Digital Commons Network^™

Scheduling And Tuning Kernels For High-Performance On Heterogeneous Processor Systems, Ye Fang

LSU Doctoral Dissertations

Accelerated parallel computing techniques using devices such as GPUs and Xeon Phis (along with CPUs) have proposed promising solutions of extending the cutting edge of high-performance computer systems. A significant performance improvement can be achieved when suitable workloads are handled by the accelerator. Traditional CPUs can handle those workloads not well suited for accelerators. Combination of multiple types of processors in a single computer system is referred to as a heterogeneous system. This dissertation addresses tuning and scheduling issues in heterogeneous systems. The first section presents work on tuning scientific workloads on three different types of processors: multi-core CPU, Xeon …

A Data Science Course For Undergraduates: Thinking With Data, Benjamin Baumer

Mathematics Sciences: Faculty Publications

Data science is an emerging interdisciplinary field that combines elements of mathematics, statistics, computer science, and knowledge in a particular application domain for the purpose of extracting meaningful information from the increasingly sophisticated array of data available in many settings. These data tend to be nontraditional, in the sense that they are often live, large, complex, and/or messy. A first course in statistics at the undergraduate level typically introduces students to a variety of techniques to analyze small, neat, and clean datasets. However, whether they pursue more formal training in statistics or not, many of these students will end up …

Classification Of Breast Cancer Patients Using Somatic Mutation Profiles And Machine Learning Approaches, Suleyman Vural

Theses & Dissertations

The high degree of heterogeneity observed in breast cancers makes it very difficult to classify cancer patients into distinct clinical subgroups and consequently limits the ability to devise effective therapeutic strategies. In this study, we explore the use of gene mutation profiles to classify, characterize and predict the subgroups of breast cancers. We analyzed the whole exome sequencing data from 358 ethnically similar breast cancer patients in The Cancer Genome Atlas (TCGA) project. Identified somatic and non-synonymous single nucleotide variants were assigned a quantitative score (C-score) that represents the extent of negative impact on the function of the gene. Using …

Pathological Brain Detection By A Novel Image Feature—Fractional Fourier Entropy, Shuihua Wang, Yudong Zhang, Xiaojun Yang, Ping Sun, Zhengchao Dong, Aijun Lu, Ti-Fei Yuan

Publications and Research

Aim: To detect pathological brain conditions early is a core procedure for patients so as to have enough time for treatment. Traditional manual detection is either cumbersome, or expensive, or time-consuming. We aim to offer a system that can automatically identify pathological brain images in this paper.Method: We propose a novel image feature, viz., Fractional Fourier Entropy (FRFE), which is based on the combination of Fractional Fourier Transform(FRFT) and Shannon entropy. Afterwards, the Welch’s t-test (WTT) and Mahalanobis distance (MD) were harnessed to select distinguishing features. Finally, we introduced an advanced classifier: twin support vector machine (TSVM). Results: A 10 …

The Performance Of Random Prototypes In Hierarchical Models Of Vision, Kendall Lee Stewart

Dissertations and Theses

I investigate properties of HMAX, a computational model of hierarchical processing in the primate visual cortex. High-level cortical neurons have been shown to respond highly to particular natural shapes, such as faces. HMAX models this property with a dictionary of natural shapes, called prototypes, that respond to the presence of those shapes. The resulting set of similarity measurements is an effective descriptor for classifying images. Curiously, prior work has shown that replacing the dictionary of natural shapes with entirely random prototypes has little impact on classification performance. This work explores that phenomenon by studying the performance of random prototypes on …

Dynamic Data Management In A Data Grid Environment, Björn Barrefors

School of Computing: Dissertations, Theses, and Student Research

A data grid is a geographically distributed set of resources providing a facility for computationally intensive analysis of large datasets to a large number of geographically distributed users. In the scientific community, data grids have become increasingly popular as scientific research is driven by large datasets. Until recently, developments in data management for data grids have focused on management of data at lower layers in the data grid architecture. With dataset sizes expected to approach exabyte scale in coming years, data management in data grids are facing a new set of challenges. In particularly, the problem of automatically placing and …

Energy Forecasting For Event Venues: Big Data And Prediction Accuracy, Katarina Grolinger, Alexandra L'Heureux, Miriam Am Capretz, Luke Seewald

Electrical and Computer Engineering Publications

Advances in sensor technologies and the proliferation of smart meters have resulted in an explosion of energy-related data sets. These Big Data have created opportunities for development of new energy services and a promise of better energy management and conservation. Sensor-based energy forecasting has been researched in the context of office buildings, schools, and residential buildings. This paper investigates sensor-based forecasting in the context of event-organizing venues, which present an especially difficult scenario due to large variations in consumption caused by the hosted events. Moreover, the significance of the data set size, specifically the impact of temporal granularity, on energy …

Analyzing Repetitive Sequences With Structured Dynamic Bayesian Networks, Thomas. L. Lake

Masters Theses

Time series often feature structure that is known a priori and easily described using natural language terms such as repetitive, symmetric, seasonal, and self-similar. However, the typical conjugate priors used in Bayesian analysis do not capture such complex phenomena well. As a result of this mismatch, known structure is modeled poorly or completely ignored. Focusing on time series with repetitive structure, this thesis proposes to overcome this problem by reducing rather than in- creasing the capacity of a well know time series model, the Hidden Markov Model. Through a careful choice in the way model capacity is reduced the model …

Evaluating The Intrinsic Similarity Between Neural Networks, Stephen Charles Ashmore

Graduate Theses and Dissertations

We present Forward Bipartite Alignment (FBA), a method that aligns the topological structures of two neural networks. Neural networks are considered to be a black box, because neural networks contain complex model surface determined by their weights that combine attributes non-linearly. Two networks that make similar predictions on training data may still generalize differently. FBA enables a diversity of applications, including visualization and canonicalization of neural networks, ensembles, and cross-over between unrelated neural networks in evolutionary optimization. We describe the FBA algorithm, and describe implementations for three applications: genetic algorithms, visualization, and ensembles. We demonstrate FBA's usefulness by comparing a …

Automatic License Plate Recognition Using Deep Learning Techniques, Naga Surya Sandeep Angara

Electrical Engineering Theses

Automatic License Plate Recognition (ALPR) systems capture a vehicles license plate and recognize the license number and other required information from the captured image. ALPR systems have number of significant applications: law enforcement, public safety agencies, toll gate systems, etc. The goal of these systems is to recognize the characters and state on the license plate with high accuracy. ALPR has been implemented using various techniques. Traditional recognition methods use handcrafted features for obtaining features from the image. Unlike conventional methods, deep learning techniques automatically select features and are one of the game changing technologies in the field of computer …

Semi-Supervised Pattern Recognition And Machine Learning For Eye-Tracking, Thomas B. Kinsman

Theses

The first step in monitoring an observer’s eye gaze is identifying and locating the image of their pupils in video recordings of their eyes. Current systems work under a range of conditions, but fail in bright sunlight and rapidly varying illumination. A computer vision system was developed to assist with the recognition of the pupil in every frame of a video, in spite of the presence of strong first-surface reflections off of the cornea. A modified Hough Circle detector was developed that incorporates knowledge that the pupil is darker than the surrounding iris of the eye, and is able to …

Distributed Approach For Peptide Identification, Naga V K Abhinav Vedanbhatla

Masters Theses & Specialist Projects

A crucial step in protein identification is peptide identification. The Peptide Spectrum Match (PSM) information set is enormous. Hence, it is a time-consuming procedure to work on a single machine. PSMs are situated by a cross connection, a factual score, or a probability that the match between the trial and speculative is right and original. This procedure takes quite a while to execute. So, there is demand for enhancement of the performance to handle extensive peptide information sets. Development of appropriate distributed frameworks are expected to lessen the processing time.

The designed framework uses a peptide handling algorithm named C-Ranker, …

Learning Relative Similarity From Data Streams: Active Online Learning Approaches, Shuji Hao, Peilin Zhao, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

Relative similarity learning, as an important learning scheme for information retrieval, aims to learn a bi-linear similarity function from a collection of labeled instance-pairs, and the learned function would assign a high similarity value for a similar instance-pair and a low value for a dissimilar pair. Existing algorithms usually assume the labels of all the pairs in data streams are always made available for learning. However, this is not always realistic in practice since the number of possible pairs is quadratic to the number of instances in the database, and manually labeling the pairs could be very costly and time …

Addressing Hospital Staffing Shortages: Dynamic Surgical Tool Tracking And Delivery Using Baxter, Sthitapragyan Parida

The Journal of Purdue Undergraduate Research

Several hospitals face nurse staffing shortages for surgeries. This research focuses on building a system with a Baxter robot capable of identifying surgical tools using computer vision and delivering them to the surgeon on demand. This would deal with the issue of nurse unavailability during simple surgical procedures. The key aspects of the project were testing the accuracies of various artificial neural networks (ANNs) in classifying surgical instruments and programming Baxter to implement a surgical tool delivery system using magnets at the tip of its 7 degrees of freedom (DOF) robotic arms. The methodology consisted of first implementing algorithms to …

Detecting, Modeling, And Predicting User Temporal Intention, Hany M. Salaheldeen

Computer Science Theses & Dissertations

The content of social media has grown exponentially in the recent years and its role has evolved from narrating life events to actually shaping them. Unfortunately, content posted and shared in social networks is vulnerable and prone to loss or change, rendering the context associated with it (a tweet, post, status, or others) meaningless. There is an inherent value in maintaining the consistency of such social records as in some cases they take over the task of being the first draft of history as collections of these social posts narrate the pulse of the street during historic events, protest, riots, …

Fault Detection And Diagnostics Of An Hvac Sub-System Using Adaptive Resonance Theory Neural Networks, Christian Birk Jones

Mechanical Engineering ETDs

The commercial building sector consumed about 20% of the total primary energy in the U.S. in 2008. A significant yet avoidable portion of the energy consumption is due to inefficient system operations. The inefficiencies can be attributed to degrading HVAC sub-systems, and undetected abnormal conditions. Recognition and remediation of these conditions through advanced data analytics can reduce energy consumption by 5% to 20%. This could save about $9 billion in utility costs in the U.S. alone. Modern buildings are constantly sending messages in the form of sensor data. However, this data is only as good as the system that collects …

Hybrid Statistical Data Mining Framework For Multi-Commodity Fixed Charge Network Flow Problem, Anurag A. Ladage

Theses

This paper presents a new approach to analyze the network structure in multi-commodity fixed charge network flow problems (MCFCNF). This methodology uses historical data produced from repeatedly solving the traditional MCFCNF mathematical model as input for the machine-learning framework. Further, we reshape the problem as a binary classification problem and employ machine-learning algorithms to predict network structure. This predicted network structure is further used as an initial solution for our mathematical model. The quality of the initial solution generated is judged on the basis of predictive accuracy, feasibility and reduction in solving time.

Homogeneous Spiking Neuromorphic System For Real-World Pattern Recognition, Xinyu Wu, Vishal Saxena, Kehan Zhu

Electrical and Computer Engineering Faculty Publications and Presentations

A neuromorphic chip that combines CMOS analog spiking neurons and memristive synapses offers a promising solution to brain-inspired computing, as it can provide massive neural network parallelism and density. Previous hybrid analog CMOS-memristor approaches required extensive CMOS circuitry for training, and thus eliminated most of the density advantages gained by the adoption of memristor synapses. Further, they used different waveforms for pre and post-synaptic spikes that added undesirable circuit overhead. Here we describe a hardware architecture that can feature a large number of memristor synapses to learn real-world patterns. We present a versatile CMOS neuron that combines integrate-and-fire behavior, drives …

Reliable Patch Trackers: Robust Visual Tracking By Exploiting Reliable Patches, Yang Li, Jianke Zhu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization. In this paper, we propose a new tracking method, Reliable Patch Trackers (RPT), which attempts to identify and exploit the reliable patches that can be tracked effectively through the whole tracking process. Specifically, we present a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework. As the reliable patches distributed over …

Information Filtering By Multiple Examples, Mingzhu Zhu

Dissertations

A key to successfully satisfy an information need lies in how users express it using keywords as queries. However, for many users, expressing their information needs using keywords is difficult, especially when the information need is complex. Search By Multiple Examples (SBME), a promising method for overcoming this problem, allows users to specify their information needs as a set of relevant documents rather than as a set of keywords.

Most of the studies on SBME adopt the Positive Unlabeled learning (PU learning) techniques by treating the user's provided examples (denoted as query examples) as positive set and the entire data …

Eliciting Knowledge Bases With Defeasible Reasoning: A Comparative Analysis With Machine Learning, Peter Keogh

Dissertations

This thesis compares the ability of an implementation of Defeasible Reasoning (via Argumentation Theory) to model a construct (mental workload) with Machine Learning. In order to perform this comparison a defeasible reasoning system was designed and implemented in software. This software was used to elicit a knowledge base from an expert in an experiment which was then compared with machine learning. The central findings of this thesis were that the knowledge based approach was better at predicting an objective performance measure, time, than machine learning. However, machine learning was better equiped to identify another object measure task membership. The knowledge …

Predicting Protein Contact Map By Bagging Decision Trees, Chuqiao Ren

Honors Theses

Proteins' function and structure are intrinsically related. In order to understand proteins' functionality, it is essential for medical and biological researchers to deter- mine proteins' three-dimensional structure. The traditional method using NMR spectroscopy or X-ray crystallography are inefficient compared to computational methods. Fortunately, substantial progress has been made in the prediction of protein structure in bioinformatics. Despite these achievements, the computational complexity of protein folding remains a challenge. Instead, many methods aim to predict a protein contact map from protein sequence using machine learning algorithms. In this thesis, we introduce a novel ensemble method for protein contact map prediction based …

Feature Identification And Reduction For Improved Generalization Accuracy In Secondary-Structure Prediction Using Temporal Context Inputs In Machine-Learning Models, Matthew Benjamin Seeley

Theses and Dissertations

A protein's properties are influenced by both its amino-acid sequence and its three-dimensional conformation. Ascertaining a protein's sequence is relatively easy using modern techniques, but determining its conformation requires much more expensive and time-consuming techniques. Consequently, it would be useful to identify a method that can accurately predict a protein's secondary-structure conformation using only the protein's sequence data. This problem is not trivial, however, because identical amino-acid subsequences in different contexts sometimes have disparate secondary structures, while highly dissimilar amino-acid subsequences sometimes have identical secondary structures. We propose (1) to develop a set of metrics that facilitates better comparisons between …

Using Instance-Level Meta-Information To Facilitate A More Principled Approach To Machine Learning, Michael Reed Smith

Theses and Dissertations

As the capability for capturing and storing data increases and becomes more ubiquitous, an increasing number of organizations are looking to use machine learning techniques as a means of understanding and leveraging their data. However, the success of applying machine learning techniques depends on which learning algorithm is selected, the hyperparameters that are provided to the selected learning algorithm, and the data that is supplied to the learning algorithm. Even among machine learning experts, selecting an appropriate learning algorithm, setting its associated hyperparameters, and preprocessing the data can be a challenging task and is generally left to the expertise of …

Leveraging Contextual Relationships Between Objects For Localization, Clinton Leif Olson

Dissertations and Theses

Object localization is currently an active area of research in computer vision. The object localization task is to identify all locations of an object class within an image by drawing a bounding box around objects that are instances of that class. Object locations are typically found by computing a classification score over a small window at multiple locations in the image, based on some chosen criteria, and choosing the highest scoring windows as the object bounding-boxes. Localization methods vary widely, but there is a growing trend towards methods that are able to make localization more accurate and efficient through the …

Vision Based Multiple Target Tracking Using Recursive Ransac, Kyle Ingersoll

Theses and Dissertations

In this thesis, the Recursive-Random Sample Consensus (R-RANSAC) multiple target tracking (MTT) algorithm is further developed and applied to video taken from static platforms. Development of R-RANSAC is primarily focused in three areas: data association, the ability to track maneuvering objects, and track management. The probabilistic data association (PDA) filter performs very well in the R-RANSAC framework and adds minimal computation cost over less sophisticated methods. The interacting multiple models (IMM) filter as well as higher-order linear models are incorporated into R-RANSAC to improve tracking of highly maneuverable targets. An effective track labeling system, a more intuitive track merging criteria, …

Deformation Twin Nucleation And Growth Characterization In Magnesium Alloys Using Novel Ebsd Pattern Analysis And Machine Learning Tools, Travis Michael Rampton

Theses and Dissertations

Deformation twinning in Magnesium alloys both facilitates slip and forms sites for failure. Currently, basic studies of twinning in Mg are facilitated by electron backscatter diffraction (EBSD) which is able to extract a myriad of information relating to crystalline microstructures. Although much information is available via EBSD, various problems relating to deformation twinning have not been solved. This dissertation provides new insights into deformation twinning in Mg alloys, with particular focus on AZ31. These insights were gained through the development of new EBSD and related machine learning tools that extract more information beyond what is currently accessed.The first tool relating …

Use Of A High-Value Social Audience Index For Target Audience Identification On Twitter, Siaw Ling Lo, David Cornforth, Raymond. Chiong

Research Collection School Of Computing and Information Systems

With the large and growing user base of social media, it is not an easy feat to identify potential customers for business. This is mainly due to the challenge of extracting commercially viable contents from the vast amount of free-form conversations. In this paper, we analyse the Twitter content of an account owner and its list of followers through various text mining methods and segment the list of followers via an index. We have termed this index as the High-Value Social Audience (HVSA) index. This HVSA index enables a company or organisation to devise their marketing and engagement plan according …

Cancer Risk Prediction With Next Generation Sequencing Data Using Machine Learning, Nihir Patel

Theses

The use of computational biology for next generation sequencing (NGS) analysis is rapidly increasing in genomics research. However, the effectiveness of NGS data to predict disease abundance is yet unclear. This research investigates the problem in the whole exome NGS data of the chronic lymphocytic leukemia (CLL) available at dbGaP. Initially, raw reads from samples are aligned to the human reference genome using burrows wheeler aligner. From the samples, structural variants, namely, Single Nucleotide Polymorphism (SNP) and Insertion Deletion (INDEL) are identified and are filtered using SAMtools as well as with Genome Analyzer Tool Kit (GATK). Subsequently, the variants are …

Electroencephalogram Based Causality Graph Analysis In Behavior Tasks Of Parkinson’S Disease Patients, Abdulaziz Saleh Almalaq

Electronic Theses and Dissertations

Electroencephalographic (EEG) signals of the human brains represent electrical activities for a number of channels recorded over a the scalp. The main purpose of this thesis is to investigate the interactions and causality of different parts of a brain using EEG signals recorded during a performance subjects of verbal fluency tasks. Subjects who have Parkinson's Disease (PD) have difficulties with mental tasks, such as switching between one behavior task and another. The behavior tasks include phonemic fluency, semantic fluency, category semantic fluency and reading fluency. This method uses verbal generation skills, activating different Broca's areas of the Brodmann's areas (BA44 …