Computer Sciences Commons^™

The Mexican Water Forest: Benefits Of Using Remote Sensing Techniques To Assess Changes In Land Use And Land Cover, Maria F. Lopez Ornelas

Master's Projects and Capstones

In the past 30 years, anthropogenic activities like urbanization, agriculture, road fragmentation and deforestation have resulted in changes in the land use and land cover (LULC) in the Mexican Water Forest. Due to the important ecosystem services, and the natural resources this forest provides, in Mexico, it has become increasingly necessary to use new technologies and tools to support the planning, implementation and integration of forest management and conservation plans, as well as ecological and socioeconomic analysis of this ecosystem. Remote Sensing techniques and Geographic Information Systems (GIS) have been a true technological and methodological revolution in the acquisition, management …

Statistical Analysis Of Binary Functional Graphs Of The Discrete Logarithm, Mitchell Orzech

Mathematical Sciences Technical Reports (MSTR)

The increased use of cryptography to protect our personal information makes us want to understand the security of cryptosystems. The security of many cryptosystems relies on solving the discrete logarithm, which is thought to be relatively difficult. Therefore, we focus on the statistical analysis of certain properties of the graph of the discrete logarithm. We discovered the expected value and variance of a certain property of the graph and compare the expected value to experimental data. Our finding did not coincide with our intuition of the data following a Gaussian distribution given a large sample size. Thus, we found the …

Exploring Data Mining Techniques For Tree Species Classification Using Co-Registered Lidar And Hyperspectral Data, Julia K. Marrs

Theses and Dissertations

NASA Goddard’s LiDAR, Hyperspectral, and Thermal imager provides co-registered remote sensing data on experimental forests. Data mining methods were used to achieve a final tree species classification accuracy of 68% using a combined LiDAR and hyperspectral dataset, and show promise for addressing deforestation and carbon sequestration on a species-specific level.

Multi-Agent Reinforcement Learning As A Rehearsal For Decentralized Planning, Landon Kraemer, Bikramjit Banerjee

Faculty Publications

Decentralized partially observable Markov decision processes (Dec-POMDPs) are a powerful tool for modeling multi-agent planning and decision-making under uncertainty. Prevalent Dec-POMDP solution techniques require centralized computation given full knowledge of the underlying model. Multi-agent reinforcement learning (MARL) based approaches have been recently proposed for distributed solution of Dec-POMDPs without full prior knowledge of the model, but these methods assume that conditions during learning and policy execution are identical. In some practical scenarios this may not be the case. We propose a novel MARL approach in which agents are allowed to rehearse with information that will not be available during policy …

Automatic Classification Of Perceived Gender From Face Images, Joseph Lemley, Sami Abdul-Wahid, Dipayan Banik

Symposium Of University Research and Creative Expression (SOURCE)

Building software that can visually and accurately perceive gender from face images is an important step in making more intelligent machines. Several approaches to this problem have been suggested in the literature. We evaluate Histogram of Oriented Gradients, Dual Tree Complex Wavelet Transform (DTCWT) Principal Component Analysis (PCA) with Support Vector Machines (SVM) and compare them to Convolutional Neural Networks for this task. We train and test our classifiers with two benchmarks containing thousands of facial images. As expected, convolutional neural networks had the best performance while the performance of DTCWT varied most depending on the dataset used

Applying Machine Learning To Predict Stock Value, Joseph Lemley, Yishui Liu, Dipayan Banik, Sadia Afroze

Symposium Of University Research and Creative Expression (SOURCE)

The purpose of this study was to compare machine learning techniques for short term stock prediction and evaluate their effectiveness. Stock value analysis is an important element of modern economies. The ability to predict future stock prices from historical price values is of tremendous interest to investors. The prediction of stock performance is still an unsolved problem with a variety of techniques being proposed. Real stock values are affected by many elements, some of which cannot be measured. In this study, we limit our analysis to stock closing prices. We use these prices to predict the future stock value using …

Decoding Of Non-Binary Multiple Insertion/Deletion Error Correcting Codes, Tuan Anh Le

Theses and Dissertations

Data that is either transmitted over a communication channel or stored in memory is not always completely error free. Many communication channels are subject to noise, and thus errors may occur during transmission from transmitter to receiver. For example, DRAM memory cell contents can change spuriously due to electromagnetic interference while magnetic flux can cause one or more bits to flip in magnetic storage devices. To combat these errors, codes capable of correcting insertion/deletion errors have been investigated.

Levenshtein codes are the foundation of this thesis. His codes, first constructed by Varshamov-Tenengol’ts, are capable of correcting one insertion/deletion error. Helberg …

Investigations Of An "Objectness" Measure For Object Localization, Lewis Richard James Coates

Dissertations and Theses

Object localization is the task of locating objects in an image, typically by finding bounding boxes that isolate those objects. Identifying objects in images that have not had regions of interest labeled by humans often requires object localization to be performed first. The sliding window method is a common naïve approach, wherein the image is covered with bounding boxes of different sizes that form windows in the image. An object classifier is then run on each of these windows to determine if each given window contains a given object. However, because object classification algorithms tend to be computationally expensive, it …

Statistics In League Of Legends: Analyzing Runes For Last-Hitting, Brian M. Hook

Mathematics: Student Scholarship & Creative Works

While other sports have statisticians to evaluate players and their stats, in electronic sports there is a need for statisticians to evaluate different parts of the game. League of Legends is the most popular of ESports and is the focus of this discussion. The mechanic of focus here is runes which give boosts to the players stats in-game like being able to do extra damage. We will be finding the effectiveness of these runes by looking at gold efficiency, help with last hitting, and extra damage dealt through the use of Python.

Cyber Security Awareness In Higher Education, Toni Hunt

Symposium Of University Research and Creative Expression (SOURCE)

With technology advancing every day our society is becoming more connected than we have ever been before. While these advances are making our daily lives easier they are also adding extra risks to our personal information. Most people do not think about their identities getting stolen when they make an online purchase, check their email, or use social media. However, each time that you put your personal information on the Internet you are at risk of that information getting stolen. This is especially true for students, who spend so much time online doing school activities. Every time that they login …

Detection Of Locations Of Key Points On Facial Images, Manoj Gyanani

Master's Projects

In field of computer vision research, One of the most important branch is Face recognition. It targets at finding size and location of human face on digital image, by identifying and separating faces from the surrounding objects like building, plants etc. For the purpose of developing an advanced face recognition algorithm, Detection of facial key points is the basic and very important task, basically it is about finding out the location of specific key points on facial images. This key points can be mouths, noses, left eyes, right eyes and so on.

For implementation of solution, I have used amazon …

The History Of Chinese Cybersecurity: Current Effects On Chinese Society Economy, And Foreign Relations, Vaughn C. Rogers

Seton Hall University Dissertations and Theses (ETDs)

Chinese cybersecurity has become an infamous topic in the field of cybersecurity today, causing a great deal of controversy. The controversy stems from whether or not censorship is hindering Chinese economy, society, and relationships with other countries. The White Papers (中国政府白皮书), the Constitution of the People’s Republic of China (中华人民共和国宪法), and The Internet in China (中国互联网状况) all suggest that there is a free flow of Internet both within and without China that promotes peaceful socioeconomic development which the Chinese government seeks to promote. But is China sacrificing lucrative business prospects to secure …

Taint And Information Flow Analysis Using Sweet.Js Macros, Prakasam Kannan

Master's Projects

JavaScript has been the primary language for application development in browsers and with the advent of JIT compilers, it is increasingly becoming popular on server side development as well. However, JavaScript suffers from vulnerabilities like cross site scripting and malicious advertisement code on the the client side and on the server side from SQL injection.

In this paper, we present a dynamic approach to efficiently track information flow and taint detection to aid in mitigation and prevention of such attacks using JavaScript based hygienic macros. We use Sweet.js and object proxies to override built-in JavaScript operators to track information flow …

Revelation Of Yin-Yang Balance In Microbial Cell Factories By Data Mining, Flux Modeling, And Metabolic Engineering, Gang Wu

McKelvey School of Engineering Graduate Student Theses & Dissertations

The long-held assumption of never-ending rapid growth in biotechnology and especially in synthetic biology has been recently questioned, due to lack of substantial return of investment. One of the main reasons for failures in synthetic biology and metabolic engineering is the metabolic burdens that result in resource losses. Metabolic burden is defined as the portion of a host cells resources either energy molecules (e.g., NADH, NADPH and ATP) or carbon building blocks (e.g., amino acids) that is used to maintain the engineered components (e.g., pathways). As a result, the effectiveness of synthetic biology tools heavily dependents on cell capability to …

Exploiting The Weak Generational Hypothesis For Write Reduction And Object Recycling, Jonathan Andrew Shidal

McKelvey School of Engineering Graduate Student Theses & Dissertations

Programming languages with automatic memory management are continuing to grow in popularity due to ease of programming. However, these languages tend to allocate objects excessively, leading to inefficient use of memory and large garbage collection and allocation overheads.

The weak generational hypothesis notes that objects tend to die young in languages with automatic dynamic memory management. Much work has been done to optimize allocation and garbage collection algorithms based on this observation. Previous work has largely focused on developing efficient software algorithms for allocation and collection. However, much less work has studied architectural solutions. In this work, we propose and …

Learning With Scalability And Compactness, Wenlin Chen

McKelvey School of Engineering Graduate Student Theses & Dissertations

Artificial Intelligence has been thriving for decades since its birth. Traditional AI features heuristic search and planning, providing good strategy for tasks that are inherently search-based problems, such as games and GPS searching. In the meantime, machine learning, arguably the hottest subfield of AI, embraces data-driven methodology with great success in a wide range of applications such as computer vision and speech recognition. As a new trend, the applications of both learning and search have shifted toward mobile and embedded devices which entails not only scalability but also compactness of the models. Under this general paradigm, we propose a series …

Visualization Of Deep Convolutional Neural Networks, Dingwen Li

McKelvey School of Engineering Graduate Student Theses & Dissertations

Deep learning has achieved great accuracy in large scale image classification and scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a classification result is achieved. The objective of this thesis is to explore several existing visualization approaches which offer intuitive visual results. The thesis focuses on three visualization approaches: (1) image masking which highlights the region of image with high influence on the classification, (2) Taylor decomposition back-propagation which generates a per pixel heat map that describes each pixel's …

Automatically Characterizing Product And Process Incentives In Collective Intelligence, Allen Brockhurst Lavoie

McKelvey School of Engineering Graduate Student Theses & Dissertations

Social media facilitate interaction and information dissemination among an unprecedented number of participants. Why do users contribute, and why do they contribute to a specific venue? Does the information they receive cover all relevant points of view, or is it biased? The substantial and increasing importance of online communication makes these questions more pressing, but also puts answers within reach of automated methods. I investigate scalable algorithms for understanding two classes of incentives which arise in collective intelligence processes. Product incentives exist when contributors have a stake in the information delivered to other users. I investigate product-relevant user behavior changes, …

Texture Modelling Using Convolutional Neural Networks, Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

MODVIS Workshop

We introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. Extending this framework to texture transfer, we introduce A Neural Algorithm of Artistic Style that …

Sign & Share: Full-Stack International Video Sharing Website, Shuxu Tian

Undergraduate University Honors Capstones

Inspired by VL2 bilingual story apps that focus on American Sign Language and English, this project provides a new application for sharing multi-lingual signed and written stories to a worldwide audience. VL2 story apps include only ASL and English, and are for purchase; VL2 also sells the code to develop stories in other languages, but the code requires technical expertise to use. My new app uses a special set of tools to allow sharing stories in any signed language and written forms of spoken languages without cost and without the need for technical expertise. Known as Sign and Share, this …

Design And Implementation Of Asymptotically Optimal Mesh Slicing Algorithms Using Parallel Processing, Christopher Dant

MS in Computer Science Project Reports

Mesh slicing is the process of taking a three dimensional model and reducing it to 2.5 dimensional layers that together create a layered representation of the model. The process is used in layered additive manufacturing, three dimensional voxelization, and other similar problems in computational geometry. The slicing process is computationally expensive, and the time required to slice an object can inhibit the viability of layered manufacturing in some industries. We designed and developed a fast implementation of the slicing process, called Sunder, that uses new asymptotically optimal algorithms and takes advantage of parallel processing platforms. To our knowledge, no other …

Survey Of Autonomic Computing And Experiments On Jmx-Based Autonomic Features, Adel R. Azzam

LSU New Orleans Theses and Dissertations

Autonomic Computing (AC) aims at solving the problem of managing the rapidly-growing complexity of Information Technology systems, by creating self-managing systems. In this thesis, we have surveyed the progress of the AC field, and studied the requirements, models and architectures of AC. The commonly recognized AC requirements are four properties - self-configuring, self-healing, self-optimizing, and self-protecting. The recommended software architecture is the MAPE-K model containing four modules, namely - monitor, analyze, plan and execute, as well as the knowledge repository.

In the modern software marketplace, Java Management Extensions (JMX) has facilitated one function of the AC requirements - monitoring. Using …

Detecting Objective-C Malware Through Memory Forensics, Andrew Case

LSU New Orleans Theses and Dissertations

Memory forensics is increasingly used to detect and analyze sophisticated malware. In the last decade, major advances in memory forensics have made analysis of kernel-level malware straightforward. Kernel-level malware has been favored by attackers because it essentially provides complete control over a machine. This has changed recently as operating systems vendors now routinely enforce driving signing and strategies for protecting kernel data, such as Patch Guard, have made userland attacks much more attractive to malware authors.

In this thesis, new techniques for detecting userland malware written in Objective-C on Mac OS X are presented. As the thesis illustrates, Objective-C provides …

A Study Of Three Paradigms For Storing Geospatial Data: Distributed-Cloud Model, Relational Database, And Indexed Flat File, Matthew A. Toups

LSU New Orleans Theses and Dissertations

Geographic Information Systems (GIS) and related applications of geospatial data were once a small software niche; today nearly all Internet and mobile users utilize some sort of mapping or location-aware software. This widespread use reaches beyond mere consumption of geodata; projects like OpenStreetMap (OSM) represent a new source of geodata production, sometimes dubbed “Volunteered Geographic Information.” The volume of geodata produced and the user demand for geodata will surely continue to grow, so the storage and query techniques for geospatial data must evolve accordingly.

This thesis compares three paradigms for systems that manage vector data. Over the past few decades …

2016-01-A3dsrinp-Csc-Sta-Cmb-522-Bps-542, Raymond Pulver, Neal Buxton, Xiaodong Wang, John Lucci, Jean Yves Hervé, Lenore Martin

Bioinformatics Software Design Projects

Cholesterol is carried and transported through bloodstream by lipoproteins. There are two types of lipoproteins: low density lipoprotein, or LDL, and high density lipoprotein, or HDL. LDL cholesterol is considered “bad” cholesterol because it can form plaque and hard deposit leading to arteries clog and make them less flexible. Heart attack or stroke will happen if the hard deposit blocks a narrowed artery. HDL cholesterol helps to remove LDL from the artery back to the liver.

Traditionally, particle counts of LDL and HDL plays an important role to understanding and prediction of heart disease risk. But recently research suggested that …

Focusing On Selection For Fixation, John K. Tsotsos, Calden Wloka, Yulia Kotseruba

MODVIS Workshop

Building on our presentation at MODVIS 2015, we continue in our quest to discover a functional, computational, explanation of the relationship among visual attention, interpretation of visual stimuli, and eye movements, and how these produce visual behavior. Here, we focus on one component, how selection is accomplished for the next fixation. The popularity of saliency map models drives the inference that this is solved; we suggested otherwise at MODVIS 2015. Here, we provide additional empirical and theoretical arguments. We then develop arguments that a cluster of complementary, conspicuity representations drive selection, modulated by task goals and history, leading to a …

Kings And Heirs: A Characterization Of The (2,2)-Domination Graphs Of Tournaments, Kim A. S. Factor, Larry J. Langley

Mathematics, Statistics and Computer Science Faculty Research and Publications

In 1980, Maurer coined the phrase king when describing any vertex of a tournament that could reach every other vertex in two or fewer steps. A (2,2)-domination graph of a digraph D, dom_2,2(D), has vertex set V(D), the vertices of D, and edge uv whenever u and v each reach all other vertices of D in two or fewer steps. In this special case of the (i,j)-domination graph, we see that Maurer’s theorem plays an important role in establishing which vertices form the kings that create some of the edges in dom_2,2(D). But of even more …

Information Seeking Practices Of Parents: Exploring Skills, Face Threats And Social Networks, Betsy Disalvo, Parisa Khanipour Roshan, Briana B. Morrison

Computer Science Faculty Proceedings & Presentations

Parents are often responsible for finding, selecting, and facilitating their children's out-of-school learning experiences. One might expect that the recent surge in online educational tools and the vast online network of information about informal learning would make this easier for all parents. Instead, the increase in these free, accessible resources is contributing to an inequality of use between children from lower and higher socio-economic status (SES). Through over 60 interviews with a diverse group of parents, we explored parents' ability to find learning opportunities and their role in facilitating educational experiences for their children. We identified differences in the use …

Graph Mining For Next Generation Sequencing: Leveraging The Assembly Graph For Biological Insights, Julia Warnke-Sommer, Hesham Ali

Computer Science Faculty Publications

Background: The assembly of Next Generation Sequencing (NGS) reads remains a challenging task. This is especially true for the assembly of metagenomics data that originate from environmental samples potentially containing hundreds to thousands of unique species. The principle objective of current assembly tools is to assemble NGS reads into contiguous stretches of sequence called contigs while maximizing for both accuracy and contig length. The end goal of this process is to produce longer contigs with the major focus being on assembly only. Sequence read assembly is an aggregative process, during which read overlap relationship information is lost as reads are …

Internet Of Things-Based Smart Classroom Environment, Amir R. Atabekov

Master of Science in Computer Science Theses

Internet of Things (IoT) is a novel paradigm that is gaining ground in the Computer Science field. There’s no doubt that IoT will make our lives easier with the advent of smart thermostats, medical wearable devices, connected vending machines and others. One important research direction in IoT is Resource Management Systems (RMS). In the current state of RMS research, very few studies were able to take advantage of indoor localization which can be very valuable, especially in the context of smart classrooms. For example, indoor localization can be used to dynamically generate seat map of students in a classroom. Indoor …