly accelerated. GPUs may ... -
A fast and accurate robotic grasp method using deep learning
(University of Missouri--Columbia, 2016)I have developed a system that is capable of quick and accurate detection of target objects using the deep learning method. Adding orientation with depth sensing then allows a robot to grasp the objects. The existing ... -
Frequency-minimal utility-maximizing cloud resources allocation for moving target defense
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] With the increase of cyber-attacks such as DDoS, intelligent resource-allocation based migration schemes are being devised as counter-strategies to ... -
Improved data processing for personnel activity detection system
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Our laboratory has implemented a personnel detection system, Smart Carpet, which can detect the walking activities. The existing system uses a SheevaPlug ... -
Map-guided hyperspectral image superpixel segmentation using semi-supervised partial membership latent Dirichlet allocation
(University of Missouri--Columbia, 2016)Many superpixel segmentation algorithms which are suitable for the regular color images like images with three channels: red, green and blue (RGB images) have been developed in the literature. However, because of the high ... -
Multi-camera high-throughput plant root phenotyping system
(University of Missouri--Columbia, 2016)Plant root phenotyping is a key component in plant breeding and selection for desireable root properties. Preferable root traits can not only help a plant to grow faster but also allow for more dense and deep root system ... -
Performance analysis of mix-kernel convolutional neural network
(University of Missouri--Columbia, 2016)Deep convolutional neural networks (DCNN) have achieved the state-of-the-art performance in a number of computer vision tasks in recent years, including object detection, classification and recognition. The DCNN is very ... -
Semi-supervised interactive unmixing for hyperspectral image analysis
(University of Missouri--Columbia, 2016)In the past several decades, hyperspectral imaging has drawn a lot of attention in the field of remote sensing. Yet, due to low spatial resolutions of hyperspectral imagers, often the response from more than one surface ... -
Stock market forecasting using recurrent neural network
(University of Missouri--Columbia, 2016)In this research, we study the problem of stock market forecasting using Recurrent Neural Network(RNN) with Long Short-Term Memory (LSTM). The purpose of this research is to examine the feasibility and performance of LSTM ... -
Wireless communication for small floor pads to detect personnel activity
(University of Missouri--Columbia, 2016)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Our laboratory has designed data acquisition systems to detect personnel activity using floor-based sensors, which we call the smart carpet. Therefore, ...